diff options
| author |   Jens Axboe <axboe@kernel.dk> | 2022-07-24 18:41:03 -0600 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2022-07-24 18:41:03 -0600 |
| commit | 4effe18fc0da27ae5d51a702841e87fa13b8a32d (patch) | |
| tree | 468f353a3713c93b27e7b2c262efd747e66ff199 | |
| parent | Merge branch 'io_uring-zerocopy-send' of git://git.kernel.org/pub/scm/linux/kernel/git/kuba/linux into for-5.20/io_uring-zerocopy-send (diff) | |
| parent | io_uring: ensure REQ_F_ISREG is set async offload (diff) | |
| download | wireguard-linux-4effe18fc0da27ae5d51a702841e87fa13b8a32d.tar.xz wireguard-linux-4effe18fc0da27ae5d51a702841e87fa13b8a32d.zip | |
Merge branch 'for-5.20/io_uring' into for-5.20/io_uring-zerocopy-send
* for-5.20/io_uring: (716 commits)
io_uring: ensure REQ_F_ISREG is set async offload
net: fix compat pointer in get_compat_msghdr()
io_uring: Don't require reinitable percpu_ref
io_uring: fix types in io_recvmsg_multishot_overflow
io_uring: Use atomic_long_try_cmpxchg in __io_account_mem
io_uring: support multishot in recvmsg
net: copy from user before calling __get_compat_msghdr
net: copy from user before calling __copy_msghdr
io_uring: support 0 length iov in buffer select in compat
io_uring: fix multishot ending when not polled
io_uring: add netmsg cache
io_uring: impose max limit on apoll cache
io_uring: add abstraction around apoll cache
io_uring: move apoll cache to poll.c
io_uring: consolidate hash_locked io-wq handling
io_uring: clear REQ_F_HASH_LOCKED on hash removal
io_uring: don't race double poll setting REQ_F_ASYNC_DATA
io_uring: don't miss setting REQ_F_DOUBLE_POLL
io_uring: disable multishot recvmsg
io_uring: only trace one of complete or overflow
...
Signed-off-by: Jens Axboe <axboe@kernel.dk>
633 files changed, 21978 insertions, 16785 deletions
@@ -627,6 +627,10 @@ S: 48287 Sawleaf S: Fremont, California 94539 S: USA +N: Tomas Cech +E: sleep_walker@suse.com +D: arm/palm treo support + N: Florent Chabaud E: florent.chabaud@polytechnique.org D: software suspend diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 2522b11e593f..c0fdb04a0435 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5197,6 +5197,30 @@ retain_initrd [RAM] Keep initrd memory after extraction + retbleed= [X86] Control mitigation of RETBleed (Arbitrary + Speculative Code Execution with Return Instructions) + vulnerability. + + off - no mitigation + auto - automatically select a migitation + auto,nosmt - automatically select a mitigation, + disabling SMT if necessary for + the full mitigation (only on Zen1 + and older without STIBP). + ibpb - mitigate short speculation windows on + basic block boundaries too. Safe, highest + perf impact. + unret - force enable untrained return thunks, + only effective on AMD f15h-f17h + based systems. + unret,nosmt - like unret, will disable SMT when STIBP + is not available. + + Selecting 'auto' will choose a mitigation method at run + time according to the CPU. + + Not specifying this option is equivalent to retbleed=auto. + rfkill.default_state= 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm, etc. communication is blocked by default. @@ -5568,6 +5592,7 @@ eibrs - enhanced IBRS eibrs,retpoline - enhanced IBRS + Retpolines eibrs,lfence - enhanced IBRS + LFENCE + ibrs - use IBRS to protect kernel Not specifying this option is equivalent to spectre_v2=auto. @@ -5771,6 +5796,24 @@ expediting. Set to zero to disable automatic expediting. + srcutree.srcu_max_nodelay [KNL] + Specifies the number of no-delay instances + per jiffy for which the SRCU grace period + worker thread will be rescheduled with zero + delay. Beyond this limit, worker thread will + be rescheduled with a sleep delay of one jiffy. + + srcutree.srcu_max_nodelay_phase [KNL] + Specifies the per-grace-period phase, number of + non-sleeping polls of readers. Beyond this limit, + grace period worker thread will be rescheduled + with a sleep delay of one jiffy, between each + rescan of the readers, for a grace period phase. + + srcutree.srcu_retry_check_delay [KNL] + Specifies number of microseconds of non-sleeping + delay between each non-sleeping poll of readers. + srcutree.small_contention_lim [KNL] Specifies the number of update-side contention events per jiffy will be tolerated before diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index d6b3f94b9f1f..0793c400d4b0 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -223,7 +223,7 @@ Module Loading Inter Module support -------------------- -Refer to the file kernel/module.c for more information. +Refer to the files in kernel/module/ for more information. Hardware Interfaces =================== diff --git a/Documentation/core-api/symbol-namespaces.rst b/Documentation/core-api/symbol-namespaces.rst index 5ad9e0abe42c..12e4aecdae94 100644 --- a/Documentation/core-api/symbol-namespaces.rst +++ b/Documentation/core-api/symbol-namespaces.rst @@ -51,8 +51,8 @@ namespace ``USB_STORAGE``, use:: The corresponding ksymtab entry struct ``kernel_symbol`` will have the member ``namespace`` set accordingly. A symbol that is exported without a namespace will refer to ``NULL``. There is no default namespace if none is defined. ``modpost`` -and kernel/module.c make use the namespace at build time or module load time, -respectively. +and kernel/module/main.c make use the namespace at build time or module load +time, respectively. 2.2 Using the DEFAULT_SYMBOL_NAMESPACE define ============================================= diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-engine.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-engine.yaml index c388ae5da1e4..c9c346e6228e 100644 --- a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-engine.yaml +++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-engine.yaml @@ -94,6 +94,7 @@ if: - allwinner,sun8i-a83t-display-engine - allwinner,sun8i-r40-display-engine - allwinner,sun9i-a80-display-engine + - allwinner,sun20i-d1-display-engine - allwinner,sun50i-a64-display-engine then: diff --git a/Documentation/devicetree/bindings/net/wireless/qca,ath9k.yaml b/Documentation/devicetree/bindings/net/wireless/qca,ath9k.yaml index 8cd0adbf7021..7029cb1f38ff 100644 --- a/Documentation/devicetree/bindings/net/wireless/qca,ath9k.yaml +++ b/Documentation/devicetree/bindings/net/wireless/qca,ath9k.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Atheros ath9k wireless devices Generic Binding maintainers: - - Kalle Valo <kvalo@codeaurora.org> + - Toke Høiland-Jørgensen <toke@toke.dk> description: | This node provides properties for configuring the ath9k wireless device. diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml index 8c01fdba134b..a677b056f112 100644 --- a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml +++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml @@ -9,7 +9,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Technologies ath11k wireless devices Generic Binding maintainers: - - Kalle Valo <kvalo@codeaurora.org> + - Kalle Valo <kvalo@kernel.org> description: | These are dt entries for Qualcomm Technologies, Inc. IEEE 802.11ax diff --git a/Documentation/devicetree/bindings/sound/qcom,lpass-cpu.yaml b/Documentation/devicetree/bindings/sound/qcom,lpass-cpu.yaml index e9a533080b32..ef18a572a1ff 100644 --- a/Documentation/devicetree/bindings/sound/qcom,lpass-cpu.yaml +++ b/Documentation/devicetree/bindings/sound/qcom,lpass-cpu.yaml @@ -25,12 +25,12 @@ properties: - qcom,sc7280-lpass-cpu reg: - minItems: 2 + minItems: 1 maxItems: 6 description: LPAIF core registers reg-names: - minItems: 2 + minItems: 1 maxItems: 6 clocks: @@ -42,12 +42,12 @@ properties: maxItems: 10 interrupts: - minItems: 2 + minItems: 1 maxItems: 4 description: LPAIF DMA buffer interrupt interrupt-names: - minItems: 2 + minItems: 1 maxItems: 4 qcom,adsp: diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 4d19b19bcc08..73a4176144b3 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -301,7 +301,7 @@ through which it can issue requests and negotiate:: void (*issue_read)(struct netfs_io_subrequest *subreq); bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, - struct folio *folio, void **_fsdata); + struct folio **foliop, void **_fsdata); void (*done)(struct netfs_io_request *rreq); }; @@ -381,8 +381,10 @@ The operations are as follows: allocated/grabbed the folio to be modified to allow the filesystem to flush conflicting state before allowing it to be modified. - It should return 0 if everything is now fine, -EAGAIN if the folio should be - regrabbed and any other error code to abort the operation. + It may unlock and discard the folio it was given and set the caller's folio + pointer to NULL. It should return 0 if everything is now fine (``*foliop`` + left set) or the op should be retried (``*foliop`` cleared) and any other + error code to abort the operation. * ``done`` diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst index 7da6c30ed596..316cfd8b1891 100644 --- a/Documentation/filesystems/overlayfs.rst +++ b/Documentation/filesystems/overlayfs.rst @@ -466,6 +466,10 @@ overlay filesystem and the value of st_ino for filesystem objects may not be persistent and could change even while the overlay filesystem is mounted, as summarized in the `Inode properties`_ table above. +4) "idmapped mounts" +When the upper or lower layers are idmapped mounts overlayfs will be mounted +without support for POSIX Access Control Lists (ACLs). This limitation will +eventually be lifted. Changes to underlying filesystems --------------------------------- diff --git a/Documentation/livepatch/module-elf-format.rst b/Documentation/livepatch/module-elf-format.rst index dbe9b400e39f..7347638895a0 100644 --- a/Documentation/livepatch/module-elf-format.rst +++ b/Documentation/livepatch/module-elf-format.rst @@ -210,11 +210,11 @@ module->symtab. ===================================== Normally, a stripped down copy of a module's symbol table (containing only "core" symbols) is made available through module->symtab (See layout_symtab() -in kernel/module.c). For livepatch modules, the symbol table copied into memory -on module load must be exactly the same as the symbol table produced when the -patch module was compiled. This is because the relocations in each livepatch -relocation section refer to their respective symbols with their symbol indices, -and the original symbol indices (and thus the symtab ordering) must be +in kernel/module/kallsyms.c). For livepatch modules, the symbol table copied +into memory on module load must be exactly the same as the symbol table produced +when the patch module was compiled. This is because the relocations in each +livepatch relocation section refer to their respective symbols with their symbol +indices, and the original symbol indices (and thus the symtab ordering) must be preserved in order for apply_relocate_add() to find the right symbol. For example, take this particular rela from a livepatch module::: diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index ed7fa76e7a40..d742ba6bd211 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -503,26 +503,108 @@ per-port PHY specific details: interface connection, MDIO bus location, etc. Driver development ================== -DSA switch drivers need to implement a dsa_switch_ops structure which will +DSA switch drivers need to implement a ``dsa_switch_ops`` structure which will contain the various members described below. -``register_switch_driver()`` registers this dsa_switch_ops in its internal list -of drivers to probe for. ``unregister_switch_driver()`` does the exact opposite. +Probing, registration and device lifetime +----------------------------------------- -Unless requested differently by setting the priv_size member accordingly, DSA -does not allocate any driver private context space. +DSA switches are regular ``device`` structures on buses (be they platform, SPI, +I2C, MDIO or otherwise). The DSA framework is not involved in their probing +with the device core. + +Switch registration from the perspective of a driver means passing a valid +``struct dsa_switch`` pointer to ``dsa_register_switch()``, usually from the +switch driver's probing function. The following members must be valid in the +provided structure: + +- ``ds->dev``: will be used to parse the switch's OF node or platform data. + +- ``ds->num_ports``: will be used to create the port list for this switch, and + to validate the port indices provided in the OF node. + +- ``ds->ops``: a pointer to the ``dsa_switch_ops`` structure holding the DSA + method implementations. + +- ``ds->priv``: backpointer to a driver-private data structure which can be + retrieved in all further DSA method callbacks. + +In addition, the following flags in the ``dsa_switch`` structure may optionally +be configured to obtain driver-specific behavior from the DSA core. Their +behavior when set is documented through comments in ``include/net/dsa.h``. + +- ``ds->vlan_filtering_is_global`` + +- ``ds->needs_standalone_vlan_filtering`` + +- ``ds->configure_vlan_while_not_filtering`` + +- ``ds->untag_bridge_pvid`` + +- ``ds->assisted_learning_on_cpu_port`` + +- ``ds->mtu_enforcement_ingress`` + +- ``ds->fdb_isolation`` + +Internally, DSA keeps an array of switch trees (group of switches) global to +the kernel, and attaches a ``dsa_switch`` structure to a tree on registration. +The tree ID to which the switch is attached is determined by the first u32 +number of the ``dsa,member`` property of the switch's OF node (0 if missing). +The switch ID within the tree is determined by the second u32 number of the +same OF property (0 if missing). Registering multiple switches with the same +switch ID and tree ID is illegal and will cause an error. Using platform data, +a single switch and a single switch tree is permitted. + +In case of a tree with multiple switches, probing takes place asymmetrically. +The first N-1 callers of ``dsa_register_switch()`` only add their ports to the +port list of the tree (``dst->ports``), each port having a backpointer to its +associated switch (``dp->ds``). Then, these switches exit their +``dsa_register_switch()`` call early, because ``dsa_tree_setup_routing_table()`` +has determined that the tree is not yet complete (not all ports referenced by +DSA links are present in the tree's port list). The tree becomes complete when +the last switch calls ``dsa_register_switch()``, and this triggers the effective +continuation of initialization (including the call to ``ds->ops->setup()``) for +all switches within that tree, all as part of the calling context of the last +switch's probe function. + +The opposite of registration takes place when calling ``dsa_unregister_switch()``, +which removes a switch's ports from the port list of the tree. The entire tree +is torn down when the first switch unregisters. + +It is mandatory for DSA switch drivers to implement the ``shutdown()`` callback +of their respective bus, and call ``dsa_switch_shutdown()`` from it (a minimal +version of the full teardown performed by ``dsa_unregister_switch()``). +The reason is that DSA keeps a reference on the master net device, and if the +driver for the master device decides to unbind on shutdown, DSA's reference +will block that operation from finalizing. + +Either ``dsa_switch_shutdown()`` or ``dsa_unregister_switch()`` must be called, +but not both, and the device driver model permits the bus' ``remove()`` method +to be called even if ``shutdown()`` was already called. Therefore, drivers are +expected to implement a mutual exclusion method between ``remove()`` and +``shutdown()`` by setting their drvdata to NULL after any of these has run, and +checking whether the drvdata is NULL before proceeding to take any action. + +After ``dsa_switch_shutdown()`` or ``dsa_unregister_switch()`` was called, no +further callbacks via the provided ``dsa_switch_ops`` may take place, and the +driver may free the data structures associated with the ``dsa_switch``. Switch configuration -------------------- -- ``tag_protocol``: this is to indicate what kind of tagging protocol is supported, - should be a valid value from the ``dsa_tag_protocol`` enum +- ``get_tag_protocol``: this is to indicate what kind of tagging protocol is + supported, should be a valid value from the ``dsa_tag_protocol`` enum. + The returned information does not have to be static; the driver is passed the + CPU port number, as well as the tagging protocol of a possibly stacked + upstream switch, in case there are hardware limitations in terms of supported + tag formats. -- ``probe``: probe routine which will be invoked by the DSA platform device upon - registration to test for the presence/absence of a switch device. For MDIO - devices, it is recommended to issue a read towards internal registers using - the switch pseudo-PHY and return whether this is a supported device. For other - buses, return a non-NULL string +- ``change_tag_protocol``: when the default tagging protocol has compatibility + problems with the master or other issues, the driver may support changing it + at runtime, either through a device tree property or through sysfs. In that + case, further calls to ``get_tag_protocol`` should report the protocol in + current use. - ``setup``: setup function for the switch, this function is responsible for setting up the ``dsa_switch_ops`` private structure with all it needs: register maps, @@ -535,7 +617,17 @@ Switch configuration fully configured and ready to serve any kind of request. It is recommended to issue a software reset of the switch during this setup function in order to avoid relying on what a previous software agent such as a bootloader/firmware - may have previously configured. + may have previously configured. The method responsible for undoing any + applicable allocations or operations done here is ``teardown``. + +- ``port_setup`` and ``port_teardown``: methods for initialization and + destruction of per-port data structures. It is mandatory for some operations + such as registering and unregistering devlink port regions to be done from + these methods, otherwise they are optional. A port will be torn down only if + it has been previously set up. It is possible for a port to be set up during + probing only to be torn down immediately afterwards, for example in case its + PHY cannot be found. In this case, probing of the DSA switch continues + without that particular port. PHY devices and link management ------------------------------- @@ -635,26 +727,198 @@ Power management ``BR_STATE_DISABLED`` and propagating changes to the hardware if this port is disabled while being a bridge member +Address databases +----------------- + +Switching hardware is expected to have a table for FDB entries, however not all +of them are active at the same time. An address database is the subset (partition) +of FDB entries that is active (can be matched by address learning on RX, or FDB +lookup on TX) depending on the state of the port. An address database may +occasionally be called "FID" (Filtering ID) in this document, although the +underlying implementation may choose whatever is available to the hardware. + +For example, all ports that belong to a VLAN-unaware bridge (which is +*currently* VLAN-unaware) are expected to learn source addresses in the +database associated by the driver with that bridge (and not with other +VLAN-unaware bridges). During forwarding and FDB lookup, a packet received on a +VLAN-unaware bridge port should be able to find a VLAN-unaware FDB entry having +the same MAC DA as the packet, which is present on another port member of the +same bridge. At the same time, the FDB lookup process must be able to not find +an FDB entry having the same MAC DA as the packet, if that entry points towards +a port which is a member of a different VLAN-unaware bridge (and is therefore +associated with a different address database). + +Similarly, each VLAN of each offloaded VLAN-aware bridge should have an +associated address database, which is shared by all ports which are members of +that VLAN, but not shared by ports belonging to different bridges that are +members of the same VID. + +In this context, a VLAN-unaware database means that all packets are expected to +match on it irrespective of VLAN ID (only MAC address lookup), whereas a +VLAN-aware database means that packets are supposed to match based on the VLAN +ID from the classified 802.1Q header (or the pvid if untagged). + +At the bridge layer, VLAN-unaware FDB entries have the special VID value of 0, +whereas VLAN-aware FDB entries have non-zero VID values. Note that a +VLAN-unaware bridge may have VLAN-aware (non-zero VID) FDB entries, and a +VLAN-aware bridge may have VLAN-unaware FDB entries. As in hardware, the +software bridge keeps separate address databases, and offloads to hardware the +FDB entries belonging to these databases, through switchdev, asynchronously +relative to the moment when the databases become active or inactive. + +When a user port operates in standalone mode, its driver should configure it to +use a separate database called a port private database. This is different from +the databases described above, and should impede operation as standalone port +(packet in, packet out to the CPU port) as little as possible. For example, +on ingress, it should not attempt to learn the MAC SA of ingress traffic, since +learning is a bridging layer service and this is a standalone port, therefore +it would consume useless space. With no address learning, the port private +database should be empty in a naive implementation, and in this case, all +received packets should be trivially flooded to the CPU port. + +DSA (cascade) and CPU ports are also called "shared" ports because they service +multiple address databases, and the database that a packet should be associated +to is usually embedded in the DSA tag. This means that the CPU port may +simultaneously transport packets coming from a standalone port (which were +classified by hardware in one address database), and from a bridge port (which +were classified to a different address database). + +Switch drivers which satisfy certain criteria are able to optimize the naive +configuration by removing the CPU port from the flooding domain of the switch, +and just program the hardware with FDB entries pointing towards the CPU port +for which it is known that software is interested in those MAC addresses. +Packets which do not match a known FDB entry will not be delivered to the CPU, +which will save CPU cycles required for creating an skb just to drop it. + +DSA is able to perform host address filtering for the following kinds of +addresses: + +- Primary unicast MAC addresses of ports (``dev->dev_addr``). These are + associated with the port private database of the respective user port, + and the driver is notified to install them through ``port_fdb_add`` towards + the CPU port. + +- Secondary unicast and multicast MAC addresses of ports (addresses added + through ``dev_uc_add()`` and ``dev_mc_add()``). These are also associated + with the port private database of the respective user port. + +- Local/permanent bridge FDB entries (``BR_FDB_LOCAL``). These are the MAC + addresses of the bridge ports, for which packets must be terminated locally + and not forwarded. They are associated with the address database for that + bridge. + +- Static bridge FDB entries installed towards foreign (non-DSA) interfaces + present in the same bridge as some DSA switch ports. These are also + associated with the address database for that bridge. + +- Dynamically learned FDB entries on foreign interfaces present in the same + bridge as some DSA switch ports, only if ``ds->assisted_learning_on_cpu_port`` + is set to true by the driver. These are associated with the address database + for that bridge. + +For various operations detailed below, DSA provides a ``dsa_db`` structure +which can be of the following types: + +- ``DSA_DB_PORT``: the FDB (or MDB) entry to be installed or deleted belongs to + the port private database of user port ``db->dp``. +- ``DSA_DB_BRIDGE``: the entry belongs to one of the address databases of bridge + ``db->bridge``. Separation between the VLAN-unaware database and the per-VID + databases of this bridge is expected to be done by the driver. +- ``DSA_DB_LAG``: the entry belongs to the address database of LAG ``db->lag``. + Note: ``DSA_DB_LAG`` is currently unused and may be removed in the future. + +The drivers which act upon the ``dsa_db`` argument in ``port_fdb_add``, +``port_mdb_add`` etc should declare ``ds->fdb_isolation`` as true. + +DSA associates each offloaded bridge and each offloaded LAG with a one-based ID +(``struct dsa_bridge :: num``, ``struct dsa_lag :: id``) for the purposes of +refcounting addresses on shared ports. Drivers may piggyback on DSA's numbering +scheme (the ID is readable through ``db->bridge.num`` and ``db->lag.id`` or may +implement their own. + +Only the drivers which declare support for FDB isolation are notified of FDB +entries on the CPU port belonging to ``DSA_DB_PORT`` databases. +For compatibility/legacy reasons, ``DSA_DB_BRIDGE`` addresses are notified to +drivers even if they do not support FDB isolation. However, ``db->bridge.num`` +and ``db->lag.id`` are always set to 0 in that case (to denote the lack of +isolation, for refcounting purposes). + +Note that it is not mandatory for a switch driver to implement physically +separate address databases for each standalone user port. Since FDB entries in +the port private databases will always point to the CPU port, there is no risk +for incorrect forwarding decisions. In this case, all standalone ports may +share the same database, but the reference counting of host-filtered addresses +(not deleting the FDB entry for a port's MAC address if it's still in use by +another port) becomes the responsibility of the driver, because DSA is unaware +that the port databases are in fact shared. This can be achieved by calling +``dsa_fdb_present_in_other_db()`` and ``dsa_mdb_present_in_other_db()``. +The down side is that the RX filtering lists of each user port are in fact +shared, which means that user port A may accept a packet with a MAC DA it +shouldn't have, only because that MAC address was in the RX filtering list of +user port B. These packets will still be dropped in software, however. + Bridge layer ------------ +Offloading the bridge forwarding plane is optional and handled by the methods +below. They may be absent, return -EOPNOTSUPP, or ``ds->max_num_bridges`` may +be non-zero and exceeded, and in this case, joining a bridge port is still +possible, but the packet forwarding will take place in software, and the ports +under a software bridge must remain configured in the same way as for +standalone operation, i.e. have all bridging service functions (address +learning etc) disabled, and send all received packets to the CPU port only. + +Concretely, a port starts offloading the forwarding plane of a bridge once it +returns success to the ``port_bridge_join`` method, and stops doing so after +``port_bridge_leave`` has been called. Offloading the bridge means autonomously +learning FDB entries in accordance with the software bridge port's state, and +autonomously forwarding (or flooding) received packets without CPU intervention. +This is optional even when offloading a bridge port. Tagging protocol drivers +are expected to call ``dsa_default_offload_fwd_mark(skb)`` for packets which +have already been autonomously forwarded in the forwarding domain of the +ingress switch port. DSA, through ``dsa_port_devlink_setup()``, considers all +switch ports part of the same tree ID to be part of the same bridge forwarding +domain (capable of autonomous forwarding to each other). + +Offloading the TX forwarding process of a bridge is a distinct concept from +simply offloading its forwarding plane, and refers to the ability of certain +driver and tag protocol combinations to transmit a single skb coming from the +bridge device's transmit function to potentially multiple egress ports (and +thereby avoid its cloning in software). + +Packets for which the bridge requests this behavior are called data plane +packets and have ``skb->offload_fwd_mark`` set to true in the tag protocol +driver's ``xmit`` function. Data plane packets are subject to FDB lookup, +hardware learning on the CPU port, and do not override the port STP state. +Additionally, replication of data plane packets (multicast, flooding) is +handled in hardware and the bridge driver will transmit a single skb for each +packet that may or may not need replication. + +When the TX forwarding offload is enabled, the tag protocol driver is +responsible to inject packets into the data plane of the hardware towards the +correct bridging domain (FID) that the port is a part of. The port may be +VLAN-unaware, and in this case the FID must be equal to the FID used by the +driver for its VLAN-unaware address database associated with that bridge. +Alternatively, the bridge may be VLAN-aware, and in that case, it is guaranteed +that the packet is also VLAN-tagged with the VLAN ID that the bridge processed +this packet in. It is the responsibility of the hardware to untag the VID on +the egress-untagged ports, or keep the tag on the egress-tagged ones. + - ``port_bridge_join``: bridge layer function invoked when a given switch port is added to a bridge, this function should do what's necessary at the switch level to permit the joining port to be added to the relevant logical domain for it to ingress/egress traffic with other members of the bridge. + By setting the ``tx_fwd_offload`` argument to true, the TX forwarding process + of this bridge is also offloaded. - ``port_bridge_leave``: bridge layer function invoked when a given switch port is removed from a bridge, this function should do what's necessary at the switch level to deny the leaving port from ingress/egress traffic from the - remaining bridge members. When the port leaves the bridge, it should be aged - out at the switch hardware for the switch to (re) learn MAC addresses behind - this port. + remaining bridge members. - ``port_stp_state_set``: bridge layer function invoked when a given switch port STP state is computed by the bridge layer and should be propagated to switch - hardware to forward/block/learn traffic. The switch driver is responsible for - computing a STP state change based on current and asked parameters and perform - the relevant ageing based on the intersection results + hardware to forward/block/learn traffic. - ``port_bridge_flags``: bridge layer function invoked when a port must configure its settings for e.g. flooding of unknown traffic or source address @@ -667,21 +931,11 @@ Bridge layer CPU port, and flooding towards the CPU port should also be enabled, due to a lack of an explicit address filtering mechanism in the DSA core. -- ``port_bridge_tx_fwd_offload``: bridge layer function invoked after - ``port_bridge_join`` when a driver sets ``ds->num_fwd_offloading_bridges`` to - a non-zero value. Returning success in this function activates the TX - forwarding offload bridge feature for this port, which enables the tagging - protocol driver to inject data plane packets towards the bridging domain that - the port is a part of. Data plane packets are subject to FDB lookup, hardware - learning on the CPU port, and do not override the port STP state. - Additionally, replication of data plane packets (multicast, flooding) is - handled in hardware and the bridge driver will transmit a single skb for each - packet that needs replication. The method is provided as a configuration - point for drivers that need to configure the hardware for enabling this - feature. - -- ``port_bridge_tx_fwd_unoffload``: bridge layer function invoked when a driver - leaves a bridge port which had the TX forwarding offload feature enabled. +- ``port_fast_age``: bridge layer function invoked when flushing the + dynamically learned FDB entries on the port is necessary. This is called when + transitioning from an STP state where learning should take place to an STP + state where it shouldn't, or when leaving a bridge, or when address learning + is turned off via ``port_bridge_flags``. Bridge VLAN filtering --------------------- @@ -697,55 +951,44 @@ Bridge VLAN filtering allowed. - ``port_vlan_add``: bridge layer function invoked when a VLAN is configured - (tagged or untagged) for the given switch port. If the operation is not - supported by the hardware, this function should return ``-EOPNOTSUPP`` to - inform the bridge code to fallback to a software implementation. + (tagged or untagged) for the given switch port. The CPU port becomes a member + of a VLAN only if a foreign bridge port is also a member of it (and + forwarding needs to take place in software), or the VLAN is installed to the + VLAN group of the bridge device itself, for termination purposes + (``bridge vlan add dev br0 vid 100 self``). VLANs on shared ports are + reference counted and removed when there is no user left. Drivers do not need + to manually install a VLAN on the CPU port. - ``port_vlan_del``: bridge layer function invoked when a VLAN is removed from the given switch port -- ``port_vlan_dump``: bridge layer function invoked with a switchdev callback - function that the driver has to call for each VLAN the given port is a member - of. A switchdev object is used to carry the VID and bridge flags. - - ``port_fdb_add``: bridge layer function invoked when the bridge wants to install a Forwarding Database entry, the switch hardware should be programmed with the specified address in the specified VLAN Id in the forwarding database - associated with this VLAN ID. If the operation is not supported, this - function should return ``-EOPNOTSUPP`` to inform the bridge code to fallback to - a software implementation. - -.. note:: VLAN ID 0 corresponds to the port private database, which, in the context - of DSA, would be its port-based VLAN, used by the associated bridge device. + associated with this VLAN ID. - ``port_fdb_del``: bridge layer function invoked when the bridge wants to remove a Forwarding Database entry, the switch hardware should be programmed to delete the specified MAC address from the specified VLAN ID if it was mapped into this port forwarding database -- ``port_fdb_dump``: bridge layer function invoked with a switchdev callback - function that the driver has to call for each MAC address known to be behind - the given port. A switchdev object is used to carry the VID and FDB info. +- ``port_fdb_dump``: bridge bypass function invoked by ``ndo_fdb_dump`` on the + physical DSA port interfaces. Since DSA does not attempt to keep in sync its + hardware FDB entries with the software bridge, this method is implemented as + a means to view the entries visible on user ports in the hardware database. + The entries reported by this function have the ``self`` flag in the output of + the ``bridge fdb show`` command. - ``port_mdb_add``: bridge layer function invoked when the bridge wants to install - a multicast database entry. If the operation is not supported, this function - should return ``-EOPNOTSUPP`` to inform the bridge code to fallback to a - software implementation. The switch hardware should be programmed with the + a multicast database entry. The switch hardware should be programmed with the specified address in the specified VLAN ID in the forwarding database associated with this VLAN ID. -.. note:: VLAN ID 0 corresponds to the port private database, which, in the context - of DSA, would be its port-based VLAN, used by the associated bridge device. - - ``port_mdb_del``: bridge layer function invoked when the bridge wants to remove a multicast database entry, the switch hardware should be programmed to delete the specified MAC address from the specified VLAN ID if it was mapped into this port forwarding database. -- ``port_mdb_dump``: bridge layer function invoked with a switchdev callback - function that the driver has to call for each MAC address known to be behind - the given port. A switchdev object is used to carry the VID and MDB info. - Link aggregation ---------------- diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 9f41961d11d5..66c72230eaad 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1052,11 +1052,7 @@ udp_rmem_min - INTEGER Default: 4K udp_wmem_min - INTEGER - Minimal size of send buffer used by UDP sockets in moderation. - Each UDP socket is able to use the size for sending data, even if - total pages of UDP sockets exceed udp_mem pressure. The unit is byte. - - Default: 4K + UDP does not have tx memory accounting and this tunable has no effect. RAW variables ============= @@ -1085,7 +1081,7 @@ cipso_cache_enable - BOOLEAN cipso_cache_bucket_size - INTEGER The CIPSO label cache consists of a fixed size hash table with each hash bucket containing a number of cache entries. This variable limits - the number of entries in each hash bucket; the larger the value the + the number of entries in each hash bucket; the larger the value is, the more CIPSO label mappings that can be cached. When the number of entries in a given hash bucket reaches this limit adding new entries causes the oldest entry in the bucket to be removed to make room. @@ -1179,7 +1175,7 @@ ip_autobind_reuse - BOOLEAN option should only be set by experts. Default: 0 -ip_dynaddr - BOOLEAN +ip_dynaddr - INTEGER If set non-zero, enables support for dynamic addresses. If set to a non-zero value larger than 1, a kernel log message will be printed when dynamic address rewriting diff --git a/Documentation/sound/soc/dai.rst b/Documentation/sound/soc/dai.rst index 009b07e5a0f3..bf8431386d26 100644 --- a/Documentation/sound/soc/dai.rst +++ b/Documentation/sound/soc/dai.rst @@ -10,7 +10,7 @@ AC97 ==== AC97 is a five wire interface commonly found on many PC sound cards. It is -now also popular in many portable devices. This DAI has a reset line and time +now also popular in many portable devices. This DAI has a RESET line and time multiplexes its data on its SDATA_OUT (playback) and SDATA_IN (capture) lines. The bit clock (BCLK) is always driven by the CODEC (usually 12.288MHz) and the frame (FRAME) (usually 48kHz) is always driven by the controller. Each AC97 diff --git a/Documentation/translations/it_IT/core-api/symbol-namespaces.rst b/Documentation/translations/it_IT/core-api/symbol-namespaces.rst index 42f5d04e38ec..0f6898860d6d 100644 --- a/Documentation/translations/it_IT/core-api/symbol-namespaces.rst +++ b/Documentation/translations/it_IT/core-api/symbol-namespaces.rst @@ -50,9 +50,9 @@ Di conseguenza, nella tabella dei simboli del kernel ci sarà una voce rappresentata dalla struttura ``kernel_symbol`` che avrà il campo ``namespace`` (spazio dei nomi) impostato. Un simbolo esportato senza uno spazio dei nomi avrà questo campo impostato a ``NULL``. Non esiste uno spazio dei nomi -di base. Il programma ``modpost`` e il codice in kernel/module.c usano lo spazio -dei nomi, rispettivamente, durante la compilazione e durante il caricamento -di un modulo. +di base. Il programma ``modpost`` e il codice in kernel/module/main.c usano lo +spazio dei nomi, rispettivamente, durante la compilazione e durante il +caricamento di un modulo. 2.2 Usare il simbolo di preprocessore DEFAULT_SYMBOL_NAMESPACE ============================================================== diff --git a/Documentation/translations/zh_CN/core-api/kernel-api.rst b/Documentation/translations/zh_CN/core-api/kernel-api.rst index e45fe80d1cd8..962d31d019d7 100644 --- a/Documentation/translations/zh_CN/core-api/kernel-api.rst +++ b/Documentation/translations/zh_CN/core-api/kernel-api.rst @@ -224,7 +224,7 @@ kernel/kmod.c 模块接口支持 ------------ -更多信息请参考文件kernel/module.c。 +更多信息请参阅kernel/module/目录下的文件。 硬件接口 ======== diff --git a/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst b/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst index 6abf7ed534ca..bb16f0611046 100644 --- a/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst +++ b/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst @@ -52,7 +52,7 @@ 相应的 ksymtab 条目结构体 ``kernel_symbol`` 将有相应的成员 ``命名空间`` 集。 导出时未指明命名空间的符号将指向 ``NULL`` 。如果没有定义命名空间，则默认没有。 -``modpost`` 和kernel/module.c分别在构建时或模块加载时使用名称空间。 +``modpost`` 和kernel/module/main.c分别在构建时或模块加载时使用名称空间。 2.2 使用DEFAULT_SYMBOL_NAMESPACE定义 ==================================== diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 11e00a46c610..98a283930307 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5657,7 +5657,8 @@ by a string of size ``name_size``. #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) - #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES + #define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) + #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN #define KVM_STATS_BASE_SHIFT 8 #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) @@ -5702,14 +5703,13 @@ Bits 0-3 of ``flags`` encode the type: by the ``hist_param`` field. The range of the Nth bucket (1 <= N < ``size``) is [``hist_param``*(N-1), ``hist_param``*N), while the range of the last bucket is [``hist_param``*(``size``-1), +INF). (+INF means positive infinity - value.) The bucket value indicates how many samples fell in the bucket's range. + value.) * ``KVM_STATS_TYPE_LOG_HIST`` The statistic is reported as a logarithmic histogram. The number of buckets is specified by the ``size`` field. The range of the first bucket is [0, 1), while the range of the last bucket is [pow(2, ``size``-2), +INF). Otherwise, The Nth bucket (1 < N < ``size``) covers - [pow(2, N-2), pow(2, N-1)). The bucket value indicates how many samples fell - in the bucket's range. + [pow(2, N-2), pow(2, N-1)). Bits 4-7 of ``flags`` encode the unit: @@ -5724,6 +5724,15 @@ Bits 4-7 of ``flags`` encode the unit: It indicates that the statistics data is used to measure time or latency. * ``KVM_STATS_UNIT_CYCLES`` It indicates that the statistics data is used to measure CPU clock cycles. + * ``KVM_STATS_UNIT_BOOLEAN`` + It indicates that the statistic will always be either 0 or 1. Boolean + statistics of "peak" type will never go back from 1 to 0. Boolean + statistics can be linear histograms (with two buckets) but not logarithmic + histograms. + +Note that, in the case of histograms, the unit applies to the bucket +ranges, while the bucket value indicates how many samples fell in the +bucket's range. Bits 8-11 of ``flags``, together with ``exponent``, encode the scale of the unit: @@ -5746,7 +5755,7 @@ the corresponding statistics data. The ``bucket_size`` field is used as a parameter for histogram statistics data. It is only used by linear histogram statistics data, specifying the size of a -bucket. +bucket in the unit expressed by bits 4-11 of ``flags`` together with ``exponent``. The ``name`` field is the name string of the statistics data. The name string starts at the end of ``struct kvm_stats_desc``. The maximum length including diff --git a/MAINTAINERS b/MAINTAINERS index f679152bdbad..08620b9a44fc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1038,6 +1038,7 @@ F: arch/arm64/boot/dts/amd/ AMD XGBE DRIVER M: Tom Lendacky <thomas.lendacky@amd.com> +M: "Shyam Sundar S K" <Shyam-sundar.S-k@amd.com> L: netdev@vger.kernel.org S: Supported F: arch/arm64/boot/dts/amd/amd-seattle-xgbe*.dtsi @@ -2497,10 +2498,8 @@ F: drivers/power/reset/oxnas-restart.c N: oxnas ARM/PALM TREO SUPPORT -M: Tomas Cech <sleep_walker@suse.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained -W: http://hackndev.com +S: Orphan F: arch/arm/mach-pxa/palmtreo.* ARM/PALMTX,PALMT5,PALMLD,PALMTE2,PALMTC SUPPORT @@ -7774,9 +7773,6 @@ F: include/linux/fs.h F: include/linux/fs_types.h F: include/uapi/linux/fs.h F: include/uapi/linux/openat2.h -X: fs/io-wq.c -X: fs/io-wq.h -X: fs/io_uring.c FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER M: Riku Voipio <riku.voipio@iki.fi> @@ -10477,9 +10473,7 @@ L: io-uring@vger.kernel.org S: Maintained T: git git://git.kernel.dk/linux-block T: git git://git.kernel.dk/liburing -F: fs/io-wq.c -F: fs/io-wq.h -F: fs/io_uring.c +F: io_uring/ F: include/linux/io_uring.h F: include/uapi/linux/io_uring.h F: tools/io_uring/ @@ -14363,7 +14357,8 @@ S: Maintained F: drivers/net/phy/nxp-c45-tja11xx.c NXP FSPI DRIVER -M: Ashish Kumar <ashish.kumar@nxp.com> +M: Han Xu <han.xu@nxp.com> +M: Haibo Chen <haibo.chen@nxp.com> R: Yogesh Gaur <yogeshgaur.83@gmail.com> L: linux-spi@vger.kernel.org S: Maintained @@ -15849,7 +15844,7 @@ PIN CONTROLLER - FREESCALE M: Dong Aisheng <aisheng.dong@nxp.com> M: Fabio Estevam <festevam@gmail.com> M: Shawn Guo <shawnguo@kernel.org> -M: Stefan Agner <stefan@agner.ch> +M: Jacky Bai <ping.bai@nxp.com> R: Pengutronix Kernel Team <kernel@pengutronix.de> L: linux-gpio@vger.kernel.org S: Maintained @@ -17273,12 +17268,15 @@ N: riscv K: riscv RISC-V/MICROCHIP POLARFIRE SOC SUPPORT -M: Lewis Hanly <lewis.hanly@microchip.com> M: Conor Dooley <conor.dooley@microchip.com> +M: Daire McNamara <daire.mcnamara@microchip.com> L: linux-riscv@lists.infradead.org S: Supported F: arch/riscv/boot/dts/microchip/ +F: drivers/char/hw_random/mpfs-rng.c +F: drivers/clk/microchip/clk-mpfs.c F: drivers/mailbox/mailbox-mpfs.c +F: drivers/pci/controller/pcie-microchip-host.c F: drivers/soc/microchip/ F: include/soc/microchip/mpfs.h @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc8 NAME = Superb Owl # *DOCUMENTATION* @@ -1097,6 +1097,7 @@ export MODULES_NSDEPS := $(extmod_prefix)modules.nsdeps ifeq ($(KBUILD_EXTMOD),) core-y += kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ core-$(CONFIG_BLOCK) += block/ +core-$(CONFIG_IO_URING) += io_uring/ vmlinux-dirs := $(patsubst %/,%,$(filter %/, \ $(core-y) $(core-m) $(drivers-y) $(drivers-m) \ diff --git a/arch/Kconfig b/arch/Kconfig index fcf9a41a4ef5..71b9272acb28 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -438,6 +438,13 @@ config MMU_GATHER_PAGE_SIZE config MMU_GATHER_NO_RANGE bool + select MMU_GATHER_MERGE_VMAS + +config MMU_GATHER_NO_FLUSH_CACHE + bool + +config MMU_GATHER_MERGE_VMAS + bool config MMU_GATHER_NO_GATHER bool diff --git a/arch/arm/boot/dts/imx6qdl-ts7970.dtsi b/arch/arm/boot/dts/imx6qdl-ts7970.dtsi index fded07f370b3..d6ba4b2a60f6 100644 --- a/arch/arm/boot/dts/imx6qdl-ts7970.dtsi +++ b/arch/arm/boot/dts/imx6qdl-ts7970.dtsi @@ -226,7 +226,7 @@ reg = <0x28>; #gpio-cells = <2>; gpio-controller; - ngpio = <32>; + ngpios = <62>; }; sgtl5000: codec@a { diff --git a/arch/arm/boot/dts/imx6ull-colibri.dtsi b/arch/arm/boot/dts/imx6ull-colibri.dtsi index 15621e03fa4d..2c3ae715c683 100644 --- a/arch/arm/boot/dts/imx6ull-colibri.dtsi +++ b/arch/arm/boot/dts/imx6ull-colibri.dtsi @@ -166,7 +166,7 @@ atmel_mxt_ts: touchscreen@4a { compatible = "atmel,maxtouch"; pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_atmel_conn>; + pinctrl-0 = <&pinctrl_atmel_conn &pinctrl_atmel_snvs_conn>; reg = <0x4a>; interrupt-parent = <&gpio5>; interrupts = <4 IRQ_TYPE_EDGE_FALLING>; /* SODIMM 107 / INT */ @@ -331,7 +331,6 @@ pinctrl_atmel_conn: atmelconngrp { fsl,pins = < MX6UL_PAD_JTAG_MOD__GPIO1_IO10 0xb0a0 /* SODIMM 106 */ - MX6ULL_PAD_SNVS_TAMPER4__GPIO5_IO04 0xb0a0 /* SODIMM 107 */ >; }; @@ -684,6 +683,12 @@ }; &iomuxc_snvs { + pinctrl_atmel_snvs_conn: atmelsnvsconngrp { + fsl,pins = < + MX6ULL_PAD_SNVS_TAMPER4__GPIO5_IO04 0xb0a0 /* SODIMM 107 */ + >; + }; + pinctrl_snvs_gpio1: snvsgpio1grp { fsl,pins = < MX6ULL_PAD_SNVS_TAMPER6__GPIO5_IO06 0x110a0 /* SODIMM 93 */ diff --git a/arch/arm/boot/dts/lan966x-kontron-kswitch-d10-mmt.dtsi b/arch/arm/boot/dts/lan966x-kontron-kswitch-d10-mmt.dtsi index 4cab1b3b3b29..725dcf707b31 100644 --- a/arch/arm/boot/dts/lan966x-kontron-kswitch-d10-mmt.dtsi +++ b/arch/arm/boot/dts/lan966x-kontron-kswitch-d10-mmt.dtsi @@ -87,22 +87,22 @@ phy4: ethernet-phy@5 { reg = <5>; - coma-mode-gpios = <&gpio 37 GPIO_ACTIVE_HIGH>; + coma-mode-gpios = <&gpio 37 GPIO_OPEN_DRAIN>; }; phy5: ethernet-phy@6 { reg = <6>; - coma-mode-gpios = <&gpio 37 GPIO_ACTIVE_HIGH>; + coma-mode-gpios = <&gpio 37 GPIO_OPEN_DRAIN>; }; phy6: ethernet-phy@7 { reg = <7>; - coma-mode-gpios = <&gpio 37 GPIO_ACTIVE_HIGH>; + coma-mode-gpios = <&gpio 37 GPIO_OPEN_DRAIN>; }; phy7: ethernet-phy@8 { reg = <8>; - coma-mode-gpios = <&gpio 37 GPIO_ACTIVE_HIGH>; + coma-mode-gpios = <&gpio 37 GPIO_OPEN_DRAIN>; }; }; diff --git a/arch/arm/boot/dts/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom-msm8974.dtsi index 814ad0b46232..c3b8a6d63027 100644 --- a/arch/arm/boot/dts/qcom-msm8974.dtsi +++ b/arch/arm/boot/dts/qcom-msm8974.dtsi @@ -506,6 +506,8 @@ interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_UART2_APPS_CLK>, <&gcc GCC_BLSP1_AHB_CLK>; clock-names = "core", "iface"; + pinctrl-names = "default"; + pinctrl-0 = <&blsp1_uart2_default>; status = "disabled"; }; @@ -581,6 +583,9 @@ interrupts = <GIC_SPI 113 IRQ_TYPE_NONE>; clocks = <&gcc GCC_BLSP2_UART1_APPS_CLK>, <&gcc GCC_BLSP2_AHB_CLK>; clock-names = "core", "iface"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&blsp2_uart1_default>; + pinctrl-1 = <&blsp2_uart1_sleep>; status = "disabled"; }; @@ -599,6 +604,8 @@ interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP2_UART4_APPS_CLK>, <&gcc GCC_BLSP2_AHB_CLK>; clock-names = "core", "iface"; + pinctrl-names = "default"; + pinctrl-0 = <&blsp2_uart4_default>; status = "disabled"; }; @@ -639,6 +646,9 @@ interrupts = <0 106 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP2_QUP6_I2C_APPS_CLK>, <&gcc GCC_BLSP2_AHB_CLK>; clock-names = "core", "iface"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&blsp2_i2c6_default>; + pinctrl-1 = <&blsp2_i2c6_sleep>; #address-cells = <1>; #size-cells = <0>; }; @@ -1256,7 +1266,7 @@ }; }; - blsp1_uart2_active: blsp1-uart2-active { + blsp1_uart2_default: blsp1-uart2-default { rx { pins = "gpio5"; function = "blsp_uart2"; @@ -1272,7 +1282,7 @@ }; }; - blsp2_uart1_active: blsp2-uart1-active { + blsp2_uart1_default: blsp2-uart1-default { tx-rts { pins = "gpio41", "gpio44"; function = "blsp_uart7"; @@ -1295,7 +1305,7 @@ bias-pull-down; }; - blsp2_uart4_active: blsp2-uart4-active { + blsp2_uart4_default: blsp2-uart4-default { tx-rts { pins = "gpio53", "gpio56"; function = "blsp_uart10"; @@ -1406,7 +1416,19 @@ bias-pull-up; }; - /* BLSP2_I2C6 info is missing - nobody uses it though? */ + blsp2_i2c6_default: blsp2-i2c6-default { + pins = "gpio87", "gpio88"; + function = "blsp_i2c12"; + drive-strength = <2>; + bias-disable; + }; + + blsp2_i2c6_sleep: blsp2-i2c6-sleep { + pins = "gpio87", "gpio88"; + function = "blsp_i2c12"; + drive-strength = <2>; + bias-pull-up; + }; spi8_default: spi8_default { mosi { diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi index 89c71d419f82..659a17fc755c 100644 --- a/arch/arm/boot/dts/sama5d2.dtsi +++ b/arch/arm/boot/dts/sama5d2.dtsi @@ -1124,7 +1124,7 @@ clocks = <&pmc PMC_TYPE_PERIPHERAL 55>, <&pmc PMC_TYPE_GCK 55>; clock-names = "pclk", "gclk"; assigned-clocks = <&pmc PMC_TYPE_CORE PMC_I2S1_MUX>; - assigned-parrents = <&pmc PMC_TYPE_GCK 55>; + assigned-clock-parents = <&pmc PMC_TYPE_GCK 55>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts b/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts index f19ed981da9d..3706216ffb40 100644 --- a/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts +++ b/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts @@ -169,7 +169,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "mxicy,mx25l1606e", "winbond,w25q128"; + compatible = "mxicy,mx25l1606e", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <40000000>; }; diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h index f1d0a7807cd0..41536feb4392 100644 --- a/arch/arm/include/asm/domain.h +++ b/arch/arm/include/asm/domain.h @@ -112,19 +112,6 @@ static __always_inline void set_domain(unsigned int val) } #endif -#ifdef CONFIG_CPU_USE_DOMAINS -#define modify_domain(dom,type) \ - do { \ - unsigned int domain = get_domain(); \ - domain &= ~domain_mask(dom); \ - domain = domain | domain_val(dom, type); \ - set_domain(domain); \ - } while (0) - -#else -static inline void modify_domain(unsigned dom, unsigned type) { } -#endif - /* * Generate the T (user) versions of the LDR/STR and related * instructions (inline assembly) diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h index 92282558caf7..2b8970d8e5a2 100644 --- a/arch/arm/include/asm/mach/map.h +++ b/arch/arm/include/asm/mach/map.h @@ -27,6 +27,7 @@ enum { MT_HIGH_VECTORS, MT_MEMORY_RWX, MT_MEMORY_RW, + MT_MEMORY_RO, MT_ROM, MT_MEMORY_RWX_NONCACHED, MT_MEMORY_RW_DTCM, diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h index 93051e2f402c..1408a6a15d0e 100644 --- a/arch/arm/include/asm/ptrace.h +++ b/arch/arm/include/asm/ptrace.h @@ -163,5 +163,31 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs) ((current_stack_pointer | (THREAD_SIZE - 1)) - 7) - 1; \ }) + +/* + * Update ITSTATE after normal execution of an IT block instruction. + * + * The 8 IT state bits are split into two parts in CPSR: + * ITSTATE<1:0> are in CPSR<26:25> + * ITSTATE<7:2> are in CPSR<15:10> + */ +static inline unsigned long it_advance(unsigned long cpsr) +{ + if ((cpsr & 0x06000400) == 0) { + /* ITSTATE<2:0> == 0 means end of IT block, so clear IT state */ + cpsr &= ~PSR_IT_MASK; + } else { + /* We need to shift left ITSTATE<4:0> */ + const unsigned long mask = 0x06001c00; /* Mask ITSTATE<4:0> */ + unsigned long it = cpsr & mask; + it <<= 1; + it |= it >> (27 - 10); /* Carry ITSTATE<2> to correct place */ + it &= mask; + cpsr &= ~mask; + cpsr |= it; + } + return cpsr; +} + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 7aa3ded4af92..6a447ac67d80 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -302,6 +302,7 @@ local_restart: b ret_fast_syscall #endif ENDPROC(vector_swi) + .ltorg /* * This is the really slow path. We're going to be doing diff --git a/arch/arm/mach-rockchip/pm.c b/arch/arm/mach-rockchip/pm.c index 87389d9456b9..30d781d80fe0 100644 --- a/arch/arm/mach-rockchip/pm.c +++ b/arch/arm/mach-rockchip/pm.c @@ -311,7 +311,7 @@ void __init rockchip_suspend_init(void) &match); if (!match) { pr_err("Failed to find PMU node\n"); - return; + goto out_put; } pm_data = (struct rockchip_pm_data *) match->data; @@ -320,9 +320,12 @@ void __init rockchip_suspend_init(void) if (ret) { pr_err("%s: matches init error %d\n", __func__, ret); - return; + goto out_put; } } suspend_set_ops(pm_data->ops); + +out_put: + of_node_put(np); } diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index a3a4589ec73b..fc439c2c16f8 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -631,7 +631,11 @@ config CPU_USE_DOMAINS bool help This option enables or disables the use of domain switching - via the set_fs() function. + using the DACR (domain access control register) to protect memory + domains from each other. In Linux we use three domains: kernel, user + and IO. The domains are used to protect userspace from kernelspace + and to handle IO-space as a special type of memory by assigning + manager or client roles to running code (such as a process). config CPU_V7M_NUM_IRQ int "Number of external interrupts connected to the NVIC" diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 6f499559d193..f8dd0b3cc8e0 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -935,6 +935,9 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (type == TYPE_LDST) do_alignment_finish_ldst(addr, instr, regs, offset); + if (thumb_mode(regs)) + regs->ARM_cpsr = it_advance(regs->ARM_cpsr); + return 0; bad_or_fault: diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 5e2be37a198e..cd17e324aa51 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -296,6 +296,13 @@ static struct mem_type mem_types[] __ro_after_init = { .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, .domain = DOMAIN_KERNEL, }, + [MT_MEMORY_RO] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_XN | L_PTE_RDONLY, + .prot_l1 = PMD_TYPE_TABLE, + .prot_sect = PMD_TYPE_SECT, + .domain = DOMAIN_KERNEL, + }, [MT_ROM] = { .prot_sect = PMD_TYPE_SECT, .domain = DOMAIN_KERNEL, @@ -489,6 +496,7 @@ static void __init build_mem_type_table(void) /* Also setup NX memory mapping */ mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_XN; + mem_types[MT_MEMORY_RO].prot_sect |= PMD_SECT_XN; } if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) { /* @@ -568,6 +576,7 @@ static void __init build_mem_type_table(void) mem_types[MT_ROM].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; + mem_types[MT_MEMORY_RO].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; #endif /* @@ -587,6 +596,8 @@ static void __init build_mem_type_table(void) mem_types[MT_MEMORY_RWX].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY_RW].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_RO].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_RO].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY_RWX_NONCACHED].prot_pte |= L_PTE_SHARED; @@ -647,6 +658,8 @@ static void __init build_mem_type_table(void) mem_types[MT_MEMORY_RWX].prot_pte |= kern_pgprot; mem_types[MT_MEMORY_RW].prot_sect |= ecc_mask | cp->pmd; mem_types[MT_MEMORY_RW].prot_pte |= kern_pgprot; + mem_types[MT_MEMORY_RO].prot_sect |= ecc_mask | cp->pmd; + mem_types[MT_MEMORY_RO].prot_pte |= kern_pgprot; mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot; mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= ecc_mask; mem_types[MT_ROM].prot_sect |= cp->pmd; @@ -1360,7 +1373,7 @@ static void __init devicemaps_init(const struct machine_desc *mdesc) map.pfn = __phys_to_pfn(__atags_pointer & SECTION_MASK); map.virtual = FDT_FIXED_BASE; map.length = FDT_FIXED_SIZE; - map.type = MT_ROM; + map.type = MT_MEMORY_RO; create_mapping(&map); } diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index fb9f3eb6bf48..8bc7a2d6d6c7 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -108,8 +108,7 @@ static unsigned int spectre_v2_install_workaround(unsigned int method) #else static unsigned int spectre_v2_install_workaround(unsigned int method) { - pr_info("CPU%u: Spectre V2: workarounds disabled by configuration\n", - smp_processor_id()); + pr_info_once("Spectre V2: workarounds disabled by configuration\n"); return SPECTRE_VULNERABLE; } @@ -209,10 +208,10 @@ static int spectre_bhb_install_workaround(int method) return SPECTRE_VULNERABLE; spectre_bhb_method = method; - } - pr_info("CPU%u: Spectre BHB: using %s workaround\n", - smp_processor_id(), spectre_bhb_method_name(method)); + pr_info("CPU%u: Spectre BHB: enabling %s workaround for all CPUs\n", + smp_processor_id(), spectre_bhb_method_name(method)); + } return SPECTRE_MITIGATED; } diff --git a/arch/arm/probes/decode.h b/arch/arm/probes/decode.h index 973173598992..facc889d05ee 100644 --- a/arch/arm/probes/decode.h +++ b/arch/arm/probes/decode.h @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/stddef.h> #include <asm/probes.h> +#include <asm/ptrace.h> #include <asm/kprobes.h> void __init arm_probes_decode_init(void); @@ -35,31 +36,6 @@ void __init find_str_pc_offset(void); #endif -/* - * Update ITSTATE after normal execution of an IT block instruction. - * - * The 8 IT state bits are split into two parts in CPSR: - * ITSTATE<1:0> are in CPSR<26:25> - * ITSTATE<7:2> are in CPSR<15:10> - */ -static inline unsigned long it_advance(unsigned long cpsr) - { - if ((cpsr & 0x06000400) == 0) { - /* ITSTATE<2:0> == 0 means end of IT block, so clear IT state */ - cpsr &= ~PSR_IT_MASK; - } else { - /* We need to shift left ITSTATE<4:0> */ - const unsigned long mask = 0x06001c00; /* Mask ITSTATE<4:0> */ - unsigned long it = cpsr & mask; - it <<= 1; - it |= it >> (27 - 10); /* Carry ITSTATE<2> to correct place */ - it &= mask; - cpsr &= ~mask; - cpsr |= it; - } - return cpsr; -} - static inline void __kprobes bx_write_pc(long pcv, struct pt_regs *regs) { long cpsr = regs->ARM_cpsr; diff --git a/arch/arm64/boot/dts/broadcom/bcm4908/bcm4906.dtsi b/arch/arm64/boot/dts/broadcom/bcm4908/bcm4906.dtsi index 66023d553524..d084c33d5ca8 100644 --- a/arch/arm64/boot/dts/broadcom/bcm4908/bcm4906.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm4908/bcm4906.dtsi @@ -9,6 +9,14 @@ /delete-node/ cpu@3; }; + timer { + compatible = "arm,armv8-timer"; + interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>, + <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>, + <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>, + <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>; + }; + pmu { compatible = "arm,cortex-a53-pmu"; interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi b/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi index a4be040a00c0..967d2cd3c3ce 100644 --- a/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi @@ -29,6 +29,8 @@ device_type = "cpu"; compatible = "brcm,brahma-b53"; reg = <0x0>; + enable-method = "spin-table"; + cpu-release-addr = <0x0 0xfff8>; next-level-cache = <&l2>; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 92465f777603..d5cdd77e5a95 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -224,9 +224,12 @@ little-endian; }; - efuse@1e80000 { + sfp: efuse@1e80000 { compatible = "fsl,ls1028a-sfp"; reg = <0x0 0x1e80000 0x0 0x10000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(4)>; + clock-names = "sfp"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi index 913d845eb51a..1977103a5ef4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi @@ -376,7 +376,8 @@ camera: &i2c7 { <&cru ACLK_VIO>, <&cru ACLK_GIC_PRE>, <&cru PCLK_DDR>, - <&cru ACLK_HDCP>; + <&cru ACLK_HDCP>, + <&cru ACLK_VDU>; assigned-clock-rates = <600000000>, <1600000000>, <1000000000>, @@ -388,6 +389,7 @@ camera: &i2c7 { <400000000>, <200000000>, <200000000>, + <400000000>, <400000000>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index fbd0346624e6..9d5b0e8c9cca 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1462,7 +1462,8 @@ <&cru HCLK_PERILP1>, <&cru PCLK_PERILP1>, <&cru ACLK_VIO>, <&cru ACLK_HDCP>, <&cru ACLK_GIC_PRE>, - <&cru PCLK_DDR>; + <&cru PCLK_DDR>, + <&cru ACLK_VDU>; assigned-clock-rates = <594000000>, <800000000>, <1000000000>, @@ -1473,7 +1474,8 @@ <100000000>, <50000000>, <400000000>, <400000000>, <200000000>, - <200000000>; + <200000000>, + <400000000>; }; grf: syscon@ff770000 { diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts index 1534e11a9ad1..fa953b736642 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts @@ -687,6 +687,7 @@ }; &usb_host0_xhci { + dr_mode = "host"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts index 7bdcecc0dfe4..02d5f5a8ca03 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts @@ -133,7 +133,7 @@ assigned-clocks = <&cru SCLK_GMAC1_RX_TX>, <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru SCLK_GMAC1>; assigned-clock-parents = <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru SCLK_GMAC1>, <&gmac1_clkin>; clock_in_out = "input"; - phy-mode = "rgmii-id"; + phy-mode = "rgmii"; phy-supply = <&vcc_3v3>; pinctrl-names = "default"; pinctrl-0 = <&gmac1m1_miim diff --git a/arch/csky/include/asm/tlb.h b/arch/csky/include/asm/tlb.h index 3498e65f59f8..702861c68874 100644 --- a/arch/csky/include/asm/tlb.h +++ b/arch/csky/include/asm/tlb.h @@ -4,21 +4,6 @@ #define __ASM_CSKY_TLB_H #include <asm/cacheflush.h> - -#define tlb_start_vma(tlb, vma) \ - do { \ - if (!(tlb)->fullmm) \ - flush_cache_range(vma, (vma)->vm_start, (vma)->vm_end); \ - } while (0) - -#define tlb_end_vma(tlb, vma) \ - do { \ - if (!(tlb)->fullmm) \ - flush_tlb_range(vma, (vma)->vm_start, (vma)->vm_end); \ - } while (0) - -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) - #include <asm-generic/tlb.h> #endif /* __ASM_CSKY_TLB_H */ diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 53a912befb62..b57daee98b89 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -108,6 +108,7 @@ config LOONGARCH select TRACE_IRQFLAGS_SUPPORT select USE_PERCPU_NUMA_NODE_ID select ZONE_DMA32 + select MMU_GATHER_MERGE_VMAS if MMU config 32BIT bool diff --git a/arch/loongarch/include/asm/tlb.h b/arch/loongarch/include/asm/tlb.h index 4f629ae9d5a9..dd24f5898f65 100644 --- a/arch/loongarch/include/asm/tlb.h +++ b/arch/loongarch/include/asm/tlb.h @@ -137,16 +137,6 @@ static inline void invtlb_all(u32 op, u32 info, u64 addr) ); } -/* - * LoongArch doesn't need any special per-pte or per-vma handling, except - * we need to flush cache for area to be unmapped. - */ -#define tlb_start_vma(tlb, vma) \ - do { \ - if (!(tlb)->fullmm) \ - flush_cache_range(vma, vma->vm_start, vma->vm_end); \ - } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) static void tlb_flush(struct mmu_gather *tlb); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 7aa12e88c580..c235648fae23 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -256,6 +256,7 @@ config PPC select IRQ_FORCED_THREADING select MMU_GATHER_PAGE_SIZE select MMU_GATHER_RCU_TABLE_FREE + select MMU_GATHER_MERGE_VMAS select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE if PPC64 || NOT_COHERENT_CACHE select NEED_PER_CPU_EMBED_FIRST_CHUNK if PPC64 diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index 09a9ae5f3656..b3de6102a907 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -19,8 +19,6 @@ #include <linux/pagemap.h> -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry __tlb_remove_tlb_entry #define tlb_flush tlb_flush diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 32ffef9f6e5b..fcbb81feb7ad 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -38,7 +38,7 @@ config RISCV select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU select ARCH_SUPPORTS_HUGETLBFS if MMU - select ARCH_SUPPORTS_PAGE_TABLE_CHECK + select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 34cf8a598617..a4c46a03d2e2 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -73,6 +73,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y) endif KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) +KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) # GCC versions that support the "-mstrict-align" option default to allowing # unaligned accesses. While unaligned accesses are explicitly allowed in the diff --git a/arch/riscv/boot/dts/canaan/canaan_kd233.dts b/arch/riscv/boot/dts/canaan/canaan_kd233.dts index 039b92abf046..f72540bd14a3 100644 --- a/arch/riscv/boot/dts/canaan/canaan_kd233.dts +++ b/arch/riscv/boot/dts/canaan/canaan_kd233.dts @@ -35,7 +35,7 @@ gpio-keys { compatible = "gpio-keys"; - key0 { + key { label = "KEY0"; linux,code = <BTN_0>; gpios = <&gpio0 10 GPIO_ACTIVE_LOW>; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts index b9e30df127fe..8abdbe26a1d0 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts @@ -47,7 +47,7 @@ gpio-keys { compatible = "gpio-keys"; - boot { + key-boot { label = "BOOT"; linux,code = <BTN_0>; gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts index 8d23401b0bbb..3c6df1ecf76f 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts @@ -52,7 +52,7 @@ gpio-keys { compatible = "gpio-keys"; - boot { + key-boot { label = "BOOT"; linux,code = <BTN_0>; gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts index 24fd83b43d9d..03c9843d503e 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts @@ -46,19 +46,19 @@ gpio-keys { compatible = "gpio-keys"; - up { + key-up { label = "UP"; linux,code = <BTN_1>; gpios = <&gpio1_0 7 GPIO_ACTIVE_LOW>; }; - press { + key-press { label = "PRESS"; linux,code = <BTN_0>; gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; }; - down { + key-down { label = "DOWN"; linux,code = <BTN_2>; gpios = <&gpio0 1 GPIO_ACTIVE_LOW>; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts index 25341f38292a..7164ad063178 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts @@ -23,7 +23,7 @@ gpio-keys { compatible = "gpio-keys"; - boot { + key-boot { label = "BOOT"; linux,code = <BTN_0>; gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi index 3095d08453a1..496d3b7642bd 100644 --- a/arch/riscv/boot/dts/microchip/mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi @@ -50,6 +50,7 @@ riscv,isa = "rv64imafdc"; clocks = <&clkcfg CLK_CPU>; tlb-split; + next-level-cache = <&cctrllr>; status = "okay"; cpu1_intc: interrupt-controller { @@ -77,6 +78,7 @@ riscv,isa = "rv64imafdc"; clocks = <&clkcfg CLK_CPU>; tlb-split; + next-level-cache = <&cctrllr>; status = "okay"; cpu2_intc: interrupt-controller { @@ -104,6 +106,7 @@ riscv,isa = "rv64imafdc"; clocks = <&clkcfg CLK_CPU>; tlb-split; + next-level-cache = <&cctrllr>; status = "okay"; cpu3_intc: interrupt-controller { @@ -131,6 +134,7 @@ riscv,isa = "rv64imafdc"; clocks = <&clkcfg CLK_CPU>; tlb-split; + next-level-cache = <&cctrllr>; status = "okay"; cpu4_intc: interrupt-controller { #interrupt-cells = <1>; diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c index 672f02b21ce0..1031038423e7 100644 --- a/arch/riscv/errata/sifive/errata.c +++ b/arch/riscv/errata/sifive/errata.c @@ -111,6 +111,7 @@ void __init_or_module sifive_errata_patch_func(struct alt_entry *begin, cpu_apply_errata |= tmp; } } - if (cpu_apply_errata != cpu_req_errata) + if (stage != RISCV_ALTERNATIVES_MODULE && + cpu_apply_errata != cpu_req_errata) warn_miss_errata(cpu_req_errata - cpu_apply_errata); } diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 5c2aba5efbd0..dc42375c2357 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -175,7 +175,7 @@ static inline pud_t pfn_pud(unsigned long pfn, pgprot_t prot) static inline unsigned long _pud_pfn(pud_t pud) { - return pud_val(pud) >> _PAGE_PFN_SHIFT; + return __page_val_to_pfn(pud_val(pud)); } static inline pmd_t *pud_pgtable(pud_t pud) @@ -278,13 +278,13 @@ static inline p4d_t pfn_p4d(unsigned long pfn, pgprot_t prot) static inline unsigned long _p4d_pfn(p4d_t p4d) { - return p4d_val(p4d) >> _PAGE_PFN_SHIFT; + return __page_val_to_pfn(p4d_val(p4d)); } static inline pud_t *p4d_pgtable(p4d_t p4d) { if (pgtable_l4_enabled) - return (pud_t *)pfn_to_virt(p4d_val(p4d) >> _PAGE_PFN_SHIFT); + return (pud_t *)pfn_to_virt(__page_val_to_pfn(p4d_val(p4d))); return (pud_t *)pud_pgtable((pud_t) { p4d_val(p4d) }); } @@ -292,7 +292,7 @@ static inline pud_t *p4d_pgtable(p4d_t p4d) static inline struct page *p4d_page(p4d_t p4d) { - return pfn_to_page(p4d_val(p4d) >> _PAGE_PFN_SHIFT); + return pfn_to_page(__page_val_to_pfn(p4d_val(p4d))); } #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) @@ -347,7 +347,7 @@ static inline void pgd_clear(pgd_t *pgd) static inline p4d_t *pgd_pgtable(pgd_t pgd) { if (pgtable_l5_enabled) - return (p4d_t *)pfn_to_virt(pgd_val(pgd) >> _PAGE_PFN_SHIFT); + return (p4d_t *)pfn_to_virt(__page_val_to_pfn(pgd_val(pgd))); return (p4d_t *)p4d_pgtable((p4d_t) { pgd_val(pgd) }); } @@ -355,7 +355,7 @@ static inline p4d_t *pgd_pgtable(pgd_t pgd) static inline struct page *pgd_page(pgd_t pgd) { - return pfn_to_page(pgd_val(pgd) >> _PAGE_PFN_SHIFT); + return pfn_to_page(__page_val_to_pfn(pgd_val(pgd))); } #define pgd_page(pgd) pgd_page(pgd) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 1d1be9d9419c..5dbd6610729b 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -261,7 +261,7 @@ static inline pgd_t pfn_pgd(unsigned long pfn, pgprot_t prot) static inline unsigned long _pgd_pfn(pgd_t pgd) { - return pgd_val(pgd) >> _PAGE_PFN_SHIFT; + return __page_val_to_pfn(pgd_val(pgd)); } static inline struct page *pmd_page(pmd_t pmd) @@ -590,14 +590,14 @@ static inline pmd_t pmd_mkinvalid(pmd_t pmd) return __pmd(pmd_val(pmd) & ~(_PAGE_PRESENT|_PAGE_PROT_NONE)); } -#define __pmd_to_phys(pmd) (pmd_val(pmd) >> _PAGE_PFN_SHIFT << PAGE_SHIFT) +#define __pmd_to_phys(pmd) (__page_val_to_pfn(pmd_val(pmd)) << PAGE_SHIFT) static inline unsigned long pmd_pfn(pmd_t pmd) { return ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT); } -#define __pud_to_phys(pud) (pud_val(pud) >> _PAGE_PFN_SHIFT << PAGE_SHIFT) +#define __pud_to_phys(pud) (__page_val_to_pfn(pud_val(pud)) << PAGE_SHIFT) static inline unsigned long pud_pfn(pud_t pud) { diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index c71d6591d539..33bb60a354cd 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -78,7 +78,7 @@ obj-$(CONFIG_SMP) += cpu_ops_sbi.o endif obj-$(CONFIG_HOTPLUG_CPU) += cpu-hotplug.o obj-$(CONFIG_KGDB) += kgdb.o -obj-$(CONFIG_KEXEC) += kexec_relocate.o crash_save_regs.o machine_kexec.o +obj-$(CONFIG_KEXEC_CORE) += kexec_relocate.o crash_save_regs.o machine_kexec.o obj-$(CONFIG_KEXEC_FILE) += elf_kexec.o machine_kexec_file.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index 9cb85095fd45..0cb94992c15b 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -349,7 +349,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, { const char *strtab, *name, *shstrtab; const Elf_Shdr *sechdrs; - Elf_Rela *relas; + Elf64_Rela *relas; int i, r_type; /* String & section header string table */ diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 1c00695ebee7..9826073fbc67 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -54,7 +54,7 @@ static inline unsigned long gstage_pte_index(gpa_t addr, u32 level) static inline unsigned long gstage_pte_page_vaddr(pte_t pte) { - return (unsigned long)pfn_to_virt(pte_val(pte) >> _PAGE_PFN_SHIFT); + return (unsigned long)pfn_to_virt(__page_val_to_pfn(pte_val(pte))); } static int gstage_page_size_to_level(unsigned long page_size, u32 *out_level) diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 7f4ad5e4373a..f3455dc013fa 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -781,9 +781,11 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) { + kvm_vcpu_srcu_read_unlock(vcpu); rcuwait_wait_event(wait, (!vcpu->arch.power_off) && (!vcpu->arch.pause), TASK_INTERRUPTIBLE); + kvm_vcpu_srcu_read_lock(vcpu); if (vcpu->arch.power_off || vcpu->arch.pause) { /* diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8cd9e56c629b..5a1a8dfda6f8 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -204,6 +204,7 @@ config S390 select IOMMU_SUPPORT if PCI select MMU_GATHER_NO_GATHER select MMU_GATHER_RCU_TABLE_FREE + select MMU_GATHER_MERGE_VMAS select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE if PCI select NEED_SG_DMA_LENGTH if PCI diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 495c68a4df1e..4cb5d17e7ead 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -82,7 +82,7 @@ endif ifdef CONFIG_EXPOLINE ifdef CONFIG_EXPOLINE_EXTERN - KBUILD_LDFLAGS_MODULE += arch/s390/lib/expoline.o + KBUILD_LDFLAGS_MODULE += arch/s390/lib/expoline/expoline.o CC_FLAGS_EXPOLINE := -mindirect-branch=thunk-extern CC_FLAGS_EXPOLINE += -mfunction-return=thunk-extern else @@ -163,6 +163,12 @@ vdso_prepare: prepare0 $(Q)$(MAKE) $(build)=arch/s390/kernel/vdso64 include/generated/vdso64-offsets.h $(if $(CONFIG_COMPAT),$(Q)$(MAKE) \ $(build)=arch/s390/kernel/vdso32 include/generated/vdso32-offsets.h) + +ifdef CONFIG_EXPOLINE_EXTERN +modules_prepare: expoline_prepare +expoline_prepare: + $(Q)$(MAKE) $(build)=arch/s390/lib/expoline arch/s390/lib/expoline/expoline.o +endif endif # Don't use tabs in echo arguments diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h index d910d71b5bb5..7e9e99523e95 100644 --- a/arch/s390/include/asm/nospec-insn.h +++ b/arch/s390/include/asm/nospec-insn.h @@ -2,8 +2,6 @@ #ifndef _ASM_S390_NOSPEC_ASM_H #define _ASM_S390_NOSPEC_ASM_H -#include <asm/alternative-asm.h> -#include <asm/asm-offsets.h> #include <asm/dwarf.h> #ifdef __ASSEMBLY__ diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index fe6407f0eb1b..3a5c8fb590e5 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -27,9 +27,6 @@ static inline void tlb_flush(struct mmu_gather *tlb); static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) - #define tlb_flush tlb_flush #define pte_free_tlb pte_free_tlb #define pmd_free_tlb pmd_free_tlb diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index 5d415b3db6d1..580d2e3265cb 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -7,7 +7,6 @@ lib-y += delay.o string.o uaccess.o find.o spinlock.o obj-y += mem.o xor.o lib-$(CONFIG_KPROBES) += probes.o lib-$(CONFIG_UPROBES) += probes.o -obj-$(CONFIG_EXPOLINE_EXTERN) += expoline.o obj-$(CONFIG_S390_KPROBES_SANITY_TEST) += test_kprobes_s390.o test_kprobes_s390-objs += test_kprobes_asm.o test_kprobes.o @@ -22,3 +21,5 @@ obj-$(CONFIG_S390_MODULES_SANITY_TEST) += test_modules.o obj-$(CONFIG_S390_MODULES_SANITY_TEST_HELPERS) += test_modules_helpers.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o + +obj-$(CONFIG_EXPOLINE_EXTERN) += expoline/ diff --git a/arch/s390/lib/expoline/Makefile b/arch/s390/lib/expoline/Makefile new file mode 100644 index 000000000000..854631d9cb03 --- /dev/null +++ b/arch/s390/lib/expoline/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y += expoline.o diff --git a/arch/s390/lib/expoline.S b/arch/s390/lib/expoline/expoline.S index 92ed8409a7a4..92ed8409a7a4 100644 --- a/arch/s390/lib/expoline.S +++ b/arch/s390/lib/expoline/expoline.S diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index cf9a3ec32406..fba90e670ed4 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -271,8 +271,12 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, #endif /* CONFIG_HAVE_IOREMAP_PROT */ #else /* CONFIG_MMU */ -#define iounmap(addr) do { } while (0) -#define ioremap(offset, size) ((void __iomem *)(unsigned long)(offset)) +static inline void __iomem *ioremap(phys_addr_t offset, size_t size) +{ + return (void __iomem *)(unsigned long)offset; +} + +static inline void iounmap(volatile void __iomem *addr) { } #endif /* CONFIG_MMU */ #define ioremap_uc ioremap diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index ba449c47effd..4f7d1dfbc608 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -67,6 +67,8 @@ config SPARC64 select HAVE_KRETPROBES select HAVE_KPROBES select MMU_GATHER_RCU_TABLE_FREE if SMP + select MMU_GATHER_MERGE_VMAS + select MMU_GATHER_NO_FLUSH_CACHE select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h index 779a5a0f0608..3037187482db 100644 --- a/arch/sparc/include/asm/tlb_64.h +++ b/arch/sparc/include/asm/tlb_64.h @@ -22,8 +22,6 @@ void smp_flush_tlb_mm(struct mm_struct *mm); void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *); void flush_tlb_pending(void); -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) #define tlb_flush(tlb) flush_tlb_pending() /* diff --git a/arch/um/include/asm/page.h b/arch/um/include/asm/page.h index 95af12e82a32..cdbd9653aa14 100644 --- a/arch/um/include/asm/page.h +++ b/arch/um/include/asm/page.h @@ -102,8 +102,8 @@ extern unsigned long uml_physmem; * casting is the right thing, but 32-bit UML can't have 64-bit virtual * addresses */ -#define __pa(virt) to_phys((void *) (unsigned long) (virt)) -#define __va(phys) to_virt((unsigned long) (phys)) +#define __pa(virt) uml_to_phys((void *) (unsigned long) (virt)) +#define __va(phys) uml_to_virt((unsigned long) (phys)) #define phys_to_pfn(p) ((p) >> PAGE_SHIFT) #define pfn_to_phys(pfn) PFN_PHYS(pfn) diff --git a/arch/um/include/shared/mem.h b/arch/um/include/shared/mem.h index 4862c91d4213..98aacd544108 100644 --- a/arch/um/include/shared/mem.h +++ b/arch/um/include/shared/mem.h @@ -9,12 +9,12 @@ extern int phys_mapping(unsigned long phys, unsigned long long *offset_out); extern unsigned long uml_physmem; -static inline unsigned long to_phys(void *virt) +static inline unsigned long uml_to_phys(void *virt) { return(((unsigned long) virt) - uml_physmem); } -static inline void *to_virt(unsigned long phys) +static inline void *uml_to_virt(unsigned long phys) { return((void *) uml_physmem + phys); } diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 0760e24f2eba..9838967d0b2f 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -432,6 +432,10 @@ void apply_retpolines(s32 *start, s32 *end) { } +void apply_returns(s32 *start, s32 *end) +{ +} + void apply_alternatives(struct alt_instr *start, struct alt_instr *end) { } diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index 87d3129e7362..c316c993a949 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -251,7 +251,7 @@ static int userspace_tramp(void *stack) signal(SIGTERM, SIG_DFL); signal(SIGWINCH, SIG_IGN); - fd = phys_mapping(to_phys(__syscall_stub_start), &offset); + fd = phys_mapping(uml_to_phys(__syscall_stub_start), &offset); addr = mmap64((void *) STUB_CODE, UM_KERN_PAGE_SIZE, PROT_EXEC, MAP_FIXED | MAP_PRIVATE, fd, offset); if (addr == MAP_FAILED) { @@ -261,7 +261,7 @@ static int userspace_tramp(void *stack) } if (stack != NULL) { - fd = phys_mapping(to_phys(stack), &offset); + fd = phys_mapping(uml_to_phys(stack), &offset); addr = mmap((void *) STUB_DATA, UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE, MAP_FIXED | MAP_SHARED, fd, offset); @@ -534,7 +534,7 @@ int copy_context_skas0(unsigned long new_stack, int pid) struct stub_data *data = (struct stub_data *) current_stack; struct stub_data *child_data = (struct stub_data *) new_stack; unsigned long long new_offset; - int new_fd = phys_mapping(to_phys((void *)new_stack), &new_offset); + int new_fd = phys_mapping(uml_to_phys((void *)new_stack), &new_offset); /* * prepare offset and fd of child's stack as argument for parent's diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index be0b95e51df6..52a7f91527fe 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -245,6 +245,7 @@ config X86 select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT + select MMU_GATHER_MERGE_VMAS select HAVE_POSIX_CPU_TIMERS_TASK_WORK select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if UNWINDER_ORC || STACK_VALIDATION @@ -462,29 +463,6 @@ config GOLDFISH def_bool y depends on X86_GOLDFISH -config RETPOLINE - bool "Avoid speculative indirect branches in kernel" - select OBJTOOL if HAVE_OBJTOOL - default y - help - Compile kernel with the retpoline compiler options to guard against - kernel-to-user data leaks by avoiding speculative indirect - branches. Requires a compiler with -mindirect-branch=thunk-extern - support for full protection. The kernel may run slower. - -config CC_HAS_SLS - def_bool $(cc-option,-mharden-sls=all) - -config SLS - bool "Mitigate Straight-Line-Speculation" - depends on CC_HAS_SLS && X86_64 - select OBJTOOL if HAVE_OBJTOOL - default n - help - Compile the kernel with straight-line-speculation options to guard - against straight line speculation. The kernel image might be slightly - larger. - config X86_CPU_RESCTRL bool "x86 CPU resource control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) @@ -2453,6 +2431,91 @@ source "kernel/livepatch/Kconfig" endmenu +config CC_HAS_SLS + def_bool $(cc-option,-mharden-sls=all) + +config CC_HAS_RETURN_THUNK + def_bool $(cc-option,-mfunction-return=thunk-extern) + +menuconfig SPECULATION_MITIGATIONS + bool "Mitigations for speculative execution vulnerabilities" + default y + help + Say Y here to enable options which enable mitigations for + speculative execution hardware vulnerabilities. + + If you say N, all mitigations will be disabled. You really + should know what you are doing to say so. + +if SPECULATION_MITIGATIONS + +config PAGE_TABLE_ISOLATION + bool "Remove the kernel mapping in user mode" + default y + depends on (X86_64 || X86_PAE) + help + This feature reduces the number of hardware side channels by + ensuring that the majority of kernel addresses are not mapped + into userspace. + + See Documentation/x86/pti.rst for more details. + +config RETPOLINE + bool "Avoid speculative indirect branches in kernel" + select OBJTOOL if HAVE_OBJTOOL + default y + help + Compile kernel with the retpoline compiler options to guard against + kernel-to-user data leaks by avoiding speculative indirect + branches. Requires a compiler with -mindirect-branch=thunk-extern + support for full protection. The kernel may run slower. + +config RETHUNK + bool "Enable return-thunks" + depends on RETPOLINE && CC_HAS_RETURN_THUNK + select OBJTOOL if HAVE_OBJTOOL + default y if X86_64 + help + Compile the kernel with the return-thunks compiler option to guard + against kernel-to-user data leaks by avoiding return speculation. + Requires a compiler with -mfunction-return=thunk-extern + support for full protection. The kernel may run slower. + +config CPU_UNRET_ENTRY + bool "Enable UNRET on kernel entry" + depends on CPU_SUP_AMD && RETHUNK && X86_64 + default y + help + Compile the kernel with support for the retbleed=unret mitigation. + +config CPU_IBPB_ENTRY + bool "Enable IBPB on kernel entry" + depends on CPU_SUP_AMD && X86_64 + default y + help + Compile the kernel with support for the retbleed=ibpb mitigation. + +config CPU_IBRS_ENTRY + bool "Enable IBRS on kernel entry" + depends on CPU_SUP_INTEL && X86_64 + default y + help + Compile the kernel with support for the spectre_v2=ibrs mitigation. + This mitigates both spectre_v2 and retbleed at great cost to + performance. + +config SLS + bool "Mitigate Straight-Line-Speculation" + depends on CC_HAS_SLS && X86_64 + select OBJTOOL if HAVE_OBJTOOL + default n + help + Compile the kernel with straight-line-speculation options to guard + against straight line speculation. The kernel image might be slightly + larger. + +endif + config ARCH_HAS_ADD_PAGES def_bool y depends on ARCH_ENABLE_MEMORY_HOTPLUG diff --git a/arch/x86/Makefile b/arch/x86/Makefile index a74886aed349..7854685c5f25 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -21,6 +21,13 @@ ifdef CONFIG_CC_IS_CLANG RETPOLINE_CFLAGS := -mretpoline-external-thunk RETPOLINE_VDSO_CFLAGS := -mretpoline endif + +ifdef CONFIG_RETHUNK +RETHUNK_CFLAGS := -mfunction-return=thunk-extern +RETPOLINE_CFLAGS += $(RETHUNK_CFLAGS) +endif + +export RETHUNK_CFLAGS export RETPOLINE_CFLAGS export RETPOLINE_VDSO_CFLAGS diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 7fec5dcf6438..eeadbd7d92cc 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -11,7 +11,7 @@ CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) CFLAGS_common.o += -fno-stack-protector -obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o +obj-y := entry.o entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o obj-y += vdso/ diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 29b36e9e4e74..f6907627172b 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -7,6 +7,8 @@ #include <asm/asm-offsets.h> #include <asm/processor-flags.h> #include <asm/ptrace-abi.h> +#include <asm/msr.h> +#include <asm/nospec-branch.h> /* @@ -283,6 +285,66 @@ For 32-bit we have the following conventions - kernel is built with #endif /* + * IBRS kernel mitigation for Spectre_v2. + * + * Assumes full context is established (PUSH_REGS, CR3 and GS) and it clobbers + * the regs it uses (AX, CX, DX). Must be called before the first RET + * instruction (NOTE! UNTRAIN_RET includes a RET instruction) + * + * The optional argument is used to save/restore the current value, + * which is used on the paranoid paths. + * + * Assumes x86_spec_ctrl_{base,current} to have SPEC_CTRL_IBRS set. + */ +.macro IBRS_ENTER save_reg +#ifdef CONFIG_CPU_IBRS_ENTRY + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + rdmsr + shl $32, %rdx + or %rdx, %rax + mov %rax, \save_reg + test $SPEC_CTRL_IBRS, %eax + jz .Ldo_wrmsr_\@ + lfence + jmp .Lend_\@ +.Ldo_wrmsr_\@: +.endif + + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_\@: +#endif +.endm + +/* + * Similar to IBRS_ENTER, requires KERNEL GS,CR3 and clobbers (AX, CX, DX) + * regs. Must be called after the last RET. + */ +.macro IBRS_EXIT save_reg +#ifdef CONFIG_CPU_IBRS_ENTRY + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + mov \save_reg, %rdx +.else + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + andl $(~SPEC_CTRL_IBRS), %edx +.endif + + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_\@: +#endif +.endm + +/* * Mitigate Spectre v1 for conditional swapgs code paths. * * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S new file mode 100644 index 000000000000..bfb7bcb362bc --- /dev/null +++ b/arch/x86/entry/entry.S @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common place for both 32- and 64-bit entry routines. + */ + +#include <linux/linkage.h> +#include <asm/export.h> +#include <asm/msr-index.h> + +.pushsection .noinstr.text, "ax" + +SYM_FUNC_START(entry_ibpb) + movl $MSR_IA32_PRED_CMD, %ecx + movl $PRED_CMD_IBPB, %eax + xorl %edx, %edx + wrmsr + RET +SYM_FUNC_END(entry_ibpb) +/* For KVM */ +EXPORT_SYMBOL_GPL(entry_ibpb); + +.popsection diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 887420844066..e309e7156038 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -698,7 +698,6 @@ SYM_CODE_START(__switch_to_asm) movl %ebx, PER_CPU_VAR(__stack_chk_guard) #endif -#ifdef CONFIG_RETPOLINE /* * When switching from a shallower to a deeper call stack * the RSB may either underflow or use entries populated @@ -707,7 +706,6 @@ SYM_CODE_START(__switch_to_asm) * speculative execution to prevent attack. */ FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW -#endif /* Restore flags or the incoming task to restore AC state. */ popfl diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4300ba49b5ee..9953d966d124 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -85,7 +85,7 @@ */ SYM_CODE_START(entry_SYSCALL_64) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR swapgs @@ -112,6 +112,11 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) movq %rsp, %rdi /* Sign extend the lower 32bit as syscall numbers are treated as int */ movslq %eax, %rsi + + /* clobbers %rax, make sure it is after saving the syscall nr */ + IBRS_ENTER + UNTRAIN_RET + call do_syscall_64 /* returns with IRQs disabled */ /* @@ -191,6 +196,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) * perf profiles. Nothing jumps here. */ syscall_return_via_sysret: + IBRS_EXIT POP_REGS pop_rdi=0 /* @@ -249,7 +255,6 @@ SYM_FUNC_START(__switch_to_asm) movq %rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset #endif -#ifdef CONFIG_RETPOLINE /* * When switching from a shallower to a deeper call stack * the RSB may either underflow or use entries populated @@ -258,7 +263,6 @@ SYM_FUNC_START(__switch_to_asm) * speculative execution to prevent attack. */ FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW -#endif /* restore callee-saved registers */ popq %r15 @@ -322,13 +326,13 @@ SYM_CODE_END(ret_from_fork) #endif .endm -/* Save all registers in pt_regs */ -SYM_CODE_START_LOCAL(push_and_clear_regs) +SYM_CODE_START_LOCAL(xen_error_entry) UNWIND_HINT_FUNC PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 + UNTRAIN_RET RET -SYM_CODE_END(push_and_clear_regs) +SYM_CODE_END(xen_error_entry) /** * idtentry_body - Macro to emit code calling the C function @@ -337,9 +341,6 @@ SYM_CODE_END(push_and_clear_regs) */ .macro idtentry_body cfunc has_error_code:req - call push_and_clear_regs - UNWIND_HINT_REGS - /* * Call error_entry() and switch to the task stack if from userspace. * @@ -349,7 +350,7 @@ SYM_CODE_END(push_and_clear_regs) * switch the CR3. So it can skip invoking error_entry(). */ ALTERNATIVE "call error_entry; movq %rax, %rsp", \ - "", X86_FEATURE_XENPV + "call xen_error_entry", X86_FEATURE_XENPV ENCODE_FRAME_POINTER UNWIND_HINT_REGS @@ -612,6 +613,7 @@ __irqentry_text_end: SYM_CODE_START_LOCAL(common_interrupt_return) SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) + IBRS_EXIT #ifdef CONFIG_DEBUG_ENTRY /* Assert that pt_regs indicates user mode. */ testb $3, CS(%rsp) @@ -897,6 +899,9 @@ SYM_CODE_END(xen_failsafe_callback) * 1 -> no SWAPGS on exit * * Y GSBASE value at entry, must be restored in paranoid_exit + * + * R14 - old CR3 + * R15 - old SPEC_CTRL */ SYM_CODE_START_LOCAL(paranoid_entry) UNWIND_HINT_FUNC @@ -940,7 +945,7 @@ SYM_CODE_START_LOCAL(paranoid_entry) * is needed here. */ SAVE_AND_SET_GSBASE scratch_reg=%rax save_reg=%rbx - RET + jmp .Lparanoid_gsbase_done .Lparanoid_entry_checkgs: /* EBX = 1 -> kernel GSBASE active, no restore required */ @@ -959,8 +964,16 @@ SYM_CODE_START_LOCAL(paranoid_entry) xorl %ebx, %ebx swapgs .Lparanoid_kernel_gsbase: - FENCE_SWAPGS_KERNEL_ENTRY +.Lparanoid_gsbase_done: + + /* + * Once we have CR3 and %GS setup save and set SPEC_CTRL. Just like + * CR3 above, keep the old value in a callee saved register. + */ + IBRS_ENTER save_reg=%r15 + UNTRAIN_RET + RET SYM_CODE_END(paranoid_entry) @@ -982,9 +995,19 @@ SYM_CODE_END(paranoid_entry) * 1 -> no SWAPGS on exit * * Y User space GSBASE, must be restored unconditionally + * + * R14 - old CR3 + * R15 - old SPEC_CTRL */ SYM_CODE_START_LOCAL(paranoid_exit) UNWIND_HINT_REGS + + /* + * Must restore IBRS state before both CR3 and %GS since we need access + * to the per-CPU x86_spec_ctrl_shadow variable. + */ + IBRS_EXIT save_reg=%r15 + /* * The order of operations is important. RESTORE_CR3 requires * kernel GSBASE. @@ -1017,6 +1040,10 @@ SYM_CODE_END(paranoid_exit) */ SYM_CODE_START_LOCAL(error_entry) UNWIND_HINT_FUNC + + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 + testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1028,9 +1055,12 @@ SYM_CODE_START_LOCAL(error_entry) FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER + UNTRAIN_RET leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */ .Lerror_entry_from_usermode_after_swapgs: + /* Put us onto the real thread stack. */ call sync_regs RET @@ -1065,6 +1095,7 @@ SYM_CODE_START_LOCAL(error_entry) .Lerror_entry_done_lfence: FENCE_SWAPGS_KERNEL_ENTRY leaq 8(%rsp), %rax /* return pt_regs pointer */ + ANNOTATE_UNRET_END RET .Lbstep_iret: @@ -1080,6 +1111,8 @@ SYM_CODE_START_LOCAL(error_entry) swapgs FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER + UNTRAIN_RET /* * Pretend that the exception came from user mode: set up pt_regs @@ -1185,6 +1218,9 @@ SYM_CODE_START(asm_exc_nmi) PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER + IBRS_ENTER + UNTRAIN_RET + /* * At this point we no longer need to worry about stack damage * due to nesting -- we're on the normal thread stack and we're @@ -1409,6 +1445,9 @@ end_repeat_nmi: movq $-1, %rsi call exc_nmi + /* Always restore stashed SPEC_CTRL value (see paranoid_entry) */ + IBRS_EXIT save_reg=%r15 + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index d1052742ad0c..682338e7e2a3 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -4,7 +4,6 @@ * * Copyright 2000-2002 Andi Kleen, SuSE Labs. */ -#include "calling.h" #include <asm/asm-offsets.h> #include <asm/current.h> #include <asm/errno.h> @@ -14,9 +13,12 @@ #include <asm/irqflags.h> #include <asm/asm.h> #include <asm/smap.h> +#include <asm/nospec-branch.h> #include <linux/linkage.h> #include <linux/err.h> +#include "calling.h" + .section .entry.text, "ax" /* @@ -47,7 +49,7 @@ * 0(%ebp) arg6 */ SYM_CODE_START(entry_SYSENTER_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR /* Interrupts are off on entry. */ swapgs @@ -88,6 +90,9 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) cld + IBRS_ENTER + UNTRAIN_RET + /* * SYSENTER doesn't filter flags, so we need to clear NT and AC * ourselves. To save a few cycles, we can check whether @@ -174,7 +179,7 @@ SYM_CODE_END(entry_SYSENTER_compat) * 0(%esp) arg6 */ SYM_CODE_START(entry_SYSCALL_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR /* Interrupts are off on entry. */ swapgs @@ -203,6 +208,9 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) PUSH_AND_CLEAR_REGS rcx=%rbp rax=$-ENOSYS UNWIND_HINT_REGS + IBRS_ENTER + UNTRAIN_RET + movq %rsp, %rdi call do_fast_syscall_32 /* XEN PV guests always use IRET path */ @@ -217,6 +225,8 @@ sysret32_from_system_call: */ STACKLEAK_ERASE + IBRS_EXIT + movq RBX(%rsp), %rbx /* pt_regs->rbx */ movq RBP(%rsp), %rbp /* pt_regs->rbp */ movq EFLAGS(%rsp), %r11 /* pt_regs->flags (in r11) */ @@ -295,7 +305,7 @@ SYM_CODE_END(entry_SYSCALL_compat) * ebp arg6 */ SYM_CODE_START(entry_INT80_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR /* * Interrupts are off on entry. @@ -337,6 +347,9 @@ SYM_CODE_START(entry_INT80_compat) cld + IBRS_ENTER + UNTRAIN_RET + movq %rsp, %rdi call do_int80_syscall_32 jmp swapgs_restore_regs_and_return_to_usermode diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index c2a8b76ae0bc..76cd790ed0bd 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -92,6 +92,7 @@ endif endif $(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) +$(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO # # vDSO code runs in userspace and -pg doesn't help with profiling anyway. diff --git a/arch/x86/entry/vsyscall/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S index 15e35159ebb6..ef2dd1827243 100644 --- a/arch/x86/entry/vsyscall/vsyscall_emu_64.S +++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S @@ -19,17 +19,20 @@ __vsyscall_page: mov $__NR_gettimeofday, %rax syscall - RET + ret + int3 .balign 1024, 0xcc mov $__NR_time, %rax syscall - RET + ret + int3 .balign 1024, 0xcc mov $__NR_getcpu, %rax syscall - RET + ret + int3 .balign 4096, 0xcc diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 13179f31fe10..4f70fb6c2c1e 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -278,9 +278,9 @@ enum { }; /* - * For formats with LBR_TSX flags (e.g. LBR_FORMAT_EIP_FLAGS2), bits 61:62 in - * MSR_LAST_BRANCH_FROM_x are the TSX flags when TSX is supported, but when - * TSX is not supported they have no consistent behavior: + * For format LBR_FORMAT_EIP_FLAGS2, bits 61:62 in MSR_LAST_BRANCH_FROM_x + * are the TSX flags when TSX is supported, but when TSX is not supported + * they have no consistent behavior: * * - For wrmsr(), bits 61:62 are considered part of the sign extension. * - For HW updates (branch captures) bits 61:62 are always OFF and are not @@ -288,7 +288,7 @@ enum { * * Therefore, if: * - * 1) LBR has TSX format + * 1) LBR format LBR_FORMAT_EIP_FLAGS2 * 2) CPU has no TSX support enabled * * ... then any value passed to wrmsr() must be sign extended to 63 bits and any @@ -300,7 +300,7 @@ static inline bool lbr_from_signext_quirk_needed(void) bool tsx_support = boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM); - return !tsx_support && x86_pmu.lbr_has_tsx; + return !tsx_support; } static DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key); @@ -1609,9 +1609,6 @@ void intel_pmu_lbr_init_hsw(void) x86_pmu.lbr_sel_map = hsw_lbr_sel_map; x86_get_pmu(smp_processor_id())->task_ctx_cache = create_lbr_kmem_cache(size, 0); - - if (lbr_from_signext_quirk_needed()) - static_branch_enable(&lbr_from_quirk_key); } /* skylake */ @@ -1702,7 +1699,11 @@ void intel_pmu_lbr_init(void) switch (x86_pmu.intel_cap.lbr_format) { case LBR_FORMAT_EIP_FLAGS2: x86_pmu.lbr_has_tsx = 1; - fallthrough; + x86_pmu.lbr_from_flags = 1; + if (lbr_from_signext_quirk_needed()) + static_branch_enable(&lbr_from_quirk_key); + break; + case LBR_FORMAT_EIP_FLAGS: x86_pmu.lbr_from_flags = 1; break; diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 9b10c8c76087..9542c582d546 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -76,6 +76,7 @@ extern int alternatives_patched; extern void alternative_instructions(void); extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); extern void apply_retpolines(s32 *start, s32 *end); +extern void apply_returns(s32 *start, s32 *end); extern void apply_ibt_endbr(s32 *start, s32 *end); struct module; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 03acc823838a..a77b915d36a8 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -203,8 +203,8 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ @@ -296,6 +296,13 @@ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ #define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ #define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ +#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */ +#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */ +#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ +#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ +#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ @@ -316,6 +323,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ @@ -447,5 +455,6 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 36369e76cc63..33d2cd04d254 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -50,6 +50,25 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif +#ifdef CONFIG_RETPOLINE +# define DISABLE_RETPOLINE 0 +#else +# define DISABLE_RETPOLINE ((1 << (X86_FEATURE_RETPOLINE & 31)) | \ + (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31))) +#endif + +#ifdef CONFIG_RETHUNK +# define DISABLE_RETHUNK 0 +#else +# define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) +#endif + +#ifdef CONFIG_CPU_UNRET_ENTRY +# define DISABLE_UNRET 0 +#else +# define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -82,7 +101,7 @@ #define DISABLED_MASK8 (DISABLE_TDX_GUEST) #define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 -#define DISABLED_MASK11 0 +#define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET) #define DISABLED_MASK12 0 #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 85865f1645bd..73ca20049835 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -19,19 +19,27 @@ #define __ALIGN_STR __stringify(__ALIGN) #endif +#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#define RET jmp __x86_return_thunk +#else /* CONFIG_RETPOLINE */ #ifdef CONFIG_SLS #define RET ret; int3 #else #define RET ret #endif +#endif /* CONFIG_RETPOLINE */ #else /* __ASSEMBLY__ */ +#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#define ASM_RET "jmp __x86_return_thunk\n\t" +#else /* CONFIG_RETPOLINE */ #ifdef CONFIG_SLS #define ASM_RET "ret; int3\n\t" #else #define ASM_RET "ret\n\t" #endif +#endif /* CONFIG_RETPOLINE */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d27e0581b777..cc615be27a54 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -51,6 +51,8 @@ #define SPEC_CTRL_STIBP BIT(SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */ #define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ +#define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ +#define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -93,6 +95,7 @@ #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a #define ARCH_CAP_RDCL_NO BIT(0) /* Not susceptible to Meltdown */ #define ARCH_CAP_IBRS_ALL BIT(1) /* Enhanced IBRS support */ +#define ARCH_CAP_RSBA BIT(2) /* RET may use alternative branch predictors */ #define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH BIT(3) /* Skip L1D flush on vmentry */ #define ARCH_CAP_SSB_NO BIT(4) /* * Not susceptible to Speculative Store Bypass @@ -140,6 +143,13 @@ * bit available to control VERW * behavior. */ +#define ARCH_CAP_RRSBA BIT(19) /* + * Indicates RET may use predictors + * other than the RSB. With eIBRS + * enabled predictions in kernel mode + * are restricted to targets in + * kernel. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -567,6 +577,9 @@ /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 +#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3 +#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1) + /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index da251a5645b0..38a3e86e665e 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -11,6 +11,7 @@ #include <asm/cpufeatures.h> #include <asm/msr-index.h> #include <asm/unwind_hints.h> +#include <asm/percpu.h> #define RETPOLINE_THUNK_SIZE 32 @@ -76,6 +77,23 @@ .endm /* + * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions + * vs RETBleed validation. + */ +#define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE + +/* + * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should + * eventually turn into it's own annotation. + */ +.macro ANNOTATE_UNRET_END +#ifdef CONFIG_DEBUG_ENTRY + ANNOTATE_RETPOLINE_SAFE + nop +#endif +.endm + +/* * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 * attack. @@ -105,10 +123,34 @@ * monstrosity above, manually. */ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req -#ifdef CONFIG_RETPOLINE ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP) .Lskip_rsb_\@: +.endm + +#ifdef CONFIG_CPU_UNRET_ENTRY +#define CALL_ZEN_UNTRAIN_RET "call zen_untrain_ret" +#else +#define CALL_ZEN_UNTRAIN_RET "" +#endif + +/* + * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the + * return thunk isn't mapped into the userspace tables (then again, AMD + * typically has NO_MELTDOWN). + * + * While zen_untrain_ret() doesn't clobber anything but requires stack, + * entry_ibpb() will clobber AX, CX, DX. + * + * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point + * where we have a stack but before any RET instruction. + */ +.macro UNTRAIN_RET +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) + ANNOTATE_UNRET_END + ALTERNATIVE_2 "", \ + CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ + "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif .endm @@ -120,17 +162,20 @@ _ASM_PTR " 999b\n\t" \ ".popsection\n\t" -#ifdef CONFIG_RETPOLINE - typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; +extern retpoline_thunk_t __x86_indirect_thunk_array[]; + +extern void __x86_return_thunk(void); +extern void zen_untrain_ret(void); +extern void entry_ibpb(void); + +#ifdef CONFIG_RETPOLINE #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN -extern retpoline_thunk_t __x86_indirect_thunk_array[]; - #ifdef CONFIG_X86_64 /* @@ -193,6 +238,7 @@ enum spectre_v2_mitigation { SPECTRE_V2_EIBRS, SPECTRE_V2_EIBRS_RETPOLINE, SPECTRE_V2_EIBRS_LFENCE, + SPECTRE_V2_IBRS, }; /* The indirect branch speculation control variants */ @@ -235,6 +281,9 @@ static inline void indirect_branch_prediction_barrier(void) /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; +DECLARE_PER_CPU(u64, x86_spec_ctrl_current); +extern void write_spec_ctrl_current(u64 val, bool force); +extern u64 spec_ctrl_current(void); /* * With retpoline, we must use IBRS to restrict branch prediction @@ -244,18 +293,18 @@ extern u64 x86_spec_ctrl_base; */ #define firmware_restrict_branch_speculation_start() \ do { \ - u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS; \ - \ preempt_disable(); \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, \ + spec_ctrl_current() | SPEC_CTRL_IBRS, \ X86_FEATURE_USE_IBRS_FW); \ + alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, \ + X86_FEATURE_USE_IBPB_FW); \ } while (0) #define firmware_restrict_branch_speculation_end() \ do { \ - u64 val = x86_spec_ctrl_base; \ - \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, \ + spec_ctrl_current(), \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 2d8dacd02643..343b722ccaf2 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -21,6 +21,16 @@ * relative displacement across sections. */ +/* + * The trampoline is 8 bytes and of the general form: + * + * jmp.d32 \func + * ud1 %esp, %ecx + * + * That trailing #UD provides both a speculation stop and serves as a unique + * 3 byte signature identifying static call trampolines. Also see tramp_ud[] + * and __static_call_fixup(). + */ #define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insns) \ asm(".pushsection .static_call.text, \"ax\" \n" \ ".align 4 \n" \ @@ -28,7 +38,7 @@ STATIC_CALL_TRAMP_STR(name) ": \n" \ ANNOTATE_NOENDBR \ insns " \n" \ - ".byte 0x53, 0x43, 0x54 \n" \ + ".byte 0x0f, 0xb9, 0xcc \n" \ ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ ".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \ ".popsection \n") @@ -36,8 +46,13 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)") +#ifdef CONFIG_RETHUNK +#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ + __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "jmp __x86_return_thunk") +#else #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop") +#endif #define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) \ ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0) @@ -48,4 +63,6 @@ ".long " STATIC_CALL_KEY_STR(name) " - . \n" \ ".popsection \n") +extern bool __static_call_fixup(void *tramp, u8 op, void *dest); + #endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index 1bfe979bb9bc..580636cdc257 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -2,9 +2,6 @@ #ifndef _ASM_X86_TLB_H #define _ASM_X86_TLB_H -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) - #define tlb_flush tlb_flush static inline void tlb_flush(struct mmu_gather *tlb); diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index 8b33674288ea..f66fbe6537dd 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -8,7 +8,11 @@ #ifdef __ASSEMBLY__ .macro UNWIND_HINT_EMPTY - UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_CALL end=1 + UNWIND_HINT type=UNWIND_HINT_TYPE_CALL end=1 +.endm + +.macro UNWIND_HINT_ENTRY + UNWIND_HINT type=UNWIND_HINT_TYPE_ENTRY end=1 .endm .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 @@ -52,6 +56,14 @@ UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC .endm +.macro UNWIND_HINT_SAVE + UNWIND_HINT type=UNWIND_HINT_TYPE_SAVE +.endm + +.macro UNWIND_HINT_RESTORE + UNWIND_HINT type=UNWIND_HINT_TYPE_RESTORE +.endm + #else #define UNWIND_HINT_FUNC \ diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 734b96454896..8d8752b44f11 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -16,6 +16,12 @@ bool cpc_supported_by_cpu(void) switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: case X86_VENDOR_HYGON: + if (boot_cpu_data.x86 == 0x19 && ((boot_cpu_data.x86_model <= 0x0f) || + (boot_cpu_data.x86_model >= 0x20 && boot_cpu_data.x86_model <= 0x2f))) + return true; + else if (boot_cpu_data.x86 == 0x17 && + boot_cpu_data.x86_model >= 0x70 && boot_cpu_data.x86_model <= 0x7f) + return true; return boot_cpu_has(X86_FEATURE_CPPC); } return false; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index e257f6c80372..62f6b8b7c4a5 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -115,6 +115,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len) } extern s32 __retpoline_sites[], __retpoline_sites_end[]; +extern s32 __return_sites[], __return_sites_end[]; extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[]; extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; @@ -507,9 +508,78 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) } } +#ifdef CONFIG_RETHUNK +/* + * Rewrite the compiler generated return thunk tail-calls. + * + * For example, convert: + * + * JMP __x86_return_thunk + * + * into: + * + * RET + */ +static int patch_return(void *addr, struct insn *insn, u8 *bytes) +{ + int i = 0; + + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + return -1; + + bytes[i++] = RET_INSN_OPCODE; + + for (; i < insn->length;) + bytes[i++] = INT3_INSN_OPCODE; + + return i; +} + +void __init_or_module noinline apply_returns(s32 *start, s32 *end) +{ + s32 *s; + + for (s = start; s < end; s++) { + void *dest = NULL, *addr = (void *)s + *s; + struct insn insn; + int len, ret; + u8 bytes[16]; + u8 op; + + ret = insn_decode_kernel(&insn, addr); + if (WARN_ON_ONCE(ret < 0)) + continue; + + op = insn.opcode.bytes[0]; + if (op == JMP32_INSN_OPCODE) + dest = addr + insn.length + insn.immediate.value; + + if (__static_call_fixup(addr, op, dest) || + WARN_ONCE(dest != &__x86_return_thunk, + "missing return thunk: %pS-%pS: %*ph", + addr, dest, 5, addr)) + continue; + + DPRINTK("return thunk at: %pS (%px) len: %d to: %pS", + addr, addr, insn.length, + addr + insn.length + insn.immediate.value); + + len = patch_return(addr, &insn, bytes); + if (len == insn.length) { + DUMP_BYTES(((u8*)addr), len, "%px: orig: ", addr); + DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr); + text_poke_early(addr, bytes, len); + } + } +} +#else +void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } +#endif /* CONFIG_RETHUNK */ + #else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { } +void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } #endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */ @@ -860,6 +930,7 @@ void __init alternative_instructions(void) * those can rewrite the retpoline thunks. */ apply_retpolines(__retpoline_sites, __retpoline_sites_end); + apply_returns(__return_sites, __return_sites_end); /* * Then patch alternatives, such that those paravirt calls that are in diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 437308004ef2..cb50589a7102 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -19,6 +19,7 @@ #include <asm/suspend.h> #include <asm/tlbflush.h> #include <asm/tdx.h> +#include "../kvm/vmx/vmx.h" #ifdef CONFIG_XEN #include <xen/interface/xen.h> @@ -107,4 +108,9 @@ static void __used common(void) OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); OFFSET(TSS_sp2, tss_struct, x86_tss.sp2); + + if (IS_ENABLED(CONFIG_KVM_INTEL)) { + BLANK(); + OFFSET(VMX_spec_ctrl, vcpu_vmx, spec_ctrl); + } } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 0c0b09796ced..35d5288394cb 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -862,6 +862,28 @@ static void init_amd_bd(struct cpuinfo_x86 *c) clear_rdrand_cpuid_bit(c); } +void init_spectral_chicken(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_CPU_UNRET_ENTRY + u64 value; + + /* + * On Zen2 we offer this chicken (bit) on the altar of Speculation. + * + * This suppresses speculation from the middle of a basic block, i.e. it + * suppresses non-branch predictions. + * + * We use STIBP as a heuristic to filter out Zen2 from the rest of F17H + */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_AMD_STIBP)) { + if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) { + value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT; + wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value); + } + } +#endif +} + static void init_amd_zn(struct cpuinfo_x86 *c) { set_cpu_cap(c, X86_FEATURE_ZEN); @@ -870,12 +892,21 @@ static void init_amd_zn(struct cpuinfo_x86 *c) node_reclaim_distance = 32; #endif - /* - * Fix erratum 1076: CPB feature bit not being set in CPUID. - * Always set it, except when running under a hypervisor. - */ - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_CPB)) - set_cpu_cap(c, X86_FEATURE_CPB); + /* Fix up CPUID bits, but only if not virtualised. */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { + + /* Erratum 1076: CPB feature bit not being set in CPUID. */ + if (!cpu_has(c, X86_FEATURE_CPB)) + set_cpu_cap(c, X86_FEATURE_CPB); + + /* + * Zen3 (Fam19 model < 0x10) parts are not susceptible to + * Branch Type Confusion, but predate the allocation of the + * BTC_NO bit. + */ + if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO)) + set_cpu_cap(c, X86_FEATURE_BTC_NO); + } } static void init_amd(struct cpuinfo_x86 *c) @@ -907,7 +938,8 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; case 0x16: init_amd_jg(c); break; - case 0x17: fallthrough; + case 0x17: init_spectral_chicken(c); + fallthrough; case 0x19: init_amd_zn(c); break; } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 74c62cc47a5f..6454bc767f0f 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -38,6 +38,8 @@ static void __init spectre_v1_select_mitigation(void); static void __init spectre_v2_select_mitigation(void); +static void __init retbleed_select_mitigation(void); +static void __init spectre_v2_user_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); @@ -48,16 +50,40 @@ static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); -/* The base value of the SPEC_CTRL MSR that always has to be preserved. */ +/* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); + +/* The current value of the SPEC_CTRL MSR with task-specific bits set */ +DEFINE_PER_CPU(u64, x86_spec_ctrl_current); +EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); + static DEFINE_MUTEX(spec_ctrl_mutex); /* - * The vendor and possibly platform specific bits which can be modified in - * x86_spec_ctrl_base. + * Keep track of the SPEC_CTRL MSR value for the current task, which may differ + * from x86_spec_ctrl_base due to STIBP/SSB in __speculation_ctrl_update(). */ -static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS; +void write_spec_ctrl_current(u64 val, bool force) +{ + if (this_cpu_read(x86_spec_ctrl_current) == val) + return; + + this_cpu_write(x86_spec_ctrl_current, val); + + /* + * When KERNEL_IBRS this MSR is written on return-to-user, unless + * forced the update can be delayed until that time. + */ + if (force || !cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS)) + wrmsrl(MSR_IA32_SPEC_CTRL, val); +} + +u64 spec_ctrl_current(void) +{ + return this_cpu_read(x86_spec_ctrl_current); +} +EXPORT_SYMBOL_GPL(spec_ctrl_current); /* * AMD specific MSR info for Speculative Store Bypass control. @@ -114,13 +140,21 @@ void __init check_bugs(void) if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); - /* Allow STIBP in MSR_SPEC_CTRL if supported */ - if (boot_cpu_has(X86_FEATURE_STIBP)) - x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; - /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); + /* + * retbleed_select_mitigation() relies on the state set by + * spectre_v2_select_mitigation(); specifically it wants to know about + * spectre_v2=ibrs. + */ + retbleed_select_mitigation(); + /* + * spectre_v2_user_select_mitigation() relies on the state set by + * retbleed_select_mitigation(); specifically the STIBP selection is + * forced for UNRET. + */ + spectre_v2_user_select_mitigation(); ssb_select_mitigation(); l1tf_select_mitigation(); md_clear_select_mitigation(); @@ -161,31 +195,17 @@ void __init check_bugs(void) #endif } +/* + * NOTE: This function is *only* called for SVM. VMX spec_ctrl handling is + * done in vmenter.S. + */ void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) { - u64 msrval, guestval, hostval = x86_spec_ctrl_base; + u64 msrval, guestval = guest_spec_ctrl, hostval = spec_ctrl_current(); struct thread_info *ti = current_thread_info(); - /* Is MSR_SPEC_CTRL implemented ? */ if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) { - /* - * Restrict guest_spec_ctrl to supported values. Clear the - * modifiable bits in the host base value and or the - * modifiable bits from the guest value. - */ - guestval = hostval & ~x86_spec_ctrl_mask; - guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; - - /* SSBD controlled in MSR_SPEC_CTRL */ - if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - static_cpu_has(X86_FEATURE_AMD_SSBD)) - hostval |= ssbd_tif_to_spec_ctrl(ti->flags); - - /* Conditional STIBP enabled? */ - if (static_branch_unlikely(&switch_to_cond_stibp)) - hostval |= stibp_tif_to_spec_ctrl(ti->flags); - if (hostval != guestval) { msrval = setguest ? guestval : hostval; wrmsrl(MSR_IA32_SPEC_CTRL, msrval); @@ -752,12 +772,180 @@ static int __init nospectre_v1_cmdline(char *str) } early_param("nospectre_v1", nospectre_v1_cmdline); -#undef pr_fmt -#define pr_fmt(fmt) "Spectre V2 : " fmt - static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = SPECTRE_V2_NONE; +#undef pr_fmt +#define pr_fmt(fmt) "RETBleed: " fmt + +enum retbleed_mitigation { + RETBLEED_MITIGATION_NONE, + RETBLEED_MITIGATION_UNRET, + RETBLEED_MITIGATION_IBPB, + RETBLEED_MITIGATION_IBRS, + RETBLEED_MITIGATION_EIBRS, +}; + +enum retbleed_mitigation_cmd { + RETBLEED_CMD_OFF, + RETBLEED_CMD_AUTO, + RETBLEED_CMD_UNRET, + RETBLEED_CMD_IBPB, +}; + +static const char * const retbleed_strings[] = { + [RETBLEED_MITIGATION_NONE] = "Vulnerable", + [RETBLEED_MITIGATION_UNRET] = "Mitigation: untrained return thunk", + [RETBLEED_MITIGATION_IBPB] = "Mitigation: IBPB", + [RETBLEED_MITIGATION_IBRS] = "Mitigation: IBRS", + [RETBLEED_MITIGATION_EIBRS] = "Mitigation: Enhanced IBRS", +}; + +static enum retbleed_mitigation retbleed_mitigation __ro_after_init = + RETBLEED_MITIGATION_NONE; +static enum retbleed_mitigation_cmd retbleed_cmd __ro_after_init = + RETBLEED_CMD_AUTO; + +static int __ro_after_init retbleed_nosmt = false; + +static int __init retbleed_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + while (str) { + char *next = strchr(str, ','); + if (next) { + *next = 0; + next++; + } + + if (!strcmp(str, "off")) { + retbleed_cmd = RETBLEED_CMD_OFF; + } else if (!strcmp(str, "auto")) { + retbleed_cmd = RETBLEED_CMD_AUTO; + } else if (!strcmp(str, "unret")) { + retbleed_cmd = RETBLEED_CMD_UNRET; + } else if (!strcmp(str, "ibpb")) { + retbleed_cmd = RETBLEED_CMD_IBPB; + } else if (!strcmp(str, "nosmt")) { + retbleed_nosmt = true; + } else { + pr_err("Ignoring unknown retbleed option (%s).", str); + } + + str = next; + } + + return 0; +} +early_param("retbleed", retbleed_parse_cmdline); + +#define RETBLEED_UNTRAIN_MSG "WARNING: BTB untrained return thunk mitigation is only effective on AMD/Hygon!\n" +#define RETBLEED_INTEL_MSG "WARNING: Spectre v2 mitigation leaves CPU vulnerable to RETBleed attacks, data leaks possible!\n" + +static void __init retbleed_select_mitigation(void) +{ + bool mitigate_smt = false; + + if (!boot_cpu_has_bug(X86_BUG_RETBLEED) || cpu_mitigations_off()) + return; + + switch (retbleed_cmd) { + case RETBLEED_CMD_OFF: + return; + + case RETBLEED_CMD_UNRET: + if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) { + retbleed_mitigation = RETBLEED_MITIGATION_UNRET; + } else { + pr_err("WARNING: kernel not compiled with CPU_UNRET_ENTRY.\n"); + goto do_cmd_auto; + } + break; + + case RETBLEED_CMD_IBPB: + if (!boot_cpu_has(X86_FEATURE_IBPB)) { + pr_err("WARNING: CPU does not support IBPB.\n"); + goto do_cmd_auto; + } else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + retbleed_mitigation = RETBLEED_MITIGATION_IBPB; + } else { + pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + goto do_cmd_auto; + } + break; + +do_cmd_auto: + case RETBLEED_CMD_AUTO: + default: + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { + if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) + retbleed_mitigation = RETBLEED_MITIGATION_UNRET; + else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY) && boot_cpu_has(X86_FEATURE_IBPB)) + retbleed_mitigation = RETBLEED_MITIGATION_IBPB; + } + + /* + * The Intel mitigation (IBRS or eIBRS) was already selected in + * spectre_v2_select_mitigation(). 'retbleed_mitigation' will + * be set accordingly below. + */ + + break; + } + + switch (retbleed_mitigation) { + case RETBLEED_MITIGATION_UNRET: + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_UNRET); + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + pr_err(RETBLEED_UNTRAIN_MSG); + + mitigate_smt = true; + break; + + case RETBLEED_MITIGATION_IBPB: + setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + mitigate_smt = true; + break; + + default: + break; + } + + if (mitigate_smt && !boot_cpu_has(X86_FEATURE_STIBP) && + (retbleed_nosmt || cpu_mitigations_auto_nosmt())) + cpu_smt_disable(false); + + /* + * Let IBRS trump all on Intel without affecting the effects of the + * retbleed= cmdline option. + */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { + switch (spectre_v2_enabled) { + case SPECTRE_V2_IBRS: + retbleed_mitigation = RETBLEED_MITIGATION_IBRS; + break; + case SPECTRE_V2_EIBRS: + case SPECTRE_V2_EIBRS_RETPOLINE: + case SPECTRE_V2_EIBRS_LFENCE: + retbleed_mitigation = RETBLEED_MITIGATION_EIBRS; + break; + default: + pr_err(RETBLEED_INTEL_MSG); + } + } + + pr_info("%s\n", retbleed_strings[retbleed_mitigation]); +} + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V2 : " fmt + static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = SPECTRE_V2_USER_NONE; static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = @@ -787,6 +975,7 @@ static inline const char *spectre_v2_module_string(void) { return ""; } #define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n" #define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n" #define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n" +#define SPECTRE_V2_IBRS_PERF_MSG "WARNING: IBRS mitigation selected on Enhanced IBRS CPU, this may cause unnecessary performance loss\n" #ifdef CONFIG_BPF_SYSCALL void unpriv_ebpf_notify(int new_state) @@ -828,6 +1017,7 @@ enum spectre_v2_mitigation_cmd { SPECTRE_V2_CMD_EIBRS, SPECTRE_V2_CMD_EIBRS_RETPOLINE, SPECTRE_V2_CMD_EIBRS_LFENCE, + SPECTRE_V2_CMD_IBRS, }; enum spectre_v2_user_cmd { @@ -868,13 +1058,15 @@ static void __init spec_v2_user_print_cond(const char *reason, bool secure) pr_info("spectre_v2_user=%s forced on command line.\n", reason); } +static __ro_after_init enum spectre_v2_mitigation_cmd spectre_v2_cmd; + static enum spectre_v2_user_cmd __init -spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd) +spectre_v2_parse_user_cmdline(void) { char arg[20]; int ret, i; - switch (v2_cmd) { + switch (spectre_v2_cmd) { case SPECTRE_V2_CMD_NONE: return SPECTRE_V2_USER_CMD_NONE; case SPECTRE_V2_CMD_FORCE: @@ -900,15 +1092,16 @@ spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd) return SPECTRE_V2_USER_CMD_AUTO; } -static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) +static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) { - return (mode == SPECTRE_V2_EIBRS || - mode == SPECTRE_V2_EIBRS_RETPOLINE || - mode == SPECTRE_V2_EIBRS_LFENCE); + return mode == SPECTRE_V2_IBRS || + mode == SPECTRE_V2_EIBRS || + mode == SPECTRE_V2_EIBRS_RETPOLINE || + mode == SPECTRE_V2_EIBRS_LFENCE; } static void __init -spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) +spectre_v2_user_select_mitigation(void) { enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE; bool smt_possible = IS_ENABLED(CONFIG_SMP); @@ -921,7 +1114,7 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) cpu_smt_control == CPU_SMT_NOT_SUPPORTED) smt_possible = false; - cmd = spectre_v2_parse_user_cmdline(v2_cmd); + cmd = spectre_v2_parse_user_cmdline(); switch (cmd) { case SPECTRE_V2_USER_CMD_NONE: goto set_mode; @@ -969,12 +1162,12 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) } /* - * If no STIBP, enhanced IBRS is enabled or SMT impossible, STIBP is not - * required. + * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible, + * STIBP is not required. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + spectre_v2_in_ibrs_mode(spectre_v2_enabled)) return; /* @@ -986,6 +1179,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) mode = SPECTRE_V2_USER_STRICT_PREFERRED; + if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET) { + if (mode != SPECTRE_V2_USER_STRICT && + mode != SPECTRE_V2_USER_STRICT_PREFERRED) + pr_info("Selecting STIBP always-on mode to complement retbleed mitigation\n"); + mode = SPECTRE_V2_USER_STRICT_PREFERRED; + } + spectre_v2_user_stibp = mode; set_mode: @@ -999,6 +1199,7 @@ static const char * const spectre_v2_strings[] = { [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", + [SPECTRE_V2_IBRS] = "Mitigation: IBRS", }; static const struct { @@ -1016,6 +1217,7 @@ static const struct { { "eibrs,lfence", SPECTRE_V2_CMD_EIBRS_LFENCE, false }, { "eibrs,retpoline", SPECTRE_V2_CMD_EIBRS_RETPOLINE, false }, { "auto", SPECTRE_V2_CMD_AUTO, false }, + { "ibrs", SPECTRE_V2_CMD_IBRS, false }, }; static void __init spec_v2_print_cond(const char *reason, bool secure) @@ -1078,6 +1280,30 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return SPECTRE_V2_CMD_AUTO; } + if (cmd == SPECTRE_V2_CMD_IBRS && !IS_ENABLED(CONFIG_CPU_IBRS_ENTRY)) { + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { + pr_err("%s selected but not Intel CPU. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_IBRS && !boot_cpu_has(X86_FEATURE_IBRS)) { + pr_err("%s selected but CPU doesn't have IBRS. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_has(X86_FEATURE_XENPV)) { + pr_err("%s selected but running as XenPV guest. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + spec_v2_print_cond(mitigation_options[i].option, mitigation_options[i].secure); return cmd; @@ -1093,6 +1319,22 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) return SPECTRE_V2_RETPOLINE; } +/* Disable in-kernel use of non-RSB RET predictors */ +static void __init spec_ctrl_disable_kernel_rrsba(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + return; + + ia32_cap = x86_read_arch_cap_msr(); + + if (ia32_cap & ARCH_CAP_RRSBA) { + x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; + write_spec_ctrl_current(x86_spec_ctrl_base, true); + } +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1117,6 +1359,15 @@ static void __init spectre_v2_select_mitigation(void) break; } + if (IS_ENABLED(CONFIG_CPU_IBRS_ENTRY) && + boot_cpu_has_bug(X86_BUG_RETBLEED) && + retbleed_cmd != RETBLEED_CMD_OFF && + boot_cpu_has(X86_FEATURE_IBRS) && + boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { + mode = SPECTRE_V2_IBRS; + break; + } + mode = spectre_v2_select_retpoline(); break; @@ -1133,6 +1384,10 @@ static void __init spectre_v2_select_mitigation(void) mode = spectre_v2_select_retpoline(); break; + case SPECTRE_V2_CMD_IBRS: + mode = SPECTRE_V2_IBRS; + break; + case SPECTRE_V2_CMD_EIBRS: mode = SPECTRE_V2_EIBRS; break; @@ -1149,10 +1404,9 @@ static void __init spectre_v2_select_mitigation(void) if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); - if (spectre_v2_in_eibrs_mode(mode)) { - /* Force it so VMEXIT will restore correctly */ + if (spectre_v2_in_ibrs_mode(mode)) { x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + write_spec_ctrl_current(x86_spec_ctrl_base, true); } switch (mode) { @@ -1160,6 +1414,12 @@ static void __init spectre_v2_select_mitigation(void) case SPECTRE_V2_EIBRS: break; + case SPECTRE_V2_IBRS: + setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS); + if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) + pr_warn(SPECTRE_V2_IBRS_PERF_MSG); + break; + case SPECTRE_V2_LFENCE: case SPECTRE_V2_EIBRS_LFENCE: setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE); @@ -1171,43 +1431,116 @@ static void __init spectre_v2_select_mitigation(void) break; } + /* + * Disable alternate RSB predictions in kernel when indirect CALLs and + * JMPs gets protection against BHI and Intramode-BTI, but RET + * prediction from a non-RSB predictor is still a risk. + */ + if (mode == SPECTRE_V2_EIBRS_LFENCE || + mode == SPECTRE_V2_EIBRS_RETPOLINE || + mode == SPECTRE_V2_RETPOLINE) + spec_ctrl_disable_kernel_rrsba(); + spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); /* - * If spectre v2 protection has been enabled, unconditionally fill - * RSB during a context switch; this protects against two independent - * issues: + * If Spectre v2 protection has been enabled, fill the RSB during a + * context switch. In general there are two types of RSB attacks + * across context switches, for which the CALLs/RETs may be unbalanced. + * + * 1) RSB underflow + * + * Some Intel parts have "bottomless RSB". When the RSB is empty, + * speculated return targets may come from the branch predictor, + * which could have a user-poisoned BTB or BHB entry. + * + * AMD has it even worse: *all* returns are speculated from the BTB, + * regardless of the state of the RSB. * - * - RSB underflow (and switch to BTB) on Skylake+ - * - SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs + * When IBRS or eIBRS is enabled, the "user -> kernel" attack + * scenario is mitigated by the IBRS branch prediction isolation + * properties, so the RSB buffer filling wouldn't be necessary to + * protect against this type of attack. + * + * The "user -> user" attack scenario is mitigated by RSB filling. + * + * 2) Poisoned RSB entry + * + * If the 'next' in-kernel return stack is shorter than 'prev', + * 'next' could be tricked into speculating with a user-poisoned RSB + * entry. + * + * The "user -> kernel" attack scenario is mitigated by SMEP and + * eIBRS. + * + * The "user -> user" scenario, also known as SpectreBHB, requires + * RSB clearing. + * + * So to mitigate all cases, unconditionally fill RSB on context + * switches. + * + * FIXME: Is this pointless for retbleed-affected AMD? */ setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n"); /* - * Retpoline means the kernel is safe because it has no indirect - * branches. Enhanced IBRS protects firmware too, so, enable restricted - * speculation around firmware calls only when Enhanced IBRS isn't - * supported. + * Similar to context switches, there are two types of RSB attacks + * after vmexit: + * + * 1) RSB underflow + * + * 2) Poisoned RSB entry + * + * When retpoline is enabled, both are mitigated by filling/clearing + * the RSB. + * + * When IBRS is enabled, while #1 would be mitigated by the IBRS branch + * prediction isolation protections, RSB still needs to be cleared + * because of #2. Note that SMEP provides no protection here, unlike + * user-space-poisoned RSB entries. + * + * eIBRS, on the other hand, has RSB-poisoning protections, so it + * doesn't need RSB clearing after vmexit. + */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) || + boot_cpu_has(X86_FEATURE_KERNEL_IBRS)) + setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); + + /* + * Retpoline protects the kernel, but doesn't protect firmware. IBRS + * and Enhanced IBRS protect firmware too, so enable IBRS around + * firmware calls only when IBRS / Enhanced IBRS aren't otherwise + * enabled. * * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because * the user might select retpoline on the kernel command line and if * the CPU supports Enhanced IBRS, kernel might un-intentionally not * enable IBRS around firmware calls. */ - if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_eibrs_mode(mode)) { + if (boot_cpu_has_bug(X86_BUG_RETBLEED) && + (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) { + + if (retbleed_cmd != RETBLEED_CMD_IBPB) { + setup_force_cpu_cap(X86_FEATURE_USE_IBPB_FW); + pr_info("Enabling Speculation Barrier for firmware calls\n"); + } + + } else if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } /* Set up IBPB and STIBP depending on the general spectre V2 command */ - spectre_v2_user_select_mitigation(cmd); + spectre_v2_cmd = cmd; } static void update_stibp_msr(void * __unused) { - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + u64 val = spec_ctrl_current() | (x86_spec_ctrl_base & SPEC_CTRL_STIBP); + write_spec_ctrl_current(val, true); } /* Update x86_spec_ctrl_base in case SMT state changed. */ @@ -1424,16 +1757,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) } /* - * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper - * bit in the mask to allow guests to use the mitigation even in the - * case where the host does not enable it. - */ - if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - static_cpu_has(X86_FEATURE_AMD_SSBD)) { - x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; - } - - /* * We have three CPU feature flags that are in play here: * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass @@ -1450,7 +1773,7 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) x86_amd_ssb_disable(); } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + write_spec_ctrl_current(x86_spec_ctrl_base, true); } } @@ -1701,7 +2024,7 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) void x86_spec_ctrl_setup_ap(void) { if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + write_spec_ctrl_current(x86_spec_ctrl_base, true); if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) x86_amd_ssb_disable(); @@ -1938,7 +2261,7 @@ static ssize_t mmio_stale_data_show_state(char *buf) static char *stibp_state(void) { - if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_ibrs_mode(spectre_v2_enabled)) return ""; switch (spectre_v2_user_stibp) { @@ -1994,6 +2317,24 @@ static ssize_t srbds_show_state(char *buf) return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); } +static ssize_t retbleed_show_state(char *buf) +{ + if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return sprintf(buf, "Vulnerable: untrained return thunk on non-Zen uarch\n"); + + return sprintf(buf, "%s; SMT %s\n", + retbleed_strings[retbleed_mitigation], + !sched_smt_active() ? "disabled" : + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? + "enabled with STIBP protection" : "vulnerable"); + } + + return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -2039,6 +2380,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_MMIO_STALE_DATA: return mmio_stale_data_show_state(buf); + case X86_BUG_RETBLEED: + return retbleed_show_state(buf); + default: break; } @@ -2095,4 +2439,9 @@ ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *at { return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); } + +ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4730b0a58f24..736262a76a12 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1205,48 +1205,60 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { {} }; +#define VULNBL(vendor, family, model, blacklist) \ + X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist) + #define VULNBL_INTEL_STEPPINGS(model, steppings, issues) \ X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, \ INTEL_FAM6_##model, steppings, \ X86_FEATURE_ANY, issues) +#define VULNBL_AMD(family, blacklist) \ + VULNBL(AMD, family, X86_MODEL_ANY, blacklist) + +#define VULNBL_HYGON(family, blacklist) \ + VULNBL(HYGON, family, X86_MODEL_ANY, blacklist) + #define SRBDS BIT(0) /* CPU is affected by X86_BUG_MMIO_STALE_DATA */ #define MMIO BIT(1) /* CPU is affected by Shared Buffers Data Sampling (SBDS), a variant of X86_BUG_MMIO_STALE_DATA */ #define MMIO_SBDS BIT(2) +/* CPU is affected by RETbleed, speculating where you would not expect it */ +#define RETBLEED BIT(3) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(HASWELL, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(HASWELL_L, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(HASWELL_G, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(HASWELL_X, BIT(2) | BIT(4), MMIO), - VULNBL_INTEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x3, 0x5), MMIO), + VULNBL_INTEL_STEPPINGS(HASWELL_X, X86_STEPPING_ANY, MMIO), + VULNBL_INTEL_STEPPINGS(BROADWELL_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO), - VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE_X, BIT(3) | BIT(4) | BIT(6) | - BIT(7) | BIT(0xB), MMIO), - VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO), - VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x9, 0xC), SRBDS | MMIO), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0x8), SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x9, 0xD), SRBDS | MMIO), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0x8), SRBDS), - VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPINGS(0x5, 0x5), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPINGS(0x1, 0x1), MMIO), - VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPINGS(0x4, 0x6), MMIO), - VULNBL_INTEL_STEPPINGS(COMETLAKE, BIT(2) | BIT(3) | BIT(5), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO), - VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPINGS(0x1, 0x1), MMIO), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO), + VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO), + VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPINGS(0x0, 0x0), MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), + + VULNBL_AMD(0x15, RETBLEED), + VULNBL_AMD(0x16, RETBLEED), + VULNBL_AMD(0x17, RETBLEED), + VULNBL_HYGON(0x18, RETBLEED), {} }; @@ -1348,6 +1360,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !arch_cap_mmio_immune(ia32_cap)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + if (!cpu_has(c, X86_FEATURE_BTC_NO)) { + if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) + setup_force_cpu_bug(X86_BUG_RETBLEED); + } + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 2a8e584fc991..7c9b5893c30a 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -61,6 +61,8 @@ static inline void tsx_init(void) { } static inline void tsx_ap_init(void) { } #endif /* CONFIG_CPU_SUP_INTEL */ +extern void init_spectral_chicken(struct cpuinfo_x86 *c); + extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void get_cpu_address_sizes(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index 3fcdda4c1e11..21fd425088fe 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -302,6 +302,12 @@ static void init_hygon(struct cpuinfo_x86 *c) /* get apicid instead of initial apic id from cpuid */ c->apicid = hard_smp_processor_id(); + /* + * XXX someone from Hygon needs to confirm this DTRT + * + init_spectral_chicken(c); + */ + set_cpu_cap(c, X86_FEATURE_ZEN); set_cpu_cap(c, X86_FEATURE_CPB); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index dbaa8326d6f2..fd44b54c90d5 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 }, + { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 5b4efc927d80..24b9fa89aa27 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -301,7 +301,7 @@ union ftrace_op_code_union { } __attribute__((packed)); }; -#define RET_SIZE 1 + IS_ENABLED(CONFIG_SLS) +#define RET_SIZE (IS_ENABLED(CONFIG_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_SLS)) static unsigned long create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) @@ -357,7 +357,10 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) goto fail; ip = trampoline + size; - memcpy(ip, retq, RET_SIZE); + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, &__x86_return_thunk, JMP32_INSN_SIZE); + else + memcpy(ip, retq, sizeof(retq)); /* No need to test direct calls on created trampolines */ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index eb8656bac99b..9b7acc9c7874 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -23,6 +23,7 @@ #include <asm/cpufeatures.h> #include <asm/percpu.h> #include <asm/nops.h> +#include <asm/nospec-branch.h> #include <asm/bootparam.h> #include <asm/export.h> #include <asm/pgtable_32.h> diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 92c4afa2b729..d860d437631b 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -389,6 +389,8 @@ SYM_CODE_START_NOALIGN(vc_boot_ghcb) UNWIND_HINT_IRET_REGS offset=8 ENDBR + ANNOTATE_UNRET_END + /* Build pt_regs */ PUSH_AND_CLEAR_REGS @@ -448,6 +450,7 @@ SYM_CODE_END(early_idt_handler_array) SYM_CODE_START_LOCAL(early_idt_handler_common) UNWIND_HINT_IRET_REGS offset=16 + ANNOTATE_UNRET_END /* * The stack is the hardware frame, an error code or zero, and the * vector number. @@ -497,6 +500,8 @@ SYM_CODE_START_NOALIGN(vc_no_ghcb) UNWIND_HINT_IRET_REGS offset=8 ENDBR + ANNOTATE_UNRET_END + /* Build pt_regs */ PUSH_AND_CLEAR_REGS diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index b98ffcf4d250..67828d973389 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -253,7 +253,7 @@ int module_finalize(const Elf_Ehdr *hdr, { const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL, *para = NULL, *orc = NULL, *orc_ip = NULL, - *retpolines = NULL, *ibt_endbr = NULL; + *retpolines = NULL, *returns = NULL, *ibt_endbr = NULL; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { @@ -271,6 +271,8 @@ int module_finalize(const Elf_Ehdr *hdr, orc_ip = s; if (!strcmp(".retpoline_sites", secstrings + s->sh_name)) retpolines = s; + if (!strcmp(".return_sites", secstrings + s->sh_name)) + returns = s; if (!strcmp(".ibt_endbr_seal", secstrings + s->sh_name)) ibt_endbr = s; } @@ -287,6 +289,10 @@ int module_finalize(const Elf_Ehdr *hdr, void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); } + if (returns) { + void *rseg = (void *)returns->sh_addr; + apply_returns(rseg, rseg + returns->sh_size); + } if (alt) { /* patch .altinstructions */ void *aseg = (void *)alt->sh_addr; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 9b2772b7e1f3..d456ce21c255 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -600,7 +600,7 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, } if (updmsr) - wrmsrl(MSR_IA32_SPEC_CTRL, msr); + write_spec_ctrl_current(msr, false); } static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index fcc8a7699103..c7c4b1917336 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -7,10 +7,12 @@ #include <linux/linkage.h> #include <asm/page_types.h> #include <asm/kexec.h> +#include <asm/nospec-branch.h> #include <asm/processor-flags.h> /* - * Must be relocatable PIC code callable as a C function + * Must be relocatable PIC code callable as a C function, in particular + * there must be a plain RET and not jump to return thunk. */ #define PTR(x) (x << 2) @@ -91,7 +93,9 @@ SYM_CODE_START_NOALIGN(relocate_kernel) movl %edi, %eax addl $(identity_mapped - relocate_kernel), %eax pushl %eax - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(relocate_kernel) SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) @@ -159,12 +163,15 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) xorl %edx, %edx xorl %esi, %esi xorl %ebp, %ebp - RET + ANNOTATE_UNRET_SAFE + ret + int3 1: popl %edx movl CP_PA_SWAP_PAGE(%edi), %esp addl $PAGE_SIZE, %esp 2: + ANNOTATE_RETPOLINE_SAFE call *%edx /* get the re-entry point of the peer system */ @@ -190,7 +197,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) movl %edi, %eax addl $(virtual_mapped - relocate_kernel), %eax pushl %eax - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(identity_mapped) SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) @@ -208,7 +217,9 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) popl %edi popl %esi popl %ebx - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(virtual_mapped) /* Do the copies */ @@ -271,7 +282,9 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) popl %edi popl %ebx popl %ebp - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(swap_pages) .globl kexec_control_code_size diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index c1d8626c53b6..4809c0dc4eb0 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -13,7 +13,8 @@ #include <asm/unwind_hints.h> /* - * Must be relocatable PIC code callable as a C function + * Must be relocatable PIC code callable as a C function, in particular + * there must be a plain RET and not jump to return thunk. */ #define PTR(x) (x << 3) @@ -105,7 +106,9 @@ SYM_CODE_START_NOALIGN(relocate_kernel) /* jump to identity mapped page */ addq $(identity_mapped - relocate_kernel), %r8 pushq %r8 - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(relocate_kernel) SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) @@ -200,7 +203,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) xorl %r14d, %r14d xorl %r15d, %r15d - RET + ANNOTATE_UNRET_SAFE + ret + int3 1: popq %rdx @@ -219,7 +224,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) call swap_pages movq $virtual_mapped, %rax pushq %rax - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(identity_mapped) SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) @@ -241,7 +248,9 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) popq %r12 popq %rbp popq %rbx - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(virtual_mapped) /* Do the copies */ @@ -298,7 +307,9 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) lea PAGE_SIZE(%rax), %rsi jmp 0b 3: - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(swap_pages) .globl kexec_control_code_size diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index aa72cefdd5be..aaaba85d6d7f 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -12,13 +12,21 @@ enum insn_type { }; /* + * ud1 %esp, %ecx - a 3 byte #UD that is unique to trampolines, chosen such + * that there is no false-positive trampoline identification while also being a + * speculation stop. + */ +static const u8 tramp_ud[] = { 0x0f, 0xb9, 0xcc }; + +/* * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax */ static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; -static void __ref __static_call_transform(void *insn, enum insn_type type, void *func) +static void __ref __static_call_transform(void *insn, enum insn_type type, + void *func, bool modinit) { const void *emulate = NULL; int size = CALL_INSN_SIZE; @@ -43,14 +51,17 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void break; case RET: - code = &retinsn; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk); + else + code = &retinsn; break; } if (memcmp(insn, code, size) == 0) return; - if (unlikely(system_state == SYSTEM_BOOTING)) + if (system_state == SYSTEM_BOOTING || modinit) return text_poke_early(insn, code, size); text_poke_bp(insn, code, size, emulate); @@ -60,7 +71,7 @@ static void __static_call_validate(void *insn, bool tail, bool tramp) { u8 opcode = *(u8 *)insn; - if (tramp && memcmp(insn+5, "SCT", 3)) { + if (tramp && memcmp(insn+5, tramp_ud, 3)) { pr_err("trampoline signature fail"); BUG(); } @@ -104,14 +115,42 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) if (tramp) { __static_call_validate(tramp, true, true); - __static_call_transform(tramp, __sc_insn(!func, true), func); + __static_call_transform(tramp, __sc_insn(!func, true), func, false); } if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site) { __static_call_validate(site, tail, false); - __static_call_transform(site, __sc_insn(!func, tail), func); + __static_call_transform(site, __sc_insn(!func, tail), func, false); } mutex_unlock(&text_mutex); } EXPORT_SYMBOL_GPL(arch_static_call_transform); + +#ifdef CONFIG_RETHUNK +/* + * This is called by apply_returns() to fix up static call trampolines, + * specifically ARCH_DEFINE_STATIC_CALL_NULL_TRAMP which is recorded as + * having a return trampoline. + * + * The problem is that static_call() is available before determining + * X86_FEATURE_RETHUNK and, by implication, running alternatives. + * + * This means that __static_call_transform() above can have overwritten the + * return trampoline and we now need to fix things up to be consistent. + */ +bool __static_call_fixup(void *tramp, u8 op, void *dest) +{ + if (memcmp(tramp+5, tramp_ud, 3)) { + /* Not a trampoline site, not our problem. */ + return false; + } + + mutex_lock(&text_mutex); + if (op == RET_INSN_OPCODE || dest == &__x86_return_thunk) + __static_call_transform(tramp, RET, NULL, true); + mutex_unlock(&text_mutex); + + return true; +} +#endif diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 9487ce8c13ee..15f29053cec4 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -141,7 +141,7 @@ SECTIONS #ifdef CONFIG_RETPOLINE __indirect_thunk_start = .; - *(.text.__x86.indirect_thunk) + *(.text.__x86.*) __indirect_thunk_end = .; #endif } :text =0xcccc @@ -283,6 +283,13 @@ SECTIONS *(.retpoline_sites) __retpoline_sites_end = .; } + + . = ALIGN(8); + .return_sites : AT(ADDR(.return_sites) - LOAD_OFFSET) { + __return_sites = .; + *(.return_sites) + __return_sites_end = .; + } #endif #ifdef CONFIG_X86_KERNEL_IBT diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 89b11e7dca8a..f8382abe22ff 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -189,9 +189,6 @@ #define X8(x...) X4(x), X4(x) #define X16(x...) X8(x), X8(x) -#define NR_FASTOP (ilog2(sizeof(ulong)) + 1) -#define FASTOP_SIZE (8 * (1 + HAS_KERNEL_IBT)) - struct opcode { u64 flags; u8 intercept; @@ -306,9 +303,15 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for * different operand sizes can be reached by calculation, rather than a jump * table (which would be bigger than the code). + * + * The 16 byte alignment, considering 5 bytes for the RET thunk, 3 for ENDBR + * and 1 for the straight line speculation INT3, leaves 7 bytes for the + * body of the function. Currently none is larger than 4. */ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); +#define FASTOP_SIZE 16 + #define __FOP_FUNC(name) \ ".align " __stringify(FASTOP_SIZE) " \n\t" \ ".type " name ", @function \n\t" \ @@ -325,13 +328,15 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define FOP_RET(name) \ __FOP_RET(#name) -#define FOP_START(op) \ +#define __FOP_START(op, align) \ extern void em_##op(struct fastop *fake); \ asm(".pushsection .text, \"ax\" \n\t" \ ".global em_" #op " \n\t" \ - ".align " __stringify(FASTOP_SIZE) " \n\t" \ + ".align " __stringify(align) " \n\t" \ "em_" #op ":\n\t" +#define FOP_START(op) __FOP_START(op, FASTOP_SIZE) + #define FOP_END \ ".popsection") @@ -435,17 +440,12 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); /* * Depending on .config the SETcc functions look like: * - * ENDBR [4 bytes; CONFIG_X86_KERNEL_IBT] - * SETcc %al [3 bytes] - * RET [1 byte] - * INT3 [1 byte; CONFIG_SLS] - * - * Which gives possible sizes 4, 5, 8 or 9. When rounded up to the - * next power-of-two alignment they become 4, 8 or 16 resp. + * ENDBR [4 bytes; CONFIG_X86_KERNEL_IBT] + * SETcc %al [3 bytes] + * RET | JMP __x86_return_thunk [1,5 bytes; CONFIG_RETHUNK] + * INT3 [1 byte; CONFIG_SLS] */ -#define SETCC_LENGTH (ENDBR_INSN_SIZE + 4 + IS_ENABLED(CONFIG_SLS)) -#define SETCC_ALIGN (4 << IS_ENABLED(CONFIG_SLS) << HAS_KERNEL_IBT) -static_assert(SETCC_LENGTH <= SETCC_ALIGN); +#define SETCC_ALIGN 16 #define FOP_SETCC(op) \ ".align " __stringify(SETCC_ALIGN) " \n\t" \ @@ -453,9 +453,10 @@ static_assert(SETCC_LENGTH <= SETCC_ALIGN); #op ": \n\t" \ ASM_ENDBR \ #op " %al \n\t" \ - __FOP_RET(#op) + __FOP_RET(#op) \ + ".skip " __stringify(SETCC_ALIGN) " - (.-" #op "), 0xcc \n\t" -FOP_START(setcc) +__FOP_START(setcc, SETCC_ALIGN) FOP_SETCC(seto) FOP_SETCC(setno) FOP_SETCC(setc) diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index dfaeb47fcf2a..723f8534986c 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -111,6 +111,15 @@ SYM_FUNC_START(__svm_vcpu_run) #endif /* + * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be + * untrained as soon as we exit the VM and are back to the + * kernel. This should be done before re-enabling interrupts + * because interrupt handlers won't sanitize 'ret' if the return is + * from the kernel. + */ + UNTRAIN_RET + + /* * Clear all general purpose registers except RSP and RAX to prevent * speculative use of the guest's values, even those that are reloaded * via the stack. In theory, an L1 cache miss when restoring registers @@ -190,6 +199,15 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif + /* + * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be + * untrained as soon as we exit the VM and are back to the + * kernel. This should be done before re-enabling interrupts + * because interrupt handlers won't sanitize RET if the return is + * from the kernel. + */ + UNTRAIN_RET + pop %_ASM_BX #ifdef CONFIG_X86_64 diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 3f430e218375..c0e24826a86f 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -4,8 +4,8 @@ #include <asm/vmx.h> -#include "lapic.h" -#include "x86.h" +#include "../lapic.h" +#include "../x86.h" extern bool __read_mostly enable_vpid; extern bool __read_mostly flexpriority_enabled; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f5cb18e00e78..ab135f9ef52f 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2278,7 +2278,6 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_TSC_SCALING | SECONDARY_EXEC_DESC); if (nested_cpu_has(vmcs12, @@ -3087,7 +3086,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) } vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, - vmx->loaded_vmcs->launched); + __vmx_vcpu_run_flags(vmx)); if (vmx->msr_autoload.host.nr) vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h new file mode 100644 index 000000000000..edc3f16cc189 --- /dev/null +++ b/arch/x86/kvm/vmx/run_flags.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_VMX_RUN_FLAGS_H +#define __KVM_X86_VMX_RUN_FLAGS_H + +#define VMX_RUN_VMRESUME (1 << 0) +#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) + +#endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 435c187927c4..4182c7ffc909 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -1,10 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <asm/asm.h> +#include <asm/asm-offsets.h> #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> +#include <asm/percpu.h> #include <asm/segment.h> +#include "run_flags.h" #define WORD_SIZE (BITS_PER_LONG / 8) @@ -31,72 +34,11 @@ .section .noinstr.text, "ax" /** - * vmx_vmenter - VM-Enter the current loaded VMCS - * - * %RFLAGS.ZF: !VMCS.LAUNCHED, i.e. controls VMLAUNCH vs. VMRESUME - * - * Returns: - * %RFLAGS.CF is set on VM-Fail Invalid - * %RFLAGS.ZF is set on VM-Fail Valid - * %RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit - * - * Note that VMRESUME/VMLAUNCH fall-through and return directly if - * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump - * to vmx_vmexit. - */ -SYM_FUNC_START_LOCAL(vmx_vmenter) - /* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */ - je 2f - -1: vmresume - RET - -2: vmlaunch - RET - -3: cmpb $0, kvm_rebooting - je 4f - RET -4: ud2 - - _ASM_EXTABLE(1b, 3b) - _ASM_EXTABLE(2b, 3b) - -SYM_FUNC_END(vmx_vmenter) - -/** - * vmx_vmexit - Handle a VMX VM-Exit - * - * Returns: - * %RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit - * - * This is vmx_vmenter's partner in crime. On a VM-Exit, control will jump - * here after hardware loads the host's state, i.e. this is the destination - * referred to by VMCS.HOST_RIP. - */ -SYM_FUNC_START(vmx_vmexit) -#ifdef CONFIG_RETPOLINE - ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE - /* Preserve guest's RAX, it's used to stuff the RSB. */ - push %_ASM_AX - - /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE - - /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ - or $1, %_ASM_AX - - pop %_ASM_AX -.Lvmexit_skip_rsb: -#endif - RET -SYM_FUNC_END(vmx_vmexit) - -/** * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode - * @vmx: struct vcpu_vmx * (forwarded to vmx_update_host_rsp) + * @vmx: struct vcpu_vmx * * @regs: unsigned long * (to guest registers) - * @launched: %true if the VMCS has been launched + * @flags: VMX_RUN_VMRESUME: use VMRESUME instead of VMLAUNCH + * VMX_RUN_SAVE_SPEC_CTRL: save guest SPEC_CTRL into vmx->spec_ctrl * * Returns: * 0 on VM-Exit, 1 on VM-Fail @@ -115,24 +57,56 @@ SYM_FUNC_START(__vmx_vcpu_run) #endif push %_ASM_BX + /* Save @vmx for SPEC_CTRL handling */ + push %_ASM_ARG1 + + /* Save @flags for SPEC_CTRL handling */ + push %_ASM_ARG3 + /* * Save @regs, _ASM_ARG2 may be modified by vmx_update_host_rsp() and * @regs is needed after VM-Exit to save the guest's register values. */ push %_ASM_ARG2 - /* Copy @launched to BL, _ASM_ARG3 is volatile. */ + /* Copy @flags to BL, _ASM_ARG3 is volatile. */ mov %_ASM_ARG3B, %bl - /* Adjust RSP to account for the CALL to vmx_vmenter(). */ - lea -WORD_SIZE(%_ASM_SP), %_ASM_ARG2 + lea (%_ASM_SP), %_ASM_ARG2 call vmx_update_host_rsp + ALTERNATIVE "jmp .Lspec_ctrl_done", "", X86_FEATURE_MSR_SPEC_CTRL + + /* + * SPEC_CTRL handling: if the guest's SPEC_CTRL value differs from the + * host's, write the MSR. + * + * IMPORTANT: To avoid RSB underflow attacks and any other nastiness, + * there must not be any returns or indirect branches between this code + * and vmentry. + */ + mov 2*WORD_SIZE(%_ASM_SP), %_ASM_DI + movl VMX_spec_ctrl(%_ASM_DI), %edi + movl PER_CPU_VAR(x86_spec_ctrl_current), %esi + cmp %edi, %esi + je .Lspec_ctrl_done + mov $MSR_IA32_SPEC_CTRL, %ecx + xor %edx, %edx + mov %edi, %eax + wrmsr + +.Lspec_ctrl_done: + + /* + * Since vmentry is serializing on affected CPUs, there's no need for + * an LFENCE to stop speculation from skipping the wrmsr. + */ + /* Load @regs to RAX. */ mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - testb %bl, %bl + testb $VMX_RUN_VMRESUME, %bl /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -154,11 +128,37 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Enter guest mode */ - call vmx_vmenter + /* Check EFLAGS.ZF from 'testb' above */ + jz .Lvmlaunch + + /* + * After a successful VMRESUME/VMLAUNCH, control flow "magically" + * resumes below at 'vmx_vmexit' due to the VMCS HOST_RIP setting. + * So this isn't a typical function and objtool needs to be told to + * save the unwind state here and restore it below. + */ + UNWIND_HINT_SAVE + +/* + * If VMRESUME/VMLAUNCH and corresponding vmexit succeed, execution resumes at + * the 'vmx_vmexit' label below. + */ +.Lvmresume: + vmresume + jmp .Lvmfail + +.Lvmlaunch: + vmlaunch + jmp .Lvmfail - /* Jump on VM-Fail. */ - jbe 2f + _ASM_EXTABLE(.Lvmresume, .Lfixup) + _ASM_EXTABLE(.Lvmlaunch, .Lfixup) + +SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) + + /* Restore unwind state from before the VMRESUME/VMLAUNCH. */ + UNWIND_HINT_RESTORE + ENDBR /* Temporarily save guest's RAX. */ push %_ASM_AX @@ -185,21 +185,23 @@ SYM_FUNC_START(__vmx_vcpu_run) mov %r15, VCPU_R15(%_ASM_AX) #endif - /* Clear RAX to indicate VM-Exit (as opposed to VM-Fail). */ - xor %eax, %eax + /* Clear return value to indicate VM-Exit (as opposed to VM-Fail). */ + xor %ebx, %ebx +.Lclear_regs: /* - * Clear all general purpose registers except RSP and RAX to prevent + * Clear all general purpose registers except RSP and RBX to prevent * speculative use of the guest's values, even those that are reloaded * via the stack. In theory, an L1 cache miss when restoring registers * could lead to speculative execution with the guest's values. * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially * free. RSP and RAX are exempt as RSP is restored by hardware during - * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail. + * VM-Exit and RBX is explicitly loaded with 0 or 1 to hold the return + * value. */ -1: xor %ecx, %ecx + xor %eax, %eax + xor %ecx, %ecx xor %edx, %edx - xor %ebx, %ebx xor %ebp, %ebp xor %esi, %esi xor %edi, %edi @@ -216,8 +218,30 @@ SYM_FUNC_START(__vmx_vcpu_run) /* "POP" @regs. */ add $WORD_SIZE, %_ASM_SP - pop %_ASM_BX + /* + * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before + * the first unbalanced RET after vmexit! + * + * For retpoline or IBRS, RSB filling is needed to prevent poisoned RSB + * entries and (in some cases) RSB underflow. + * + * eIBRS has its own protection against poisoned RSB, so it doesn't + * need the RSB filling sequence. But it does need to be enabled + * before the first unbalanced RET. + */ + + FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT + + pop %_ASM_ARG2 /* @flags */ + pop %_ASM_ARG1 /* @vmx */ + + call vmx_spec_ctrl_restore_host + + /* Put return value in AX */ + mov %_ASM_BX, %_ASM_AX + + pop %_ASM_BX #ifdef CONFIG_X86_64 pop %r12 pop %r13 @@ -230,9 +254,15 @@ SYM_FUNC_START(__vmx_vcpu_run) pop %_ASM_BP RET - /* VM-Fail. Out-of-line to avoid a taken Jcc after VM-Exit. */ -2: mov $1, %eax - jmp 1b +.Lfixup: + cmpb $0, kvm_rebooting + jne .Lvmfail + ud2 +.Lvmfail: + /* VM-Fail: set return value to 1 */ + mov $1, %_ASM_BX + jmp .Lclear_regs + SYM_FUNC_END(__vmx_vcpu_run) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 3a919e49129b..be7c19374fdd 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -383,9 +383,9 @@ static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) if (!vmx->disable_fb_clear) return; - rdmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL); msr |= FB_CLEAR_DIS; - wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); /* Cache the MSR value to avoid reading it later */ vmx->msr_ia32_mcu_opt_ctrl = msr; } @@ -396,7 +396,7 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) return; vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; - wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); } static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) @@ -839,6 +839,24 @@ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) MSR_IA32_SPEC_CTRL); } +unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) +{ + unsigned int flags = 0; + + if (vmx->loaded_vmcs->launched) + flags |= VMX_RUN_VMRESUME; + + /* + * If writes to the SPEC_CTRL MSR aren't intercepted, the guest is free + * to change it directly without causing a vmexit. In that case read + * it after vmexit and store it in vmx->spec_ctrl. + */ + if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) + flags |= VMX_RUN_SAVE_SPEC_CTRL; + + return flags; +} + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { @@ -6813,6 +6831,31 @@ void noinstr vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) } } +void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, + unsigned int flags) +{ + u64 hostval = this_cpu_read(x86_spec_ctrl_current); + + if (!cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) + return; + + if (flags & VMX_RUN_SAVE_SPEC_CTRL) + vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL); + + /* + * If the guest/host SPEC_CTRL values differ, restore the host value. + * + * For legacy IBRS, the IBRS bit always needs to be written after + * transitioning from a less privileged predictor mode, regardless of + * whether the guest/host values differ. + */ + if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) || + vmx->spec_ctrl != hostval) + native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval); + + barrier_nospec(); +} + static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { switch (to_vmx(vcpu)->exit_reason.basic) { @@ -6826,7 +6869,8 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) } static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, - struct vcpu_vmx *vmx) + struct vcpu_vmx *vmx, + unsigned long flags) { guest_state_enter_irqoff(); @@ -6845,7 +6889,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, native_write_cr2(vcpu->arch.cr2); vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, - vmx->loaded_vmcs->launched); + flags); vcpu->arch.cr2 = native_read_cr2(); @@ -6944,36 +6988,8 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_wait_lapic_expire(vcpu); - /* - * If this vCPU has touched SPEC_CTRL, restore the guest's value if - * it's non-zero. Since vmentry is serialising on affected CPUs, there - * is no need to worry about the conditional branch over the wrmsr - * being speculatively taken. - */ - x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0); - /* The actual VMENTER/EXIT is in the .noinstr.text section. */ - vmx_vcpu_enter_exit(vcpu, vmx); - - /* - * We do not use IBRS in the kernel. If this vCPU has used the - * SPEC_CTRL MSR it may have left it on; save the value and - * turn it off. This is much more efficient than blindly adding - * it to the atomic save/restore list. Especially as the former - * (Saving guest MSRs on vmexit) doesn't even exist in KVM. - * - * For non-nested case: - * If the L01 MSR bitmap does not intercept the MSR, then we need to - * save it. - * - * For nested case: - * If the L02 MSR bitmap does not intercept the MSR, then we need to - * save it. - */ - if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) - vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - - x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); + vmx_vcpu_enter_exit(vcpu, vmx, __vmx_vcpu_run_flags(vmx)); /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) { diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 8d2342ede0c5..1e7f9453894b 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -8,11 +8,12 @@ #include <asm/intel_pt.h> #include "capabilities.h" -#include "kvm_cache_regs.h" +#include "../kvm_cache_regs.h" #include "posted_intr.h" #include "vmcs.h" #include "vmx_ops.h" -#include "cpuid.h" +#include "../cpuid.h" +#include "run_flags.h" #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 @@ -404,7 +405,10 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr); void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu); void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); -bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); +void vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, unsigned int flags); +unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx); +bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, + unsigned int flags); int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr); void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 5e7f41225780..5cfc49ddb1b4 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -8,7 +8,7 @@ #include "evmcs.h" #include "vmcs.h" -#include "x86.h" +#include "../x86.h" asmlinkage void vmread_error(unsigned long field, bool fault); __attribute__((regparm(0))) void vmread_error_trampoline(unsigned long field, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1910e1e78b15..e5fa335a4ea7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -298,7 +298,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, directed_yield_successful), STATS_DESC_COUNTER(VCPU, preemption_reported), STATS_DESC_COUNTER(VCPU, preemption_other), - STATS_DESC_ICOUNTER(VCPU, guest_mode) + STATS_DESC_IBOOLEAN(VCPU, guest_mode) }; const struct kvm_stats_header kvm_vcpu_stats_header = { @@ -6029,6 +6029,11 @@ split_irqchip_unlock: r = 0; break; case KVM_CAP_X86_USER_SPACE_MSR: + r = -EINVAL; + if (cap->args[0] & ~(KVM_MSR_EXIT_REASON_INVAL | + KVM_MSR_EXIT_REASON_UNKNOWN | + KVM_MSR_EXIT_REASON_FILTER)) + break; kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; break; @@ -6183,6 +6188,9 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) return -EFAULT; + if (filter.flags & ~KVM_MSR_FILTER_DEFAULT_DENY) + return -EINVAL; + for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) empty &= !filter.ranges[i].nmsrs; @@ -9143,15 +9151,17 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, */ static void kvm_pv_kick_cpu_op(struct kvm *kvm, int apicid) { - struct kvm_lapic_irq lapic_irq; - - lapic_irq.shorthand = APIC_DEST_NOSHORT; - lapic_irq.dest_mode = APIC_DEST_PHYSICAL; - lapic_irq.level = 0; - lapic_irq.dest_id = apicid; - lapic_irq.msi_redir_hint = false; + /* + * All other fields are unused for APIC_DM_REMRD, but may be consumed by + * common code, e.g. for tracing. Defer initialization to the compiler. + */ + struct kvm_lapic_irq lapic_irq = { + .delivery_mode = APIC_DM_REMRD, + .dest_mode = APIC_DEST_PHYSICAL, + .shorthand = APIC_DEST_NOSHORT, + .dest_id = apicid, + }; - lapic_irq.delivery_mode = APIC_DM_REMRD; kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } @@ -12631,9 +12641,9 @@ void kvm_arch_end_assignment(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); -bool kvm_arch_has_assigned_device(struct kvm *kvm) +bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) { - return atomic_read(&kvm->arch.assigned_device_count); + return arch_atomic_read(&kvm->arch.assigned_device_count); } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index d83cba364e31..724bbf83eb5b 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -39,7 +39,7 @@ SYM_FUNC_START(__memmove) /* FSRM implies ERMS => no length checks, do the copy directly */ .Lmemmove_begin_forward: ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM - ALTERNATIVE "", __stringify(movq %rdx, %rcx; rep movsb; RET), X86_FEATURE_ERMS + ALTERNATIVE "", "jmp .Lmemmove_erms", X86_FEATURE_ERMS /* * movsq instruction have many startup latency @@ -205,6 +205,11 @@ SYM_FUNC_START(__memmove) movb %r11b, (%rdi) 13: RET + +.Lmemmove_erms: + movq %rdx, %rcx + rep movsb + RET SYM_FUNC_END(__memmove) EXPORT_SYMBOL(__memmove) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index b2b2366885a2..073289a55f84 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -33,9 +33,9 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) UNWIND_HINT_EMPTY ANNOTATE_NOENDBR - ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ - __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE + ALTERNATIVE_2 __stringify(RETPOLINE \reg), \ + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE, \ + __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), ALT_NOT(X86_FEATURE_RETPOLINE) .endm @@ -67,3 +67,76 @@ SYM_CODE_END(__x86_indirect_thunk_array) #define GEN(reg) EXPORT_THUNK(reg) #include <asm/GEN-for-each-reg.h> #undef GEN + +/* + * This function name is magical and is used by -mfunction-return=thunk-extern + * for the compiler to generate JMPs to it. + */ +#ifdef CONFIG_RETHUNK + + .section .text.__x86.return_thunk + +/* + * Safety details here pertain to the AMD Zen{1,2} microarchitecture: + * 1) The RET at __x86_return_thunk must be on a 64 byte boundary, for + * alignment within the BTB. + * 2) The instruction at zen_untrain_ret must contain, and not + * end with, the 0xc3 byte of the RET. + * 3) STIBP must be enabled, or SMT disabled, to prevent the sibling thread + * from re-poisioning the BTB prediction. + */ + .align 64 + .skip 63, 0xcc +SYM_FUNC_START_NOALIGN(zen_untrain_ret); + + /* + * As executed from zen_untrain_ret, this is: + * + * TEST $0xcc, %bl + * LFENCE + * JMP __x86_return_thunk + * + * Executing the TEST instruction has a side effect of evicting any BTB + * prediction (potentially attacker controlled) attached to the RET, as + * __x86_return_thunk + 1 isn't an instruction boundary at the moment. + */ + .byte 0xf6 + + /* + * As executed from __x86_return_thunk, this is a plain RET. + * + * As part of the TEST above, RET is the ModRM byte, and INT3 the imm8. + * + * We subsequently jump backwards and architecturally execute the RET. + * This creates a correct BTB prediction (type=ret), but in the + * meantime we suffer Straight Line Speculation (because the type was + * no branch) which is halted by the INT3. + * + * With SMT enabled and STIBP active, a sibling thread cannot poison + * RET's prediction to a type of its choice, but can evict the + * prediction due to competitive sharing. If the prediction is + * evicted, __x86_return_thunk will suffer Straight Line Speculation + * which will be contained safely by the INT3. + */ +SYM_INNER_LABEL(__x86_return_thunk, SYM_L_GLOBAL) + ret + int3 +SYM_CODE_END(__x86_return_thunk) + + /* + * Ensure the TEST decoding / BTB invalidation is complete. + */ + lfence + + /* + * Jump back and execute the RET in the middle of the TEST instruction. + * INT3 is for SLS protection. + */ + jmp __x86_return_thunk + int3 +SYM_FUNC_END(zen_untrain_ret) +__EXPORT_THUNK(zen_untrain_ret) + +EXPORT_SYMBOL(__x86_return_thunk) + +#endif /* CONFIG_RETHUNK */ diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index d8cfce221275..57ba5502aecf 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -77,10 +77,20 @@ static uint8_t __pte2cachemode_tbl[8] = { [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC, }; -/* Check that the write-protect PAT entry is set for write-protect */ +/* + * Check that the write-protect PAT entry is set for write-protect. + * To do this without making assumptions how PAT has been set up (Xen has + * another layout than the kernel), translate the _PAGE_CACHE_MODE_WP cache + * mode via the __cachemode2pte_tbl[] into protection bits (those protection + * bits will select a cache mode of WP or better), and then translate the + * protection bits back into the cache mode using __pte2cm_idx() and the + * __pte2cachemode_tbl[] array. This will return the really used cache mode. + */ bool x86_has_pat_wp(void) { - return __pte2cachemode_tbl[_PAGE_CACHE_MODE_WP] == _PAGE_CACHE_MODE_WP; + uint16_t prot = __cachemode2pte_tbl[_PAGE_CACHE_MODE_WP]; + + return __pte2cachemode_tbl[__pte2cm_idx(prot)] == _PAGE_CACHE_MODE_WP; } enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 3d1dba05fce4..9de3d900bc92 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -65,7 +65,10 @@ SYM_FUNC_START(sme_encrypt_execute) movq %rbp, %rsp /* Restore original stack pointer */ pop %rbp - RET + /* Offset to __x86_return_thunk would be wrong here */ + ANNOTATE_UNRET_SAFE + ret + int3 SYM_FUNC_END(sme_encrypt_execute) SYM_FUNC_START(__enc_copy) @@ -151,6 +154,9 @@ SYM_FUNC_START(__enc_copy) pop %r12 pop %r15 - RET + /* Offset to __x86_return_thunk would be wrong here */ + ANNOTATE_UNRET_SAFE + ret + int3 .L__enc_copy_end: SYM_FUNC_END(__enc_copy) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index c98b8c0ed3b8..b808c9a80d1b 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -412,16 +412,30 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) { u8 *prog = *pprog; -#ifdef CONFIG_RETPOLINE if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { OPTIMIZER_HIDE_VAR(reg); emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); - } else -#endif - EMIT2(0xFF, 0xE0 + reg); + } else { + EMIT2(0xFF, 0xE0 + reg); + } + + *pprog = prog; +} + +static void emit_return(u8 **pprog, u8 *ip) +{ + u8 *prog = *pprog; + + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + emit_jump(&prog, &__x86_return_thunk, ip); + } else { + EMIT1(0xC3); /* ret */ + if (IS_ENABLED(CONFIG_SLS)) + EMIT1(0xCC); /* int3 */ + } *pprog = prog; } @@ -1686,7 +1700,7 @@ emit_jmp: ctx->cleanup_addr = proglen; pop_callee_regs(&prog, callee_regs_used); EMIT1(0xC9); /* leave */ - EMIT1(0xC3); /* ret */ + emit_return(&prog, image + addrs[i - 1] + (prog - temp)); break; default: @@ -2189,7 +2203,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (flags & BPF_TRAMP_F_SKIP_FRAME) /* skip our return address and return to parent */ EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */ - EMIT1(0xC3); /* ret */ + emit_return(&prog, prog); /* Make sure the trampoline generation logic doesn't overflow */ if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) { ret = -EFAULT; diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index 9ffe2bad27d5..4e5257a4811b 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -23,6 +23,7 @@ #include <linux/objtool.h> #include <asm/page_types.h> #include <asm/segment.h> +#include <asm/nospec-branch.h> .text .code64 @@ -75,7 +76,9 @@ STACK_FRAME_NON_STANDARD __efi64_thunk 1: movq 0x20(%rsp), %rsp pop %rbx pop %rbp - RET + ANNOTATE_UNRET_SAFE + ret + int3 .code32 2: pushl $__KERNEL_CS diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 81aa46f770c5..cfa99e8f054b 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -918,7 +918,7 @@ void xen_enable_sysenter(void) if (!boot_cpu_has(sysenter_feature)) return; - ret = register_callback(CALLBACKTYPE_sysenter, xen_sysenter_target); + ret = register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat); if(ret != 0) setup_clear_cpu_cap(sysenter_feature); } @@ -927,7 +927,7 @@ void xen_enable_syscall(void) { int ret; - ret = register_callback(CALLBACKTYPE_syscall, xen_syscall_target); + ret = register_callback(CALLBACKTYPE_syscall, xen_entry_SYSCALL_64); if (ret != 0) { printk(KERN_ERR "Failed to set syscall callback: %d\n", ret); /* Pretty fatal; 64-bit userspace has no other @@ -936,7 +936,7 @@ void xen_enable_syscall(void) if (boot_cpu_has(X86_FEATURE_SYSCALL32)) { ret = register_callback(CALLBACKTYPE_syscall32, - xen_syscall32_target); + xen_entry_SYSCALL_compat); if (ret != 0) setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); } diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index caa9bc2fa100..6b4fdf6b9542 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -121,7 +121,7 @@ SYM_FUNC_END(xen_read_cr2_direct); .macro xen_pv_trap name SYM_CODE_START(xen_\name) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR pop %rcx pop %r11 @@ -234,8 +234,8 @@ SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode) */ /* Normal 64-bit system call target */ -SYM_CODE_START(xen_syscall_target) - UNWIND_HINT_EMPTY +SYM_CODE_START(xen_entry_SYSCALL_64) + UNWIND_HINT_ENTRY ENDBR popq %rcx popq %r11 @@ -249,13 +249,13 @@ SYM_CODE_START(xen_syscall_target) movq $__USER_CS, 1*8(%rsp) jmp entry_SYSCALL_64_after_hwframe -SYM_CODE_END(xen_syscall_target) +SYM_CODE_END(xen_entry_SYSCALL_64) #ifdef CONFIG_IA32_EMULATION /* 32-bit compat syscall target */ -SYM_CODE_START(xen_syscall32_target) - UNWIND_HINT_EMPTY +SYM_CODE_START(xen_entry_SYSCALL_compat) + UNWIND_HINT_ENTRY ENDBR popq %rcx popq %r11 @@ -269,11 +269,11 @@ SYM_CODE_START(xen_syscall32_target) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSCALL_compat_after_hwframe -SYM_CODE_END(xen_syscall32_target) +SYM_CODE_END(xen_entry_SYSCALL_compat) /* 32-bit compat sysenter target */ -SYM_CODE_START(xen_sysenter_target) - UNWIND_HINT_EMPTY +SYM_CODE_START(xen_entry_SYSENTER_compat) + UNWIND_HINT_ENTRY ENDBR /* * NB: Xen is polite and clears TF from EFLAGS for us. This means @@ -291,19 +291,19 @@ SYM_CODE_START(xen_sysenter_target) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSENTER_compat_after_hwframe -SYM_CODE_END(xen_sysenter_target) +SYM_CODE_END(xen_entry_SYSENTER_compat) #else /* !CONFIG_IA32_EMULATION */ -SYM_CODE_START(xen_syscall32_target) -SYM_CODE_START(xen_sysenter_target) - UNWIND_HINT_EMPTY +SYM_CODE_START(xen_entry_SYSCALL_compat) +SYM_CODE_START(xen_entry_SYSENTER_compat) + UNWIND_HINT_ENTRY ENDBR lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax pushq $0 jmp hypercall_iret -SYM_CODE_END(xen_sysenter_target) -SYM_CODE_END(xen_syscall32_target) +SYM_CODE_END(xen_entry_SYSENTER_compat) +SYM_CODE_END(xen_entry_SYSCALL_compat) #endif /* CONFIG_IA32_EMULATION */ diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 13af6fe453e3..ffaa62167f6e 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -26,6 +26,7 @@ SYM_CODE_START(hypercall_page) .rept (PAGE_SIZE / 32) UNWIND_HINT_FUNC ANNOTATE_NOENDBR + ANNOTATE_UNRET_SAFE ret /* * Xen will write the hypercall page, and sort out ENDBR. diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index fd0fec6e92f4..9a8bb972193d 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -10,10 +10,10 @@ /* These are code, but not functions. Defined in entry.S */ extern const char xen_failsafe_callback[]; -void xen_sysenter_target(void); +void xen_entry_SYSENTER_compat(void); #ifdef CONFIG_X86_64 -void xen_syscall_target(void); -void xen_syscall32_target(void); +void xen_entry_SYSCALL_64(void); +void xen_entry_SYSCALL_compat(void); #endif extern void *xen_initial_gdt; diff --git a/block/blk-merge.c b/block/blk-merge.c index 7771dacc99cb..f5e6527ebc9c 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -345,6 +345,7 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio, /* there isn't chance to merge the splitted bio */ split->bi_opf |= REQ_NOMERGE; + blkcg_bio_issue_init(split); bio_chain(split, *bio); trace_block_split(split, (*bio)->bi_iter.bi_sector); submit_bio_noacct(*bio); diff --git a/certs/Kconfig b/certs/Kconfig index 476755703cf8..bf9b511573d7 100644 --- a/certs/Kconfig +++ b/certs/Kconfig @@ -43,6 +43,7 @@ config SYSTEM_TRUSTED_KEYRING bool "Provide system-wide ring of trusted keys" depends on KEYS depends on ASYMMETRIC_KEY_TYPE + depends on X509_CERTIFICATE_PARSER help Provide a system keyring to which trusted keys can be added. Keys in the keyring are considered to be trusted. Keys may be added at will diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 43177c20ce4f..eaea733b368a 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -73,7 +73,7 @@ module_param(device_id_scheme, bool, 0444); static int only_lcd = -1; module_param(only_lcd, int, 0444); -static bool has_backlight; +static bool may_report_brightness_keys; static int register_count; static DEFINE_MUTEX(register_count_mutex); static DEFINE_MUTEX(video_list_lock); @@ -1224,7 +1224,7 @@ acpi_video_bus_get_one_device(struct acpi_device *device, acpi_video_device_find_cap(data); if (data->cap._BCM && data->cap._BCL) - has_backlight = true; + may_report_brightness_keys = true; mutex_lock(&video->device_list_lock); list_add_tail(&data->entry, &video->video_device_list); @@ -1693,6 +1693,9 @@ static void acpi_video_device_notify(acpi_handle handle, u32 event, void *data) break; } + if (keycode) + may_report_brightness_keys = true; + acpi_notifier_call_chain(device, event, 0); if (keycode && (report_key_events & REPORT_BRIGHTNESS_KEY_EVENTS)) { @@ -2253,7 +2256,7 @@ void acpi_video_unregister(void) if (register_count) { acpi_bus_unregister_driver(&acpi_video_bus); register_count = 0; - has_backlight = false; + may_report_brightness_keys = false; } mutex_unlock(®ister_count_mutex); } @@ -2275,7 +2278,7 @@ void acpi_video_unregister_backlight(void) bool acpi_video_handles_brightness_key_presses(void) { - return has_backlight && + return may_report_brightness_keys && (report_key_events & REPORT_BRIGHTNESS_KEY_EVENTS); } EXPORT_SYMBOL(acpi_video_handles_brightness_key_presses); diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 6ff1901d7d43..3c6d4ef87be0 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -782,7 +782,8 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) if (!osc_cpc_flexible_adr_space_confirmed) { pr_debug("Flexible address space capability not supported\n"); - goto out_free; + if (!cpc_supported_by_cpu()) + goto out_free; } addr = ioremap(gas_t->address, gas_t->bit_width/8); @@ -809,7 +810,8 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) } if (!osc_cpc_flexible_adr_space_confirmed) { pr_debug("Flexible address space capability not supported\n"); - goto out_free; + if (!cpc_supported_by_cpu()) + goto out_free; } } else { if (gas_t->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE || !cpc_ffh_supported()) { diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 0e3ed5eb367b..0cb20324da16 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -493,13 +493,8 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent) goto skip_probe; ret = amba_read_periphid(dev); - if (ret) { - if (ret != -EPROBE_DEFER) { - amba_device_put(dev); - goto err_out; - } + if (ret) goto err_release; - } skip_probe: ret = device_add(&dev->dev); @@ -546,6 +541,7 @@ static int amba_deferred_retry(void) continue; list_del_init(&ddev->node); + amba_device_put(ddev->dev); kfree(ddev); } diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index a97776ea9d99..4c98849577d4 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -570,6 +570,12 @@ ssize_t __weak cpu_show_mmio_stale_data(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_retbleed(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -580,6 +586,7 @@ static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL); static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL); static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL); static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); +static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -592,6 +599,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_itlb_multihit.attr, &dev_attr_srbds.attr, &dev_attr_mmio_stale_data.attr, + &dev_attr_retbleed.attr, NULL }; diff --git a/drivers/char/random.c b/drivers/char/random.c index e3dd1dd3dd22..a1af90bacc9f 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1174,7 +1174,7 @@ static void __cold entropy_timer(struct timer_list *timer) */ static void __cold try_to_generate_entropy(void) { - enum { NUM_TRIAL_SAMPLES = 8192, MAX_SAMPLES_PER_BIT = 32 }; + enum { NUM_TRIAL_SAMPLES = 8192, MAX_SAMPLES_PER_BIT = HZ / 30 }; struct entropy_timer_state stack; unsigned int i, num_different = 0; unsigned long last = random_get_entropy(); diff --git a/drivers/clk/clk-lan966x.c b/drivers/clk/clk-lan966x.c index d1535ac13e89..81cb90955d68 100644 --- a/drivers/clk/clk-lan966x.c +++ b/drivers/clk/clk-lan966x.c @@ -213,7 +213,7 @@ static int lan966x_gate_clk_register(struct device *dev, hw_data->hws[i] = devm_clk_hw_register_gate(dev, clk_gate_desc[idx].name, - "lan966x", 0, base, + "lan966x", 0, gate_base, clk_gate_desc[idx].bit_idx, 0, &clk_gate_lock); diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c index 37a1eb20f5ba..76f6b3884e6b 100644 --- a/drivers/cpufreq/mediatek-cpufreq.c +++ b/drivers/cpufreq/mediatek-cpufreq.c @@ -439,9 +439,13 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu) /* Both presence and absence of sram regulator are valid cases. */ info->sram_reg = regulator_get_optional(cpu_dev, "sram"); - if (IS_ERR(info->sram_reg)) + if (IS_ERR(info->sram_reg)) { + ret = PTR_ERR(info->sram_reg); + if (ret == -EPROBE_DEFER) + goto out_free_resources; + info->sram_reg = NULL; - else { + } else { ret = regulator_enable(info->sram_reg); if (ret) { dev_warn(cpu_dev, "cpu%d: failed to enable vsram\n", cpu); diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 0cce6e4ec946..205acb2c744d 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -343,7 +343,7 @@ void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, if (old->context != context) continue; - dma_resv_list_set(list, i, replacement, usage); + dma_resv_list_set(list, i, dma_fence_get(replacement), usage); dma_fence_put(old); } } diff --git a/drivers/firmware/efi/reboot.c b/drivers/firmware/efi/reboot.c index 73089a24f04b..ceae84c19d22 100644 --- a/drivers/firmware/efi/reboot.c +++ b/drivers/firmware/efi/reboot.c @@ -6,7 +6,7 @@ #include <linux/efi.h> #include <linux/reboot.h> -static void (*orig_pm_power_off)(void); +static struct sys_off_handler *efi_sys_off_handler; int efi_reboot_quirk_mode = -1; @@ -51,15 +51,11 @@ bool __weak efi_poweroff_required(void) return false; } -static void efi_power_off(void) +static int efi_power_off(struct sys_off_data *data) { efi.reset_system(EFI_RESET_SHUTDOWN, EFI_SUCCESS, 0, NULL); - /* - * The above call should not return, if it does fall back to - * the original power off method (typically ACPI poweroff). - */ - if (orig_pm_power_off) - orig_pm_power_off(); + + return NOTIFY_DONE; } static int __init efi_shutdown_init(void) @@ -68,8 +64,13 @@ static int __init efi_shutdown_init(void) return -ENODEV; if (efi_poweroff_required()) { - orig_pm_power_off = pm_power_off; - pm_power_off = efi_power_off; + /* SYS_OFF_PRIO_FIRMWARE + 1 so that it runs before acpi_power_off */ + efi_sys_off_handler = + register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, + SYS_OFF_PRIO_FIRMWARE + 1, + efi_power_off, NULL); + if (IS_ERR(efi_sys_off_handler)) + return PTR_ERR(efi_sys_off_handler); } return 0; diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 08bc52c3cdcb..ecd7d169470b 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -351,6 +351,9 @@ static const struct regmap_config pca953x_i2c_regmap = { .reg_bits = 8, .val_bits = 8, + .use_single_read = true, + .use_single_write = true, + .readable_reg = pca953x_readable_register, .writeable_reg = pca953x_writeable_register, .volatile_reg = pca953x_volatile_register, @@ -906,15 +909,18 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, static int device_pca95xx_init(struct pca953x_chip *chip, u32 invert) { DECLARE_BITMAP(val, MAX_LINE); + u8 regaddr; int ret; - ret = regcache_sync_region(chip->regmap, chip->regs->output, - chip->regs->output + NBANK(chip)); + regaddr = pca953x_recalc_addr(chip, chip->regs->output, 0); + ret = regcache_sync_region(chip->regmap, regaddr, + regaddr + NBANK(chip) - 1); if (ret) goto out; - ret = regcache_sync_region(chip->regmap, chip->regs->direction, - chip->regs->direction + NBANK(chip)); + regaddr = pca953x_recalc_addr(chip, chip->regs->direction, 0); + ret = regcache_sync_region(chip->regmap, regaddr, + regaddr + NBANK(chip) - 1); if (ret) goto out; @@ -1127,14 +1133,14 @@ static int pca953x_regcache_sync(struct device *dev) * sync these registers first and only then sync the rest. */ regaddr = pca953x_recalc_addr(chip, chip->regs->direction, 0); - ret = regcache_sync_region(chip->regmap, regaddr, regaddr + NBANK(chip)); + ret = regcache_sync_region(chip->regmap, regaddr, regaddr + NBANK(chip) - 1); if (ret) { dev_err(dev, "Failed to sync GPIO dir registers: %d\n", ret); return ret; } regaddr = pca953x_recalc_addr(chip, chip->regs->output, 0); - ret = regcache_sync_region(chip->regmap, regaddr, regaddr + NBANK(chip)); + ret = regcache_sync_region(chip->regmap, regaddr, regaddr + NBANK(chip) - 1); if (ret) { dev_err(dev, "Failed to sync GPIO out registers: %d\n", ret); return ret; @@ -1144,7 +1150,7 @@ static int pca953x_regcache_sync(struct device *dev) if (chip->driver_data & PCA_PCAL) { regaddr = pca953x_recalc_addr(chip, PCAL953X_IN_LATCH, 0); ret = regcache_sync_region(chip->regmap, regaddr, - regaddr + NBANK(chip)); + regaddr + NBANK(chip) - 1); if (ret) { dev_err(dev, "Failed to sync INT latch registers: %d\n", ret); @@ -1153,7 +1159,7 @@ static int pca953x_regcache_sync(struct device *dev) regaddr = pca953x_recalc_addr(chip, PCAL953X_INT_MASK, 0); ret = regcache_sync_region(chip->regmap, regaddr, - regaddr + NBANK(chip)); + regaddr + NBANK(chip) - 1); if (ret) { dev_err(dev, "Failed to sync INT mask registers: %d\n", ret); diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 98109839102f..1020c2feb249 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -991,28 +991,22 @@ static struct configfs_attribute *gpio_sim_device_config_attrs[] = { }; struct gpio_sim_chip_name_ctx { - struct gpio_sim_device *dev; + struct fwnode_handle *swnode; char *page; }; static int gpio_sim_emit_chip_name(struct device *dev, void *data) { struct gpio_sim_chip_name_ctx *ctx = data; - struct fwnode_handle *swnode; - struct gpio_sim_bank *bank; /* This would be the sysfs device exported in /sys/class/gpio. */ if (dev->class) return 0; - swnode = dev_fwnode(dev); + if (device_match_fwnode(dev, ctx->swnode)) + return sprintf(ctx->page, "%s\n", dev_name(dev)); - list_for_each_entry(bank, &ctx->dev->bank_list, siblings) { - if (bank->swnode == swnode) - return sprintf(ctx->page, "%s\n", dev_name(dev)); - } - - return -ENODATA; + return 0; } static ssize_t gpio_sim_bank_config_chip_name_show(struct config_item *item, @@ -1020,7 +1014,7 @@ static ssize_t gpio_sim_bank_config_chip_name_show(struct config_item *item, { struct gpio_sim_bank *bank = to_gpio_sim_bank(item); struct gpio_sim_device *dev = gpio_sim_bank_get_device(bank); - struct gpio_sim_chip_name_ctx ctx = { dev, page }; + struct gpio_sim_chip_name_ctx ctx = { bank->swnode, page }; int ret; mutex_lock(&dev->lock); diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c index b6d3a57e27ed..7f8e2fed2988 100644 --- a/drivers/gpio/gpio-xilinx.c +++ b/drivers/gpio/gpio-xilinx.c @@ -99,7 +99,7 @@ static inline void xgpio_set_value32(unsigned long *map, int bit, u32 v) const unsigned long offset = (bit % BITS_PER_LONG) & BIT(5); map[index] &= ~(0xFFFFFFFFul << offset); - map[index] |= v << offset; + map[index] |= (unsigned long)v << offset; } static inline int xgpio_regoffset(struct xgpio_instance *chip, int ch) diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 0c9a63becfef..b26e64338376 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -421,6 +421,10 @@ out_free_lh: * @work: the worker that implements software debouncing * @sw_debounced: flag indicating if the software debouncer is active * @level: the current debounced physical level of the line + * @hdesc: the Hardware Timestamp Engine (HTE) descriptor + * @raw_level: the line level at the time of event + * @total_discard_seq: the running counter of the discarded events + * @last_seqno: the last sequence number before debounce period expires */ struct line { struct gpio_desc *desc; diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index e88c497fa010..f65656df3619 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -256,7 +256,6 @@ config DRM_AMDGPU select HWMON select BACKLIGHT_CLASS_DEVICE select INTERVAL_TREE - select DRM_BUDDY help Choose this option if you have a recent AMD Radeon graphics card. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 6b6d46e29e6e..4608599ba6bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1364,16 +1364,10 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev, struct amdgpu_vm *vm) { struct amdkfd_process_info *process_info = vm->process_info; - struct amdgpu_bo *pd = vm->root.bo; if (!process_info) return; - /* Release eviction fence from PD */ - amdgpu_bo_reserve(pd, false); - amdgpu_bo_fence(pd, NULL, false); - amdgpu_bo_unreserve(pd); - /* Update process info */ mutex_lock(&process_info->lock); process_info->n_vms--; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index 714178f1b6c6..2168163aad2d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -40,7 +40,7 @@ static void amdgpu_bo_list_free_rcu(struct rcu_head *rcu) { struct amdgpu_bo_list *list = container_of(rcu, struct amdgpu_bo_list, rhead); - + mutex_destroy(&list->bo_list_mutex); kvfree(list); } @@ -136,6 +136,7 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp, trace_amdgpu_cs_bo_status(list->num_entries, total_size); + mutex_init(&list->bo_list_mutex); *result = list; return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h index 529d52a204cf..9caea1688fc3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h @@ -47,6 +47,10 @@ struct amdgpu_bo_list { struct amdgpu_bo *oa_obj; unsigned first_userptr; unsigned num_entries; + + /* Protect access during command submission. + */ + struct mutex bo_list_mutex; }; int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index b28af04b0c3e..d8f1335bc68f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -519,6 +519,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, return r; } + mutex_lock(&p->bo_list->bo_list_mutex); + /* One for TTM and one for the CS job */ amdgpu_bo_list_for_each_entry(e, p->bo_list) e->tv.num_shared = 2; @@ -651,6 +653,7 @@ out_free_user_pages: kvfree(e->user_pages); e->user_pages = NULL; } + mutex_unlock(&p->bo_list->bo_list_mutex); } return r; } @@ -690,9 +693,11 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, { unsigned i; - if (error && backoff) + if (error && backoff) { ttm_eu_backoff_reservation(&parser->ticket, &parser->validated); + mutex_unlock(&parser->bo_list->bo_list_mutex); + } for (i = 0; i < parser->num_post_deps; i++) { drm_syncobj_put(parser->post_deps[i].syncobj); @@ -832,12 +837,16 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) continue; r = amdgpu_vm_bo_update(adev, bo_va, false); - if (r) + if (r) { + mutex_unlock(&p->bo_list->bo_list_mutex); return r; + } r = amdgpu_sync_fence(&p->job->sync, bo_va->last_pt_update); - if (r) + if (r) { + mutex_unlock(&p->bo_list->bo_list_mutex); return r; + } } r = amdgpu_vm_handle_moved(adev, vm); @@ -1278,6 +1287,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence); mutex_unlock(&p->adev->notifier_lock); + mutex_unlock(&p->bo_list->bo_list_mutex); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 17c9bbe0cbc5..4dfd6724b3ca 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -1528,6 +1528,21 @@ bool amdgpu_crtc_get_scanout_position(struct drm_crtc *crtc, stime, etime, mode); } +static bool +amdgpu_display_robj_is_fb(struct amdgpu_device *adev, struct amdgpu_bo *robj) +{ + struct drm_device *dev = adev_to_drm(adev); + struct drm_fb_helper *fb_helper = dev->fb_helper; + + if (!fb_helper || !fb_helper->buffer) + return false; + + if (gem_to_amdgpu_bo(fb_helper->buffer->gem) != robj) + return false; + + return true; +} + int amdgpu_display_suspend_helper(struct amdgpu_device *adev) { struct drm_device *dev = adev_to_drm(adev); @@ -1563,10 +1578,12 @@ int amdgpu_display_suspend_helper(struct amdgpu_device *adev) continue; } robj = gem_to_amdgpu_bo(fb->obj[0]); - r = amdgpu_bo_reserve(robj, true); - if (r == 0) { - amdgpu_bo_unpin(robj); - amdgpu_bo_unreserve(robj); + if (!amdgpu_display_robj_is_fb(adev, robj)) { + r = amdgpu_bo_reserve(robj, true); + if (r == 0) { + amdgpu_bo_unpin(robj); + amdgpu_bo_unreserve(robj); + } } } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h index 6546552e596c..acfa207cf970 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h @@ -30,15 +30,12 @@ #include <drm/ttm/ttm_resource.h> #include <drm/ttm/ttm_range_manager.h> -#include "amdgpu_vram_mgr.h" - /* state back for walking over vram_mgr and gtt_mgr allocations */ struct amdgpu_res_cursor { uint64_t start; uint64_t size; uint64_t remaining; - void *node; - uint32_t mem_type; + struct drm_mm_node *node; }; /** @@ -55,63 +52,27 @@ static inline void amdgpu_res_first(struct ttm_resource *res, uint64_t start, uint64_t size, struct amdgpu_res_cursor *cur) { - struct drm_buddy_block *block; - struct list_head *head, *next; struct drm_mm_node *node; - if (!res) - goto fallback; - - BUG_ON(start + size > res->num_pages << PAGE_SHIFT); - - cur->mem_type = res->mem_type; - - switch (cur->mem_type) { - case TTM_PL_VRAM: - head = &to_amdgpu_vram_mgr_resource(res)->blocks; - - block = list_first_entry_or_null(head, - struct drm_buddy_block, - link); - if (!block) - goto fallback; - - while (start >= amdgpu_vram_mgr_block_size(block)) { - start -= amdgpu_vram_mgr_block_size(block); - - next = block->link.next; - if (next != head) - block = list_entry(next, struct drm_buddy_block, link); - } - - cur->start = amdgpu_vram_mgr_block_start(block) + start; - cur->size = min(amdgpu_vram_mgr_block_size(block) - start, size); - cur->remaining = size; - cur->node = block; - break; - case TTM_PL_TT: - node = to_ttm_range_mgr_node(res)->mm_nodes; - while (start >= node->size << PAGE_SHIFT) - start -= node++->size << PAGE_SHIFT; - - cur->start = (node->start << PAGE_SHIFT) + start; - cur->size = min((node->size << PAGE_SHIFT) - start, size); + if (!res || res->mem_type == TTM_PL_SYSTEM) { + cur->start = start; + cur->size = size; cur->remaining = size; - cur->node = node; - break; - default: - goto fallback; + cur->node = NULL; + WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT); + return; } - return; + BUG_ON(start + size > res->num_pages << PAGE_SHIFT); -fallback: - cur->start = start; - cur->size = size; + node = to_ttm_range_mgr_node(res)->mm_nodes; + while (start >= node->size << PAGE_SHIFT) + start -= node++->size << PAGE_SHIFT; + + cur->start = (node->start << PAGE_SHIFT) + start; + cur->size = min((node->size << PAGE_SHIFT) - start, size); cur->remaining = size; - cur->node = NULL; - WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT); - return; + cur->node = node; } /** @@ -124,9 +85,7 @@ fallback: */ static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size) { - struct drm_buddy_block *block; - struct drm_mm_node *node; - struct list_head *next; + struct drm_mm_node *node = cur->node; BUG_ON(size > cur->remaining); @@ -140,27 +99,9 @@ static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size) return; } - switch (cur->mem_type) { - case TTM_PL_VRAM: - block = cur->node; - - next = block->link.next; - block = list_entry(next, struct drm_buddy_block, link); - - cur->node = block; - cur->start = amdgpu_vram_mgr_block_start(block); - cur->size = min(amdgpu_vram_mgr_block_size(block), cur->remaining); - break; - case TTM_PL_TT: - node = cur->node; - - cur->node = ++node; - cur->start = node->start << PAGE_SHIFT; - cur->size = min(node->size << PAGE_SHIFT, cur->remaining); - break; - default: - return; - } + cur->node = ++node; + cur->start = node->start << PAGE_SHIFT; + cur->size = min(node->size << PAGE_SHIFT, cur->remaining); } #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 6a70818039dd..9120ae80ef52 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -26,7 +26,6 @@ #include <linux/dma-direction.h> #include <drm/gpu_scheduler.h> -#include "amdgpu_vram_mgr.h" #include "amdgpu.h" #define AMDGPU_PL_GDS (TTM_PL_PRIV + 0) @@ -39,6 +38,15 @@ #define AMDGPU_POISON 0xd0bed0be +struct amdgpu_vram_mgr { + struct ttm_resource_manager manager; + struct drm_mm mm; + spinlock_t lock; + struct list_head reservations_pending; + struct list_head reserved_pages; + atomic64_t vis_usage; +}; + struct amdgpu_gtt_mgr { struct ttm_resource_manager manager; struct drm_mm mm; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index 576849e95296..108e8e8a1a36 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -496,7 +496,8 @@ static int amdgpu_vkms_sw_init(void *handle) adev_to_drm(adev)->mode_config.max_height = YRES_MAX; adev_to_drm(adev)->mode_config.preferred_depth = 24; - adev_to_drm(adev)->mode_config.prefer_shadow = 1; + /* disable prefer shadow for now due to hibernation issues */ + adev_to_drm(adev)->mode_config.prefer_shadow = 0; adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 49e4092f447f..0a7611648573 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -32,10 +32,8 @@ #include "atom.h" struct amdgpu_vram_reservation { - u64 start; - u64 size; - struct list_head allocated; - struct list_head blocks; + struct list_head node; + struct drm_mm_node mm_node; }; static inline struct amdgpu_vram_mgr * @@ -188,18 +186,18 @@ const struct attribute_group amdgpu_vram_mgr_attr_group = { }; /** - * amdgpu_vram_mgr_vis_size - Calculate visible block size + * amdgpu_vram_mgr_vis_size - Calculate visible node size * * @adev: amdgpu_device pointer - * @block: DRM BUDDY block structure + * @node: MM node structure * - * Calculate how many bytes of the DRM BUDDY block are inside visible VRAM + * Calculate how many bytes of the MM node are inside visible VRAM */ static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev, - struct drm_buddy_block *block) + struct drm_mm_node *node) { - u64 start = amdgpu_vram_mgr_block_start(block); - u64 end = start + amdgpu_vram_mgr_block_size(block); + uint64_t start = node->start << PAGE_SHIFT; + uint64_t end = (node->size + node->start) << PAGE_SHIFT; if (start >= adev->gmc.visible_vram_size) return 0; @@ -220,9 +218,9 @@ u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct ttm_resource *res = bo->tbo.resource; - struct amdgpu_vram_mgr_resource *vres = to_amdgpu_vram_mgr_resource(res); - struct drm_buddy_block *block; - u64 usage = 0; + unsigned pages = res->num_pages; + struct drm_mm_node *mm; + u64 usage; if (amdgpu_gmc_vram_full_visible(&adev->gmc)) return amdgpu_bo_size(bo); @@ -230,8 +228,9 @@ u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo) if (res->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT) return 0; - list_for_each_entry(block, &vres->blocks, link) - usage += amdgpu_vram_mgr_vis_size(adev, block); + mm = &container_of(res, struct ttm_range_mgr_node, base)->mm_nodes[0]; + for (usage = 0; pages; pages -= mm->size, mm++) + usage += amdgpu_vram_mgr_vis_size(adev, mm); return usage; } @@ -241,30 +240,23 @@ static void amdgpu_vram_mgr_do_reserve(struct ttm_resource_manager *man) { struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_device *adev = to_amdgpu_device(mgr); - struct drm_buddy *mm = &mgr->mm; + struct drm_mm *mm = &mgr->mm; struct amdgpu_vram_reservation *rsv, *temp; - struct drm_buddy_block *block; uint64_t vis_usage; - list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, blocks) { - if (drm_buddy_alloc_blocks(mm, rsv->start, rsv->start + rsv->size, - rsv->size, mm->chunk_size, &rsv->allocated, - DRM_BUDDY_RANGE_ALLOCATION)) - continue; - - block = amdgpu_vram_mgr_first_block(&rsv->allocated); - if (!block) + list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, node) { + if (drm_mm_reserve_node(mm, &rsv->mm_node)) continue; dev_dbg(adev->dev, "Reservation 0x%llx - %lld, Succeeded\n", - rsv->start, rsv->size); + rsv->mm_node.start, rsv->mm_node.size); - vis_usage = amdgpu_vram_mgr_vis_size(adev, block); + vis_usage = amdgpu_vram_mgr_vis_size(adev, &rsv->mm_node); atomic64_add(vis_usage, &mgr->vis_usage); spin_lock(&man->bdev->lru_lock); - man->usage += rsv->size; + man->usage += rsv->mm_node.size << PAGE_SHIFT; spin_unlock(&man->bdev->lru_lock); - list_move(&rsv->blocks, &mgr->reserved_pages); + list_move(&rsv->node, &mgr->reserved_pages); } } @@ -286,16 +278,14 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr, if (!rsv) return -ENOMEM; - INIT_LIST_HEAD(&rsv->allocated); - INIT_LIST_HEAD(&rsv->blocks); + INIT_LIST_HEAD(&rsv->node); + rsv->mm_node.start = start >> PAGE_SHIFT; + rsv->mm_node.size = size >> PAGE_SHIFT; - rsv->start = start; - rsv->size = size; - - mutex_lock(&mgr->lock); - list_add_tail(&rsv->blocks, &mgr->reservations_pending); + spin_lock(&mgr->lock); + list_add_tail(&rsv->node, &mgr->reservations_pending); amdgpu_vram_mgr_do_reserve(&mgr->manager); - mutex_unlock(&mgr->lock); + spin_unlock(&mgr->lock); return 0; } @@ -317,19 +307,19 @@ int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, struct amdgpu_vram_reservation *rsv; int ret; - mutex_lock(&mgr->lock); + spin_lock(&mgr->lock); - list_for_each_entry(rsv, &mgr->reservations_pending, blocks) { - if (rsv->start <= start && - (start < (rsv->start + rsv->size))) { + list_for_each_entry(rsv, &mgr->reservations_pending, node) { + if ((rsv->mm_node.start <= start) && + (start < (rsv->mm_node.start + rsv->mm_node.size))) { ret = -EBUSY; goto out; } } - list_for_each_entry(rsv, &mgr->reserved_pages, blocks) { - if (rsv->start <= start && - (start < (rsv->start + rsv->size))) { + list_for_each_entry(rsv, &mgr->reserved_pages, node) { + if ((rsv->mm_node.start <= start) && + (start < (rsv->mm_node.start + rsv->mm_node.size))) { ret = 0; goto out; } @@ -337,11 +327,33 @@ int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, ret = -ENOENT; out: - mutex_unlock(&mgr->lock); + spin_unlock(&mgr->lock); return ret; } /** + * amdgpu_vram_mgr_virt_start - update virtual start address + * + * @mem: ttm_resource to update + * @node: just allocated node + * + * Calculate a virtual BO start address to easily check if everything is CPU + * accessible. + */ +static void amdgpu_vram_mgr_virt_start(struct ttm_resource *mem, + struct drm_mm_node *node) +{ + unsigned long start; + + start = node->start + node->size; + if (start > mem->num_pages) + start -= mem->num_pages; + else + start = 0; + mem->start = max(mem->start, start); +} + +/** * amdgpu_vram_mgr_new - allocate new ranges * * @man: TTM memory type manager @@ -356,44 +368,46 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, const struct ttm_place *place, struct ttm_resource **res) { - u64 vis_usage = 0, max_bytes, cur_size, min_block_size; + unsigned long lpfn, num_nodes, pages_per_node, pages_left, pages; struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_device *adev = to_amdgpu_device(mgr); - struct amdgpu_vram_mgr_resource *vres; - u64 size, remaining_size, lpfn, fpfn; - struct drm_buddy *mm = &mgr->mm; - struct drm_buddy_block *block; - unsigned long pages_per_block; + uint64_t vis_usage = 0, mem_bytes, max_bytes; + struct ttm_range_mgr_node *node; + struct drm_mm *mm = &mgr->mm; + enum drm_mm_insert_mode mode; + unsigned i; int r; - lpfn = place->lpfn << PAGE_SHIFT; + lpfn = place->lpfn; if (!lpfn) - lpfn = man->size; - - fpfn = place->fpfn << PAGE_SHIFT; + lpfn = man->size >> PAGE_SHIFT; max_bytes = adev->gmc.mc_vram_size; if (tbo->type != ttm_bo_type_kernel) max_bytes -= AMDGPU_VM_RESERVED_VRAM; + mem_bytes = tbo->base.size; if (place->flags & TTM_PL_FLAG_CONTIGUOUS) { - pages_per_block = ~0ul; + pages_per_node = ~0ul; + num_nodes = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - pages_per_block = HPAGE_PMD_NR; + pages_per_node = HPAGE_PMD_NR; #else /* default to 2MB */ - pages_per_block = 2UL << (20UL - PAGE_SHIFT); + pages_per_node = 2UL << (20UL - PAGE_SHIFT); #endif - pages_per_block = max_t(uint32_t, pages_per_block, - tbo->page_alignment); + pages_per_node = max_t(uint32_t, pages_per_node, + tbo->page_alignment); + num_nodes = DIV_ROUND_UP_ULL(PFN_UP(mem_bytes), pages_per_node); } - vres = kzalloc(sizeof(*vres), GFP_KERNEL); - if (!vres) + node = kvmalloc(struct_size(node, mm_nodes, num_nodes), + GFP_KERNEL | __GFP_ZERO); + if (!node) return -ENOMEM; - ttm_resource_init(tbo, place, &vres->base); + ttm_resource_init(tbo, place, &node->base); /* bail out quickly if there's likely not enough VRAM for this BO */ if (ttm_resource_manager_usage(man) > max_bytes) { @@ -401,130 +415,66 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, goto error_fini; } - INIT_LIST_HEAD(&vres->blocks); - + mode = DRM_MM_INSERT_BEST; if (place->flags & TTM_PL_FLAG_TOPDOWN) - vres->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION; - - if (fpfn || lpfn != man->size) - /* Allocate blocks in desired range */ - vres->flags |= DRM_BUDDY_RANGE_ALLOCATION; - - remaining_size = vres->base.num_pages << PAGE_SHIFT; - - mutex_lock(&mgr->lock); - while (remaining_size) { - if (tbo->page_alignment) - min_block_size = tbo->page_alignment << PAGE_SHIFT; - else - min_block_size = mgr->default_page_size; - - BUG_ON(min_block_size < mm->chunk_size); - - /* Limit maximum size to 2GiB due to SG table limitations */ - size = min(remaining_size, 2ULL << 30); - - if (size >= pages_per_block << PAGE_SHIFT) - min_block_size = pages_per_block << PAGE_SHIFT; - - cur_size = size; - - if (fpfn + size != place->lpfn << PAGE_SHIFT) { - /* - * Except for actual range allocation, modify the size and - * min_block_size conforming to continuous flag enablement - */ - if (place->flags & TTM_PL_FLAG_CONTIGUOUS) { - size = roundup_pow_of_two(size); - min_block_size = size; - /* - * Modify the size value if size is not - * aligned with min_block_size - */ - } else if (!IS_ALIGNED(size, min_block_size)) { - size = round_up(size, min_block_size); + mode = DRM_MM_INSERT_HIGH; + + pages_left = node->base.num_pages; + + /* Limit maximum size to 2GB due to SG table limitations */ + pages = min(pages_left, 2UL << (30 - PAGE_SHIFT)); + + i = 0; + spin_lock(&mgr->lock); + while (pages_left) { + uint32_t alignment = tbo->page_alignment; + + if (pages >= pages_per_node) + alignment = pages_per_node; + + r = drm_mm_insert_node_in_range(mm, &node->mm_nodes[i], pages, + alignment, 0, place->fpfn, + lpfn, mode); + if (unlikely(r)) { + if (pages > pages_per_node) { + if (is_power_of_2(pages)) + pages = pages / 2; + else + pages = rounddown_pow_of_two(pages); + continue; } + goto error_free; } - r = drm_buddy_alloc_blocks(mm, fpfn, - lpfn, - size, - min_block_size, - &vres->blocks, - vres->flags); - if (unlikely(r)) - goto error_free_blocks; - - if (size > remaining_size) - remaining_size = 0; - else - remaining_size -= size; - } - mutex_unlock(&mgr->lock); - - if (cur_size != size) { - struct drm_buddy_block *block; - struct list_head *trim_list; - u64 original_size; - LIST_HEAD(temp); - - trim_list = &vres->blocks; - original_size = vres->base.num_pages << PAGE_SHIFT; - - /* - * If size value is rounded up to min_block_size, trim the last - * block to the required size - */ - if (!list_is_singular(&vres->blocks)) { - block = list_last_entry(&vres->blocks, typeof(*block), link); - list_move_tail(&block->link, &temp); - trim_list = &temp; - /* - * Compute the original_size value by subtracting the - * last block size with (aligned size - original size) - */ - original_size = amdgpu_vram_mgr_block_size(block) - (size - cur_size); - } + vis_usage += amdgpu_vram_mgr_vis_size(adev, &node->mm_nodes[i]); + amdgpu_vram_mgr_virt_start(&node->base, &node->mm_nodes[i]); + pages_left -= pages; + ++i; - mutex_lock(&mgr->lock); - drm_buddy_block_trim(mm, - original_size, - trim_list); - mutex_unlock(&mgr->lock); - - if (!list_empty(&temp)) - list_splice_tail(trim_list, &vres->blocks); - } - - list_for_each_entry(block, &vres->blocks, link) - vis_usage += amdgpu_vram_mgr_vis_size(adev, block); - - block = amdgpu_vram_mgr_first_block(&vres->blocks); - if (!block) { - r = -EINVAL; - goto error_fini; + if (pages > pages_left) + pages = pages_left; } + spin_unlock(&mgr->lock); - vres->base.start = amdgpu_vram_mgr_block_start(block) >> PAGE_SHIFT; - - if (amdgpu_is_vram_mgr_blocks_contiguous(&vres->blocks)) - vres->base.placement |= TTM_PL_FLAG_CONTIGUOUS; + if (i == 1) + node->base.placement |= TTM_PL_FLAG_CONTIGUOUS; if (adev->gmc.xgmi.connected_to_cpu) - vres->base.bus.caching = ttm_cached; + node->base.bus.caching = ttm_cached; else - vres->base.bus.caching = ttm_write_combined; + node->base.bus.caching = ttm_write_combined; atomic64_add(vis_usage, &mgr->vis_usage); - *res = &vres->base; + *res = &node->base; return 0; -error_free_blocks: - drm_buddy_free_list(mm, &vres->blocks); - mutex_unlock(&mgr->lock); +error_free: + while (i--) + drm_mm_remove_node(&node->mm_nodes[i]); + spin_unlock(&mgr->lock); error_fini: - ttm_resource_fini(man, &vres->base); - kfree(vres); + ttm_resource_fini(man, &node->base); + kvfree(node); return r; } @@ -540,26 +490,27 @@ error_fini: static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, struct ttm_resource *res) { - struct amdgpu_vram_mgr_resource *vres = to_amdgpu_vram_mgr_resource(res); + struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_device *adev = to_amdgpu_device(mgr); - struct drm_buddy *mm = &mgr->mm; - struct drm_buddy_block *block; uint64_t vis_usage = 0; + unsigned i, pages; - mutex_lock(&mgr->lock); - list_for_each_entry(block, &vres->blocks, link) - vis_usage += amdgpu_vram_mgr_vis_size(adev, block); + spin_lock(&mgr->lock); + for (i = 0, pages = res->num_pages; pages; + pages -= node->mm_nodes[i].size, ++i) { + struct drm_mm_node *mm = &node->mm_nodes[i]; + drm_mm_remove_node(mm); + vis_usage += amdgpu_vram_mgr_vis_size(adev, mm); + } amdgpu_vram_mgr_do_reserve(man); - - drm_buddy_free_list(mm, &vres->blocks); - mutex_unlock(&mgr->lock); + spin_unlock(&mgr->lock); atomic64_sub(vis_usage, &mgr->vis_usage); ttm_resource_fini(man, res); - kfree(vres); + kvfree(node); } /** @@ -591,7 +542,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, if (!*sgt) return -ENOMEM; - /* Determine the number of DRM_BUDDY blocks to export */ + /* Determine the number of DRM_MM nodes to export */ amdgpu_res_first(res, offset, length, &cursor); while (cursor.remaining) { num_entries++; @@ -607,10 +558,10 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, sg->length = 0; /* - * Walk down DRM_BUDDY blocks to populate scatterlist nodes - * @note: Use iterator api to get first the DRM_BUDDY block + * Walk down DRM_MM nodes to populate scatterlist nodes + * @note: Use iterator api to get first the DRM_MM node * and the number of bytes from it. Access the following - * DRM_BUDDY block(s) if more buffer needs to exported + * DRM_MM node(s) if more buffer needs to exported */ amdgpu_res_first(res, offset, length, &cursor); for_each_sgtable_sg((*sgt), sg, i) { @@ -697,22 +648,13 @@ static void amdgpu_vram_mgr_debug(struct ttm_resource_manager *man, struct drm_printer *printer) { struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); - struct drm_buddy *mm = &mgr->mm; - struct drm_buddy_block *block; drm_printf(printer, " vis usage:%llu\n", amdgpu_vram_mgr_vis_usage(mgr)); - mutex_lock(&mgr->lock); - drm_printf(printer, "default_page_size: %lluKiB\n", - mgr->default_page_size >> 10); - - drm_buddy_print(mm, printer); - - drm_printf(printer, "reserved:\n"); - list_for_each_entry(block, &mgr->reserved_pages, link) - drm_buddy_block_print(mm, block, printer); - mutex_unlock(&mgr->lock); + spin_lock(&mgr->lock); + drm_mm_print(&mgr->mm, printer); + spin_unlock(&mgr->lock); } static const struct ttm_resource_manager_func amdgpu_vram_mgr_func = { @@ -732,21 +674,16 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev) { struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr; struct ttm_resource_manager *man = &mgr->manager; - int err; ttm_resource_manager_init(man, &adev->mman.bdev, adev->gmc.real_vram_size); man->func = &amdgpu_vram_mgr_func; - err = drm_buddy_init(&mgr->mm, man->size, PAGE_SIZE); - if (err) - return err; - - mutex_init(&mgr->lock); + drm_mm_init(&mgr->mm, 0, man->size >> PAGE_SHIFT); + spin_lock_init(&mgr->lock); INIT_LIST_HEAD(&mgr->reservations_pending); INIT_LIST_HEAD(&mgr->reserved_pages); - mgr->default_page_size = PAGE_SIZE; ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, &mgr->manager); ttm_resource_manager_set_used(man, true); @@ -774,16 +711,16 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev) if (ret) return; - mutex_lock(&mgr->lock); - list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, blocks) + spin_lock(&mgr->lock); + list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, node) kfree(rsv); - list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) { - drm_buddy_free_list(&mgr->mm, &rsv->blocks); + list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, node) { + drm_mm_remove_node(&rsv->mm_node); kfree(rsv); } - drm_buddy_fini(&mgr->mm); - mutex_unlock(&mgr->lock); + drm_mm_takedown(&mgr->mm); + spin_unlock(&mgr->lock); ttm_resource_manager_cleanup(man); ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, NULL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h deleted file mode 100644 index 9a2db87186c7..000000000000 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h +++ /dev/null @@ -1,89 +0,0 @@ -/* SPDX-License-Identifier: MIT - * Copyright 2021 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - */ - -#ifndef __AMDGPU_VRAM_MGR_H__ -#define __AMDGPU_VRAM_MGR_H__ - -#include <drm/drm_buddy.h> - -struct amdgpu_vram_mgr { - struct ttm_resource_manager manager; - struct drm_buddy mm; - /* protects access to buffer objects */ - struct mutex lock; - struct list_head reservations_pending; - struct list_head reserved_pages; - atomic64_t vis_usage; - u64 default_page_size; -}; - -struct amdgpu_vram_mgr_resource { - struct ttm_resource base; - struct list_head blocks; - unsigned long flags; -}; - -static inline u64 amdgpu_vram_mgr_block_start(struct drm_buddy_block *block) -{ - return drm_buddy_block_offset(block); -} - -static inline u64 amdgpu_vram_mgr_block_size(struct drm_buddy_block *block) -{ - return PAGE_SIZE << drm_buddy_block_order(block); -} - -static inline struct drm_buddy_block * -amdgpu_vram_mgr_first_block(struct list_head *list) -{ - return list_first_entry_or_null(list, struct drm_buddy_block, link); -} - -static inline bool amdgpu_is_vram_mgr_blocks_contiguous(struct list_head *head) -{ - struct drm_buddy_block *block; - u64 start, size; - - block = amdgpu_vram_mgr_first_block(head); - if (!block) - return false; - - while (head != block->link.next) { - start = amdgpu_vram_mgr_block_start(block); - size = amdgpu_vram_mgr_block_size(block); - - block = list_entry(block->link.next, struct drm_buddy_block, link); - if (start + size != amdgpu_vram_mgr_block_start(block)) - return false; - } - - return true; -} - -static inline struct amdgpu_vram_mgr_resource * -to_amdgpu_vram_mgr_resource(struct ttm_resource *res) -{ - return container_of(res, struct amdgpu_vram_mgr_resource, base); -} - -#endif diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index 288fce7dc0ed..9c964cd3b5d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -2796,7 +2796,8 @@ static int dce_v10_0_sw_init(void *handle) adev_to_drm(adev)->mode_config.max_height = 16384; adev_to_drm(adev)->mode_config.preferred_depth = 24; - adev_to_drm(adev)->mode_config.prefer_shadow = 1; + /* disable prefer shadow for now due to hibernation issues */ + adev_to_drm(adev)->mode_config.prefer_shadow = 0; adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index cbe5250b31cb..e0ad9f27dc3f 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -2914,7 +2914,8 @@ static int dce_v11_0_sw_init(void *handle) adev_to_drm(adev)->mode_config.max_height = 16384; adev_to_drm(adev)->mode_config.preferred_depth = 24; - adev_to_drm(adev)->mode_config.prefer_shadow = 1; + /* disable prefer shadow for now due to hibernation issues */ + adev_to_drm(adev)->mode_config.prefer_shadow = 0; adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index 982855e6cf52..3caf6f386042 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -2673,7 +2673,8 @@ static int dce_v6_0_sw_init(void *handle) adev_to_drm(adev)->mode_config.max_width = 16384; adev_to_drm(adev)->mode_config.max_height = 16384; adev_to_drm(adev)->mode_config.preferred_depth = 24; - adev_to_drm(adev)->mode_config.prefer_shadow = 1; + /* disable prefer shadow for now due to hibernation issues */ + adev_to_drm(adev)->mode_config.prefer_shadow = 0; adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true; adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index 84440741c60b..7c75df5bffed 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -2693,7 +2693,8 @@ static int dce_v8_0_sw_init(void *handle) adev_to_drm(adev)->mode_config.max_height = 16384; adev_to_drm(adev)->mode_config.preferred_depth = 24; - adev_to_drm(adev)->mode_config.prefer_shadow = 1; + /* disable prefer shadow for now due to hibernation issues */ + adev_to_drm(adev)->mode_config.prefer_shadow = 0; adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index bf4200457772..a08769c5e94b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -184,6 +184,8 @@ static void kfd_device_info_init(struct kfd_dev *kfd, /* Navi2x+, Navi1x+ */ if (gc_version == IP_VERSION(10, 3, 6)) kfd->device_info.no_atomic_fw_version = 14; + else if (gc_version == IP_VERSION(10, 3, 7)) + kfd->device_info.no_atomic_fw_version = 3; else if (gc_version >= IP_VERSION(10, 3, 0)) kfd->device_info.no_atomic_fw_version = 92; else if (gc_version >= IP_VERSION(10, 1, 1)) diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index b4029c0d5d8c..0ba0598eba20 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -6,7 +6,7 @@ config DRM_AMD_DC bool "AMD DC - Enable new display engine" default y select SND_HDA_COMPONENT if SND_HDA_CORE - select DRM_AMD_DC_DCN if (X86 || PPC64) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS) + select DRM_AMD_DC_DCN if X86 && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS) help Choose this option if you want to use the new display engine support for AMDGPU. This adds required support for Vega and diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 9dd2e0601ea8..3087dd1a1856 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -72,6 +72,7 @@ #include <linux/pci.h> #include <linux/firmware.h> #include <linux/component.h> +#include <linux/dmi.h> #include <drm/display/drm_dp_mst_helper.h> #include <drm/display/drm_hdmi_helper.h> @@ -462,6 +463,26 @@ static void dm_pflip_high_irq(void *interrupt_params) vrr_active, (int) !e); } +static void dm_crtc_handle_vblank(struct amdgpu_crtc *acrtc) +{ + struct drm_crtc *crtc = &acrtc->base; + struct drm_device *dev = crtc->dev; + unsigned long flags; + + drm_crtc_handle_vblank(crtc); + + spin_lock_irqsave(&dev->event_lock, flags); + + /* Send completion event for cursor-only commits */ + if (acrtc->event && acrtc->pflip_status != AMDGPU_FLIP_SUBMITTED) { + drm_crtc_send_vblank_event(crtc, acrtc->event); + drm_crtc_vblank_put(crtc); + acrtc->event = NULL; + } + + spin_unlock_irqrestore(&dev->event_lock, flags); +} + static void dm_vupdate_high_irq(void *interrupt_params) { struct common_irq_params *irq_params = interrupt_params; @@ -500,7 +521,7 @@ static void dm_vupdate_high_irq(void *interrupt_params) * if a pageflip happened inside front-porch. */ if (vrr_active) { - drm_crtc_handle_vblank(&acrtc->base); + dm_crtc_handle_vblank(acrtc); /* BTR processing for pre-DCE12 ASICs */ if (acrtc->dm_irq_params.stream && @@ -552,7 +573,7 @@ static void dm_crtc_high_irq(void *interrupt_params) * to dm_vupdate_high_irq after end of front-porch. */ if (!vrr_active) - drm_crtc_handle_vblank(&acrtc->base); + dm_crtc_handle_vblank(acrtc); /** * Following stuff must happen at start of vblank, for crc @@ -1382,6 +1403,41 @@ static bool dm_should_disable_stutter(struct pci_dev *pdev) return false; } +static const struct dmi_system_id hpd_disconnect_quirk_table[] = { + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3660"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3260"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3460"), + }, + }, + {} +}; + +static void retrieve_dmi_info(struct amdgpu_display_manager *dm) +{ + const struct dmi_system_id *dmi_id; + + dm->aux_hpd_discon_quirk = false; + + dmi_id = dmi_first_match(hpd_disconnect_quirk_table); + if (dmi_id) { + dm->aux_hpd_discon_quirk = true; + DRM_INFO("aux_hpd_discon_quirk attached\n"); + } +} + static int amdgpu_dm_init(struct amdgpu_device *adev) { struct dc_init_data init_data; @@ -1508,6 +1564,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) } INIT_LIST_HEAD(&adev->dm.da_list); + + retrieve_dmi_info(&adev->dm); + /* Display Core create. */ adev->dm.dc = dc_create(&init_data); @@ -1594,7 +1653,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) adev->dm.crc_rd_wrk = amdgpu_dm_crtc_secure_display_create_work(); #endif - if (dc_enable_dmub_notifications(adev->dm.dc)) { + if (dc_is_dmub_outbox_supported(adev->dm.dc)) { init_completion(&adev->dm.dmub_aux_transfer_done); adev->dm.dmub_notify = kzalloc(sizeof(struct dmub_notification), GFP_KERNEL); if (!adev->dm.dmub_notify) { @@ -1630,6 +1689,13 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) goto error; } + /* Enable outbox notification only after IRQ handlers are registered and DMUB is alive. + * It is expected that DMUB will resend any pending notifications at this point, for + * example HPD from DPIA. + */ + if (dc_is_dmub_outbox_supported(adev->dm.dc)) + dc_enable_dmub_outbox(adev->dm.dc); + /* create fake encoders for MST */ dm_dp_create_fake_mst_encoders(adev); @@ -2619,9 +2685,6 @@ static int dm_resume(void *handle) */ link_enc_cfg_copy(adev->dm.dc->current_state, dc_state); - if (dc_enable_dmub_notifications(adev->dm.dc)) - amdgpu_dm_outbox_init(adev); - r = dm_dmub_hw_init(adev); if (r) DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r); @@ -2639,6 +2702,11 @@ static int dm_resume(void *handle) } } + if (dc_is_dmub_outbox_supported(adev->dm.dc)) { + amdgpu_dm_outbox_init(adev); + dc_enable_dmub_outbox(adev->dm.dc); + } + WARN_ON(!dc_commit_state(dm->dc, dc_state)); dm_gpureset_commit_state(dm->cached_dc_state, dm); @@ -2660,13 +2728,15 @@ static int dm_resume(void *handle) /* TODO: Remove dc_state->dccg, use dc->dccg directly. */ dc_resource_state_construct(dm->dc, dm_state->context); - /* Re-enable outbox interrupts for DPIA. */ - if (dc_enable_dmub_notifications(adev->dm.dc)) - amdgpu_dm_outbox_init(adev); - /* Before powering on DC we need to re-initialize DMUB. */ dm_dmub_hw_resume(adev); + /* Re-enable outbox interrupts for DPIA. */ + if (dc_is_dmub_outbox_supported(adev->dm.dc)) { + amdgpu_dm_outbox_init(adev); + dc_enable_dmub_outbox(adev->dm.dc); + } + /* power on hardware */ dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0); @@ -3822,7 +3892,8 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev) adev_to_drm(adev)->mode_config.max_height = 16384; adev_to_drm(adev)->mode_config.preferred_depth = 24; - adev_to_drm(adev)->mode_config.prefer_shadow = 1; + /* disable prefer shadow for now due to hibernation issues */ + adev_to_drm(adev)->mode_config.prefer_shadow = 0; /* indicates support for immediate flip */ adev_to_drm(adev)->mode_config.async_page_flip = true; @@ -5406,7 +5477,7 @@ fill_blending_from_plane_state(const struct drm_plane_state *plane_state, } } - if (per_pixel_alpha && plane_state->pixel_blend_mode == DRM_MODE_BLEND_COVERAGE) + if (*per_pixel_alpha && plane_state->pixel_blend_mode == DRM_MODE_BLEND_COVERAGE) *pre_multiplied_alpha = false; } @@ -9134,6 +9205,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, struct amdgpu_bo *abo; uint32_t target_vblank, last_flip_vblank; bool vrr_active = amdgpu_dm_vrr_active(acrtc_state); + bool cursor_update = false; bool pflip_present = false; struct { struct dc_surface_update surface_updates[MAX_SURFACES]; @@ -9169,8 +9241,13 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, struct dm_plane_state *dm_new_plane_state = to_dm_plane_state(new_plane_state); /* Cursor plane is handled after stream updates */ - if (plane->type == DRM_PLANE_TYPE_CURSOR) + if (plane->type == DRM_PLANE_TYPE_CURSOR) { + if ((fb && crtc == pcrtc) || + (old_plane_state->fb && old_plane_state->crtc == pcrtc)) + cursor_update = true; + continue; + } if (!fb || !crtc || pcrtc != crtc) continue; @@ -9333,6 +9410,17 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bundle->stream_update.vrr_infopacket = &acrtc_state->stream->vrr_infopacket; } + } else if (cursor_update && acrtc_state->active_planes > 0 && + !acrtc_state->force_dpms_off && + acrtc_attach->base.state->event) { + drm_crtc_vblank_get(pcrtc); + + spin_lock_irqsave(&pcrtc->dev->event_lock, flags); + + acrtc_attach->event = acrtc_attach->base.state->event; + acrtc_attach->base.state->event = NULL; + + spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); } /* Update the planes if changed or disable if we don't have any. */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index aa34c0068f41..e80ef93f6550 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -540,6 +540,14 @@ struct amdgpu_display_manager { * last successfully applied backlight values. */ u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP]; + + /** + * @aux_hpd_discon_quirk: + * + * quirk for hpd discon while aux is on-going. + * occurred on certain intel platform + */ + bool aux_hpd_discon_quirk; }; enum dsc_clock_force_state { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 9221b6690a4a..2b9b095e5f03 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -56,6 +56,8 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, ssize_t result = 0; struct aux_payload payload; enum aux_return_code_type operation_result; + struct amdgpu_device *adev; + struct ddc_service *ddc; if (WARN_ON(msg->size > 16)) return -E2BIG; @@ -74,6 +76,21 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload, &operation_result); + /* + * w/a on certain intel platform where hpd is unexpected to pull low during + * 1st sideband message transaction by return AUX_RET_ERROR_HPD_DISCON + * aux transaction is succuess in such case, therefore bypass the error + */ + ddc = TO_DM_AUX(aux)->ddc_service; + adev = ddc->ctx->driver_context; + if (adev->dm.aux_hpd_discon_quirk) { + if (msg->address == DP_SIDEBAND_MSG_DOWN_REQ_BASE && + operation_result == AUX_RET_ERROR_HPD_DISCON) { + result = 0; + operation_result = AUX_RET_SUCCESS; + } + } + if (payload.write && result >= 0) result = msg->size; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 6774dd8bb53e..3fe3fbac1e63 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1117,12 +1117,13 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) * on certain displays, such as the Sharp 4k. 36bpp is needed * to support SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 and * SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616 with actual > 10 bpc - * precision on at least DCN display engines. However, at least - * Carrizo with DCE_VERSION_11_0 does not like 36 bpp lb depth, - * so use only 30 bpp on DCE_VERSION_11_0. Testing with DCE 11.2 and 8.3 - * did not show such problems, so this seems to be the exception. + * precision on DCN display engines, but apparently not for DCE, as + * far as testing on DCE-11.2 and DCE-8 showed. Various DCE parts have + * problems: Carrizo with DCE_VERSION_11_0 does not like 36 bpp lb depth, + * neither do DCE-8 at 4k resolution, or DCE-11.2 (broken identify pixel + * passthrough). Therefore only use 36 bpp on DCN where it is actually needed. */ - if (plane_state->ctx->dce_version > DCE_VERSION_11_0) + if (plane_state->ctx->dce_version > DCE_VERSION_MAX) pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_36BPP; else pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index 5f8809f6990d..2fbd2926a531 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1228,6 +1228,8 @@ int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu, uint32_t crystal_clock_freq = 2500; uint32_t tach_period; + if (speed == 0) + return -EINVAL; /* * To prevent from possible overheat, some ASICs may have requirement * for minimum fan speed: diff --git a/drivers/gpu/drm/bridge/fsl-ldb.c b/drivers/gpu/drm/bridge/fsl-ldb.c index b2675c769a55..4b503c544256 100644 --- a/drivers/gpu/drm/bridge/fsl-ldb.c +++ b/drivers/gpu/drm/bridge/fsl-ldb.c @@ -74,22 +74,6 @@ static int fsl_ldb_attach(struct drm_bridge *bridge, bridge, flags); } -static int fsl_ldb_atomic_check(struct drm_bridge *bridge, - struct drm_bridge_state *bridge_state, - struct drm_crtc_state *crtc_state, - struct drm_connector_state *conn_state) -{ - /* Invert DE signal polarity. */ - bridge_state->input_bus_cfg.flags &= ~(DRM_BUS_FLAG_DE_LOW | - DRM_BUS_FLAG_DE_HIGH); - if (bridge_state->output_bus_cfg.flags & DRM_BUS_FLAG_DE_LOW) - bridge_state->input_bus_cfg.flags |= DRM_BUS_FLAG_DE_HIGH; - else if (bridge_state->output_bus_cfg.flags & DRM_BUS_FLAG_DE_HIGH) - bridge_state->input_bus_cfg.flags |= DRM_BUS_FLAG_DE_LOW; - - return 0; -} - static void fsl_ldb_atomic_enable(struct drm_bridge *bridge, struct drm_bridge_state *old_bridge_state) { @@ -153,7 +137,7 @@ static void fsl_ldb_atomic_enable(struct drm_bridge *bridge, reg = LDB_CTRL_CH0_ENABLE; if (fsl_ldb->lvds_dual_link) - reg |= LDB_CTRL_CH1_ENABLE; + reg |= LDB_CTRL_CH1_ENABLE | LDB_CTRL_SPLIT_MODE; if (lvds_format_24bpp) { reg |= LDB_CTRL_CH0_DATA_WIDTH; @@ -233,7 +217,7 @@ fsl_ldb_mode_valid(struct drm_bridge *bridge, { struct fsl_ldb *fsl_ldb = to_fsl_ldb(bridge); - if (mode->clock > (fsl_ldb->lvds_dual_link ? 80000 : 160000)) + if (mode->clock > (fsl_ldb->lvds_dual_link ? 160000 : 80000)) return MODE_CLOCK_HIGH; return MODE_OK; @@ -241,7 +225,6 @@ fsl_ldb_mode_valid(struct drm_bridge *bridge, static const struct drm_bridge_funcs funcs = { .attach = fsl_ldb_attach, - .atomic_check = fsl_ldb_atomic_check, .atomic_enable = fsl_ldb_atomic_enable, .atomic_disable = fsl_ldb_atomic_disable, .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, diff --git a/drivers/gpu/drm/drm_gem_ttm_helper.c b/drivers/gpu/drm/drm_gem_ttm_helper.c index d5962a34c01d..e5fc875990c4 100644 --- a/drivers/gpu/drm/drm_gem_ttm_helper.c +++ b/drivers/gpu/drm/drm_gem_ttm_helper.c @@ -64,8 +64,13 @@ int drm_gem_ttm_vmap(struct drm_gem_object *gem, struct iosys_map *map) { struct ttm_buffer_object *bo = drm_gem_ttm_of_gem(gem); + int ret; + + dma_resv_lock(gem->resv, NULL); + ret = ttm_bo_vmap(bo, map); + dma_resv_unlock(gem->resv); - return ttm_bo_vmap(bo, map); + return ret; } EXPORT_SYMBOL(drm_gem_ttm_vmap); @@ -82,7 +87,9 @@ void drm_gem_ttm_vunmap(struct drm_gem_object *gem, { struct ttm_buffer_object *bo = drm_gem_ttm_of_gem(gem); + dma_resv_lock(gem->resv, NULL); ttm_bo_vunmap(bo, map); + dma_resv_unlock(gem->resv); } EXPORT_SYMBOL(drm_gem_ttm_vunmap); diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index df87ba99a87c..d4e0f2e85548 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -286,6 +286,21 @@ static const struct dmi_system_id orientation_data[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X9"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, + }, { /* Lenovo Yoga Tablet 2 830F / 830L */ + .matches = { + /* + * Note this also matches the Lenovo Yoga Tablet 2 1050F/L + * since that uses the same mainboard. The resolution match + * will limit this to only matching on the 830F/L. Neither has + * any external video outputs so those are not a concern. + */ + DMI_MATCH(DMI_SYS_VENDOR, "Intel Corp."), + DMI_MATCH(DMI_PRODUCT_NAME, "VALLEYVIEW C0 PLATFORM"), + DMI_MATCH(DMI_BOARD_NAME, "BYT-T FFD8"), + /* Partial match on beginning of BIOS version */ + DMI_MATCH(DMI_BIOS_VERSION, "BLADE_21"), + }, + .driver_data = (void *)&lcd1200x1920_rightside_up, }, { /* OneGX1 Pro */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SYSTEM_MANUFACTURER"), diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 061b277e5ce7..14d2a64193b2 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -839,6 +839,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo ret = drm_connector_init(dev, connector, &intel_dp_mst_connector_funcs, DRM_MODE_CONNECTOR_DisplayPort); if (ret) { + drm_dp_mst_put_port_malloc(port); intel_connector_free(intel_connector); return NULL; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c index f46ee16a323a..a4fb577eceb4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_region.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c @@ -60,6 +60,8 @@ __i915_gem_object_create_region(struct intel_memory_region *mem, if (page_size) default_page_size = page_size; + /* We should be able to fit a page within an sg entry */ + GEM_BUG_ON(overflows_type(default_page_size, u32)); GEM_BUG_ON(!is_power_of_2_u64(default_page_size)); GEM_BUG_ON(default_page_size < PAGE_SIZE); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 4c25d9b2f138..8f1bb6a4b7d1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -620,10 +620,15 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj, struct ttm_resource *res) { struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + u32 page_alignment; if (!i915_ttm_gtt_binds_lmem(res)) return i915_ttm_tt_get_st(bo->ttm); + page_alignment = bo->page_alignment << PAGE_SHIFT; + if (!page_alignment) + page_alignment = obj->mm.region->min_page_size; + /* * If CPU mapping differs, we need to add the ttm_tt pages to * the resulting st. Might make sense for GGTT. @@ -634,7 +639,8 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj, struct i915_refct_sgt *rsgt; rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region, - res); + res, + page_alignment); if (IS_ERR(rsgt)) return rsgt; @@ -643,7 +649,8 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj, return i915_refct_sgt_get(obj->ttm.cached_io_rsgt); } - return intel_region_ttm_resource_to_rsgt(obj->mm.region, res); + return intel_region_ttm_resource_to_rsgt(obj->mm.region, res, + page_alignment); } static int i915_ttm_truncate(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index 319936f91ac5..e6e01c2a74a6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -9,6 +9,7 @@ #include <linux/jiffies.h> #include "gt/intel_engine.h" +#include "gt/intel_rps.h" #include "i915_gem_ioctls.h" #include "i915_gem_object.h" @@ -31,6 +32,37 @@ i915_gem_object_wait_fence(struct dma_fence *fence, timeout); } +static void +i915_gem_object_boost(struct dma_resv *resv, unsigned int flags) +{ + struct dma_resv_iter cursor; + struct dma_fence *fence; + + /* + * Prescan all fences for potential boosting before we begin waiting. + * + * When we wait, we wait on outstanding fences serially. If the + * dma-resv contains a sequence such as 1:1, 1:2 instead of a reduced + * form 1:2, then as we look at each wait in turn we see that each + * request is currently executing and not worthy of boosting. But if + * we only happen to look at the final fence in the sequence (because + * of request coalescing or splitting between read/write arrays by + * the iterator), then we would boost. As such our decision to boost + * or not is delicately balanced on the order we wait on fences. + * + * So instead of looking for boosts sequentially, look for all boosts + * upfront and then wait on the outstanding fences. + */ + + dma_resv_iter_begin(&cursor, resv, + dma_resv_usage_rw(flags & I915_WAIT_ALL)); + dma_resv_for_each_fence_unlocked(&cursor, fence) + if (dma_fence_is_i915(fence) && + !i915_request_started(to_request(fence))) + intel_rps_boost(to_request(fence)); + dma_resv_iter_end(&cursor); +} + static long i915_gem_object_wait_reservation(struct dma_resv *resv, unsigned int flags, @@ -40,6 +72,8 @@ i915_gem_object_wait_reservation(struct dma_resv *resv, struct dma_fence *fence; long ret = timeout ?: 1; + i915_gem_object_boost(resv, flags); + dma_resv_iter_begin(&cursor, resv, dma_resv_usage_rw(flags & I915_WAIT_ALL)); dma_resv_for_each_fence_unlocked(&cursor, fence) { diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 09f82545789f..44e7339e7a4a 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -273,10 +273,17 @@ struct intel_context { u8 child_index; /** @guc: GuC specific members for parallel submission */ struct { - /** @wqi_head: head pointer in work queue */ + /** @wqi_head: cached head pointer in work queue */ u16 wqi_head; - /** @wqi_tail: tail pointer in work queue */ + /** @wqi_tail: cached tail pointer in work queue */ u16 wqi_tail; + /** @wq_head: pointer to the actual head in work queue */ + u32 *wq_head; + /** @wq_tail: pointer to the actual head in work queue */ + u32 *wq_tail; + /** @wq_status: pointer to the status in work queue */ + u32 *wq_status; + /** * @parent_page: page in context state (ce->state) used * by parent for work queue, process descriptor diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 86f7a9ac1c39..2b0266cab66b 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -661,6 +661,16 @@ static inline void execlists_schedule_out(struct i915_request *rq) i915_request_put(rq); } +static u32 map_i915_prio_to_lrc_desc_prio(int prio) +{ + if (prio > I915_PRIORITY_NORMAL) + return GEN12_CTX_PRIORITY_HIGH; + else if (prio < I915_PRIORITY_NORMAL) + return GEN12_CTX_PRIORITY_LOW; + else + return GEN12_CTX_PRIORITY_NORMAL; +} + static u64 execlists_update_context(struct i915_request *rq) { struct intel_context *ce = rq->context; @@ -669,7 +679,7 @@ static u64 execlists_update_context(struct i915_request *rq) desc = ce->lrc.desc; if (rq->engine->flags & I915_ENGINE_HAS_EU_PRIORITY) - desc |= lrc_desc_priority(rq_prio(rq)); + desc |= map_i915_prio_to_lrc_desc_prio(rq_prio(rq)); /* * WaIdleLiteRestore:bdw,skl diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 51a0fe60c050..531af6ad7007 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -1209,6 +1209,20 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt) mutex_lock(>->tlb_invalidate_lock); intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL); + spin_lock_irq(&uncore->lock); /* serialise invalidate with GT reset */ + + for_each_engine(engine, gt, id) { + struct reg_and_bit rb; + + rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); + if (!i915_mmio_reg_offset(rb.reg)) + continue; + + intel_uncore_write_fw(uncore, rb.reg, rb.bit); + } + + spin_unlock_irq(&uncore->lock); + for_each_engine(engine, gt, id) { /* * HW architecture suggest typical invalidation time at 40us, @@ -1223,7 +1237,6 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt) if (!i915_mmio_reg_offset(rb.reg)) continue; - intel_uncore_write_fw(uncore, rb.reg, rb.bit); if (__intel_wait_for_register_fw(uncore, rb.reg, rb.bit, 0, timeout_us, timeout_ms, diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h index 31be734010db..a390f0813c8b 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.h +++ b/drivers/gpu/drm/i915/gt/intel_lrc.h @@ -111,16 +111,6 @@ enum { #define XEHP_SW_COUNTER_SHIFT 58 #define XEHP_SW_COUNTER_WIDTH 6 -static inline u32 lrc_desc_priority(int prio) -{ - if (prio > I915_PRIORITY_NORMAL) - return GEN12_CTX_PRIORITY_HIGH; - else if (prio < I915_PRIORITY_NORMAL) - return GEN12_CTX_PRIORITY_LOW; - else - return GEN12_CTX_PRIORITY_NORMAL; -} - static inline void lrc_runtime_start(struct intel_context *ce) { struct intel_context_stats *stats = &ce->stats; diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index a5338c3fde7a..c68d36fb5bbd 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -300,9 +300,9 @@ static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask) return err; } -static int gen6_reset_engines(struct intel_gt *gt, - intel_engine_mask_t engine_mask, - unsigned int retry) +static int __gen6_reset_engines(struct intel_gt *gt, + intel_engine_mask_t engine_mask, + unsigned int retry) { struct intel_engine_cs *engine; u32 hw_mask; @@ -321,6 +321,20 @@ static int gen6_reset_engines(struct intel_gt *gt, return gen6_hw_domain_reset(gt, hw_mask); } +static int gen6_reset_engines(struct intel_gt *gt, + intel_engine_mask_t engine_mask, + unsigned int retry) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(>->uncore->lock, flags); + ret = __gen6_reset_engines(gt, engine_mask, retry); + spin_unlock_irqrestore(>->uncore->lock, flags); + + return ret; +} + static struct intel_engine_cs *find_sfc_paired_vecs_engine(struct intel_engine_cs *engine) { int vecs_id; @@ -487,9 +501,9 @@ static void gen11_unlock_sfc(struct intel_engine_cs *engine) rmw_clear_fw(uncore, sfc_lock.lock_reg, sfc_lock.lock_bit); } -static int gen11_reset_engines(struct intel_gt *gt, - intel_engine_mask_t engine_mask, - unsigned int retry) +static int __gen11_reset_engines(struct intel_gt *gt, + intel_engine_mask_t engine_mask, + unsigned int retry) { struct intel_engine_cs *engine; intel_engine_mask_t tmp; @@ -583,8 +597,11 @@ static int gen8_reset_engines(struct intel_gt *gt, struct intel_engine_cs *engine; const bool reset_non_ready = retry >= 1; intel_engine_mask_t tmp; + unsigned long flags; int ret; + spin_lock_irqsave(>->uncore->lock, flags); + for_each_engine_masked(engine, gt, engine_mask, tmp) { ret = gen8_engine_reset_prepare(engine); if (ret && !reset_non_ready) @@ -612,17 +629,19 @@ static int gen8_reset_engines(struct intel_gt *gt, * This is best effort, so ignore any error from the initial reset. */ if (IS_DG2(gt->i915) && engine_mask == ALL_ENGINES) - gen11_reset_engines(gt, gt->info.engine_mask, 0); + __gen11_reset_engines(gt, gt->info.engine_mask, 0); if (GRAPHICS_VER(gt->i915) >= 11) - ret = gen11_reset_engines(gt, engine_mask, retry); + ret = __gen11_reset_engines(gt, engine_mask, retry); else - ret = gen6_reset_engines(gt, engine_mask, retry); + ret = __gen6_reset_engines(gt, engine_mask, retry); skip_reset: for_each_engine_masked(engine, gt, engine_mask, tmp) gen8_engine_reset_cancel(engine); + spin_unlock_irqrestore(>->uncore->lock, flags); + return ret; } diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 8b2c11dbe354..1109088fe8f6 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -176,8 +176,8 @@ static int live_lrc_layout(void *arg) continue; hw = shmem_pin_map(engine->default_state); - if (IS_ERR(hw)) { - err = PTR_ERR(hw); + if (!hw) { + err = -ENOMEM; break; } hw += LRC_STATE_OFFSET / sizeof(*hw); @@ -365,8 +365,8 @@ static int live_lrc_fixed(void *arg) continue; hw = shmem_pin_map(engine->default_state); - if (IS_ERR(hw)) { - err = PTR_ERR(hw); + if (!hw) { + err = -ENOMEM; break; } hw += LRC_STATE_OFFSET / sizeof(*hw); diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h index 4ef9990ed7f8..29ef8afc8c2e 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h @@ -122,6 +122,9 @@ enum intel_guc_action { INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE = 0x1002, INTEL_GUC_ACTION_SCHED_ENGINE_MODE_SET = 0x1003, INTEL_GUC_ACTION_SCHED_ENGINE_MODE_DONE = 0x1004, + INTEL_GUC_ACTION_V69_SET_CONTEXT_PRIORITY = 0x1005, + INTEL_GUC_ACTION_V69_SET_CONTEXT_EXECUTION_QUANTUM = 0x1006, + INTEL_GUC_ACTION_V69_SET_CONTEXT_PREEMPTION_TIMEOUT = 0x1007, INTEL_GUC_ACTION_CONTEXT_RESET_NOTIFICATION = 0x1008, INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION = 0x1009, INTEL_GUC_ACTION_HOST2GUC_UPDATE_CONTEXT_POLICIES = 0x100B, diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 966e69a8b1c1..9feda105f913 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -170,6 +170,11 @@ struct intel_guc { /** @ads_engine_usage_size: size of engine usage in the ADS */ u32 ads_engine_usage_size; + /** @lrc_desc_pool_v69: object allocated to hold the GuC LRC descriptor pool */ + struct i915_vma *lrc_desc_pool_v69; + /** @lrc_desc_pool_vaddr_v69: contents of the GuC LRC descriptor pool */ + void *lrc_desc_pool_vaddr_v69; + /** * @context_lookup: used to resolve intel_context from guc_id, if a * context is present in this structure it is registered with the GuC diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h index 42cb7a9a6199..89a7e5ec0614 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h @@ -203,6 +203,20 @@ struct guc_wq_item { u32 fence_id; } __packed; +struct guc_process_desc_v69 { + u32 stage_id; + u64 db_base_addr; + u32 head; + u32 tail; + u32 error_offset; + u64 wq_base_addr; + u32 wq_size_bytes; + u32 wq_status; + u32 engine_presence; + u32 priority; + u32 reserved[36]; +} __packed; + struct guc_sched_wq_desc { u32 head; u32 tail; @@ -227,6 +241,37 @@ struct guc_ctxt_registration_info { }; #define CONTEXT_REGISTRATION_FLAG_KMD BIT(0) +/* Preempt to idle on quantum expiry */ +#define CONTEXT_POLICY_FLAG_PREEMPT_TO_IDLE_V69 BIT(0) + +/* + * GuC Context registration descriptor. + * FIXME: This is only required to exist during context registration. + * The current 1:1 between guc_lrc_desc and LRCs for the lifetime of the LRC + * is not required. + */ +struct guc_lrc_desc_v69 { + u32 hw_context_desc; + u32 slpm_perf_mode_hint; /* SPLC v1 only */ + u32 slpm_freq_hint; + u32 engine_submit_mask; /* In logical space */ + u8 engine_class; + u8 reserved0[3]; + u32 priority; + u32 process_desc; + u32 wq_addr; + u32 wq_size; + u32 context_flags; /* CONTEXT_REGISTRATION_* */ + /* Time for one workload to execute. (in micro seconds) */ + u32 execution_quantum; + /* Time to wait for a preemption request to complete before issuing a + * reset. (in micro seconds). + */ + u32 preemption_timeout; + u32 policy_flags; /* CONTEXT_POLICY_* */ + u32 reserved1[19]; +} __packed; + /* 32-bit KLV structure as used by policy updates and others */ struct guc_klv_generic_dw_t { u32 kl; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 1726f0f19901..9ffb343d0f79 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -414,12 +414,15 @@ struct sync_semaphore { }; struct parent_scratch { - struct guc_sched_wq_desc wq_desc; + union guc_descs { + struct guc_sched_wq_desc wq_desc; + struct guc_process_desc_v69 pdesc; + } descs; struct sync_semaphore go; struct sync_semaphore join[MAX_ENGINE_INSTANCE + 1]; - u8 unused[WQ_OFFSET - sizeof(struct guc_sched_wq_desc) - + u8 unused[WQ_OFFSET - sizeof(union guc_descs) - sizeof(struct sync_semaphore) * (MAX_ENGINE_INSTANCE + 2)]; u32 wq[WQ_SIZE / sizeof(u32)]; @@ -456,17 +459,23 @@ __get_parent_scratch(struct intel_context *ce) LRC_STATE_OFFSET) / sizeof(u32))); } +static struct guc_process_desc_v69 * +__get_process_desc_v69(struct intel_context *ce) +{ + struct parent_scratch *ps = __get_parent_scratch(ce); + + return &ps->descs.pdesc; +} + static struct guc_sched_wq_desc * -__get_wq_desc(struct intel_context *ce) +__get_wq_desc_v70(struct intel_context *ce) { struct parent_scratch *ps = __get_parent_scratch(ce); - return &ps->wq_desc; + return &ps->descs.wq_desc; } -static u32 *get_wq_pointer(struct guc_sched_wq_desc *wq_desc, - struct intel_context *ce, - u32 wqi_size) +static u32 *get_wq_pointer(struct intel_context *ce, u32 wqi_size) { /* * Check for space in work queue. Caching a value of head pointer in @@ -476,7 +485,7 @@ static u32 *get_wq_pointer(struct guc_sched_wq_desc *wq_desc, #define AVAILABLE_SPACE \ CIRC_SPACE(ce->parallel.guc.wqi_tail, ce->parallel.guc.wqi_head, WQ_SIZE) if (wqi_size > AVAILABLE_SPACE) { - ce->parallel.guc.wqi_head = READ_ONCE(wq_desc->head); + ce->parallel.guc.wqi_head = READ_ONCE(*ce->parallel.guc.wq_head); if (wqi_size > AVAILABLE_SPACE) return NULL; @@ -495,11 +504,55 @@ static inline struct intel_context *__get_context(struct intel_guc *guc, u32 id) return ce; } +static struct guc_lrc_desc_v69 *__get_lrc_desc_v69(struct intel_guc *guc, u32 index) +{ + struct guc_lrc_desc_v69 *base = guc->lrc_desc_pool_vaddr_v69; + + if (!base) + return NULL; + + GEM_BUG_ON(index >= GUC_MAX_CONTEXT_ID); + + return &base[index]; +} + +static int guc_lrc_desc_pool_create_v69(struct intel_guc *guc) +{ + u32 size; + int ret; + + size = PAGE_ALIGN(sizeof(struct guc_lrc_desc_v69) * + GUC_MAX_CONTEXT_ID); + ret = intel_guc_allocate_and_map_vma(guc, size, &guc->lrc_desc_pool_v69, + (void **)&guc->lrc_desc_pool_vaddr_v69); + if (ret) + return ret; + + return 0; +} + +static void guc_lrc_desc_pool_destroy_v69(struct intel_guc *guc) +{ + if (!guc->lrc_desc_pool_vaddr_v69) + return; + + guc->lrc_desc_pool_vaddr_v69 = NULL; + i915_vma_unpin_and_release(&guc->lrc_desc_pool_v69, I915_VMA_RELEASE_MAP); +} + static inline bool guc_submission_initialized(struct intel_guc *guc) { return guc->submission_initialized; } +static inline void _reset_lrc_desc_v69(struct intel_guc *guc, u32 id) +{ + struct guc_lrc_desc_v69 *desc = __get_lrc_desc_v69(guc, id); + + if (desc) + memset(desc, 0, sizeof(*desc)); +} + static inline bool ctx_id_mapped(struct intel_guc *guc, u32 id) { return __get_context(guc, id); @@ -526,6 +579,8 @@ static inline void clr_ctx_id_mapping(struct intel_guc *guc, u32 id) if (unlikely(!guc_submission_initialized(guc))) return; + _reset_lrc_desc_v69(guc, id); + /* * xarray API doesn't have xa_erase_irqsave wrapper, so calling * the lower level functions directly. @@ -611,7 +666,7 @@ int intel_guc_wait_for_idle(struct intel_guc *guc, long timeout) true, timeout); } -static int guc_context_policy_init(struct intel_context *ce, bool loop); +static int guc_context_policy_init_v70(struct intel_context *ce, bool loop); static int try_context_registration(struct intel_context *ce, bool loop); static int __guc_add_request(struct intel_guc *guc, struct i915_request *rq) @@ -639,7 +694,7 @@ static int __guc_add_request(struct intel_guc *guc, struct i915_request *rq) GEM_BUG_ON(context_guc_id_invalid(ce)); if (context_policy_required(ce)) { - err = guc_context_policy_init(ce, false); + err = guc_context_policy_init_v70(ce, false); if (err) return err; } @@ -737,9 +792,7 @@ static u32 wq_space_until_wrap(struct intel_context *ce) return (WQ_SIZE - ce->parallel.guc.wqi_tail); } -static void write_wqi(struct guc_sched_wq_desc *wq_desc, - struct intel_context *ce, - u32 wqi_size) +static void write_wqi(struct intel_context *ce, u32 wqi_size) { BUILD_BUG_ON(!is_power_of_2(WQ_SIZE)); @@ -750,13 +803,12 @@ static void write_wqi(struct guc_sched_wq_desc *wq_desc, ce->parallel.guc.wqi_tail = (ce->parallel.guc.wqi_tail + wqi_size) & (WQ_SIZE - 1); - WRITE_ONCE(wq_desc->tail, ce->parallel.guc.wqi_tail); + WRITE_ONCE(*ce->parallel.guc.wq_tail, ce->parallel.guc.wqi_tail); } static int guc_wq_noop_append(struct intel_context *ce) { - struct guc_sched_wq_desc *wq_desc = __get_wq_desc(ce); - u32 *wqi = get_wq_pointer(wq_desc, ce, wq_space_until_wrap(ce)); + u32 *wqi = get_wq_pointer(ce, wq_space_until_wrap(ce)); u32 len_dw = wq_space_until_wrap(ce) / sizeof(u32) - 1; if (!wqi) @@ -775,7 +827,6 @@ static int __guc_wq_item_append(struct i915_request *rq) { struct intel_context *ce = request_to_scheduling_context(rq); struct intel_context *child; - struct guc_sched_wq_desc *wq_desc = __get_wq_desc(ce); unsigned int wqi_size = (ce->parallel.number_children + 4) * sizeof(u32); u32 *wqi; @@ -795,7 +846,7 @@ static int __guc_wq_item_append(struct i915_request *rq) return ret; } - wqi = get_wq_pointer(wq_desc, ce, wqi_size); + wqi = get_wq_pointer(ce, wqi_size); if (!wqi) return -EBUSY; @@ -810,7 +861,7 @@ static int __guc_wq_item_append(struct i915_request *rq) for_each_child(ce, child) *wqi++ = child->ring->tail / sizeof(u64); - write_wqi(wq_desc, ce, wqi_size); + write_wqi(ce, wqi_size); return 0; } @@ -1868,20 +1919,34 @@ static void reset_fail_worker_func(struct work_struct *w); int intel_guc_submission_init(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); + int ret; if (guc->submission_initialized) return 0; + if (guc->fw.major_ver_found < 70) { + ret = guc_lrc_desc_pool_create_v69(guc); + if (ret) + return ret; + } + guc->submission_state.guc_ids_bitmap = bitmap_zalloc(NUMBER_MULTI_LRC_GUC_ID(guc), GFP_KERNEL); - if (!guc->submission_state.guc_ids_bitmap) - return -ENOMEM; + if (!guc->submission_state.guc_ids_bitmap) { + ret = -ENOMEM; + goto destroy_pool; + } guc->timestamp.ping_delay = (POLL_TIME_CLKS / gt->clock_frequency + 1) * HZ; guc->timestamp.shift = gpm_timestamp_shift(gt); guc->submission_initialized = true; return 0; + +destroy_pool: + guc_lrc_desc_pool_destroy_v69(guc); + + return ret; } void intel_guc_submission_fini(struct intel_guc *guc) @@ -1890,6 +1955,7 @@ void intel_guc_submission_fini(struct intel_guc *guc) return; guc_flush_destroyed_contexts(guc); + guc_lrc_desc_pool_destroy_v69(guc); i915_sched_engine_put(guc->sched_engine); bitmap_free(guc->submission_state.guc_ids_bitmap); guc->submission_initialized = false; @@ -2147,10 +2213,34 @@ static void unpin_guc_id(struct intel_guc *guc, struct intel_context *ce) spin_unlock_irqrestore(&guc->submission_state.lock, flags); } -static int __guc_action_register_multi_lrc(struct intel_guc *guc, - struct intel_context *ce, - struct guc_ctxt_registration_info *info, - bool loop) +static int __guc_action_register_multi_lrc_v69(struct intel_guc *guc, + struct intel_context *ce, + u32 guc_id, + u32 offset, + bool loop) +{ + struct intel_context *child; + u32 action[4 + MAX_ENGINE_INSTANCE]; + int len = 0; + + GEM_BUG_ON(ce->parallel.number_children > MAX_ENGINE_INSTANCE); + + action[len++] = INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC; + action[len++] = guc_id; + action[len++] = ce->parallel.number_children + 1; + action[len++] = offset; + for_each_child(ce, child) { + offset += sizeof(struct guc_lrc_desc_v69); + action[len++] = offset; + } + + return guc_submission_send_busy_loop(guc, action, len, 0, loop); +} + +static int __guc_action_register_multi_lrc_v70(struct intel_guc *guc, + struct intel_context *ce, + struct guc_ctxt_registration_info *info, + bool loop) { struct intel_context *child; u32 action[13 + (MAX_ENGINE_INSTANCE * 2)]; @@ -2190,9 +2280,24 @@ static int __guc_action_register_multi_lrc(struct intel_guc *guc, return guc_submission_send_busy_loop(guc, action, len, 0, loop); } -static int __guc_action_register_context(struct intel_guc *guc, - struct guc_ctxt_registration_info *info, - bool loop) +static int __guc_action_register_context_v69(struct intel_guc *guc, + u32 guc_id, + u32 offset, + bool loop) +{ + u32 action[] = { + INTEL_GUC_ACTION_REGISTER_CONTEXT, + guc_id, + offset, + }; + + return guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), + 0, loop); +} + +static int __guc_action_register_context_v70(struct intel_guc *guc, + struct guc_ctxt_registration_info *info, + bool loop) { u32 action[] = { INTEL_GUC_ACTION_REGISTER_CONTEXT, @@ -2213,24 +2318,52 @@ static int __guc_action_register_context(struct intel_guc *guc, 0, loop); } -static void prepare_context_registration_info(struct intel_context *ce, - struct guc_ctxt_registration_info *info); +static void prepare_context_registration_info_v69(struct intel_context *ce); +static void prepare_context_registration_info_v70(struct intel_context *ce, + struct guc_ctxt_registration_info *info); -static int register_context(struct intel_context *ce, bool loop) +static int +register_context_v69(struct intel_guc *guc, struct intel_context *ce, bool loop) +{ + u32 offset = intel_guc_ggtt_offset(guc, guc->lrc_desc_pool_v69) + + ce->guc_id.id * sizeof(struct guc_lrc_desc_v69); + + prepare_context_registration_info_v69(ce); + + if (intel_context_is_parent(ce)) + return __guc_action_register_multi_lrc_v69(guc, ce, ce->guc_id.id, + offset, loop); + else + return __guc_action_register_context_v69(guc, ce->guc_id.id, + offset, loop); +} + +static int +register_context_v70(struct intel_guc *guc, struct intel_context *ce, bool loop) { struct guc_ctxt_registration_info info; + + prepare_context_registration_info_v70(ce, &info); + + if (intel_context_is_parent(ce)) + return __guc_action_register_multi_lrc_v70(guc, ce, &info, loop); + else + return __guc_action_register_context_v70(guc, &info, loop); +} + +static int register_context(struct intel_context *ce, bool loop) +{ struct intel_guc *guc = ce_to_guc(ce); int ret; GEM_BUG_ON(intel_context_is_child(ce)); trace_intel_context_register(ce); - prepare_context_registration_info(ce, &info); - - if (intel_context_is_parent(ce)) - ret = __guc_action_register_multi_lrc(guc, ce, &info, loop); + if (guc->fw.major_ver_found >= 70) + ret = register_context_v70(guc, ce, loop); else - ret = __guc_action_register_context(guc, &info, loop); + ret = register_context_v69(guc, ce, loop); + if (likely(!ret)) { unsigned long flags; @@ -2238,7 +2371,8 @@ static int register_context(struct intel_context *ce, bool loop) set_context_registered(ce); spin_unlock_irqrestore(&ce->guc_state.lock, flags); - guc_context_policy_init(ce, loop); + if (guc->fw.major_ver_found >= 70) + guc_context_policy_init_v70(ce, loop); } return ret; @@ -2335,7 +2469,7 @@ static int __guc_context_set_context_policies(struct intel_guc *guc, 0, loop); } -static int guc_context_policy_init(struct intel_context *ce, bool loop) +static int guc_context_policy_init_v70(struct intel_context *ce, bool loop) { struct intel_engine_cs *engine = ce->engine; struct intel_guc *guc = &engine->gt->uc.guc; @@ -2394,8 +2528,108 @@ static int guc_context_policy_init(struct intel_context *ce, bool loop) return ret; } -static void prepare_context_registration_info(struct intel_context *ce, - struct guc_ctxt_registration_info *info) +static void guc_context_policy_init_v69(struct intel_engine_cs *engine, + struct guc_lrc_desc_v69 *desc) +{ + desc->policy_flags = 0; + + if (engine->flags & I915_ENGINE_WANT_FORCED_PREEMPTION) + desc->policy_flags |= CONTEXT_POLICY_FLAG_PREEMPT_TO_IDLE_V69; + + /* NB: For both of these, zero means disabled. */ + desc->execution_quantum = engine->props.timeslice_duration_ms * 1000; + desc->preemption_timeout = engine->props.preempt_timeout_ms * 1000; +} + +static u32 map_guc_prio_to_lrc_desc_prio(u8 prio) +{ + /* + * this matches the mapping we do in map_i915_prio_to_guc_prio() + * (e.g. prio < I915_PRIORITY_NORMAL maps to GUC_CLIENT_PRIORITY_NORMAL) + */ + switch (prio) { + default: + MISSING_CASE(prio); + fallthrough; + case GUC_CLIENT_PRIORITY_KMD_NORMAL: + return GEN12_CTX_PRIORITY_NORMAL; + case GUC_CLIENT_PRIORITY_NORMAL: + return GEN12_CTX_PRIORITY_LOW; + case GUC_CLIENT_PRIORITY_HIGH: + case GUC_CLIENT_PRIORITY_KMD_HIGH: + return GEN12_CTX_PRIORITY_HIGH; + } +} + +static void prepare_context_registration_info_v69(struct intel_context *ce) +{ + struct intel_engine_cs *engine = ce->engine; + struct intel_guc *guc = &engine->gt->uc.guc; + u32 ctx_id = ce->guc_id.id; + struct guc_lrc_desc_v69 *desc; + struct intel_context *child; + + GEM_BUG_ON(!engine->mask); + + /* + * Ensure LRC + CT vmas are is same region as write barrier is done + * based on CT vma region. + */ + GEM_BUG_ON(i915_gem_object_is_lmem(guc->ct.vma->obj) != + i915_gem_object_is_lmem(ce->ring->vma->obj)); + + desc = __get_lrc_desc_v69(guc, ctx_id); + desc->engine_class = engine_class_to_guc_class(engine->class); + desc->engine_submit_mask = engine->logical_mask; + desc->hw_context_desc = ce->lrc.lrca; + desc->priority = ce->guc_state.prio; + desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD; + guc_context_policy_init_v69(engine, desc); + + /* + * If context is a parent, we need to register a process descriptor + * describing a work queue and register all child contexts. + */ + if (intel_context_is_parent(ce)) { + struct guc_process_desc_v69 *pdesc; + + ce->parallel.guc.wqi_tail = 0; + ce->parallel.guc.wqi_head = 0; + + desc->process_desc = i915_ggtt_offset(ce->state) + + __get_parent_scratch_offset(ce); + desc->wq_addr = i915_ggtt_offset(ce->state) + + __get_wq_offset(ce); + desc->wq_size = WQ_SIZE; + + pdesc = __get_process_desc_v69(ce); + memset(pdesc, 0, sizeof(*(pdesc))); + pdesc->stage_id = ce->guc_id.id; + pdesc->wq_base_addr = desc->wq_addr; + pdesc->wq_size_bytes = desc->wq_size; + pdesc->wq_status = WQ_STATUS_ACTIVE; + + ce->parallel.guc.wq_head = &pdesc->head; + ce->parallel.guc.wq_tail = &pdesc->tail; + ce->parallel.guc.wq_status = &pdesc->wq_status; + + for_each_child(ce, child) { + desc = __get_lrc_desc_v69(guc, child->guc_id.id); + + desc->engine_class = + engine_class_to_guc_class(engine->class); + desc->hw_context_desc = child->lrc.lrca; + desc->priority = ce->guc_state.prio; + desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD; + guc_context_policy_init_v69(engine, desc); + } + + clear_children_join_go_memory(ce); + } +} + +static void prepare_context_registration_info_v70(struct intel_context *ce, + struct guc_ctxt_registration_info *info) { struct intel_engine_cs *engine = ce->engine; struct intel_guc *guc = &engine->gt->uc.guc; @@ -2420,6 +2654,8 @@ static void prepare_context_registration_info(struct intel_context *ce, */ info->hwlrca_lo = lower_32_bits(ce->lrc.lrca); info->hwlrca_hi = upper_32_bits(ce->lrc.lrca); + if (engine->flags & I915_ENGINE_HAS_EU_PRIORITY) + info->hwlrca_lo |= map_guc_prio_to_lrc_desc_prio(ce->guc_state.prio); info->flags = CONTEXT_REGISTRATION_FLAG_KMD; /* @@ -2443,10 +2679,14 @@ static void prepare_context_registration_info(struct intel_context *ce, info->wq_base_hi = upper_32_bits(wq_base_offset); info->wq_size = WQ_SIZE; - wq_desc = __get_wq_desc(ce); + wq_desc = __get_wq_desc_v70(ce); memset(wq_desc, 0, sizeof(*wq_desc)); wq_desc->wq_status = WQ_STATUS_ACTIVE; + ce->parallel.guc.wq_head = &wq_desc->head; + ce->parallel.guc.wq_tail = &wq_desc->tail; + ce->parallel.guc.wq_status = &wq_desc->wq_status; + clear_children_join_go_memory(ce); } } @@ -2761,11 +3001,21 @@ static void __guc_context_set_preemption_timeout(struct intel_guc *guc, u16 guc_id, u32 preemption_timeout) { - struct context_policy policy; + if (guc->fw.major_ver_found >= 70) { + struct context_policy policy; - __guc_context_policy_start_klv(&policy, guc_id); - __guc_context_policy_add_preemption_timeout(&policy, preemption_timeout); - __guc_context_set_context_policies(guc, &policy, true); + __guc_context_policy_start_klv(&policy, guc_id); + __guc_context_policy_add_preemption_timeout(&policy, preemption_timeout); + __guc_context_set_context_policies(guc, &policy, true); + } else { + u32 action[] = { + INTEL_GUC_ACTION_V69_SET_CONTEXT_PREEMPTION_TIMEOUT, + guc_id, + preemption_timeout + }; + + intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true); + } } static void guc_context_ban(struct intel_context *ce, struct i915_request *rq) @@ -3013,11 +3263,21 @@ static int guc_context_alloc(struct intel_context *ce) static void __guc_context_set_prio(struct intel_guc *guc, struct intel_context *ce) { - struct context_policy policy; + if (guc->fw.major_ver_found >= 70) { + struct context_policy policy; - __guc_context_policy_start_klv(&policy, ce->guc_id.id); - __guc_context_policy_add_priority(&policy, ce->guc_state.prio); - __guc_context_set_context_policies(guc, &policy, true); + __guc_context_policy_start_klv(&policy, ce->guc_id.id); + __guc_context_policy_add_priority(&policy, ce->guc_state.prio); + __guc_context_set_context_policies(guc, &policy, true); + } else { + u32 action[] = { + INTEL_GUC_ACTION_V69_SET_CONTEXT_PRIORITY, + ce->guc_id.id, + ce->guc_state.prio, + }; + + guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true); + } } static void guc_context_set_prio(struct intel_guc *guc, @@ -4527,17 +4787,19 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, guc_log_context_priority(p, ce); if (intel_context_is_parent(ce)) { - struct guc_sched_wq_desc *wq_desc = __get_wq_desc(ce); struct intel_context *child; drm_printf(p, "\t\tNumber children: %u\n", ce->parallel.number_children); - drm_printf(p, "\t\tWQI Head: %u\n", - READ_ONCE(wq_desc->head)); - drm_printf(p, "\t\tWQI Tail: %u\n", - READ_ONCE(wq_desc->tail)); - drm_printf(p, "\t\tWQI Status: %u\n\n", - READ_ONCE(wq_desc->wq_status)); + + if (ce->parallel.guc.wq_status) { + drm_printf(p, "\t\tWQI Head: %u\n", + READ_ONCE(*ce->parallel.guc.wq_head)); + drm_printf(p, "\t\tWQI Tail: %u\n", + READ_ONCE(*ce->parallel.guc.wq_tail)); + drm_printf(p, "\t\tWQI Status: %u\n\n", + READ_ONCE(*ce->parallel.guc.wq_status)); + } if (ce->engine->emit_bb_start == emit_bb_start_parent_no_preempt_mid_batch) { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index f0d7b57b741e..703f42ba5ddd 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -70,6 +70,10 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, fw_def(BROXTON, 0, guc_def(bxt, 70, 1, 1)) \ fw_def(SKYLAKE, 0, guc_def(skl, 70, 1, 1)) +#define INTEL_GUC_FIRMWARE_DEFS_FALLBACK(fw_def, guc_def) \ + fw_def(ALDERLAKE_P, 0, guc_def(adlp, 69, 0, 3)) \ + fw_def(ALDERLAKE_S, 0, guc_def(tgl, 69, 0, 3)) + #define INTEL_HUC_FIRMWARE_DEFS(fw_def, huc_def) \ fw_def(ALDERLAKE_P, 0, huc_def(tgl, 7, 9, 3)) \ fw_def(ALDERLAKE_S, 0, huc_def(tgl, 7, 9, 3)) \ @@ -105,6 +109,7 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, MODULE_FIRMWARE(uc_); INTEL_GUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_GUC_FW_PATH) +INTEL_GUC_FIRMWARE_DEFS_FALLBACK(INTEL_UC_MODULE_FW, MAKE_GUC_FW_PATH) INTEL_HUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_HUC_FW_PATH) /* The below structs and macros are used to iterate across the list of blobs */ @@ -149,6 +154,9 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) static const struct uc_fw_platform_requirement blobs_guc[] = { INTEL_GUC_FIRMWARE_DEFS(MAKE_FW_LIST, GUC_FW_BLOB) }; + static const struct uc_fw_platform_requirement blobs_guc_fallback[] = { + INTEL_GUC_FIRMWARE_DEFS_FALLBACK(MAKE_FW_LIST, GUC_FW_BLOB) + }; static const struct uc_fw_platform_requirement blobs_huc[] = { INTEL_HUC_FIRMWARE_DEFS(MAKE_FW_LIST, HUC_FW_BLOB) }; @@ -162,6 +170,15 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) u8 rev = INTEL_REVID(i915); int i; + /* + * The only difference between the ADL GuC FWs is the HWConfig support. + * ADL-N does not support HWConfig, so we should use the same binary as + * ADL-S, otherwise the GuC might attempt to fetch a config table that + * does not exist. + */ + if (IS_ADLP_N(i915)) + p = INTEL_ALDERLAKE_S; + GEM_BUG_ON(uc_fw->type >= ARRAY_SIZE(blobs_all)); fw_blobs = blobs_all[uc_fw->type].blobs; fw_count = blobs_all[uc_fw->type].count; @@ -170,12 +187,29 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) if (p == fw_blobs[i].p && rev >= fw_blobs[i].rev) { const struct uc_fw_blob *blob = &fw_blobs[i].blob; uc_fw->path = blob->path; + uc_fw->wanted_path = blob->path; uc_fw->major_ver_wanted = blob->major; uc_fw->minor_ver_wanted = blob->minor; break; } } + if (uc_fw->type == INTEL_UC_FW_TYPE_GUC) { + const struct uc_fw_platform_requirement *blobs = blobs_guc_fallback; + u32 count = ARRAY_SIZE(blobs_guc_fallback); + + for (i = 0; i < count && p <= blobs[i].p; i++) { + if (p == blobs[i].p && rev >= blobs[i].rev) { + const struct uc_fw_blob *blob = &blobs[i].blob; + + uc_fw->fallback.path = blob->path; + uc_fw->fallback.major_ver = blob->major; + uc_fw->fallback.minor_ver = blob->minor; + break; + } + } + } + /* make sure the list is ordered as expected */ if (IS_ENABLED(CONFIG_DRM_I915_SELFTEST)) { for (i = 1; i < fw_count; i++) { @@ -329,7 +363,24 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) __force_fw_fetch_failures(uc_fw, -EINVAL); __force_fw_fetch_failures(uc_fw, -ESTALE); - err = request_firmware(&fw, uc_fw->path, dev); + err = firmware_request_nowarn(&fw, uc_fw->path, dev); + if (err && !intel_uc_fw_is_overridden(uc_fw) && uc_fw->fallback.path) { + err = firmware_request_nowarn(&fw, uc_fw->fallback.path, dev); + if (!err) { + drm_notice(&i915->drm, + "%s firmware %s is recommended, but only %s was found\n", + intel_uc_fw_type_repr(uc_fw->type), + uc_fw->wanted_path, + uc_fw->fallback.path); + drm_info(&i915->drm, + "Consider updating your linux-firmware pkg or downloading from %s\n", + INTEL_UC_FIRMWARE_URL); + + uc_fw->path = uc_fw->fallback.path; + uc_fw->major_ver_wanted = uc_fw->fallback.major_ver; + uc_fw->minor_ver_wanted = uc_fw->fallback.minor_ver; + } + } if (err) goto fail; @@ -428,8 +479,8 @@ fail: INTEL_UC_FIRMWARE_MISSING : INTEL_UC_FIRMWARE_ERROR); - drm_notice(&i915->drm, "%s firmware %s: fetch failed with error %d\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, err); + i915_probe_error(i915, "%s firmware %s: fetch failed with error %d\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, err); drm_info(&i915->drm, "%s firmware(s) can be downloaded from %s\n", intel_uc_fw_type_repr(uc_fw->type), INTEL_UC_FIRMWARE_URL); @@ -787,7 +838,13 @@ size_t intel_uc_fw_copy_rsa(struct intel_uc_fw *uc_fw, void *dst, u32 max_len) void intel_uc_fw_dump(const struct intel_uc_fw *uc_fw, struct drm_printer *p) { drm_printf(p, "%s firmware: %s\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->path); + intel_uc_fw_type_repr(uc_fw->type), uc_fw->wanted_path); + if (uc_fw->fallback.path) { + drm_printf(p, "%s firmware fallback: %s\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->fallback.path); + drm_printf(p, "fallback selected: %s\n", + str_yes_no(uc_fw->path == uc_fw->fallback.path)); + } drm_printf(p, "\tstatus: %s\n", intel_uc_fw_status_repr(uc_fw->status)); drm_printf(p, "\tversion: wanted %u.%u, found %u.%u\n", diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h index 3229018877d3..562acdf88adb 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h @@ -74,6 +74,7 @@ struct intel_uc_fw { const enum intel_uc_fw_status status; enum intel_uc_fw_status __status; /* no accidental overwrites */ }; + const char *wanted_path; const char *path; bool user_overridden; size_t size; @@ -98,6 +99,12 @@ struct intel_uc_fw { u16 major_ver_found; u16 minor_ver_found; + struct { + const char *path; + u16 major_ver; + u16 minor_ver; + } fallback; + u32 rsa_size; u32 ucode_size; diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index b9eb75a2b400..1c35a41620ae 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -3117,9 +3117,9 @@ void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu) continue; vaddr = shmem_pin_map(engine->default_state); - if (IS_ERR(vaddr)) { - gvt_err("failed to map %s->default state, err:%zd\n", - engine->name, PTR_ERR(vaddr)); + if (!vaddr) { + gvt_err("failed to map %s->default state\n", + engine->name); return; } diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c index 159571b9bd24..dcc081874ec8 100644 --- a/drivers/gpu/drm/i915/i915_scatterlist.c +++ b/drivers/gpu/drm/i915/i915_scatterlist.c @@ -68,6 +68,7 @@ void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size) * drm_mm_node * @node: The drm_mm_node. * @region_start: An offset to add to the dma addresses of the sg list. + * @page_alignment: Required page alignment for each sg entry. Power of two. * * Create a struct sg_table, initializing it from a struct drm_mm_node, * taking a maximum segment length into account, splitting into segments @@ -77,22 +78,25 @@ void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size) * error code cast to an error pointer on failure. */ struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node, - u64 region_start) + u64 region_start, + u32 page_alignment) { - const u64 max_segment = SZ_1G; /* Do we have a limit on this? */ - u64 segment_pages = max_segment >> PAGE_SHIFT; + const u32 max_segment = round_down(UINT_MAX, page_alignment); + const u32 segment_pages = max_segment >> PAGE_SHIFT; u64 block_size, offset, prev_end; struct i915_refct_sgt *rsgt; struct sg_table *st; struct scatterlist *sg; + GEM_BUG_ON(!max_segment); + rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL); if (!rsgt) return ERR_PTR(-ENOMEM); i915_refct_sgt_init(rsgt, node->size << PAGE_SHIFT); st = &rsgt->table; - if (sg_alloc_table(st, DIV_ROUND_UP(node->size, segment_pages), + if (sg_alloc_table(st, DIV_ROUND_UP_ULL(node->size, segment_pages), GFP_KERNEL)) { i915_refct_sgt_put(rsgt); return ERR_PTR(-ENOMEM); @@ -112,12 +116,14 @@ struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node, sg = __sg_next(sg); sg_dma_address(sg) = region_start + offset; + GEM_BUG_ON(!IS_ALIGNED(sg_dma_address(sg), + page_alignment)); sg_dma_len(sg) = 0; sg->length = 0; st->nents++; } - len = min(block_size, max_segment - sg->length); + len = min_t(u64, block_size, max_segment - sg->length); sg->length += len; sg_dma_len(sg) += len; @@ -138,6 +144,7 @@ struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node, * i915_buddy_block list * @res: The struct i915_ttm_buddy_resource. * @region_start: An offset to add to the dma addresses of the sg list. + * @page_alignment: Required page alignment for each sg entry. Power of two. * * Create a struct sg_table, initializing it from struct i915_buddy_block list, * taking a maximum segment length into account, splitting into segments @@ -147,11 +154,12 @@ struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node, * error code cast to an error pointer on failure. */ struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res, - u64 region_start) + u64 region_start, + u32 page_alignment) { struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res); const u64 size = res->num_pages << PAGE_SHIFT; - const u64 max_segment = rounddown(UINT_MAX, PAGE_SIZE); + const u32 max_segment = round_down(UINT_MAX, page_alignment); struct drm_buddy *mm = bman_res->mm; struct list_head *blocks = &bman_res->blocks; struct drm_buddy_block *block; @@ -161,6 +169,7 @@ struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res, resource_size_t prev_end; GEM_BUG_ON(list_empty(blocks)); + GEM_BUG_ON(!max_segment); rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL); if (!rsgt) @@ -191,12 +200,14 @@ struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res, sg = __sg_next(sg); sg_dma_address(sg) = region_start + offset; + GEM_BUG_ON(!IS_ALIGNED(sg_dma_address(sg), + page_alignment)); sg_dma_len(sg) = 0; sg->length = 0; st->nents++; } - len = min(block_size, max_segment - sg->length); + len = min_t(u64, block_size, max_segment - sg->length); sg->length += len; sg_dma_len(sg) += len; diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h index 12c6a1684081..9ddb3e743a3e 100644 --- a/drivers/gpu/drm/i915/i915_scatterlist.h +++ b/drivers/gpu/drm/i915/i915_scatterlist.h @@ -213,9 +213,11 @@ static inline void __i915_refct_sgt_init(struct i915_refct_sgt *rsgt, void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size); struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node, - u64 region_start); + u64 region_start, + u32 page_alignment); struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res, - u64 region_start); + u64 region_start, + u32 page_alignment); #endif diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 0bffb70b3c5f..04d12f278f57 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1637,10 +1637,10 @@ static void force_unbind(struct i915_vma *vma) GEM_BUG_ON(drm_mm_node_allocated(&vma->node)); } -static void release_references(struct i915_vma *vma, bool vm_ddestroy) +static void release_references(struct i915_vma *vma, struct intel_gt *gt, + bool vm_ddestroy) { struct drm_i915_gem_object *obj = vma->obj; - struct intel_gt *gt = vma->vm->gt; GEM_BUG_ON(i915_vma_is_active(vma)); @@ -1695,11 +1695,12 @@ void i915_vma_destroy_locked(struct i915_vma *vma) force_unbind(vma); list_del_init(&vma->vm_link); - release_references(vma, false); + release_references(vma, vma->vm->gt, false); } void i915_vma_destroy(struct i915_vma *vma) { + struct intel_gt *gt; bool vm_ddestroy; mutex_lock(&vma->vm->mutex); @@ -1707,8 +1708,11 @@ void i915_vma_destroy(struct i915_vma *vma) list_del_init(&vma->vm_link); vm_ddestroy = vma->vm_ddestroy; vma->vm_ddestroy = false; + + /* vma->vm may be freed when releasing vma->vm->mutex. */ + gt = vma->vm->gt; mutex_unlock(&vma->vm->mutex); - release_references(vma, vm_ddestroy); + release_references(vma, gt, vm_ddestroy); } void i915_vma_parked(struct intel_gt *gt) diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c index 62ff77445b01..575d67bc6ffe 100644 --- a/drivers/gpu/drm/i915/intel_region_ttm.c +++ b/drivers/gpu/drm/i915/intel_region_ttm.c @@ -152,6 +152,7 @@ int intel_region_ttm_fini(struct intel_memory_region *mem) * Convert an opaque TTM resource manager resource to a refcounted sg_table. * @mem: The memory region. * @res: The resource manager resource obtained from the TTM resource manager. + * @page_alignment: Required page alignment for each sg entry. Power of two. * * The gem backends typically use sg-tables for operations on the underlying * io_memory. So provide a way for the backends to translate the @@ -161,16 +162,19 @@ int intel_region_ttm_fini(struct intel_memory_region *mem) */ struct i915_refct_sgt * intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem, - struct ttm_resource *res) + struct ttm_resource *res, + u32 page_alignment) { if (mem->is_range_manager) { struct ttm_range_mgr_node *range_node = to_ttm_range_mgr_node(res); return i915_rsgt_from_mm_node(&range_node->mm_nodes[0], - mem->region.start); + mem->region.start, + page_alignment); } else { - return i915_rsgt_from_buddy_resource(res, mem->region.start); + return i915_rsgt_from_buddy_resource(res, mem->region.start, + page_alignment); } } diff --git a/drivers/gpu/drm/i915/intel_region_ttm.h b/drivers/gpu/drm/i915/intel_region_ttm.h index cf9d86dcf409..5bb8d8b582ae 100644 --- a/drivers/gpu/drm/i915/intel_region_ttm.h +++ b/drivers/gpu/drm/i915/intel_region_ttm.h @@ -24,7 +24,8 @@ int intel_region_ttm_fini(struct intel_memory_region *mem); struct i915_refct_sgt * intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem, - struct ttm_resource *res); + struct ttm_resource *res, + u32 page_alignment); void intel_region_ttm_resource_free(struct intel_memory_region *mem, struct ttm_resource *res); diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 8633bec18fa7..ab9f17fc85bc 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -742,7 +742,7 @@ static int pot_hole(struct i915_address_space *vm, u64 addr; for (addr = round_up(hole_start + min_alignment, step) - min_alignment; - addr <= round_down(hole_end - (2 * min_alignment), step) - min_alignment; + hole_end > addr && hole_end - addr >= 2 * min_alignment; addr += step) { err = i915_vma_pin(vma, 0, 0, addr | flags); if (err) { diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c index 73eb53edb8de..3b18e5905c86 100644 --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c @@ -451,7 +451,6 @@ out_put: static int igt_mock_max_segment(void *arg) { - const unsigned int max_segment = rounddown(UINT_MAX, PAGE_SIZE); struct intel_memory_region *mem = arg; struct drm_i915_private *i915 = mem->i915; struct i915_ttm_buddy_resource *res; @@ -460,7 +459,10 @@ static int igt_mock_max_segment(void *arg) struct drm_buddy *mm; struct list_head *blocks; struct scatterlist *sg; + I915_RND_STATE(prng); LIST_HEAD(objects); + unsigned int max_segment; + unsigned int ps; u64 size; int err = 0; @@ -472,7 +474,13 @@ static int igt_mock_max_segment(void *arg) */ size = SZ_8G; - mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0, 0); + ps = PAGE_SIZE; + if (i915_prandom_u64_state(&prng) & 1) + ps = SZ_64K; /* For something like DG2 */ + + max_segment = round_down(UINT_MAX, ps); + + mem = mock_region_create(i915, 0, size, ps, 0, 0); if (IS_ERR(mem)) return PTR_ERR(mem); @@ -498,12 +506,21 @@ static int igt_mock_max_segment(void *arg) } for (sg = obj->mm.pages->sgl; sg; sg = sg_next(sg)) { + dma_addr_t daddr = sg_dma_address(sg); + if (sg->length > max_segment) { pr_err("%s: Created an oversized scatterlist entry, %u > %u\n", __func__, sg->length, max_segment); err = -EINVAL; goto out_close; } + + if (!IS_ALIGNED(daddr, ps)) { + pr_err("%s: Created an unaligned scatterlist entry, addr=%pa, ps=%u\n", + __func__, &daddr, ps); + err = -EINVAL; + goto out_close; + } } out_close: diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c index 670557ce1024..bac21fe84ca5 100644 --- a/drivers/gpu/drm/i915/selftests/mock_region.c +++ b/drivers/gpu/drm/i915/selftests/mock_region.c @@ -33,7 +33,8 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj) return PTR_ERR(obj->mm.res); obj->mm.rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region, - obj->mm.res); + obj->mm.res, + obj->mm.region->min_page_size); if (IS_ERR(obj->mm.rsgt)) { err = PTR_ERR(obj->mm.rsgt); goto err_free_resource; diff --git a/drivers/gpu/drm/imx/dcss/dcss-dev.c b/drivers/gpu/drm/imx/dcss/dcss-dev.c index c849533ca83e..3f5750cc2673 100644 --- a/drivers/gpu/drm/imx/dcss/dcss-dev.c +++ b/drivers/gpu/drm/imx/dcss/dcss-dev.c @@ -207,6 +207,7 @@ struct dcss_dev *dcss_dev_create(struct device *dev, bool hdmi_output) ret = dcss_submodules_init(dcss); if (ret) { + of_node_put(dcss->of_port); dev_err(dev, "submodules initialization failed\n"); goto clks_err; } @@ -237,6 +238,8 @@ void dcss_dev_destroy(struct dcss_dev *dcss) dcss_clocks_disable(dcss); } + of_node_put(dcss->of_port); + pm_runtime_disable(dcss->dev); dcss_submodules_stop(dcss); diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index c96014464355..a189982601a4 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -713,7 +713,7 @@ static int generic_edp_panel_probe(struct device *dev, struct panel_edp *panel) of_property_read_u32(dev->of_node, "hpd-reliable-delay-ms", &reliable_ms); desc->delay.hpd_reliable = reliable_ms; of_property_read_u32(dev->of_node, "hpd-absent-delay-ms", &absent_ms); - desc->delay.hpd_reliable = absent_ms; + desc->delay.hpd_absent = absent_ms; /* Power the panel on so we can read the EDID */ ret = pm_runtime_get_sync(dev); diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 087e69b98d06..b1e6d238674f 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -433,8 +433,8 @@ static int panfrost_ioctl_madvise(struct drm_device *dev, void *data, if (args->retained) { if (args->madv == PANFROST_MADV_DONTNEED) - list_add_tail(&bo->base.madv_list, - &pfdev->shrinker_list); + list_move_tail(&bo->base.madv_list, + &pfdev->shrinker_list); else if (args->madv == PANFROST_MADV_WILLNEED) list_del_init(&bo->base.madv_list); } diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index d3f82b26a631..b285a8001b1d 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -518,7 +518,7 @@ err_map: err_pages: drm_gem_shmem_put_pages(&bo->base); err_bo: - drm_gem_object_put(&bo->base.base); + panfrost_gem_mapping_put(bomapping); return ret; } diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 67d38f53d3e5..13ed33e74457 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -23,6 +23,14 @@ #include <drm/drm_probe_helper.h> #include <drm/drm_vblank.h> +#if defined(CONFIG_ARM_DMA_USE_IOMMU) +#include <asm/dma-iommu.h> +#else +#define arm_iommu_detach_device(...) ({ }) +#define arm_iommu_release_mapping(...) ({ }) +#define to_dma_iommu_mapping(dev) NULL +#endif + #include "rockchip_drm_drv.h" #include "rockchip_drm_fb.h" #include "rockchip_drm_gem.h" @@ -49,6 +57,15 @@ int rockchip_drm_dma_attach_device(struct drm_device *drm_dev, if (!private->domain) return 0; + if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) { + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); + + if (mapping) { + arm_iommu_detach_device(dev); + arm_iommu_release_mapping(mapping); + } + } + ret = iommu_attach_device(private->domain, dev); if (ret) { DRM_DEV_ERROR(dev, "Failed to attach iommu device\n"); diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 191c56064f19..6b25b2f4f5a3 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -190,7 +190,7 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) } EXPORT_SYMBOL(drm_sched_entity_flush); -static void drm_sched_entity_kill_jobs_irq_work(struct irq_work *wrk) +static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk) { struct drm_sched_job *job = container_of(wrk, typeof(*job), work); @@ -207,8 +207,8 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, struct drm_sched_job *job = container_of(cb, struct drm_sched_job, finish_cb); - init_irq_work(&job->work, drm_sched_entity_kill_jobs_irq_work); - irq_work_queue(&job->work); + INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work); + schedule_work(&job->work); } static struct dma_fence * diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c index 08394444dd6e..f4886e66ff34 100644 --- a/drivers/gpu/drm/solomon/ssd130x.c +++ b/drivers/gpu/drm/solomon/ssd130x.c @@ -350,7 +350,7 @@ static int ssd130x_init(struct ssd130x_device *ssd130x) /* Set precharge period in number of ticks from the internal clock */ precharge = (SSD130X_SET_PRECHARGE_PERIOD1_SET(ssd130x->prechargep1) | - SSD130X_SET_PRECHARGE_PERIOD1_SET(ssd130x->prechargep2)); + SSD130X_SET_PRECHARGE_PERIOD2_SET(ssd130x->prechargep2)); ret = ssd130x_write_cmd(ssd130x, 2, SSD130X_SET_PRECHARGE_PERIOD, precharge); if (ret < 0) return ret; diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index 3d6f8ee355bf..630cfa4ddd46 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -388,9 +388,9 @@ static irqreturn_t cdns_i2c_slave_isr(void *ptr) */ static irqreturn_t cdns_i2c_master_isr(void *ptr) { - unsigned int isr_status, avail_bytes, updatetx; + unsigned int isr_status, avail_bytes; unsigned int bytes_to_send; - bool hold_quirk; + bool updatetx; struct cdns_i2c *id = ptr; /* Signal completion only after everything is updated */ int done_flag = 0; @@ -410,11 +410,7 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr) * Check if transfer size register needs to be updated again for a * large data receive operation. */ - updatetx = 0; - if (id->recv_count > id->curr_recv_count) - updatetx = 1; - - hold_quirk = (id->quirks & CDNS_I2C_BROKEN_HOLD_BIT) && updatetx; + updatetx = id->recv_count > id->curr_recv_count; /* When receiving, handle data interrupt and completion interrupt */ if (id->p_recv_buf && @@ -445,7 +441,7 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr) break; } - if (cdns_is_holdquirk(id, hold_quirk)) + if (cdns_is_holdquirk(id, updatetx)) break; } @@ -456,7 +452,7 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr) * maintain transfer size non-zero while performing a large * receive operation. */ - if (cdns_is_holdquirk(id, hold_quirk)) { + if (cdns_is_holdquirk(id, updatetx)) { /* wait while fifo is full */ while (cdns_i2c_readreg(CDNS_I2C_XFER_SIZE_OFFSET) != (id->curr_recv_count - CDNS_I2C_FIFO_DEPTH)) @@ -478,22 +474,6 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr) CDNS_I2C_XFER_SIZE_OFFSET); id->curr_recv_count = id->recv_count; } - } else if (id->recv_count && !hold_quirk && - !id->curr_recv_count) { - - /* Set the slave address in address register*/ - cdns_i2c_writereg(id->p_msg->addr & CDNS_I2C_ADDR_MASK, - CDNS_I2C_ADDR_OFFSET); - - if (id->recv_count > CDNS_I2C_TRANSFER_SIZE) { - cdns_i2c_writereg(CDNS_I2C_TRANSFER_SIZE, - CDNS_I2C_XFER_SIZE_OFFSET); - id->curr_recv_count = CDNS_I2C_TRANSFER_SIZE; - } else { - cdns_i2c_writereg(id->recv_count, - CDNS_I2C_XFER_SIZE_OFFSET); - id->curr_recv_count = id->recv_count; - } } /* Clear hold (if not repeated start) and signal completion */ diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index e9e2db68b9fb..78fb1a4274a6 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -66,7 +66,7 @@ /* IMX I2C registers: * the I2C register offset is different between SoCs, - * to provid support for all these chips, split the + * to provide support for all these chips, split the * register offset into a fixed base address and a * variable shift value, then the full register offset * will be calculated by diff --git a/drivers/i2c/busses/i2c-mlxcpld.c b/drivers/i2c/busses/i2c-mlxcpld.c index 56aa424fd71d..815cc561386b 100644 --- a/drivers/i2c/busses/i2c-mlxcpld.c +++ b/drivers/i2c/busses/i2c-mlxcpld.c @@ -49,7 +49,7 @@ #define MLXCPLD_LPCI2C_NACK_IND 2 #define MLXCPLD_I2C_FREQ_1000KHZ_SET 0x04 -#define MLXCPLD_I2C_FREQ_400KHZ_SET 0x0c +#define MLXCPLD_I2C_FREQ_400KHZ_SET 0x0e #define MLXCPLD_I2C_FREQ_100KHZ_SET 0x42 enum mlxcpld_i2c_frequency { diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 424ef470223d..f5c6802aa6c3 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -47,11 +47,13 @@ #include <linux/tick.h> #include <trace/events/power.h> #include <linux/sched.h> +#include <linux/sched/smt.h> #include <linux/notifier.h> #include <linux/cpu.h> #include <linux/moduleparam.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> +#include <asm/nospec-branch.h> #include <asm/mwait.h> #include <asm/msr.h> @@ -106,6 +108,12 @@ static unsigned int mwait_substates __initdata; #define CPUIDLE_FLAG_ALWAYS_ENABLE BIT(15) /* + * Disable IBRS across idle (when KERNEL_IBRS), is exclusive vs IRQ_ENABLE + * above. + */ +#define CPUIDLE_FLAG_IBRS BIT(16) + +/* * MWAIT takes an 8-bit "hint" in EAX "suggesting" * the C-state (top nibble) and sub-state (bottom nibble) * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc. @@ -159,6 +167,24 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev, return ret; } +static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + bool smt_active = sched_smt_active(); + u64 spec_ctrl = spec_ctrl_current(); + int ret; + + if (smt_active) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + + ret = __intel_idle(dev, drv, index); + + if (smt_active) + wrmsrl(MSR_IA32_SPEC_CTRL, spec_ctrl); + + return ret; +} + /** * intel_idle_s2idle - Ask the processor to enter the given idle state. * @dev: cpuidle device of the target CPU. @@ -680,7 +706,7 @@ static struct cpuidle_state skl_cstates[] __initdata = { { .name = "C6", .desc = "MWAIT 0x20", - .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 85, .target_residency = 200, .enter = &intel_idle, @@ -688,7 +714,7 @@ static struct cpuidle_state skl_cstates[] __initdata = { { .name = "C7s", .desc = "MWAIT 0x33", - .flags = MWAIT2flg(0x33) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x33) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 124, .target_residency = 800, .enter = &intel_idle, @@ -696,7 +722,7 @@ static struct cpuidle_state skl_cstates[] __initdata = { { .name = "C8", .desc = "MWAIT 0x40", - .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 200, .target_residency = 800, .enter = &intel_idle, @@ -704,7 +730,7 @@ static struct cpuidle_state skl_cstates[] __initdata = { { .name = "C9", .desc = "MWAIT 0x50", - .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 480, .target_residency = 5000, .enter = &intel_idle, @@ -712,7 +738,7 @@ static struct cpuidle_state skl_cstates[] __initdata = { { .name = "C10", .desc = "MWAIT 0x60", - .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 890, .target_residency = 5000, .enter = &intel_idle, @@ -741,7 +767,7 @@ static struct cpuidle_state skx_cstates[] __initdata = { { .name = "C6", .desc = "MWAIT 0x20", - .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS, .exit_latency = 133, .target_residency = 600, .enter = &intel_idle, @@ -1819,6 +1845,12 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE) drv->states[drv->state_count].enter = intel_idle_irq; + if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && + cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IBRS) { + WARN_ON_ONCE(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE); + drv->states[drv->state_count].enter = intel_idle_ibrs; + } + if ((disabled_states_mask & BIT(drv->state_count)) || ((icpu->use_acpi || force_use_acpi) && intel_idle_off_by_default(mwait_hint) && diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index 638bf4a1ed94..646fa8677490 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -4231,10 +4231,6 @@ void irdma_cm_teardown_connections(struct irdma_device *iwdev, u32 *ipaddr, struct irdma_cm_node *cm_node; struct list_head teardown_list; struct ib_qp_attr attr; - struct irdma_sc_vsi *vsi = &iwdev->vsi; - struct irdma_sc_qp *sc_qp; - struct irdma_qp *qp; - int i; INIT_LIST_HEAD(&teardown_list); @@ -4251,52 +4247,6 @@ void irdma_cm_teardown_connections(struct irdma_device *iwdev, u32 *ipaddr, irdma_cm_disconn(cm_node->iwqp); irdma_rem_ref_cm_node(cm_node); } - if (!iwdev->roce_mode) - return; - - INIT_LIST_HEAD(&teardown_list); - for (i = 0; i < IRDMA_MAX_USER_PRIORITY; i++) { - mutex_lock(&vsi->qos[i].qos_mutex); - list_for_each_safe (list_node, list_core_temp, - &vsi->qos[i].qplist) { - u32 qp_ip[4]; - - sc_qp = container_of(list_node, struct irdma_sc_qp, - list); - if (sc_qp->qp_uk.qp_type != IRDMA_QP_TYPE_ROCE_RC) - continue; - - qp = sc_qp->qp_uk.back_qp; - if (!disconnect_all) { - if (nfo->ipv4) - qp_ip[0] = qp->udp_info.local_ipaddr[3]; - else - memcpy(qp_ip, - &qp->udp_info.local_ipaddr[0], - sizeof(qp_ip)); - } - - if (disconnect_all || - (nfo->vlan_id == (qp->udp_info.vlan_tag & VLAN_VID_MASK) && - !memcmp(qp_ip, ipaddr, nfo->ipv4 ? 4 : 16))) { - spin_lock(&iwdev->rf->qptable_lock); - if (iwdev->rf->qp_table[sc_qp->qp_uk.qp_id]) { - irdma_qp_add_ref(&qp->ibqp); - list_add(&qp->teardown_entry, - &teardown_list); - } - spin_unlock(&iwdev->rf->qptable_lock); - } - } - mutex_unlock(&vsi->qos[i].qos_mutex); - } - - list_for_each_safe (list_node, list_core_temp, &teardown_list) { - qp = container_of(list_node, struct irdma_qp, teardown_entry); - attr.qp_state = IB_QPS_ERR; - irdma_modify_qp_roce(&qp->ibqp, &attr, IB_QP_STATE, NULL); - irdma_qp_rem_ref(&qp->ibqp); - } } /** diff --git a/drivers/infiniband/hw/irdma/i40iw_hw.c b/drivers/infiniband/hw/irdma/i40iw_hw.c index e46fc110004d..50299f58b6b3 100644 --- a/drivers/infiniband/hw/irdma/i40iw_hw.c +++ b/drivers/infiniband/hw/irdma/i40iw_hw.c @@ -201,6 +201,7 @@ void i40iw_init_hw(struct irdma_sc_dev *dev) dev->hw_attrs.uk_attrs.max_hw_read_sges = I40IW_MAX_SGE_RD; dev->hw_attrs.max_hw_device_pages = I40IW_MAX_PUSH_PAGE_COUNT; dev->hw_attrs.uk_attrs.max_hw_inline = I40IW_MAX_INLINE_DATA_SIZE; + dev->hw_attrs.page_size_cap = SZ_4K | SZ_2M; dev->hw_attrs.max_hw_ird = I40IW_MAX_IRD_SIZE; dev->hw_attrs.max_hw_ord = I40IW_MAX_ORD_SIZE; dev->hw_attrs.max_hw_wqes = I40IW_MAX_WQ_ENTRIES; diff --git a/drivers/infiniband/hw/irdma/icrdma_hw.c b/drivers/infiniband/hw/irdma/icrdma_hw.c index cf53b17510cd..5986fd906308 100644 --- a/drivers/infiniband/hw/irdma/icrdma_hw.c +++ b/drivers/infiniband/hw/irdma/icrdma_hw.c @@ -139,6 +139,7 @@ void icrdma_init_hw(struct irdma_sc_dev *dev) dev->cqp_db = dev->hw_regs[IRDMA_CQPDB]; dev->cq_ack_db = dev->hw_regs[IRDMA_CQACK]; dev->irq_ops = &icrdma_irq_ops; + dev->hw_attrs.page_size_cap = SZ_4K | SZ_2M | SZ_1G; dev->hw_attrs.max_hw_ird = ICRDMA_MAX_IRD_SIZE; dev->hw_attrs.max_hw_ord = ICRDMA_MAX_ORD_SIZE; dev->hw_attrs.max_stat_inst = ICRDMA_MAX_STATS_COUNT; diff --git a/drivers/infiniband/hw/irdma/irdma.h b/drivers/infiniband/hw/irdma/irdma.h index 46c12334c735..4789e85d717b 100644 --- a/drivers/infiniband/hw/irdma/irdma.h +++ b/drivers/infiniband/hw/irdma/irdma.h @@ -127,6 +127,7 @@ struct irdma_hw_attrs { u64 max_hw_outbound_msg_size; u64 max_hw_inbound_msg_size; u64 max_mr_size; + u64 page_size_cap; u32 min_hw_qp_id; u32 min_hw_aeq_size; u32 max_hw_aeq_size; diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index c4412ece5a6d..96135a228f26 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -32,7 +32,7 @@ static int irdma_query_device(struct ib_device *ibdev, props->vendor_part_id = pcidev->device; props->hw_ver = rf->pcidev->revision; - props->page_size_cap = SZ_4K | SZ_2M | SZ_1G; + props->page_size_cap = hw_attrs->page_size_cap; props->max_mr_size = hw_attrs->max_mr_size; props->max_qp = rf->max_qp - rf->used_qps; props->max_qp_wr = hw_attrs->max_qp_wr; @@ -2781,7 +2781,7 @@ static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len, if (req.reg_type == IRDMA_MEMREG_TYPE_MEM) { iwmr->page_size = ib_umem_find_best_pgsz(region, - SZ_4K | SZ_2M | SZ_1G, + iwdev->rf->sc_dev.hw_attrs.page_size_cap, virt); if (unlikely(!iwmr->page_size)) { kfree(iwmr); diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index 3ad9870db108..aa45a9fee6a0 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -900,6 +900,11 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts) } else { dev_warn(dev, "Unexpected ACPI resources: gpio_count %d, gpio_int_idx %d\n", ts->gpio_count, ts->gpio_int_idx); + /* + * On some devices _PS0 does a reset for us and + * sometimes this is necessary for things to work. + */ + acpi_device_fix_up_power(ACPI_COMPANION(dev)); return -EINVAL; } diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c index 43c521f50c85..3dda6eaabdab 100644 --- a/drivers/input/touchscreen/usbtouchscreen.c +++ b/drivers/input/touchscreen/usbtouchscreen.c @@ -1654,6 +1654,9 @@ static int usbtouch_probe(struct usb_interface *intf, if (id->driver_info == DEVTYPE_IGNORE) return -ENODEV; + if (id->driver_info >= ARRAY_SIZE(usbtouch_dev_info)) + return -ENODEV; + endpoint = usbtouch_get_input_endpoint(intf->cur_altsetting); if (!endpoint) return -ENXIO; diff --git a/drivers/input/touchscreen/wm97xx-core.c b/drivers/input/touchscreen/wm97xx-core.c index 2757c7768ffe..f51ab5614532 100644 --- a/drivers/input/touchscreen/wm97xx-core.c +++ b/drivers/input/touchscreen/wm97xx-core.c @@ -758,7 +758,9 @@ batt_err: static int wm97xx_mfd_remove(struct platform_device *pdev) { - return wm97xx_remove(&pdev->dev); + wm97xx_remove(&pdev->dev); + + return 0; } static int __maybe_unused wm97xx_suspend(struct device *dev) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 20e53b167f81..c8539d0e12dd 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7304,7 +7304,9 @@ static struct r5conf *setup_conf(struct mddev *mddev) goto abort; conf->mddev = mddev; - if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL) + ret = -ENOMEM; + conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!conf->stripe_hashtbl) goto abort; /* We init hash_locks[0] separately to that it can be used diff --git a/drivers/misc/lkdtm/Makefile b/drivers/misc/lkdtm/Makefile index 2e0aa74ac185..95ef971b5e1c 100644 --- a/drivers/misc/lkdtm/Makefile +++ b/drivers/misc/lkdtm/Makefile @@ -13,10 +13,13 @@ lkdtm-$(CONFIG_LKDTM) += cfi.o lkdtm-$(CONFIG_LKDTM) += fortify.o lkdtm-$(CONFIG_PPC_64S_HASH_MMU) += powerpc.o -KASAN_SANITIZE_rodata.o := n KASAN_SANITIZE_stackleak.o := n -KCOV_INSTRUMENT_rodata.o := n -CFLAGS_REMOVE_rodata.o += $(CC_FLAGS_LTO) + +KASAN_SANITIZE_rodata.o := n +KCSAN_SANITIZE_rodata.o := n +KCOV_INSTRUMENT_rodata.o := n +OBJECT_FILES_NON_STANDARD_rodata.o := y +CFLAGS_REMOVE_rodata.o += $(CC_FLAGS_LTO) $(RETHUNK_CFLAGS) OBJCOPYFLAGS := OBJCOPYFLAGS_rodata_objcopy.o := \ diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c index 86e867ffbb10..033be559a730 100644 --- a/drivers/mmc/host/sdhci-omap.c +++ b/drivers/mmc/host/sdhci-omap.c @@ -1298,8 +1298,9 @@ static int sdhci_omap_probe(struct platform_device *pdev) /* * omap_device_pm_domain has callbacks to enable the main * functional clock, interface clock and also configure the - * SYSCONFIG register of omap devices. The callback will be invoked - * as part of pm_runtime_get_sync. + * SYSCONFIG register to clear any boot loader set voltage + * capabilities before calling sdhci_setup_host(). The + * callback will be invoked as part of pm_runtime_get_sync. */ pm_runtime_use_autosuspend(dev); pm_runtime_set_autosuspend_delay(dev, 50); @@ -1441,7 +1442,8 @@ static int __maybe_unused sdhci_omap_runtime_suspend(struct device *dev) struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_omap_host *omap_host = sdhci_pltfm_priv(pltfm_host); - sdhci_runtime_suspend_host(host); + if (omap_host->con != -EINVAL) + sdhci_runtime_suspend_host(host); sdhci_omap_context_save(omap_host); @@ -1458,10 +1460,10 @@ static int __maybe_unused sdhci_omap_runtime_resume(struct device *dev) pinctrl_pm_select_default_state(dev); - if (omap_host->con != -EINVAL) + if (omap_host->con != -EINVAL) { sdhci_omap_context_restore(omap_host); - - sdhci_runtime_resume_host(host, 0); + sdhci_runtime_resume_host(host, 0); + } return 0; } diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c index 889e40329956..93da23682d86 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c @@ -850,9 +850,10 @@ static int gpmi_nfc_compute_timings(struct gpmi_nand_data *this, unsigned int tRP_ps; bool use_half_period; int sample_delay_ps, sample_delay_factor; - u16 busy_timeout_cycles; + unsigned int busy_timeout_cycles; u8 wrn_dly_sel; unsigned long clk_rate, min_rate; + u64 busy_timeout_ps; if (sdr->tRC_min >= 30000) { /* ONFI non-EDO modes [0-3] */ @@ -885,7 +886,8 @@ static int gpmi_nfc_compute_timings(struct gpmi_nand_data *this, addr_setup_cycles = TO_CYCLES(sdr->tALS_min, period_ps); data_setup_cycles = TO_CYCLES(sdr->tDS_min, period_ps); data_hold_cycles = TO_CYCLES(sdr->tDH_min, period_ps); - busy_timeout_cycles = TO_CYCLES(sdr->tWB_max + sdr->tR_max, period_ps); + busy_timeout_ps = max(sdr->tBERS_max, sdr->tPROG_max); + busy_timeout_cycles = TO_CYCLES(busy_timeout_ps, period_ps); hw->timing0 = BF_GPMI_TIMING0_ADDRESS_SETUP(addr_setup_cycles) | BF_GPMI_TIMING0_DATA_HOLD(data_hold_cycles) | diff --git a/drivers/net/amt.c b/drivers/net/amt.c index be2719a3ba70..e019526e1df6 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -563,7 +563,7 @@ static struct sk_buff *amt_build_igmp_gq(struct amt_dev *amt) ihv3->nsrcs = 0; ihv3->resv = 0; ihv3->suppress = false; - ihv3->qrv = amt->net->ipv4.sysctl_igmp_qrv; + ihv3->qrv = READ_ONCE(amt->net->ipv4.sysctl_igmp_qrv); ihv3->csum = 0; csum = &ihv3->csum; csum_start = (void *)ihv3; @@ -577,14 +577,14 @@ static struct sk_buff *amt_build_igmp_gq(struct amt_dev *amt) return skb; } -static void __amt_update_gw_status(struct amt_dev *amt, enum amt_status status, - bool validate) +static void amt_update_gw_status(struct amt_dev *amt, enum amt_status status, + bool validate) { if (validate && amt->status >= status) return; netdev_dbg(amt->dev, "Update GW status %s -> %s", status_str[amt->status], status_str[status]); - amt->status = status; + WRITE_ONCE(amt->status, status); } static void __amt_update_relay_status(struct amt_tunnel_list *tunnel, @@ -600,14 +600,6 @@ static void __amt_update_relay_status(struct amt_tunnel_list *tunnel, tunnel->status = status; } -static void amt_update_gw_status(struct amt_dev *amt, enum amt_status status, - bool validate) -{ - spin_lock_bh(&amt->lock); - __amt_update_gw_status(amt, status, validate); - spin_unlock_bh(&amt->lock); -} - static void amt_update_relay_status(struct amt_tunnel_list *tunnel, enum amt_status status, bool validate) { @@ -700,9 +692,7 @@ static void amt_send_discovery(struct amt_dev *amt) if (unlikely(net_xmit_eval(err))) amt->dev->stats.tx_errors++; - spin_lock_bh(&amt->lock); - __amt_update_gw_status(amt, AMT_STATUS_SENT_DISCOVERY, true); - spin_unlock_bh(&amt->lock); + amt_update_gw_status(amt, AMT_STATUS_SENT_DISCOVERY, true); out: rcu_read_unlock(); } @@ -900,6 +890,28 @@ static void amt_send_mld_gq(struct amt_dev *amt, struct amt_tunnel_list *tunnel) } #endif +static bool amt_queue_event(struct amt_dev *amt, enum amt_event event, + struct sk_buff *skb) +{ + int index; + + spin_lock_bh(&amt->lock); + if (amt->nr_events >= AMT_MAX_EVENTS) { + spin_unlock_bh(&amt->lock); + return 1; + } + + index = (amt->event_idx + amt->nr_events) % AMT_MAX_EVENTS; + amt->events[index].event = event; + amt->events[index].skb = skb; + amt->nr_events++; + amt->event_idx %= AMT_MAX_EVENTS; + queue_work(amt_wq, &amt->event_wq); + spin_unlock_bh(&amt->lock); + + return 0; +} + static void amt_secret_work(struct work_struct *work) { struct amt_dev *amt = container_of(to_delayed_work(work), @@ -913,58 +925,72 @@ static void amt_secret_work(struct work_struct *work) msecs_to_jiffies(AMT_SECRET_TIMEOUT)); } -static void amt_discovery_work(struct work_struct *work) +static void amt_event_send_discovery(struct amt_dev *amt) { - struct amt_dev *amt = container_of(to_delayed_work(work), - struct amt_dev, - discovery_wq); - - spin_lock_bh(&amt->lock); if (amt->status > AMT_STATUS_SENT_DISCOVERY) goto out; get_random_bytes(&amt->nonce, sizeof(__be32)); - spin_unlock_bh(&amt->lock); amt_send_discovery(amt); - spin_lock_bh(&amt->lock); out: mod_delayed_work(amt_wq, &amt->discovery_wq, msecs_to_jiffies(AMT_DISCOVERY_TIMEOUT)); - spin_unlock_bh(&amt->lock); } -static void amt_req_work(struct work_struct *work) +static void amt_discovery_work(struct work_struct *work) { struct amt_dev *amt = container_of(to_delayed_work(work), struct amt_dev, - req_wq); + discovery_wq); + + if (amt_queue_event(amt, AMT_EVENT_SEND_DISCOVERY, NULL)) + mod_delayed_work(amt_wq, &amt->discovery_wq, + msecs_to_jiffies(AMT_DISCOVERY_TIMEOUT)); +} + +static void amt_event_send_request(struct amt_dev *amt) +{ u32 exp; - spin_lock_bh(&amt->lock); if (amt->status < AMT_STATUS_RECEIVED_ADVERTISEMENT) goto out; if (amt->req_cnt > AMT_MAX_REQ_COUNT) { netdev_dbg(amt->dev, "Gateway is not ready"); amt->qi = AMT_INIT_REQ_TIMEOUT; - amt->ready4 = false; - amt->ready6 = false; + WRITE_ONCE(amt->ready4, false); + WRITE_ONCE(amt->ready6, false); amt->remote_ip = 0; - __amt_update_gw_status(amt, AMT_STATUS_INIT, false); + amt_update_gw_status(amt, AMT_STATUS_INIT, false); amt->req_cnt = 0; + amt->nonce = 0; goto out; } - spin_unlock_bh(&amt->lock); + + if (!amt->req_cnt) { + WRITE_ONCE(amt->ready4, false); + WRITE_ONCE(amt->ready6, false); + get_random_bytes(&amt->nonce, sizeof(__be32)); + } amt_send_request(amt, false); amt_send_request(amt, true); - spin_lock_bh(&amt->lock); - __amt_update_gw_status(amt, AMT_STATUS_SENT_REQUEST, true); + amt_update_gw_status(amt, AMT_STATUS_SENT_REQUEST, true); amt->req_cnt++; out: exp = min_t(u32, (1 * (1 << amt->req_cnt)), AMT_MAX_REQ_TIMEOUT); mod_delayed_work(amt_wq, &amt->req_wq, msecs_to_jiffies(exp * 1000)); - spin_unlock_bh(&amt->lock); +} + +static void amt_req_work(struct work_struct *work) +{ + struct amt_dev *amt = container_of(to_delayed_work(work), + struct amt_dev, + req_wq); + + if (amt_queue_event(amt, AMT_EVENT_SEND_REQUEST, NULL)) + mod_delayed_work(amt_wq, &amt->req_wq, + msecs_to_jiffies(100)); } static bool amt_send_membership_update(struct amt_dev *amt, @@ -1220,7 +1246,8 @@ static netdev_tx_t amt_dev_xmit(struct sk_buff *skb, struct net_device *dev) /* Gateway only passes IGMP/MLD packets */ if (!report) goto free; - if ((!v6 && !amt->ready4) || (v6 && !amt->ready6)) + if ((!v6 && !READ_ONCE(amt->ready4)) || + (v6 && !READ_ONCE(amt->ready6))) goto free; if (amt_send_membership_update(amt, skb, v6)) goto free; @@ -2236,6 +2263,10 @@ static bool amt_advertisement_handler(struct amt_dev *amt, struct sk_buff *skb) ipv4_is_zeronet(amta->ip4)) return true; + if (amt->status != AMT_STATUS_SENT_DISCOVERY || + amt->nonce != amta->nonce) + return true; + amt->remote_ip = amta->ip4; netdev_dbg(amt->dev, "advertised remote ip = %pI4\n", &amt->remote_ip); mod_delayed_work(amt_wq, &amt->req_wq, 0); @@ -2251,6 +2282,9 @@ static bool amt_multicast_data_handler(struct amt_dev *amt, struct sk_buff *skb) struct ethhdr *eth; struct iphdr *iph; + if (READ_ONCE(amt->status) != AMT_STATUS_SENT_UPDATE) + return true; + hdr_size = sizeof(*amtmd) + sizeof(struct udphdr); if (!pskb_may_pull(skb, hdr_size)) return true; @@ -2325,6 +2359,9 @@ static bool amt_membership_query_handler(struct amt_dev *amt, if (amtmq->reserved || amtmq->version) return true; + if (amtmq->nonce != amt->nonce) + return true; + hdr_size -= sizeof(*eth); if (iptunnel_pull_header(skb, hdr_size, htons(ETH_P_TEB), false)) return true; @@ -2339,6 +2376,9 @@ static bool amt_membership_query_handler(struct amt_dev *amt, iph = ip_hdr(skb); if (iph->version == 4) { + if (READ_ONCE(amt->ready4)) + return true; + if (!pskb_may_pull(skb, sizeof(*iph) + AMT_IPHDR_OPTS + sizeof(*ihv3))) return true; @@ -2349,12 +2389,10 @@ static bool amt_membership_query_handler(struct amt_dev *amt, ihv3 = skb_pull(skb, sizeof(*iph) + AMT_IPHDR_OPTS); skb_reset_transport_header(skb); skb_push(skb, sizeof(*iph) + AMT_IPHDR_OPTS); - spin_lock_bh(&amt->lock); - amt->ready4 = true; + WRITE_ONCE(amt->ready4, true); amt->mac = amtmq->response_mac; amt->req_cnt = 0; amt->qi = ihv3->qqic; - spin_unlock_bh(&amt->lock); skb->protocol = htons(ETH_P_IP); eth->h_proto = htons(ETH_P_IP); ip_eth_mc_map(iph->daddr, eth->h_dest); @@ -2363,6 +2401,9 @@ static bool amt_membership_query_handler(struct amt_dev *amt, struct mld2_query *mld2q; struct ipv6hdr *ip6h; + if (READ_ONCE(amt->ready6)) + return true; + if (!pskb_may_pull(skb, sizeof(*ip6h) + AMT_IP6HDR_OPTS + sizeof(*mld2q))) return true; @@ -2374,12 +2415,10 @@ static bool amt_membership_query_handler(struct amt_dev *amt, mld2q = skb_pull(skb, sizeof(*ip6h) + AMT_IP6HDR_OPTS); skb_reset_transport_header(skb); skb_push(skb, sizeof(*ip6h) + AMT_IP6HDR_OPTS); - spin_lock_bh(&amt->lock); - amt->ready6 = true; + WRITE_ONCE(amt->ready6, true); amt->mac = amtmq->response_mac; amt->req_cnt = 0; amt->qi = mld2q->mld2q_qqic; - spin_unlock_bh(&amt->lock); skb->protocol = htons(ETH_P_IPV6); eth->h_proto = htons(ETH_P_IPV6); ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); @@ -2392,12 +2431,14 @@ static bool amt_membership_query_handler(struct amt_dev *amt, skb->pkt_type = PACKET_MULTICAST; skb->ip_summed = CHECKSUM_NONE; len = skb->len; + local_bh_disable(); if (__netif_rx(skb) == NET_RX_SUCCESS) { amt_update_gw_status(amt, AMT_STATUS_RECEIVED_QUERY, true); dev_sw_netstats_rx_add(amt->dev, len); } else { amt->dev->stats.rx_dropped++; } + local_bh_enable(); return false; } @@ -2638,7 +2679,9 @@ static bool amt_request_handler(struct amt_dev *amt, struct sk_buff *skb) if (tunnel->ip4 == iph->saddr) goto send; + spin_lock_bh(&amt->lock); if (amt->nr_tunnels >= amt->max_tunnels) { + spin_unlock_bh(&amt->lock); icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); return true; } @@ -2646,8 +2689,10 @@ static bool amt_request_handler(struct amt_dev *amt, struct sk_buff *skb) tunnel = kzalloc(sizeof(*tunnel) + (sizeof(struct hlist_head) * amt->hash_buckets), GFP_ATOMIC); - if (!tunnel) + if (!tunnel) { + spin_unlock_bh(&amt->lock); return true; + } tunnel->source_port = udph->source; tunnel->ip4 = iph->saddr; @@ -2660,10 +2705,9 @@ static bool amt_request_handler(struct amt_dev *amt, struct sk_buff *skb) INIT_DELAYED_WORK(&tunnel->gc_wq, amt_tunnel_expire); - spin_lock_bh(&amt->lock); list_add_tail_rcu(&tunnel->list, &amt->tunnel_list); tunnel->key = amt->key; - amt_update_relay_status(tunnel, AMT_STATUS_RECEIVED_REQUEST, true); + __amt_update_relay_status(tunnel, AMT_STATUS_RECEIVED_REQUEST, true); amt->nr_tunnels++; mod_delayed_work(amt_wq, &tunnel->gc_wq, msecs_to_jiffies(amt_gmi(amt))); @@ -2688,6 +2732,38 @@ send: return false; } +static void amt_gw_rcv(struct amt_dev *amt, struct sk_buff *skb) +{ + int type = amt_parse_type(skb); + int err = 1; + + if (type == -1) + goto drop; + + if (amt->mode == AMT_MODE_GATEWAY) { + switch (type) { + case AMT_MSG_ADVERTISEMENT: + err = amt_advertisement_handler(amt, skb); + break; + case AMT_MSG_MEMBERSHIP_QUERY: + err = amt_membership_query_handler(amt, skb); + if (!err) + return; + break; + default: + netdev_dbg(amt->dev, "Invalid type of Gateway\n"); + break; + } + } +drop: + if (err) { + amt->dev->stats.rx_dropped++; + kfree_skb(skb); + } else { + consume_skb(skb); + } +} + static int amt_rcv(struct sock *sk, struct sk_buff *skb) { struct amt_dev *amt; @@ -2719,8 +2795,12 @@ static int amt_rcv(struct sock *sk, struct sk_buff *skb) err = true; goto drop; } - err = amt_advertisement_handler(amt, skb); - break; + if (amt_queue_event(amt, AMT_EVENT_RECEIVE, skb)) { + netdev_dbg(amt->dev, "AMT Event queue full\n"); + err = true; + goto drop; + } + goto out; case AMT_MSG_MULTICAST_DATA: if (iph->saddr != amt->remote_ip) { netdev_dbg(amt->dev, "Invalid Relay IP\n"); @@ -2738,11 +2818,12 @@ static int amt_rcv(struct sock *sk, struct sk_buff *skb) err = true; goto drop; } - err = amt_membership_query_handler(amt, skb); - if (err) + if (amt_queue_event(amt, AMT_EVENT_RECEIVE, skb)) { + netdev_dbg(amt->dev, "AMT Event queue full\n"); + err = true; goto drop; - else - goto out; + } + goto out; default: err = true; netdev_dbg(amt->dev, "Invalid type of Gateway\n"); @@ -2780,6 +2861,46 @@ out: return 0; } +static void amt_event_work(struct work_struct *work) +{ + struct amt_dev *amt = container_of(work, struct amt_dev, event_wq); + struct sk_buff *skb; + u8 event; + int i; + + for (i = 0; i < AMT_MAX_EVENTS; i++) { + spin_lock_bh(&amt->lock); + if (amt->nr_events == 0) { + spin_unlock_bh(&amt->lock); + return; + } + event = amt->events[amt->event_idx].event; + skb = amt->events[amt->event_idx].skb; + amt->events[amt->event_idx].event = AMT_EVENT_NONE; + amt->events[amt->event_idx].skb = NULL; + amt->nr_events--; + amt->event_idx++; + amt->event_idx %= AMT_MAX_EVENTS; + spin_unlock_bh(&amt->lock); + + switch (event) { + case AMT_EVENT_RECEIVE: + amt_gw_rcv(amt, skb); + break; + case AMT_EVENT_SEND_DISCOVERY: + amt_event_send_discovery(amt); + break; + case AMT_EVENT_SEND_REQUEST: + amt_event_send_request(amt); + break; + default: + if (skb) + kfree_skb(skb); + break; + } + } +} + static int amt_err_lookup(struct sock *sk, struct sk_buff *skb) { struct amt_dev *amt; @@ -2804,7 +2925,7 @@ static int amt_err_lookup(struct sock *sk, struct sk_buff *skb) break; case AMT_MSG_REQUEST: case AMT_MSG_MEMBERSHIP_UPDATE: - if (amt->status >= AMT_STATUS_RECEIVED_ADVERTISEMENT) + if (READ_ONCE(amt->status) >= AMT_STATUS_RECEIVED_ADVERTISEMENT) mod_delayed_work(amt_wq, &amt->req_wq, 0); break; default: @@ -2867,6 +2988,8 @@ static int amt_dev_open(struct net_device *dev) amt->ready4 = false; amt->ready6 = false; + amt->event_idx = 0; + amt->nr_events = 0; err = amt_socket_create(amt); if (err) @@ -2874,6 +2997,7 @@ static int amt_dev_open(struct net_device *dev) amt->req_cnt = 0; amt->remote_ip = 0; + amt->nonce = 0; get_random_bytes(&amt->key, sizeof(siphash_key_t)); amt->status = AMT_STATUS_INIT; @@ -2892,6 +3016,8 @@ static int amt_dev_stop(struct net_device *dev) struct amt_dev *amt = netdev_priv(dev); struct amt_tunnel_list *tunnel, *tmp; struct socket *sock; + struct sk_buff *skb; + int i; cancel_delayed_work_sync(&amt->req_wq); cancel_delayed_work_sync(&amt->discovery_wq); @@ -2904,6 +3030,15 @@ static int amt_dev_stop(struct net_device *dev) if (sock) udp_tunnel_sock_release(sock); + cancel_work_sync(&amt->event_wq); + for (i = 0; i < AMT_MAX_EVENTS; i++) { + skb = amt->events[i].skb; + if (skb) + kfree_skb(skb); + amt->events[i].event = AMT_EVENT_NONE; + amt->events[i].skb = NULL; + } + amt->ready4 = false; amt->ready6 = false; amt->req_cnt = 0; @@ -3095,7 +3230,7 @@ static int amt_newlink(struct net *net, struct net_device *dev, goto err; } if (amt->mode == AMT_MODE_RELAY) { - amt->qrv = amt->net->ipv4.sysctl_igmp_qrv; + amt->qrv = READ_ONCE(amt->net->ipv4.sysctl_igmp_qrv); amt->qri = 10; dev->needed_headroom = amt->stream_dev->needed_headroom + AMT_RELAY_HLEN; @@ -3146,8 +3281,8 @@ static int amt_newlink(struct net *net, struct net_device *dev, INIT_DELAYED_WORK(&amt->discovery_wq, amt_discovery_work); INIT_DELAYED_WORK(&amt->req_wq, amt_req_work); INIT_DELAYED_WORK(&amt->secret_wq, amt_secret_work); + INIT_WORK(&amt->event_wq, amt_event_work); INIT_LIST_HEAD(&amt->tunnel_list); - return 0; err: dev_put(amt->stream_dev); @@ -3280,7 +3415,7 @@ static int __init amt_init(void) if (err < 0) goto unregister_notifier; - amt_wq = alloc_workqueue("amt", WQ_UNBOUND, 1); + amt_wq = alloc_workqueue("amt", WQ_UNBOUND, 0); if (!amt_wq) { err = -ENOMEM; goto rtnl_unregister; diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index ba42cef10a53..cb0321ea853c 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -1843,6 +1843,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) of_child = of_get_child_by_name(pdev->dev.of_node, name); if (of_child && of_device_is_available(of_child)) channels_mask |= BIT(i); + of_node_put(of_child); } if (chip_id != RENESAS_RZG2L) { diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 9b47b07162fe..bc6518504fd4 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -1690,8 +1690,8 @@ static int mcp251xfd_register_chip_detect(struct mcp251xfd_priv *priv) u32 osc; int err; - /* The OSC_LPMEN is only supported on MCP2518FD, so use it to - * autodetect the model. + /* The OSC_LPMEN is only supported on MCP2518FD and MCP251863, + * so use it to autodetect the model. */ err = regmap_update_bits(priv->map_reg, MCP251XFD_REG_OSC, MCP251XFD_REG_OSC_LPMEN, @@ -1703,10 +1703,18 @@ static int mcp251xfd_register_chip_detect(struct mcp251xfd_priv *priv) if (err) return err; - if (osc & MCP251XFD_REG_OSC_LPMEN) - devtype_data = &mcp251xfd_devtype_data_mcp2518fd; - else + if (osc & MCP251XFD_REG_OSC_LPMEN) { + /* We cannot distinguish between MCP2518FD and + * MCP251863. If firmware specifies MCP251863, keep + * it, otherwise set to MCP2518FD. + */ + if (mcp251xfd_is_251863(priv)) + devtype_data = &mcp251xfd_devtype_data_mcp251863; + else + devtype_data = &mcp251xfd_devtype_data_mcp2518fd; + } else { devtype_data = &mcp251xfd_devtype_data_mcp2517fd; + } if (!mcp251xfd_is_251XFD(priv) && priv->devtype_data.model != devtype_data->model) { diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 9ca8c8d7740f..92a500e1ccd2 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1038,18 +1038,21 @@ int ksz_switch_register(struct ksz_device *dev, ports = of_get_child_by_name(dev->dev->of_node, "ethernet-ports"); if (!ports) ports = of_get_child_by_name(dev->dev->of_node, "ports"); - if (ports) + if (ports) { for_each_available_child_of_node(ports, port) { if (of_property_read_u32(port, "reg", &port_num)) continue; if (!(dev->port_mask & BIT(port_num))) { of_node_put(port); + of_node_put(ports); return -EINVAL; } of_get_phy_mode(port, &dev->ports[port_num].interface); } + of_node_put(ports); + } dev->synclko_125 = of_property_read_bool(dev->dev->of_node, "microchip,synclko-125"); dev->synclko_disable = of_property_read_bool(dev->dev->of_node, diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 72b6fc1932b5..698c7d1fb45c 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -3382,12 +3382,28 @@ static const struct of_device_id sja1105_dt_ids[] = { }; MODULE_DEVICE_TABLE(of, sja1105_dt_ids); +static const struct spi_device_id sja1105_spi_ids[] = { + { "sja1105e" }, + { "sja1105t" }, + { "sja1105p" }, + { "sja1105q" }, + { "sja1105r" }, + { "sja1105s" }, + { "sja1110a" }, + { "sja1110b" }, + { "sja1110c" }, + { "sja1110d" }, + { }, +}; +MODULE_DEVICE_TABLE(spi, sja1105_spi_ids); + static struct spi_driver sja1105_driver = { .driver = { .name = "sja1105", .owner = THIS_MODULE, .of_match_table = of_match_ptr(sja1105_dt_ids), }, + .id_table = sja1105_spi_ids, .probe = sja1105_probe, .remove = sja1105_remove, .shutdown = sja1105_shutdown, diff --git a/drivers/net/dsa/vitesse-vsc73xx-spi.c b/drivers/net/dsa/vitesse-vsc73xx-spi.c index 3110895358d8..97a92e6da60d 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-spi.c +++ b/drivers/net/dsa/vitesse-vsc73xx-spi.c @@ -205,10 +205,20 @@ static const struct of_device_id vsc73xx_of_match[] = { }; MODULE_DEVICE_TABLE(of, vsc73xx_of_match); +static const struct spi_device_id vsc73xx_spi_ids[] = { + { "vsc7385" }, + { "vsc7388" }, + { "vsc7395" }, + { "vsc7398" }, + { }, +}; +MODULE_DEVICE_TABLE(spi, vsc73xx_spi_ids); + static struct spi_driver vsc73xx_spi_driver = { .probe = vsc73xx_spi_probe, .remove = vsc73xx_spi_remove, .shutdown = vsc73xx_spi_shutdown, + .id_table = vsc73xx_spi_ids, .driver = { .name = "vsc73xx-spi", .of_match_table = vsc73xx_of_match, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 831833911a52..8647125d60ae 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -379,7 +379,7 @@ static void aq_pci_shutdown(struct pci_dev *pdev) } } -static int aq_suspend_common(struct device *dev, bool deep) +static int aq_suspend_common(struct device *dev) { struct aq_nic_s *nic = pci_get_drvdata(to_pci_dev(dev)); @@ -392,17 +392,15 @@ static int aq_suspend_common(struct device *dev, bool deep) if (netif_running(nic->ndev)) aq_nic_stop(nic); - if (deep) { - aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol); - aq_nic_set_power(nic); - } + aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol); + aq_nic_set_power(nic); rtnl_unlock(); return 0; } -static int atl_resume_common(struct device *dev, bool deep) +static int atl_resume_common(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct aq_nic_s *nic; @@ -415,11 +413,6 @@ static int atl_resume_common(struct device *dev, bool deep) pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); - if (deep) { - /* Reinitialize Nic/Vecs objects */ - aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol); - } - if (netif_running(nic->ndev)) { ret = aq_nic_init(nic); if (ret) @@ -444,22 +437,22 @@ err_exit: static int aq_pm_freeze(struct device *dev) { - return aq_suspend_common(dev, true); + return aq_suspend_common(dev); } static int aq_pm_suspend_poweroff(struct device *dev) { - return aq_suspend_common(dev, true); + return aq_suspend_common(dev); } static int aq_pm_thaw(struct device *dev) { - return atl_resume_common(dev, true); + return atl_resume_common(dev); } static int aq_pm_resume_restore(struct device *dev) { - return atl_resume_common(dev, true); + return atl_resume_common(dev); } static const struct dev_pm_ops aq_pm_ops = { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 56b46b8206a7..cf9b00576ed3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7790,7 +7790,7 @@ hwrm_dbg_qcaps_exit: static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp); -static int bnxt_hwrm_func_qcaps(struct bnxt *bp) +int bnxt_hwrm_func_qcaps(struct bnxt *bp) { int rc; @@ -10065,7 +10065,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up) if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE) resc_reinit = true; - if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE) + if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE || + test_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) fw_reset = true; else bnxt_remap_fw_health_regs(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index a1dca8c58f54..075c6206325c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2314,6 +2314,7 @@ int bnxt_cancel_reservations(struct bnxt *bp, bool fw_reset); int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp); int bnxt_hwrm_free_wol_fltr(struct bnxt *bp); int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all); +int bnxt_hwrm_func_qcaps(struct bnxt *bp); int bnxt_hwrm_fw_set_time(struct bnxt *); int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_half_open_nic(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 3528ce9849e6..6b3d4f4c2a75 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -979,9 +979,11 @@ static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req, if (rc) return rc; - rc = bnxt_dl_livepatch_info_put(bp, req, BNXT_FW_SRT_PATCH); - if (rc) - return rc; + if (BNXT_CHIP_P5(bp)) { + rc = bnxt_dl_livepatch_info_put(bp, req, BNXT_FW_SRT_PATCH); + if (rc) + return rc; + } return bnxt_dl_livepatch_info_put(bp, req, BNXT_FW_CRT_PATCH); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 562f8f68a47d..7f3c0875b6f5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -76,14 +76,23 @@ static int bnxt_refclk_read(struct bnxt *bp, struct ptp_system_timestamp *sts, u64 *ns) { struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + u32 high_before, high_now, low; if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) return -EIO; + high_before = readl(bp->bar0 + ptp->refclk_mapped_regs[1]); ptp_read_system_prets(sts); - *ns = readl(bp->bar0 + ptp->refclk_mapped_regs[0]); + low = readl(bp->bar0 + ptp->refclk_mapped_regs[0]); ptp_read_system_postts(sts); - *ns |= (u64)readl(bp->bar0 + ptp->refclk_mapped_regs[1]) << 32; + high_now = readl(bp->bar0 + ptp->refclk_mapped_regs[1]); + if (high_now != high_before) { + ptp_read_system_prets(sts); + low = readl(bp->bar0 + ptp->refclk_mapped_regs[0]); + ptp_read_system_postts(sts); + } + *ns = ((u64)high_now << 32) | low; + return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index ddf2f3963abe..a1a2c7a64fd5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -823,8 +823,10 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs) goto err_out2; rc = pci_enable_sriov(bp->pdev, *num_vfs); - if (rc) + if (rc) { + bnxt_ulp_sriov_cfg(bp, 0); goto err_out2; + } return 0; @@ -832,6 +834,9 @@ err_out2: /* Free the resources reserved for various VF's */ bnxt_hwrm_func_vf_resource_free(bp, *num_vfs); + /* Restore the max resources */ + bnxt_hwrm_func_qcaps(bp); + err_out1: bnxt_free_vf_resources(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index f02fe906dedb..f53387ed0167 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -28,7 +28,7 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct xdp_buff *xdp) { struct skb_shared_info *sinfo; - struct bnxt_sw_tx_bd *tx_buf, *first_buf; + struct bnxt_sw_tx_bd *tx_buf; struct tx_bd *txbd; int num_frags = 0; u32 flags; @@ -43,13 +43,14 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, /* fill up the first buffer */ prod = txr->tx_prod; tx_buf = &txr->tx_buf_ring[prod]; - first_buf = tx_buf; tx_buf->nr_frags = num_frags; if (xdp) tx_buf->page = virt_to_head_page(xdp->data); txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)]; - flags = ((len) << TX_BD_LEN_SHIFT) | ((num_frags + 1) << TX_BD_FLAGS_BD_CNT_SHIFT); + flags = (len << TX_BD_LEN_SHIFT) | + ((num_frags + 1) << TX_BD_FLAGS_BD_CNT_SHIFT) | + bnxt_lhint_arr[len >> 9]; txbd->tx_bd_len_flags_type = cpu_to_le32(flags); txbd->tx_bd_opaque = prod; txbd->tx_bd_haddr = cpu_to_le64(mapping); @@ -82,7 +83,6 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, flags = frag_len << TX_BD_LEN_SHIFT; txbd->tx_bd_len_flags_type = cpu_to_le32(flags); - txbd->tx_bd_opaque = prod; txbd->tx_bd_haddr = cpu_to_le64(frag_mapping); len = frag_len; @@ -96,7 +96,7 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, prod = NEXT_TX(prod); txr->tx_prod = prod; - return first_buf; + return tx_buf; } static void __bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr, diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 4af5561cbfc5..ddfe9208529a 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1236,8 +1236,8 @@ static struct sock *chtls_recv_sock(struct sock *lsk, csk->sndbuf = newsk->sk_sndbuf; csk->smac_idx = ((struct port_info *)netdev_priv(ndev))->smt_idx; RCV_WSCALE(tp) = select_rcv_wscale(tcp_full_space(newsk), - sock_net(newsk)-> - ipv4.sysctl_tcp_window_scaling, + READ_ONCE(sock_net(newsk)-> + ipv4.sysctl_tcp_window_scaling), tp->window_clamp); neigh_release(n); inet_inherit_port(&tcp_hashinfo, lsk, newsk); @@ -1384,7 +1384,7 @@ static void chtls_pass_accept_request(struct sock *sk, #endif } if (req->tcpopt.wsf <= 14 && - sock_net(sk)->ipv4.sysctl_tcp_window_scaling) { + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) { inet_rsk(oreq)->wscale_ok = 1; inet_rsk(oreq)->snd_wscale = req->tcpopt.wsf; } @@ -1392,7 +1392,7 @@ static void chtls_pass_accept_request(struct sock *sk, th_ecn = tcph->ece && tcph->cwr; if (th_ecn) { ect = !INET_ECN_is_not_ect(ip_dsfield); - ecn_ok = sock_net(sk)->ipv4.sysctl_tcp_ecn; + ecn_ok = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn); if ((!ect && ecn_ok) || tcp_ca_needs_ecn(sk)) inet_rsk(oreq)->ecn_ok = 1; } diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 528eb0f223b1..b4f5e57d0285 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -2287,7 +2287,7 @@ err: /* Uses sync mcc */ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter, - u8 page_num, u8 *data) + u8 page_num, u32 off, u32 len, u8 *data) { struct be_dma_mem cmd; struct be_mcc_wrb *wrb; @@ -2321,10 +2321,10 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter, req->port = cpu_to_le32(adapter->hba_port_num); req->page_num = cpu_to_le32(page_num); status = be_mcc_notify_wait(adapter); - if (!status) { + if (!status && len > 0) { struct be_cmd_resp_port_type *resp = cmd.va; - memcpy(data, resp->page_data, PAGE_DATA_LEN); + memcpy(data, resp->page_data + off, len); } err: mutex_unlock(&adapter->mcc_lock); @@ -2415,7 +2415,7 @@ int be_cmd_query_cable_type(struct be_adapter *adapter) int status; status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0, - page_data); + 0, PAGE_DATA_LEN, page_data); if (!status) { switch (adapter->phy.interface_type) { case PHY_TYPE_QSFP: @@ -2440,7 +2440,7 @@ int be_cmd_query_sfp_info(struct be_adapter *adapter) int status; status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0, - page_data); + 0, PAGE_DATA_LEN, page_data); if (!status) { strlcpy(adapter->phy.vendor_name, page_data + SFP_VENDOR_NAME_OFFSET, SFP_VENDOR_NAME_LEN - 1); diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index db1f3b908582..e2085c68c0ee 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -2427,7 +2427,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num, u8 beacon, int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state); int be_cmd_read_port_transceiver_data(struct be_adapter *adapter, - u8 page_num, u8 *data); + u8 page_num, u32 off, u32 len, u8 *data); int be_cmd_query_cable_type(struct be_adapter *adapter); int be_cmd_query_sfp_info(struct be_adapter *adapter); int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd, diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index dfa784339781..bd0df189d871 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -1344,7 +1344,7 @@ static int be_get_module_info(struct net_device *netdev, return -EOPNOTSUPP; status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0, - page_data); + 0, PAGE_DATA_LEN, page_data); if (!status) { if (!page_data[SFP_PLUS_SFF_8472_COMP]) { modinfo->type = ETH_MODULE_SFF_8079; @@ -1362,25 +1362,32 @@ static int be_get_module_eeprom(struct net_device *netdev, { struct be_adapter *adapter = netdev_priv(netdev); int status; + u32 begin, end; if (!check_privilege(adapter, MAX_PRIVILEGES)) return -EOPNOTSUPP; - status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0, - data); - if (status) - goto err; + begin = eeprom->offset; + end = eeprom->offset + eeprom->len; + + if (begin < PAGE_DATA_LEN) { + status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0, begin, + min_t(u32, end, PAGE_DATA_LEN) - begin, + data); + if (status) + goto err; + + data += PAGE_DATA_LEN - begin; + begin = PAGE_DATA_LEN; + } - if (eeprom->offset + eeprom->len > PAGE_DATA_LEN) { - status = be_cmd_read_port_transceiver_data(adapter, - TR_PAGE_A2, - data + - PAGE_DATA_LEN); + if (end > PAGE_DATA_LEN) { + status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A2, + begin - PAGE_DATA_LEN, + end - begin, data); if (status) goto err; } - if (eeprom->offset) - memcpy(data, data + eeprom->offset, eeprom->len); err: return be_cmd_status(status); } diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 5231818943c6..c03663785a8d 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1764,6 +1764,19 @@ cleanup_clk: return rc; } +static bool ftgmac100_has_child_node(struct device_node *np, const char *name) +{ + struct device_node *child_np = of_get_child_by_name(np, name); + bool ret = false; + + if (child_np) { + ret = true; + of_node_put(child_np); + } + + return ret; +} + static int ftgmac100_probe(struct platform_device *pdev) { struct resource *res; @@ -1883,7 +1896,7 @@ static int ftgmac100_probe(struct platform_device *pdev) /* Display what we found */ phy_attached_info(phy); - } else if (np && !of_get_child_by_name(np, "mdio")) { + } else if (np && !ftgmac100_has_child_node(np, "mdio")) { /* Support legacy ASPEED devicetree descriptions that decribe a * MAC with an embedded MDIO controller but have no "mdio" * child node. Automatically scan the MDIO bus for available diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 13382df2f2ef..bcf680e83811 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -630,7 +630,6 @@ struct e1000_phy_info { bool disable_polarity_correction; bool is_mdix; bool polarity_correction; - bool reset_disable; bool speed_downgraded; bool autoneg_wait_to_complete; }; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index e6c8e6d5234f..9466f65a6da7 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -2050,10 +2050,6 @@ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw) bool blocked = false; int i = 0; - /* Check the PHY (LCD) reset flag */ - if (hw->phy.reset_disable) - return true; - while ((blocked = !(er32(FWSM) & E1000_ICH_FWSM_RSPCIPHY)) && (i++ < 30)) usleep_range(10000, 11000); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index 638a3ddd7ada..2504b11c3169 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -271,7 +271,6 @@ #define I217_CGFREG_ENABLE_MTA_RESET 0x0002 #define I217_MEMPWR PHY_REG(772, 26) #define I217_MEMPWR_DISABLE_SMB_RELEASE 0x0010 -#define I217_MEMPWR_MOEM 0x1000 /* Receive Address Initial CRC Calculation */ #define E1000_PCH_RAICC(_n) (0x05F50 + ((_n) * 4)) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index fa06f68c8c80..f1729940e46c 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6494,6 +6494,10 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && hw->mac.type >= e1000_pch_adp) { + /* Keep the GPT clock enabled for CSME */ + mac_data = er32(FEXTNVM); + mac_data |= BIT(3); + ew32(FEXTNVM, mac_data); /* Request ME unconfigure the device from S0ix */ mac_data = er32(H2ME); mac_data &= ~E1000_H2ME_START_DPG; @@ -6987,21 +6991,8 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev) struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); - struct e1000_hw *hw = &adapter->hw; - u16 phy_data; int rc; - if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && - hw->mac.type >= e1000_pch_adp) { - /* Mask OEM Bits / Gig Disable / Restart AN (772_26[12] = 1) */ - e1e_rphy(hw, I217_MEMPWR, &phy_data); - phy_data |= I217_MEMPWR_MOEM; - e1e_wphy(hw, I217_MEMPWR, phy_data); - - /* Disable LCD reset */ - hw->phy.reset_disable = true; - } - e1000e_flush_lpic(pdev); e1000e_pm_freeze(dev); @@ -7023,8 +7014,6 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev) struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); - struct e1000_hw *hw = &adapter->hw; - u16 phy_data; int rc; /* Introduce S0ix implementation */ @@ -7035,17 +7024,6 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev) if (rc) return rc; - if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && - hw->mac.type >= e1000_pch_adp) { - /* Unmask OEM Bits / Gig Disable / Restart AN 772_26[12] = 0 */ - e1e_rphy(hw, I217_MEMPWR, &phy_data); - phy_data &= ~I217_MEMPWR_MOEM; - e1e_wphy(hw, I217_MEMPWR, phy_data); - - /* Enable LCD reset */ - hw->phy.reset_disable = false; - } - return e1000e_pm_thaw(dev); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index aa786fd55951..7f1a0d90dc51 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -10650,7 +10650,7 @@ static int i40e_reset(struct i40e_pf *pf) **/ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) { - int old_recovery_mode_bit = test_bit(__I40E_RECOVERY_MODE, pf->state); + const bool is_recovery_mode_reported = i40e_check_recovery_mode(pf); struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_hw *hw = &pf->hw; i40e_status ret; @@ -10658,13 +10658,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) int v; if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) && - i40e_check_recovery_mode(pf)) { + is_recovery_mode_reported) i40e_set_ethtool_ops(pf->vsi[pf->lan_vsi]->netdev); - } if (test_bit(__I40E_DOWN, pf->state) && - !test_bit(__I40E_RECOVERY_MODE, pf->state) && - !old_recovery_mode_bit) + !test_bit(__I40E_RECOVERY_MODE, pf->state)) goto clear_recovery; dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n"); @@ -10691,13 +10689,12 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) * accordingly with regard to resources initialization * and deinitialization */ - if (test_bit(__I40E_RECOVERY_MODE, pf->state) || - old_recovery_mode_bit) { + if (test_bit(__I40E_RECOVERY_MODE, pf->state)) { if (i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities)) goto end_unlock; - if (test_bit(__I40E_RECOVERY_MODE, pf->state)) { + if (is_recovery_mode_reported) { /* we're staying in recovery mode so we'll reinitialize * misc vector here */ diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 49aed3e506a6..0ea0361cd86b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -64,7 +64,6 @@ struct iavf_vsi { u16 id; DECLARE_BITMAP(state, __IAVF_VSI_STATE_SIZE__); int base_vector; - u16 work_limit; u16 qs_handle; void *priv; /* client driver data reference. */ }; @@ -159,8 +158,12 @@ struct iavf_vlan { struct iavf_vlan_filter { struct list_head list; struct iavf_vlan vlan; - bool remove; /* filter needs to be removed */ - bool add; /* filter needs to be added */ + struct { + u8 is_new_vlan:1; /* filter is new, wait for PF answer */ + u8 remove:1; /* filter needs to be removed */ + u8 add:1; /* filter needs to be added */ + u8 padding:5; + }; }; #define IAVF_MAX_TRAFFIC_CLASS 4 @@ -461,6 +464,10 @@ static inline const char *iavf_state_str(enum iavf_state_t state) return "__IAVF_INIT_VERSION_CHECK"; case __IAVF_INIT_GET_RESOURCES: return "__IAVF_INIT_GET_RESOURCES"; + case __IAVF_INIT_EXTENDED_CAPS: + return "__IAVF_INIT_EXTENDED_CAPS"; + case __IAVF_INIT_CONFIG_ADAPTER: + return "__IAVF_INIT_CONFIG_ADAPTER"; case __IAVF_INIT_SW: return "__IAVF_INIT_SW"; case __IAVF_INIT_FAILED: @@ -520,6 +527,7 @@ int iavf_get_vf_config(struct iavf_adapter *adapter); int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter); int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter); void iavf_set_queue_vlan_tag_loc(struct iavf_adapter *adapter); +u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter); void iavf_irq_enable(struct iavf_adapter *adapter, bool flush); void iavf_configure_queues(struct iavf_adapter *adapter); void iavf_deconfigure_queues(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 3bb56714beb0..e535d4c3da49 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -692,12 +692,8 @@ static int __iavf_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, int queue) { struct iavf_adapter *adapter = netdev_priv(netdev); - struct iavf_vsi *vsi = &adapter->vsi; struct iavf_ring *rx_ring, *tx_ring; - ec->tx_max_coalesced_frames = vsi->work_limit; - ec->rx_max_coalesced_frames = vsi->work_limit; - /* Rx and Tx usecs per queue value. If user doesn't specify the * queue, return queue 0's value to represent. */ @@ -825,12 +821,8 @@ static int __iavf_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, int queue) { struct iavf_adapter *adapter = netdev_priv(netdev); - struct iavf_vsi *vsi = &adapter->vsi; int i; - if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq) - vsi->work_limit = ec->tx_max_coalesced_frames_irq; - if (ec->rx_coalesce_usecs == 0) { if (ec->use_adaptive_rx_coalesce) netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); @@ -1969,8 +1961,6 @@ static int iavf_set_rxfh(struct net_device *netdev, const u32 *indir, static const struct ethtool_ops iavf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | - ETHTOOL_COALESCE_MAX_FRAMES | - ETHTOOL_COALESCE_MAX_FRAMES_IRQ | ETHTOOL_COALESCE_USE_ADAPTIVE, .get_drvinfo = iavf_get_drvinfo, .get_link = ethtool_op_get_link, diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index f3ecb3bca33d..2e2c153ce46a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -843,7 +843,7 @@ static void iavf_restore_filters(struct iavf_adapter *adapter) * iavf_get_num_vlans_added - get number of VLANs added * @adapter: board private structure */ -static u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter) +u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter) { return bitmap_weight(adapter->vsi.active_cvlans, VLAN_N_VID) + bitmap_weight(adapter->vsi.active_svlans, VLAN_N_VID); @@ -906,11 +906,6 @@ static int iavf_vlan_rx_add_vid(struct net_device *netdev, if (!iavf_add_vlan(adapter, IAVF_VLAN(vid, be16_to_cpu(proto)))) return -ENOMEM; - if (proto == cpu_to_be16(ETH_P_8021Q)) - set_bit(vid, adapter->vsi.active_cvlans); - else - set_bit(vid, adapter->vsi.active_svlans); - return 0; } @@ -2245,7 +2240,6 @@ int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter) adapter->vsi.back = adapter; adapter->vsi.base_vector = 1; - adapter->vsi.work_limit = IAVF_DEFAULT_IRQ_WORK; vsi->netdev = adapter->netdev; vsi->qs_handle = adapter->vsi_res->qset_handle; if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) { @@ -2956,6 +2950,9 @@ continue_reset: adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; iavf_misc_irq_enable(adapter); + bitmap_clear(adapter->vsi.active_cvlans, 0, VLAN_N_VID); + bitmap_clear(adapter->vsi.active_svlans, 0, VLAN_N_VID); + mod_delayed_work(iavf_wq, &adapter->watchdog_task, 2); /* We were running when the reset started, so we need to restore some diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 978f651c6b09..06d18797d25a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -194,7 +194,7 @@ static bool iavf_clean_tx_irq(struct iavf_vsi *vsi, struct iavf_tx_buffer *tx_buf; struct iavf_tx_desc *tx_desc; unsigned int total_bytes = 0, total_packets = 0; - unsigned int budget = vsi->work_limit; + unsigned int budget = IAVF_DEFAULT_IRQ_WORK; tx_buf = &tx_ring->tx_bi[i]; tx_desc = IAVF_TX_DESC(tx_ring, i); @@ -1285,11 +1285,10 @@ static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring, { struct iavf_rx_buffer *rx_buffer; - if (!size) - return NULL; - rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; prefetchw(rx_buffer->page); + if (!size) + return rx_buffer; /* we are reusing so sync this buffer for CPU use */ dma_sync_single_range_for_cpu(rx_ring->dev, diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 782450d5c12f..1603e99bae4a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -627,6 +627,33 @@ static void iavf_mac_add_reject(struct iavf_adapter *adapter) } /** + * iavf_vlan_add_reject + * @adapter: adapter structure + * + * Remove VLAN filters from list based on PF response. + **/ +static void iavf_vlan_add_reject(struct iavf_adapter *adapter) +{ + struct iavf_vlan_filter *f, *ftmp; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { + if (f->is_new_vlan) { + if (f->vlan.tpid == ETH_P_8021Q) + clear_bit(f->vlan.vid, + adapter->vsi.active_cvlans); + else + clear_bit(f->vlan.vid, + adapter->vsi.active_svlans); + + list_del(&f->list); + kfree(f); + } + } + spin_unlock_bh(&adapter->mac_vlan_list_lock); +} + +/** * iavf_add_vlans * @adapter: adapter structure * @@ -683,6 +710,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vvfl->vlan_id[i] = f->vlan.vid; i++; f->add = false; + f->is_new_vlan = true; if (i == count) break; } @@ -695,10 +723,18 @@ void iavf_add_vlans(struct iavf_adapter *adapter) iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_VLAN, (u8 *)vvfl, len); kfree(vvfl); } else { + u16 max_vlans = adapter->vlan_v2_caps.filtering.max_filters; + u16 current_vlans = iavf_get_num_vlans_added(adapter); struct virtchnl_vlan_filter_list_v2 *vvfl_v2; adapter->current_op = VIRTCHNL_OP_ADD_VLAN_V2; + if ((count + current_vlans) > max_vlans && + current_vlans < max_vlans) { + count = max_vlans - iavf_get_num_vlans_added(adapter); + more = true; + } + len = sizeof(*vvfl_v2) + ((count - 1) * sizeof(struct virtchnl_vlan_filter)); if (len > IAVF_MAX_AQ_BUF_SIZE) { @@ -725,6 +761,9 @@ void iavf_add_vlans(struct iavf_adapter *adapter) &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; + if (i == count) + break; + /* give priority over outer if it's enabled */ if (filtering_support->outer) vlan = &vvfl_v2->filters[i].outer; @@ -736,8 +775,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) i++; f->add = false; - if (i == count) - break; + f->is_new_vlan = true; } } @@ -2080,6 +2118,11 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, */ iavf_netdev_features_vlan_strip_set(netdev, true); break; + case VIRTCHNL_OP_ADD_VLAN_V2: + iavf_vlan_add_reject(adapter); + dev_warn(&adapter->pdev->dev, "Failed to add VLAN filter, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + break; default: dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", v_retval, iavf_stat_str(&adapter->hw, v_retval), @@ -2332,6 +2375,24 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->adv_rss_lock); } break; + case VIRTCHNL_OP_ADD_VLAN_V2: { + struct iavf_vlan_filter *f; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->is_new_vlan) { + f->is_new_vlan = false; + if (f->vlan.tpid == ETH_P_8021Q) + set_bit(f->vlan.vid, + adapter->vsi.active_cvlans); + else + set_bit(f->vlan.vid, + adapter->vsi.active_svlans); + } + } + spin_unlock_bh(&adapter->mac_vlan_list_lock); + } + break; case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: /* PF enabled vlan strip on this VF. * Update netdev->features if needed to be in sync with ethtool. diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index 61dd2f18dee8..b41bc3dc1745 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -5,6 +5,7 @@ #define _ICE_DEVIDS_H_ /* Device IDs */ +#define ICE_DEV_ID_E822_SI_DFLT 0x1888 /* Intel(R) Ethernet Connection E823-L for backplane */ #define ICE_DEV_ID_E823L_BACKPLANE 0x124C /* Intel(R) Ethernet Connection E823-L for SFP */ diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 3991d62473bf..3337314a7b35 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -814,6 +814,8 @@ void ice_devlink_destroy_vf_port(struct ice_vf *vf) devlink_port_unregister(devlink_port); } +#define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024) + /** * ice_devlink_nvm_snapshot - Capture a snapshot of the NVM flash contents * @devlink: the devlink instance @@ -840,8 +842,9 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, struct ice_pf *pf = devlink_priv(devlink); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - void *nvm_data; - u32 nvm_size; + u8 *nvm_data, *tmp, i; + u32 nvm_size, left; + s8 num_blks; int status; nvm_size = hw->flash.flash_size; @@ -849,26 +852,44 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, if (!nvm_data) return -ENOMEM; - status = ice_acquire_nvm(hw, ICE_RES_READ); - if (status) { - dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", - status, hw->adminq.sq_last_status); - NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); - vfree(nvm_data); - return status; - } - status = ice_read_flat_nvm(hw, 0, &nvm_size, nvm_data, false); - if (status) { - dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n", - nvm_size, status, hw->adminq.sq_last_status); - NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents"); + num_blks = DIV_ROUND_UP(nvm_size, ICE_DEVLINK_READ_BLK_SIZE); + tmp = nvm_data; + left = nvm_size; + + /* Some systems take longer to read the NVM than others which causes the + * FW to reclaim the NVM lock before the entire NVM has been read. Fix + * this by breaking the reads of the NVM into smaller chunks that will + * probably not take as long. This has some overhead since we are + * increasing the number of AQ commands, but it should always work + */ + for (i = 0; i < num_blks; i++) { + u32 read_sz = min_t(u32, ICE_DEVLINK_READ_BLK_SIZE, left); + + status = ice_acquire_nvm(hw, ICE_RES_READ); + if (status) { + dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", + status, hw->adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); + vfree(nvm_data); + return -EIO; + } + + status = ice_read_flat_nvm(hw, i * ICE_DEVLINK_READ_BLK_SIZE, + &read_sz, tmp, false); + if (status) { + dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n", + read_sz, status, hw->adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents"); + ice_release_nvm(hw); + vfree(nvm_data); + return -EIO; + } ice_release_nvm(hw); - vfree(nvm_data); - return status; - } - ice_release_nvm(hw); + tmp += read_sz; + left -= read_sz; + } *data = nvm_data; diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index 665a344fb9c0..3dc5662d62a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -736,7 +736,87 @@ static int ice_finalize_update(struct pldmfw *context) return 0; } -static const struct pldmfw_ops ice_fwu_ops = { +struct ice_pldm_pci_record_id { + u32 vendor; + u32 device; + u32 subsystem_vendor; + u32 subsystem_device; +}; + +/** + * ice_op_pci_match_record - Check if a PCI device matches the record + * @context: PLDM fw update structure + * @record: list of records extracted from the PLDM image + * + * Determine if the PCI device associated with this device matches the record + * data provided. + * + * Searches the descriptor TLVs and extracts the relevant descriptor data into + * a pldm_pci_record_id. This is then compared against the PCI device ID + * information. + * + * Returns: true if the device matches the record, false otherwise. + */ +static bool +ice_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record) +{ + struct pci_dev *pdev = to_pci_dev(context->dev); + struct ice_pldm_pci_record_id id = { + .vendor = PCI_ANY_ID, + .device = PCI_ANY_ID, + .subsystem_vendor = PCI_ANY_ID, + .subsystem_device = PCI_ANY_ID, + }; + struct pldmfw_desc_tlv *desc; + + list_for_each_entry(desc, &record->descs, entry) { + u16 value; + int *ptr; + + switch (desc->type) { + case PLDM_DESC_ID_PCI_VENDOR_ID: + ptr = &id.vendor; + break; + case PLDM_DESC_ID_PCI_DEVICE_ID: + ptr = &id.device; + break; + case PLDM_DESC_ID_PCI_SUBVENDOR_ID: + ptr = &id.subsystem_vendor; + break; + case PLDM_DESC_ID_PCI_SUBDEV_ID: + ptr = &id.subsystem_device; + break; + default: + /* Skip unrelated TLVs */ + continue; + } + + value = get_unaligned_le16(desc->data); + /* A value of zero for one of the descriptors is sometimes + * used when the record should ignore this field when matching + * device. For example if the record applies to any subsystem + * device or vendor. + */ + if (value) + *ptr = value; + else + *ptr = PCI_ANY_ID; + } + + /* the E822 device can have a generic device ID so check for that */ + if ((id.vendor == PCI_ANY_ID || id.vendor == pdev->vendor) && + (id.device == PCI_ANY_ID || id.device == pdev->device || + id.device == ICE_DEV_ID_E822_SI_DFLT) && + (id.subsystem_vendor == PCI_ANY_ID || + id.subsystem_vendor == pdev->subsystem_vendor) && + (id.subsystem_device == PCI_ANY_ID || + id.subsystem_device == pdev->subsystem_device)) + return true; + + return false; +} + +static const struct pldmfw_ops ice_fwu_ops_e810 = { .match_record = &pldmfw_op_pci_match_record, .send_package_data = &ice_send_package_data, .send_component_table = &ice_send_component_table, @@ -744,6 +824,14 @@ static const struct pldmfw_ops ice_fwu_ops = { .finalize_update = &ice_finalize_update, }; +static const struct pldmfw_ops ice_fwu_ops_e822 = { + .match_record = &ice_op_pci_match_record, + .send_package_data = &ice_send_package_data, + .send_component_table = &ice_send_component_table, + .flash_component = &ice_flash_component, + .finalize_update = &ice_finalize_update, +}; + /** * ice_get_pending_updates - Check if the component has a pending update * @pf: the PF driver structure @@ -921,7 +1009,11 @@ int ice_devlink_flash_update(struct devlink *devlink, memset(&priv, 0, sizeof(priv)); - priv.context.ops = &ice_fwu_ops; + /* the E822 device needs a slightly different ops */ + if (hw->mac_type == ICE_MAC_GENERIC) + priv.context.ops = &ice_fwu_ops_e822; + else + priv.context.ops = &ice_fwu_ops_e810; priv.context.dev = dev; priv.extack = extack; priv.pf = pf; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index c1ac2f746714..ff2eac2f8c64 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5413,6 +5413,7 @@ static const struct pci_device_id ice_pci_tbl[] = { { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_10G_BASE_T), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_1GBE), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_QSFP), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822_SI_DFLT), 0 }, /* required last entry */ { 0, } }; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index ae17af44fe02..a5ebee7df4a8 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6171,6 +6171,9 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg) u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr); u32 value = 0; + if (IGC_REMOVED(hw_addr)) + return ~value; + value = readl(&hw_addr[reg]); /* reads should not return all F's */ diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index e197a33d93a0..026c3b65fc37 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -306,7 +306,8 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg); #define wr32(reg, val) \ do { \ u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \ - writel((val), &hw_addr[(reg)]); \ + if (!IGC_REMOVED(hw_addr)) \ + writel((val), &hw_addr[(reg)]); \ } while (0) #define rd32(reg) (igc_rd32(hw, reg)) @@ -318,4 +319,6 @@ do { \ #define array_rd32(reg, offset) (igc_rd32(hw, (reg) + ((offset) << 2))) +#define IGC_REMOVED(h) unlikely(!(h)) + #endif diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 921a4d977d65..8813b4dd6872 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -779,6 +779,7 @@ struct ixgbe_adapter { #ifdef CONFIG_IXGBE_IPSEC struct ixgbe_ipsec *ipsec; #endif /* CONFIG_IXGBE_IPSEC */ + spinlock_t vfs_lock; }; static inline int ixgbe_determine_xdp_q_idx(int cpu) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 77c2e70b0860..55f91c9ff047 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6403,6 +6403,9 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, /* n-tuple support exists, always init our spinlock */ spin_lock_init(&adapter->fdir_perfect_lock); + /* init spinlock to avoid concurrency of VF resources */ + spin_lock_init(&adapter->vfs_lock); + #ifdef CONFIG_IXGBE_DCB ixgbe_init_dcb(adapter); #endif diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index d4e63f0644c3..a1e69c734863 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -205,10 +205,13 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs) int ixgbe_disable_sriov(struct ixgbe_adapter *adapter) { unsigned int num_vfs = adapter->num_vfs, vf; + unsigned long flags; int rss; + spin_lock_irqsave(&adapter->vfs_lock, flags); /* set num VFs to 0 to prevent access to vfinfo */ adapter->num_vfs = 0; + spin_unlock_irqrestore(&adapter->vfs_lock, flags); /* put the reference to all of the vf devices */ for (vf = 0; vf < num_vfs; ++vf) { @@ -1355,8 +1358,10 @@ static void ixgbe_rcv_ack_from_vf(struct ixgbe_adapter *adapter, u32 vf) void ixgbe_msg_task(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; + unsigned long flags; u32 vf; + spin_lock_irqsave(&adapter->vfs_lock, flags); for (vf = 0; vf < adapter->num_vfs; vf++) { /* process any reset requests */ if (!ixgbe_check_for_rst(hw, vf)) @@ -1370,6 +1375,7 @@ void ixgbe_msg_task(struct ixgbe_adapter *adapter) if (!ixgbe_check_for_ack(hw, vf)) ixgbe_rcv_ack_from_vf(adapter, vf); } + spin_unlock_irqrestore(&adapter->vfs_lock, flags); } static inline void ixgbe_ping_vf(struct ixgbe_adapter *adapter, int vf) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.c b/drivers/net/ethernet/marvell/prestera/prestera_flower.c index d43e503c644f..4d93ad6a284c 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_flower.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.c @@ -167,12 +167,12 @@ static int prestera_flower_parse_meta(struct prestera_acl_rule *rule, } port = netdev_priv(ingress_dev); - mask = htons(0x1FFF); - key = htons(port->hw_id); + mask = htons(0x1FFF << 3); + key = htons(port->hw_id << 3); rule_match_set(r_match->key, SYS_PORT, key); rule_match_set(r_match->mask, SYS_PORT, mask); - mask = htons(0x1FF); + mask = htons(0x3FF); key = htons(port->dev_id); rule_match_set(r_match->key, SYS_DEV, key); rule_match_set(r_match->mask, SYS_DEV, mask); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_router.c b/drivers/net/ethernet/marvell/prestera/prestera_router.c index 3754d8aec76d..3c8116f16b4d 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_router.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_router.c @@ -588,6 +588,7 @@ err_router_lib_init: void prestera_router_fini(struct prestera_switch *sw) { + unregister_fib_notifier(&init_net, &sw->router->fib_nb); unregister_inetaddr_notifier(&sw->router->inetaddr_nb); unregister_inetaddr_validator_notifier(&sw->router->inetaddr_valid_nb); rhashtable_destroy(&sw->router->kern_fib_cache_ht); diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c index 90e7dfd011c9..5d457bc9acc1 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c @@ -93,6 +93,9 @@ mtk_flow_get_wdma_info(struct net_device *dev, const u8 *addr, struct mtk_wdma_i }; struct net_device_path path = {}; + if (!ctx.dev) + return -ENODEV; + memcpy(ctx.daddr, addr, sizeof(ctx.daddr)); if (!IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED)) diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 8f0cd3196aac..29be2fcafea3 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -651,7 +651,7 @@ mtk_wed_tx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs) * WDMA RX. */ - BUG_ON(idx > ARRAY_SIZE(dev->tx_ring)); + BUG_ON(idx >= ARRAY_SIZE(dev->tx_ring)); if (mtk_wed_ring_alloc(dev, ring, MTK_WED_TX_RING_SIZE)) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 25f51f80a9b4..ba171c7f0a67 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -76,6 +76,7 @@ struct mlx5_tc_ct_priv { struct mlx5_ct_fs *fs; struct mlx5_ct_fs_ops *fs_ops; spinlock_t ht_lock; /* protects ft entries */ + struct workqueue_struct *wq; struct mlx5_tc_ct_debugfs debugfs; }; @@ -941,14 +942,11 @@ static void mlx5_tc_ct_entry_del_work(struct work_struct *work) static void __mlx5_tc_ct_entry_put(struct mlx5_ct_entry *entry) { - struct mlx5e_priv *priv; - if (!refcount_dec_and_test(&entry->refcnt)) return; - priv = netdev_priv(entry->ct_priv->netdev); INIT_WORK(&entry->work, mlx5_tc_ct_entry_del_work); - queue_work(priv->wq, &entry->work); + queue_work(entry->ct_priv->wq, &entry->work); } static struct mlx5_ct_counter * @@ -1759,19 +1757,16 @@ mlx5_tc_ct_flush_ft_entry(void *ptr, void *arg) static void mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) { - struct mlx5e_priv *priv; - if (!refcount_dec_and_test(&ft->refcount)) return; + flush_workqueue(ct_priv->wq); nf_flow_table_offload_del_cb(ft->nf_ft, mlx5_tc_ct_block_flow_offload, ft); rhashtable_remove_fast(&ct_priv->zone_ht, &ft->node, zone_params); rhashtable_free_and_destroy(&ft->ct_entries_ht, mlx5_tc_ct_flush_ft_entry, ct_priv); - priv = netdev_priv(ct_priv->netdev); - flush_workqueue(priv->wq); mlx5_tc_ct_free_pre_ct_tables(ft); mapping_remove(ct_priv->zone_mapping, ft->zone_restore_id); kfree(ft); @@ -2176,6 +2171,12 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, if (rhashtable_init(&ct_priv->ct_tuples_nat_ht, &tuples_nat_ht_params)) goto err_ct_tuples_nat_ht; + ct_priv->wq = alloc_ordered_workqueue("mlx5e_ct_priv_wq", 0); + if (!ct_priv->wq) { + err = -ENOMEM; + goto err_wq; + } + err = mlx5_tc_ct_fs_init(ct_priv); if (err) goto err_init_fs; @@ -2184,6 +2185,8 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, return ct_priv; err_init_fs: + destroy_workqueue(ct_priv->wq); +err_wq: rhashtable_destroy(&ct_priv->ct_tuples_nat_ht); err_ct_tuples_nat_ht: rhashtable_destroy(&ct_priv->ct_tuples_ht); @@ -2213,6 +2216,7 @@ mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv) if (!ct_priv) return; + destroy_workqueue(ct_priv->wq); mlx5_ct_tc_remove_dbgfs(ct_priv); chains = ct_priv->chains; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index 0bb0633b7542..27483aa7be8a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -231,8 +231,7 @@ mlx5e_set_ktls_rx_priv_ctx(struct tls_context *tls_ctx, struct mlx5e_ktls_offload_context_rx **ctx = __tls_driver_ctx(tls_ctx, TLS_OFFLOAD_CTX_DIR_RX); - BUILD_BUG_ON(sizeof(struct mlx5e_ktls_offload_context_rx *) > - TLS_OFFLOAD_CONTEXT_SIZE_RX); + BUILD_BUG_ON(sizeof(priv_rx) > TLS_DRIVER_STATE_SIZE_RX); *ctx = priv_rx; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 4b6f0d1ea59a..f239fb2e832f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -68,8 +68,7 @@ mlx5e_set_ktls_tx_priv_ctx(struct tls_context *tls_ctx, struct mlx5e_ktls_offload_context_tx **ctx = __tls_driver_ctx(tls_ctx, TLS_OFFLOAD_CTX_DIR_TX); - BUILD_BUG_ON(sizeof(struct mlx5e_ktls_offload_context_tx *) > - TLS_OFFLOAD_CONTEXT_SIZE_TX); + BUILD_BUG_ON(sizeof(priv_tx) > TLS_DRIVER_STATE_SIZE_TX); *ctx = priv_tx; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 57fa0489eeb8..1e87bb2b7541 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -688,7 +688,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vnic_env) u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {}; struct mlx5_core_dev *mdev = priv->mdev; - if (!MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard)) + if (!mlx5e_stats_grp_vnic_env_num_stats(priv)) return; MLX5_SET(query_vnic_env_in, in, opcode, MLX5_CMD_OP_QUERY_VNIC_ENV); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3a39a50146dd..9ca2c8763237 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3793,7 +3793,7 @@ static bool is_lag_dev(struct mlx5e_priv *priv, static bool is_multiport_eligible(struct mlx5e_priv *priv, struct net_device *out_dev) { - if (mlx5e_eswitch_uplink_rep(out_dev) && + if (same_hw_reps(priv, out_dev) && MLX5_CAP_PORT_SELECTION(priv->mdev, port_select_flow_table) && MLX5_CAP_GEN(priv->mdev, create_lag_when_not_master_up)) return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 50d14cec4894..9a7250be229f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -341,6 +341,26 @@ static void mlx5e_tx_check_stop(struct mlx5e_txqsq *sq) } } +static void mlx5e_tx_flush(struct mlx5e_txqsq *sq) +{ + struct mlx5e_tx_wqe_info *wi; + struct mlx5e_tx_wqe *wqe; + u16 pi; + + /* Must not be called when a MPWQE session is active but empty. */ + mlx5e_tx_mpwqe_ensure_complete(sq); + + pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc); + wi = &sq->db.wqe_info[pi]; + + *wi = (struct mlx5e_tx_wqe_info) { + .num_wqebbs = 1, + }; + + wqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc); + mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl); +} + static inline void mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, const struct mlx5e_tx_attr *attr, @@ -459,6 +479,7 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, err_drop: stats->dropped++; dev_kfree_skb_any(skb); + mlx5e_tx_flush(sq); } static bool mlx5e_tx_skb_supports_mpwqe(struct sk_buff *skb, struct mlx5e_tx_attr *attr) @@ -560,6 +581,13 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_ctrl_seg *cseg; struct mlx5e_xmit_data txd; + txd.data = skb->data; + txd.len = skb->len; + + txd.dma_addr = dma_map_single(sq->pdev, txd.data, txd.len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(sq->pdev, txd.dma_addr))) + goto err_unmap; + if (!mlx5e_tx_mpwqe_session_is_active(sq)) { mlx5e_tx_mpwqe_session_start(sq, eseg); } else if (!mlx5e_tx_mpwqe_same_eseg(sq, eseg)) { @@ -569,18 +597,9 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, sq->stats->xmit_more += xmit_more; - txd.data = skb->data; - txd.len = skb->len; - - txd.dma_addr = dma_map_single(sq->pdev, txd.data, txd.len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(sq->pdev, txd.dma_addr))) - goto err_unmap; mlx5e_dma_push(sq, txd.dma_addr, txd.len, MLX5E_DMA_MAP_SINGLE); - mlx5e_skb_fifo_push(&sq->db.skb_fifo, skb); - mlx5e_tx_mpwqe_add_dseg(sq, &txd); - mlx5e_tx_skb_update_hwts_flags(skb); if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe, sq->max_sq_mpw_wqebbs))) { @@ -602,6 +621,7 @@ err_unmap: mlx5e_dma_unmap_wqe_err(sq, 1); sq->stats->dropped++; dev_kfree_skb_any(skb); + mlx5e_tx_flush(sq); } void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq) @@ -1006,5 +1026,6 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, err_drop: stats->dropped++; dev_kfree_skb_any(skb); + mlx5e_tx_flush(sq); } #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c index 9d17206d1625..fabe49a35a5c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c @@ -11,6 +11,7 @@ #include "mlx5_core.h" #include "eswitch.h" #include "fs_core.h" +#include "fs_ft_pool.h" #include "esw/qos.h" enum { @@ -95,8 +96,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw) if (!flow_group_in) return -ENOMEM; - table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size)); - ft_attr.max_fte = table_size; + ft_attr.max_fte = POOL_NEXT_SIZE; ft_attr.prio = LEGACY_FDB_PRIO; fdb = mlx5_create_flow_table(root_ns, &ft_attr); if (IS_ERR(fdb)) { @@ -105,6 +105,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw) goto out; } esw->fdb_table.legacy.fdb = fdb; + table_size = fdb->max_fte; /* Addresses group : Full match unicast/multicast addresses */ MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c index 15e41dc84d53..b8feaf0f5c4c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c @@ -44,7 +44,7 @@ static int port_sel_mode_show(struct seq_file *file, void *priv) ldev = dev->priv.lag; mutex_lock(&ldev->lock); if (__mlx5_lag_is_active(ldev)) - mode = mlx5_get_str_port_sel_mode(ldev); + mode = mlx5_get_str_port_sel_mode(ldev->mode, ldev->mode_flags); else ret = -EINVAL; mutex_unlock(&ldev->lock); @@ -72,6 +72,7 @@ static int state_show(struct seq_file *file, void *priv) static int flags_show(struct seq_file *file, void *priv) { struct mlx5_core_dev *dev = file->private; + bool fdb_sel_mode_native; struct mlx5_lag *ldev; bool shared_fdb; bool lag_active; @@ -79,14 +80,21 @@ static int flags_show(struct seq_file *file, void *priv) ldev = dev->priv.lag; mutex_lock(&ldev->lock); lag_active = __mlx5_lag_is_active(ldev); - if (lag_active) - shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags); + if (!lag_active) + goto unlock; + + shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags); + fdb_sel_mode_native = test_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, + &ldev->mode_flags); +unlock: mutex_unlock(&ldev->lock); if (!lag_active) return -EINVAL; seq_printf(file, "%s:%s\n", "shared_fdb", shared_fdb ? "on" : "off"); + seq_printf(file, "%s:%s\n", "fdb_selection_mode", + fdb_sel_mode_native ? "native" : "affinity"); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 2a8fc547eb37..5d41e19378e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -68,14 +68,15 @@ static int get_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags) static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 *ports, int mode, unsigned long flags) { - bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags); + bool fdb_sel_mode = test_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, + &flags); int port_sel_mode = get_port_sel_mode(mode, flags); u32 in[MLX5_ST_SZ_DW(create_lag_in)] = {}; void *lag_ctx; lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx); MLX5_SET(create_lag_in, in, opcode, MLX5_CMD_OP_CREATE_LAG); - MLX5_SET(lagc, lag_ctx, fdb_selection_mode, shared_fdb); + MLX5_SET(lagc, lag_ctx, fdb_selection_mode, fdb_sel_mode); if (port_sel_mode == MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY) { MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, ports[0]); MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, ports[1]); @@ -471,8 +472,13 @@ static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode, bool roce_lag = mode == MLX5_LAG_MODE_ROCE; *flags = 0; - if (shared_fdb) + if (shared_fdb) { set_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, flags); + set_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, flags); + } + + if (mode == MLX5_LAG_MODE_MPESW) + set_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, flags); if (roce_lag) return mlx5_lag_set_port_sel_mode_roce(ldev, flags); @@ -481,9 +487,9 @@ static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode, return 0; } -char *mlx5_get_str_port_sel_mode(struct mlx5_lag *ldev) +char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags) { - int port_sel_mode = get_port_sel_mode(ldev->mode, ldev->mode_flags); + int port_sel_mode = get_port_sel_mode(mode, flags); switch (port_sel_mode) { case MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY: return "queue_affinity"; @@ -507,7 +513,7 @@ static int mlx5_create_lag(struct mlx5_lag *ldev, if (tracker) mlx5_lag_print_mapping(dev0, ldev, tracker, flags); mlx5_core_info(dev0, "shared_fdb:%d mode:%s\n", - shared_fdb, mlx5_get_str_port_sel_mode(ldev)); + shared_fdb, mlx5_get_str_port_sel_mode(mode, flags)); err = mlx5_cmd_create_lag(dev0, ldev->v2p_map, mode, flags); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index c81b173156d2..ce2ce8ccbd70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -24,6 +24,7 @@ enum { enum { MLX5_LAG_MODE_FLAG_HASH_BASED, MLX5_LAG_MODE_FLAG_SHARED_FDB, + MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, }; enum mlx5_lag_mode { @@ -114,7 +115,7 @@ bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev); void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev); int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev); -char *mlx5_get_str_port_sel_mode(struct mlx5_lag *ldev); +char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags); void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports, u8 *ports, int *num_enabled); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index ee4b25a50315..f643202b29c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -41,7 +41,6 @@ void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev) int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev = dev->priv.lag; - bool shared_fdb; int err = 0; if (!ldev) @@ -55,8 +54,8 @@ int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev) err = -EINVAL; goto out; } - shared_fdb = mlx5_shared_fdb_supported(ldev); - err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, shared_fdb); + + err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, false); if (err) mlx5_core_warn(dev, "Failed to create LAG in MPESW mode (%d)\n", err); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 0d8a0068e4ca..ce33dbde124d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -5384,7 +5384,7 @@ static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp, { const struct fib_nh *nh = fib_info_nh(fi, 0); - return nh->fib_nh_scope == RT_SCOPE_LINK || + return nh->fib_nh_gw_family || mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, nh, NULL); } @@ -10324,7 +10324,7 @@ static void mlxsw_sp_mp4_hash_init(struct mlxsw_sp *mlxsw_sp, unsigned long *fields = config->fields; u32 hash_fields; - switch (net->ipv4.sysctl_fib_multipath_hash_policy) { + switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) { case 0: mlxsw_sp_mp4_hash_outer_addr(config); break; @@ -10342,7 +10342,7 @@ static void mlxsw_sp_mp4_hash_init(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_mp_hash_inner_l3(config); break; case 3: - hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); /* Outer */ MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_NOT_TCP_NOT_UDP); MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_TCP_UDP); @@ -10523,13 +10523,14 @@ static int mlxsw_sp_dscp_init(struct mlxsw_sp *mlxsw_sp) static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) { struct net *net = mlxsw_sp_net(mlxsw_sp); - bool usp = net->ipv4.sysctl_ip_fwd_update_priority; char rgcr_pl[MLXSW_REG_RGCR_LEN]; u64 max_rifs; + bool usp; if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS)) return -EIO; max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); + usp = READ_ONCE(net->ipv4.sysctl_ip_fwd_update_priority); mlxsw_reg_rgcr_pack(rgcr_pl, true, true); mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c index 005e56ea5da1..5893770bfd94 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c @@ -75,6 +75,9 @@ static int __lan966x_mac_learn(struct lan966x *lan966x, int pgid, unsigned int vid, enum macaccess_entry_type type) { + int ret; + + spin_lock(&lan966x->mac_lock); lan966x_mac_select(lan966x, mac, vid); /* Issue a write command */ @@ -86,7 +89,10 @@ static int __lan966x_mac_learn(struct lan966x *lan966x, int pgid, ANA_MACACCESS_MAC_TABLE_CMD_SET(MACACCESS_CMD_LEARN), lan966x, ANA_MACACCESS); - return lan966x_mac_wait_for_completion(lan966x); + ret = lan966x_mac_wait_for_completion(lan966x); + spin_unlock(&lan966x->mac_lock); + + return ret; } /* The mask of the front ports is encoded inside the mac parameter via a call @@ -113,11 +119,13 @@ int lan966x_mac_learn(struct lan966x *lan966x, int port, return __lan966x_mac_learn(lan966x, port, false, mac, vid, type); } -int lan966x_mac_forget(struct lan966x *lan966x, - const unsigned char mac[ETH_ALEN], - unsigned int vid, - enum macaccess_entry_type type) +static int lan966x_mac_forget_locked(struct lan966x *lan966x, + const unsigned char mac[ETH_ALEN], + unsigned int vid, + enum macaccess_entry_type type) { + lockdep_assert_held(&lan966x->mac_lock); + lan966x_mac_select(lan966x, mac, vid); /* Issue a forget command */ @@ -128,6 +136,20 @@ int lan966x_mac_forget(struct lan966x *lan966x, return lan966x_mac_wait_for_completion(lan966x); } +int lan966x_mac_forget(struct lan966x *lan966x, + const unsigned char mac[ETH_ALEN], + unsigned int vid, + enum macaccess_entry_type type) +{ + int ret; + + spin_lock(&lan966x->mac_lock); + ret = lan966x_mac_forget_locked(lan966x, mac, vid, type); + spin_unlock(&lan966x->mac_lock); + + return ret; +} + int lan966x_mac_cpu_learn(struct lan966x *lan966x, const char *addr, u16 vid) { return lan966x_mac_learn(lan966x, PGID_CPU, addr, vid, ENTRYTYPE_LOCKED); @@ -161,7 +183,7 @@ static struct lan966x_mac_entry *lan966x_mac_alloc_entry(const unsigned char *ma { struct lan966x_mac_entry *mac_entry; - mac_entry = kzalloc(sizeof(*mac_entry), GFP_KERNEL); + mac_entry = kzalloc(sizeof(*mac_entry), GFP_ATOMIC); if (!mac_entry) return NULL; @@ -179,7 +201,6 @@ static struct lan966x_mac_entry *lan966x_mac_find_entry(struct lan966x *lan966x, struct lan966x_mac_entry *res = NULL; struct lan966x_mac_entry *mac_entry; - spin_lock(&lan966x->mac_lock); list_for_each_entry(mac_entry, &lan966x->mac_entries, list) { if (mac_entry->vid == vid && ether_addr_equal(mac, mac_entry->mac) && @@ -188,7 +209,6 @@ static struct lan966x_mac_entry *lan966x_mac_find_entry(struct lan966x *lan966x, break; } } - spin_unlock(&lan966x->mac_lock); return res; } @@ -231,8 +251,11 @@ int lan966x_mac_add_entry(struct lan966x *lan966x, struct lan966x_port *port, { struct lan966x_mac_entry *mac_entry; - if (lan966x_mac_lookup(lan966x, addr, vid, ENTRYTYPE_NORMAL)) + spin_lock(&lan966x->mac_lock); + if (lan966x_mac_lookup(lan966x, addr, vid, ENTRYTYPE_NORMAL)) { + spin_unlock(&lan966x->mac_lock); return 0; + } /* In case the entry already exists, don't add it again to SW, * just update HW, but we need to look in the actual HW because @@ -241,21 +264,25 @@ int lan966x_mac_add_entry(struct lan966x *lan966x, struct lan966x_port *port, * add the entry but without the extern_learn flag. */ mac_entry = lan966x_mac_find_entry(lan966x, addr, vid, port->chip_port); - if (mac_entry) - return lan966x_mac_learn(lan966x, port->chip_port, - addr, vid, ENTRYTYPE_LOCKED); + if (mac_entry) { + spin_unlock(&lan966x->mac_lock); + goto mac_learn; + } mac_entry = lan966x_mac_alloc_entry(addr, vid, port->chip_port); - if (!mac_entry) + if (!mac_entry) { + spin_unlock(&lan966x->mac_lock); return -ENOMEM; + } - spin_lock(&lan966x->mac_lock); list_add_tail(&mac_entry->list, &lan966x->mac_entries); spin_unlock(&lan966x->mac_lock); - lan966x_mac_learn(lan966x, port->chip_port, addr, vid, ENTRYTYPE_LOCKED); lan966x_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED, addr, vid, port->dev); +mac_learn: + lan966x_mac_learn(lan966x, port->chip_port, addr, vid, ENTRYTYPE_LOCKED); + return 0; } @@ -269,8 +296,9 @@ int lan966x_mac_del_entry(struct lan966x *lan966x, const unsigned char *addr, list) { if (mac_entry->vid == vid && ether_addr_equal(addr, mac_entry->mac)) { - lan966x_mac_forget(lan966x, mac_entry->mac, mac_entry->vid, - ENTRYTYPE_LOCKED); + lan966x_mac_forget_locked(lan966x, mac_entry->mac, + mac_entry->vid, + ENTRYTYPE_LOCKED); list_del(&mac_entry->list); kfree(mac_entry); @@ -288,8 +316,8 @@ void lan966x_mac_purge_entries(struct lan966x *lan966x) spin_lock(&lan966x->mac_lock); list_for_each_entry_safe(mac_entry, tmp, &lan966x->mac_entries, list) { - lan966x_mac_forget(lan966x, mac_entry->mac, mac_entry->vid, - ENTRYTYPE_LOCKED); + lan966x_mac_forget_locked(lan966x, mac_entry->mac, + mac_entry->vid, ENTRYTYPE_LOCKED); list_del(&mac_entry->list); kfree(mac_entry); @@ -325,10 +353,13 @@ static void lan966x_mac_irq_process(struct lan966x *lan966x, u32 row, { struct lan966x_mac_entry *mac_entry, *tmp; unsigned char mac[ETH_ALEN] __aligned(2); + struct list_head mac_deleted_entries; u32 dest_idx; u32 column; u16 vid; + INIT_LIST_HEAD(&mac_deleted_entries); + spin_lock(&lan966x->mac_lock); list_for_each_entry_safe(mac_entry, tmp, &lan966x->mac_entries, list) { bool found = false; @@ -362,20 +393,26 @@ static void lan966x_mac_irq_process(struct lan966x *lan966x, u32 row, } if (!found) { - /* Notify the bridge that the entry doesn't exist - * anymore in the HW and remove the entry from the SW - * list - */ - lan966x_mac_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, - mac_entry->mac, mac_entry->vid, - lan966x->ports[mac_entry->port_index]->dev); - list_del(&mac_entry->list); - kfree(mac_entry); + /* Move the entry from SW list to a tmp list such that + * it would be deleted later + */ + list_add_tail(&mac_entry->list, &mac_deleted_entries); } } spin_unlock(&lan966x->mac_lock); + list_for_each_entry_safe(mac_entry, tmp, &mac_deleted_entries, list) { + /* Notify the bridge that the entry doesn't exist + * anymore in the HW + */ + lan966x_mac_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, + mac_entry->mac, mac_entry->vid, + lan966x->ports[mac_entry->port_index]->dev); + list_del(&mac_entry->list); + kfree(mac_entry); + } + /* Now go to the list of columns and see if any entry was not in the SW * list, then that means that the entry is new so it needs to notify the * bridge. @@ -396,13 +433,20 @@ static void lan966x_mac_irq_process(struct lan966x *lan966x, u32 row, if (WARN_ON(dest_idx >= lan966x->num_phys_ports)) continue; + spin_lock(&lan966x->mac_lock); + mac_entry = lan966x_mac_find_entry(lan966x, mac, vid, dest_idx); + if (mac_entry) { + spin_unlock(&lan966x->mac_lock); + continue; + } + mac_entry = lan966x_mac_alloc_entry(mac, vid, dest_idx); - if (!mac_entry) + if (!mac_entry) { + spin_unlock(&lan966x->mac_lock); return; + } mac_entry->row = row; - - spin_lock(&lan966x->mac_lock); list_add_tail(&mac_entry->list, &lan966x->mac_entries); spin_unlock(&lan966x->mac_lock); @@ -424,6 +468,7 @@ irqreturn_t lan966x_mac_irq_handler(struct lan966x *lan966x) lan966x, ANA_MACTINDX); while (1) { + spin_lock(&lan966x->mac_lock); lan_rmw(ANA_MACACCESS_MAC_TABLE_CMD_SET(MACACCESS_CMD_SYNC_GET_NEXT), ANA_MACACCESS_MAC_TABLE_CMD, lan966x, ANA_MACACCESS); @@ -447,12 +492,15 @@ irqreturn_t lan966x_mac_irq_handler(struct lan966x *lan966x) stop = false; if (column == LAN966X_MAC_COLUMNS - 1 && - index == 0 && stop) + index == 0 && stop) { + spin_unlock(&lan966x->mac_lock); break; + } entry[column].mach = lan_rd(lan966x, ANA_MACHDATA); entry[column].macl = lan_rd(lan966x, ANA_MACLDATA); entry[column].maca = lan_rd(lan966x, ANA_MACACCESS); + spin_unlock(&lan966x->mac_lock); /* Once all the columns are read process them */ if (column == LAN966X_MAC_COLUMNS - 1) { diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 083fddd263ec..8e3894cf5f7c 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -94,19 +94,18 @@ static void ocelot_fdma_activate_chan(struct ocelot *ocelot, dma_addr_t dma, ocelot_fdma_writel(ocelot, MSCC_FDMA_CH_ACTIVATE, BIT(chan)); } +static u32 ocelot_fdma_read_ch_safe(struct ocelot *ocelot) +{ + return ocelot_fdma_readl(ocelot, MSCC_FDMA_CH_SAFE); +} + static int ocelot_fdma_wait_chan_safe(struct ocelot *ocelot, int chan) { - unsigned long timeout; u32 safe; - timeout = jiffies + usecs_to_jiffies(OCELOT_FDMA_CH_SAFE_TIMEOUT_US); - do { - safe = ocelot_fdma_readl(ocelot, MSCC_FDMA_CH_SAFE); - if (safe & BIT(chan)) - return 0; - } while (time_after(jiffies, timeout)); - - return -ETIMEDOUT; + return readx_poll_timeout_atomic(ocelot_fdma_read_ch_safe, ocelot, safe, + safe & BIT(chan), 0, + OCELOT_FDMA_CH_SAFE_TIMEOUT_US); } static void ocelot_fdma_dcb_set_data(struct ocelot_fdma_dcb *dcb, diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 0147de405365..ffb6f6d05a07 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -474,7 +474,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, set_tun->ttl = ip4_dst_hoplimit(&rt->dst); ip_rt_put(rt); } else { - set_tun->ttl = net->ipv4.sysctl_ip_default_ttl; + set_tun->ttl = READ_ONCE(net->ipv4.sysctl_ip_default_ttl); } } diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 6bf3ec448e7e..97dcf8db7ed2 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -447,7 +447,8 @@ void nfp_tun_unlink_and_update_nn_entries(struct nfp_app *app, static void nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, - void *flow, struct neighbour *neigh, bool is_ipv6) + void *flow, struct neighbour *neigh, bool is_ipv6, + bool override) { bool neigh_invalid = !(neigh->nud_state & NUD_VALID) || neigh->dead; size_t neigh_size = is_ipv6 ? sizeof(struct nfp_tun_neigh_v6) : @@ -546,6 +547,13 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, if (nn_entry->flow) list_del(&nn_entry->list_head); kfree(nn_entry); + } else if (nn_entry && !neigh_invalid && override) { + mtype = is_ipv6 ? NFP_FLOWER_CMSG_TYPE_TUN_NEIGH_V6 : + NFP_FLOWER_CMSG_TYPE_TUN_NEIGH; + nfp_tun_link_predt_entries(app, nn_entry); + nfp_flower_xmit_tun_conf(app, mtype, neigh_size, + nn_entry->payload, + GFP_ATOMIC); } spin_unlock_bh(&priv->predt_lock); @@ -610,7 +618,7 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, dst_release(dst); } - nfp_tun_write_neigh(n->dev, app, &flow6, n, true); + nfp_tun_write_neigh(n->dev, app, &flow6, n, true, false); #else return NOTIFY_DONE; #endif /* CONFIG_IPV6 */ @@ -633,7 +641,7 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, ip_rt_put(rt); } - nfp_tun_write_neigh(n->dev, app, &flow4, n, false); + nfp_tun_write_neigh(n->dev, app, &flow4, n, false, false); } #else return NOTIFY_DONE; @@ -676,7 +684,7 @@ void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb) ip_rt_put(rt); if (!n) goto fail_rcu_unlock; - nfp_tun_write_neigh(n->dev, app, &flow, n, false); + nfp_tun_write_neigh(n->dev, app, &flow, n, false, true); neigh_release(n); rcu_read_unlock(); return; @@ -718,7 +726,7 @@ void nfp_tunnel_request_route_v6(struct nfp_app *app, struct sk_buff *skb) if (!n) goto fail_rcu_unlock; - nfp_tun_write_neigh(n->dev, app, &flow, n, true); + nfp_tun_write_neigh(n->dev, app, &flow, n, true, true); neigh_release(n); rcu_read_unlock(); return; diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c index e509d6dcba5c..805071d64a20 100644 --- a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c @@ -125,17 +125,18 @@ nfp_nfdk_tx_csum(struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec, static int nfp_nfdk_tx_maybe_close_block(struct nfp_net_tx_ring *tx_ring, - unsigned int nr_frags, struct sk_buff *skb) + struct sk_buff *skb) { unsigned int n_descs, wr_p, nop_slots; const skb_frag_t *frag, *fend; struct nfp_nfdk_tx_desc *txd; + unsigned int nr_frags; unsigned int wr_idx; int err; recount_descs: n_descs = nfp_nfdk_headlen_to_segs(skb_headlen(skb)); - + nr_frags = skb_shinfo(skb)->nr_frags; frag = skb_shinfo(skb)->frags; fend = frag + nr_frags; for (; frag < fend; frag++) @@ -281,10 +282,13 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) if (unlikely((int)metadata < 0)) goto err_flush; - nr_frags = skb_shinfo(skb)->nr_frags; - if (nfp_nfdk_tx_maybe_close_block(tx_ring, nr_frags, skb)) + if (nfp_nfdk_tx_maybe_close_block(tx_ring, skb)) goto err_flush; + /* nr_frags will change after skb_linearize so we get nr_frags after + * nfp_nfdk_tx_maybe_close_block function + */ + nr_frags = skb_shinfo(skb)->nr_frags; /* DMA map all */ wr_idx = D_IDX(tx_ring, tx_ring->wr_p); txd = &tx_ring->ktxds[wr_idx]; @@ -310,7 +314,16 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) /* FIELD_PREP() implicitly truncates to chunk */ dma_len -= 1; - dlen_type = FIELD_PREP(NFDK_DESC_TX_DMA_LEN_HEAD, dma_len) | + + /* We will do our best to pass as much data as we can in descriptor + * and we need to make sure the first descriptor includes whole head + * since there is limitation in firmware side. Sometimes the value of + * dma_len bitwise and NFDK_DESC_TX_DMA_LEN_HEAD will less than + * headlen. + */ + dlen_type = FIELD_PREP(NFDK_DESC_TX_DMA_LEN_HEAD, + dma_len > NFDK_DESC_TX_DMA_LEN_HEAD ? + NFDK_DESC_TX_DMA_LEN_HEAD : dma_len) | FIELD_PREP(NFDK_DESC_TX_TYPE_HEAD, type); txd->dma_len_type = cpu_to_le16(dlen_type); @@ -925,7 +938,9 @@ nfp_nfdk_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, /* FIELD_PREP() implicitly truncates to chunk */ dma_len -= 1; - dlen_type = FIELD_PREP(NFDK_DESC_TX_DMA_LEN_HEAD, dma_len) | + dlen_type = FIELD_PREP(NFDK_DESC_TX_DMA_LEN_HEAD, + dma_len > NFDK_DESC_TX_DMA_LEN_HEAD ? + NFDK_DESC_TX_DMA_LEN_HEAD : dma_len) | FIELD_PREP(NFDK_DESC_TX_TYPE_HEAD, type); txd->dma_len_type = cpu_to_le16(dlen_type); @@ -1303,7 +1318,7 @@ nfp_nfdk_ctrl_tx_one(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, skb_push(skb, 4)); } - if (nfp_nfdk_tx_maybe_close_block(tx_ring, 0, skb)) + if (nfp_nfdk_tx_maybe_close_block(tx_ring, skb)) goto err_free; /* DMA map all */ @@ -1328,7 +1343,9 @@ nfp_nfdk_ctrl_tx_one(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, txbuf++; dma_len -= 1; - dlen_type = FIELD_PREP(NFDK_DESC_TX_DMA_LEN_HEAD, dma_len) | + dlen_type = FIELD_PREP(NFDK_DESC_TX_DMA_LEN_HEAD, + dma_len > NFDK_DESC_TX_DMA_LEN_HEAD ? + NFDK_DESC_TX_DMA_LEN_HEAD : dma_len) | FIELD_PREP(NFDK_DESC_TX_TYPE_HEAD, type); txd->dma_len_type = cpu_to_le16(dlen_type); diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 186cb28c03bd..8b62ce21aff3 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1932,7 +1932,10 @@ static int efx_ef10_try_update_nic_stats_vf(struct efx_nic *efx) efx_update_sw_stats(efx, stats); out: + /* releasing a DMA coherent buffer with BH disabled can panic */ + spin_unlock_bh(&efx->stats_lock); efx_nic_free_buffer(efx, &stats_buf); + spin_lock_bh(&efx->stats_lock); return rc; } diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c index 7f5aa4a8c451..92550c7e85ce 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.c +++ b/drivers/net/ethernet/sfc/ef10_sriov.c @@ -408,8 +408,9 @@ fail1: static int efx_ef10_pci_sriov_disable(struct efx_nic *efx, bool force) { struct pci_dev *dev = efx->pci_dev; + struct efx_ef10_nic_data *nic_data = efx->nic_data; unsigned int vfs_assigned = pci_vfs_assigned(dev); - int rc = 0; + int i, rc = 0; if (vfs_assigned && !force) { netif_info(efx, drv, efx->net_dev, "VFs are assigned to guests; " @@ -417,10 +418,13 @@ static int efx_ef10_pci_sriov_disable(struct efx_nic *efx, bool force) return -EBUSY; } - if (!vfs_assigned) + if (!vfs_assigned) { + for (i = 0; i < efx->vf_count; i++) + nic_data->vf[i].pci_dev = NULL; pci_disable_sriov(dev); - else + } else { rc = -EBUSY; + } efx_ef10_sriov_free_vf_vswitching(efx); efx->vf_count = 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index bc91fd867dcd..358fc26f8d1f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -361,6 +361,7 @@ bypass_clk_reset_gpio: data->fix_mac_speed = tegra_eqos_fix_speed; data->init = tegra_eqos_init; data->bsp_priv = eqos; + data->sph_disable = 1; err = tegra_eqos_init(pdev, eqos); if (err < 0) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c index 9a6d819b84ae..378b4dd826bb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c @@ -273,7 +273,8 @@ static int ingenic_mac_probe(struct platform_device *pdev) mac->tx_delay = tx_delay_ps * 1000; } else { dev_err(&pdev->dev, "Invalid TX clock delay: %dps\n", tx_delay_ps); - return -EINVAL; + ret = -EINVAL; + goto err_remove_config_dt; } } @@ -283,7 +284,8 @@ static int ingenic_mac_probe(struct platform_device *pdev) mac->rx_delay = rx_delay_ps * 1000; } else { dev_err(&pdev->dev, "Invalid RX clock delay: %dps\n", rx_delay_ps); - return -EINVAL; + ret = -EINVAL; + goto err_remove_config_dt; } } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 38fe77d1035e..3fe720c5dc9f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -298,6 +298,11 @@ static void get_arttime(struct mii_bus *mii, int intel_adhoc_addr, *art_time = ns; } +static int stmmac_cross_ts_isr(struct stmmac_priv *priv) +{ + return (readl(priv->ioaddr + GMAC_INT_STATUS) & GMAC_INT_TSIE); +} + static int intel_crosststamp(ktime_t *device, struct system_counterval_t *system, void *ctx) @@ -313,8 +318,6 @@ static int intel_crosststamp(ktime_t *device, u32 num_snapshot; u32 gpio_value; u32 acr_value; - int ret; - u32 v; int i; if (!boot_cpu_has(X86_FEATURE_ART)) @@ -328,6 +331,8 @@ static int intel_crosststamp(ktime_t *device, if (priv->plat->ext_snapshot_en) return -EBUSY; + priv->plat->int_snapshot_en = 1; + mutex_lock(&priv->aux_ts_lock); /* Enable Internal snapshot trigger */ acr_value = readl(ptpaddr + PTP_ACR); @@ -347,6 +352,7 @@ static int intel_crosststamp(ktime_t *device, break; default: mutex_unlock(&priv->aux_ts_lock); + priv->plat->int_snapshot_en = 0; return -EINVAL; } writel(acr_value, ptpaddr + PTP_ACR); @@ -368,13 +374,12 @@ static int intel_crosststamp(ktime_t *device, gpio_value |= GMAC_GPO1; writel(gpio_value, ioaddr + GMAC_GPIO_STATUS); - /* Poll for time sync operation done */ - ret = readl_poll_timeout(priv->ioaddr + GMAC_INT_STATUS, v, - (v & GMAC_INT_TSIE), 100, 10000); - - if (ret == -ETIMEDOUT) { - pr_err("%s: Wait for time sync operation timeout\n", __func__); - return ret; + /* Time sync done Indication - Interrupt method */ + if (!wait_event_interruptible_timeout(priv->tstamp_busy_wait, + stmmac_cross_ts_isr(priv), + HZ / 100)) { + priv->plat->int_snapshot_en = 0; + return -ETIMEDOUT; } num_snapshot = (readl(ioaddr + GMAC_TIMESTAMP_STATUS) & @@ -392,6 +397,7 @@ static int intel_crosststamp(ktime_t *device, } system->cycles *= intel_priv->crossts_adj; + priv->plat->int_snapshot_en = 0; return 0; } @@ -576,6 +582,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->has_crossts = true; plat->crosststamp = intel_crosststamp; + plat->int_snapshot_en = 0; /* Setup MSI vector offset specific to Intel mGbE controller */ plat->msi_mac_vec = 29; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index 6ff88df58767..ca8ab290013c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -576,32 +576,7 @@ static int mediatek_dwmac_init(struct platform_device *pdev, void *priv) } } - ret = clk_bulk_prepare_enable(variant->num_clks, plat->clks); - if (ret) { - dev_err(plat->dev, "failed to enable clks, err = %d\n", ret); - return ret; - } - - ret = clk_prepare_enable(plat->rmii_internal_clk); - if (ret) { - dev_err(plat->dev, "failed to enable rmii internal clk, err = %d\n", ret); - goto err_clk; - } - return 0; - -err_clk: - clk_bulk_disable_unprepare(variant->num_clks, plat->clks); - return ret; -} - -static void mediatek_dwmac_exit(struct platform_device *pdev, void *priv) -{ - struct mediatek_dwmac_plat_data *plat = priv; - const struct mediatek_dwmac_variant *variant = plat->variant; - - clk_disable_unprepare(plat->rmii_internal_clk); - clk_bulk_disable_unprepare(variant->num_clks, plat->clks); } static int mediatek_dwmac_clks_config(void *priv, bool enabled) @@ -643,7 +618,6 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev, plat->addr64 = priv_plat->variant->dma_bit_mask; plat->bsp_priv = priv_plat; plat->init = mediatek_dwmac_init; - plat->exit = mediatek_dwmac_exit; plat->clks_config = mediatek_dwmac_clks_config; if (priv_plat->variant->dwmac_fix_mac_speed) plat->fix_mac_speed = priv_plat->variant->dwmac_fix_mac_speed; @@ -712,13 +686,32 @@ static int mediatek_dwmac_probe(struct platform_device *pdev) mediatek_dwmac_common_data(pdev, plat_dat, priv_plat); mediatek_dwmac_init(pdev, priv_plat); + ret = mediatek_dwmac_clks_config(priv_plat, true); + if (ret) + return ret; + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) { stmmac_remove_config_dt(pdev, plat_dat); - return ret; + goto err_drv_probe; } return 0; + +err_drv_probe: + mediatek_dwmac_clks_config(priv_plat, false); + return ret; +} + +static int mediatek_dwmac_remove(struct platform_device *pdev) +{ + struct mediatek_dwmac_plat_data *priv_plat = get_stmmac_bsp_priv(&pdev->dev); + int ret; + + ret = stmmac_pltfr_remove(pdev); + mediatek_dwmac_clks_config(priv_plat, false); + + return ret; } static const struct of_device_id mediatek_dwmac_match[] = { @@ -733,7 +726,7 @@ MODULE_DEVICE_TABLE(of, mediatek_dwmac_match); static struct platform_driver mediatek_dwmac_driver = { .probe = mediatek_dwmac_probe, - .remove = stmmac_pltfr_remove, + .remove = mediatek_dwmac_remove, .driver = { .name = "dwmac-mediatek", .pm = &stmmac_pltfr_pm_ops, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 462ca7ed095a..71dad409f78b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -150,7 +150,8 @@ #define GMAC_PCS_IRQ_DEFAULT (GMAC_INT_RGSMIIS | GMAC_INT_PCS_LINK | \ GMAC_INT_PCS_ANE) -#define GMAC_INT_DEFAULT_ENABLE (GMAC_INT_PMT_EN | GMAC_INT_LPI_EN) +#define GMAC_INT_DEFAULT_ENABLE (GMAC_INT_PMT_EN | GMAC_INT_LPI_EN | \ + GMAC_INT_TSIE) enum dwmac4_irq_status { time_stamp_irq = 0x00001000, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index fd41db65fe1d..d8f1fbc25bdd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -23,6 +23,7 @@ static void dwmac4_core_init(struct mac_device_info *hw, struct net_device *dev) { + struct stmmac_priv *priv = netdev_priv(dev); void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_CONFIG); @@ -58,6 +59,9 @@ static void dwmac4_core_init(struct mac_device_info *hw, value |= GMAC_INT_FPE_EN; writel(value, ioaddr + GMAC_INT_EN); + + if (GMAC_INT_DEFAULT_ENABLE & GMAC_INT_TSIE) + init_waitqueue_head(&priv->tstamp_busy_wait); } static void dwmac4_rx_queue_enable(struct mac_device_info *hw, @@ -219,6 +223,9 @@ static void dwmac4_map_mtl_dma(struct mac_device_info *hw, u32 queue, u32 chan) if (queue == 0 || queue == 4) { value &= ~MTL_RXQ_DMA_Q04MDMACH_MASK; value |= MTL_RXQ_DMA_Q04MDMACH(chan); + } else if (queue > 4) { + value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue - 4); + value |= MTL_RXQ_DMA_QXMDMACH(chan, queue - 4); } else { value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue); value |= MTL_RXQ_DMA_QXMDMACH(chan, queue); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 57970ae2178d..f9e83964aa7e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -266,6 +266,7 @@ struct stmmac_priv { rwlock_t ptp_lock; /* Protects auxiliary snapshot registers from concurrent access. */ struct mutex aux_ts_lock; + wait_queue_head_t tstamp_busy_wait; void __iomem *mmcaddr; void __iomem *ptpaddr; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index abfb3cd5958d..9c3055ee2608 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -803,14 +803,6 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, netdev_warn(priv->dev, "Setting EEE tx-lpi is not supported\n"); - if (priv->hw->xpcs) { - ret = xpcs_config_eee(priv->hw->xpcs, - priv->plat->mult_fact_100ns, - edata->eee_enabled); - if (ret) - return ret; - } - if (!edata->eee_enabled) stmmac_disable_eee_mode(priv); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 92d32940aff0..764832f4dae1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -179,6 +179,11 @@ static void timestamp_interrupt(struct stmmac_priv *priv) u64 ptp_time; int i; + if (priv->plat->int_snapshot_en) { + wake_up(&priv->tstamp_busy_wait); + return; + } + tsync_int = readl(priv->ioaddr + GMAC_INT_STATUS) & GMAC_INT_TSIE; if (!tsync_int) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d1a7cf4567bc..c5f33630e771 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -834,19 +834,10 @@ int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags) struct timespec64 now; u32 sec_inc = 0; u64 temp = 0; - int ret; if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) return -EOPNOTSUPP; - ret = clk_prepare_enable(priv->plat->clk_ptp_ref); - if (ret < 0) { - netdev_warn(priv->dev, - "failed to enable PTP reference clock: %pe\n", - ERR_PTR(ret)); - return ret; - } - stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags); priv->systime_flags = systime_flags; @@ -3270,6 +3261,14 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register) stmmac_mmc_setup(priv); + if (ptp_register) { + ret = clk_prepare_enable(priv->plat->clk_ptp_ref); + if (ret < 0) + netdev_warn(priv->dev, + "failed to enable PTP reference clock: %pe\n", + ERR_PTR(ret)); + } + ret = stmmac_init_ptp(priv); if (ret == -EOPNOTSUPP) netdev_info(priv->dev, "PTP not supported by HW\n"); @@ -7213,8 +7212,6 @@ int stmmac_dvr_remove(struct device *dev) netdev_info(priv->dev, "%s: removing driver", __func__); pm_runtime_get_sync(dev); - pm_runtime_disable(dev); - pm_runtime_put_noidle(dev); stmmac_stop_all_dma(priv); stmmac_mac_set(priv, priv->ioaddr, false); @@ -7241,6 +7238,9 @@ int stmmac_dvr_remove(struct device *dev) mutex_destroy(&priv->lock); bitmap_free(priv->af_xdp_zc_qps); + pm_runtime_disable(dev); + pm_runtime_put_noidle(dev); + return 0; } EXPORT_SYMBOL_GPL(stmmac_dvr_remove); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 11e1055e8260..9f5cac4000da 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -815,7 +815,13 @@ static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev) if (ret) return ret; - stmmac_init_tstamp_counter(priv, priv->systime_flags); + ret = clk_prepare_enable(priv->plat->clk_ptp_ref); + if (ret < 0) { + netdev_warn(priv->dev, + "failed to enable PTP reference clock: %pe\n", + ERR_PTR(ret)); + return ret; + } } return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index e45fb191d8e6..4d11980dcd64 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -175,11 +175,10 @@ static int stmmac_enable(struct ptp_clock_info *ptp, struct stmmac_priv *priv = container_of(ptp, struct stmmac_priv, ptp_clock_ops); void __iomem *ptpaddr = priv->ptpaddr; - void __iomem *ioaddr = priv->hw->pcsr; struct stmmac_pps_cfg *cfg; - u32 intr_value, acr_value; int ret = -EOPNOTSUPP; unsigned long flags; + u32 acr_value; switch (rq->type) { case PTP_CLK_REQ_PEROUT: @@ -213,19 +212,10 @@ static int stmmac_enable(struct ptp_clock_info *ptp, netdev_dbg(priv->dev, "Auxiliary Snapshot %d enabled.\n", priv->plat->ext_snapshot_num >> PTP_ACR_ATSEN_SHIFT); - /* Enable Timestamp Interrupt */ - intr_value = readl(ioaddr + GMAC_INT_EN); - intr_value |= GMAC_INT_TSIE; - writel(intr_value, ioaddr + GMAC_INT_EN); - } else { netdev_dbg(priv->dev, "Auxiliary Snapshot %d disabled.\n", priv->plat->ext_snapshot_num >> PTP_ACR_ATSEN_SHIFT); - /* Disable Timestamp Interrupt */ - intr_value = readl(ioaddr + GMAC_INT_EN); - intr_value &= ~GMAC_INT_TSIE; - writel(intr_value, ioaddr + GMAC_INT_EN); } writel(acr_value, ptpaddr + PTP_ACR); mutex_unlock(&priv->aux_ts_lock); diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 77e5dffb558f..8594ee839628 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -545,43 +545,24 @@ static int try_next_permutation(struct happy_meal *hp, void __iomem *tregs) static void display_link_mode(struct happy_meal *hp, void __iomem *tregs) { - printk(KERN_INFO "%s: Link is up using ", hp->dev->name); - if (hp->tcvr_type == external) - printk("external "); - else - printk("internal "); - printk("transceiver at "); hp->sw_lpa = happy_meal_tcvr_read(hp, tregs, MII_LPA); - if (hp->sw_lpa & (LPA_100HALF | LPA_100FULL)) { - if (hp->sw_lpa & LPA_100FULL) - printk("100Mb/s, Full Duplex.\n"); - else - printk("100Mb/s, Half Duplex.\n"); - } else { - if (hp->sw_lpa & LPA_10FULL) - printk("10Mb/s, Full Duplex.\n"); - else - printk("10Mb/s, Half Duplex.\n"); - } + + netdev_info(hp->dev, + "Link is up using %s transceiver at %dMb/s, %s Duplex.\n", + hp->tcvr_type == external ? "external" : "internal", + hp->sw_lpa & (LPA_100HALF | LPA_100FULL) ? 100 : 10, + hp->sw_lpa & (LPA_100FULL | LPA_10FULL) ? "Full" : "Half"); } static void display_forced_link_mode(struct happy_meal *hp, void __iomem *tregs) { - printk(KERN_INFO "%s: Link has been forced up using ", hp->dev->name); - if (hp->tcvr_type == external) - printk("external "); - else - printk("internal "); - printk("transceiver at "); hp->sw_bmcr = happy_meal_tcvr_read(hp, tregs, MII_BMCR); - if (hp->sw_bmcr & BMCR_SPEED100) - printk("100Mb/s, "); - else - printk("10Mb/s, "); - if (hp->sw_bmcr & BMCR_FULLDPLX) - printk("Full Duplex.\n"); - else - printk("Half Duplex.\n"); + + netdev_info(hp->dev, + "Link has been forced up using %s transceiver at %dMb/s, %s Duplex.\n", + hp->tcvr_type == external ? "external" : "internal", + hp->sw_bmcr & BMCR_SPEED100 ? 100 : 10, + hp->sw_bmcr & BMCR_FULLDPLX ? "Full" : "Half"); } static int set_happy_link_modes(struct happy_meal *hp, void __iomem *tregs) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index fb92d4c1547d..f4a6b590a1e3 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2467,7 +2467,6 @@ static int am65_cpsw_nuss_register_devlink(struct am65_cpsw_common *common) port->port_id, ret); goto dl_port_unreg; } - devlink_port_type_eth_set(dl_port, port->ndev); } devlink_register(common->devlink); return ret; @@ -2511,6 +2510,7 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common) static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) { struct device *dev = common->dev; + struct devlink_port *dl_port; struct am65_cpsw_port *port; int ret = 0, i; @@ -2527,6 +2527,10 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) return ret; } + ret = am65_cpsw_nuss_register_devlink(common); + if (ret) + return ret; + for (i = 0; i < common->port_num; i++) { port = &common->ports[i]; @@ -2539,25 +2543,24 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) i, ret); goto err_cleanup_ndev; } + + dl_port = &port->devlink_port; + devlink_port_type_eth_set(dl_port, port->ndev); } ret = am65_cpsw_register_notifiers(common); if (ret) goto err_cleanup_ndev; - ret = am65_cpsw_nuss_register_devlink(common); - if (ret) - goto clean_unregister_notifiers; - /* can't auto unregister ndev using devm_add_action() due to * devres release sequence in DD core for DMA */ return 0; -clean_unregister_notifiers: - am65_cpsw_unregister_notifiers(common); + err_cleanup_ndev: am65_cpsw_nuss_cleanup_ndev(common); + am65_cpsw_unregister_devlink(common); return ret; } diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 7389d6ef8569..0f6efaabaa32 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -32,7 +32,7 @@ #define NETNEXT_VERSION "12" /* Information for net */ -#define NET_VERSION "12" +#define NET_VERSION "13" #define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>" @@ -2156,7 +2156,7 @@ static inline void rtl_rx_vlan_tag(struct rx_desc *desc, struct sk_buff *skb) } static int r8152_tx_csum(struct r8152 *tp, struct tx_desc *desc, - struct sk_buff *skb, u32 len, u32 transport_offset) + struct sk_buff *skb, u32 len) { u32 mss = skb_shinfo(skb)->gso_size; u32 opts1, opts2 = 0; @@ -2167,6 +2167,8 @@ static int r8152_tx_csum(struct r8152 *tp, struct tx_desc *desc, opts1 = len | TX_FS | TX_LS; if (mss) { + u32 transport_offset = (u32)skb_transport_offset(skb); + if (transport_offset > GTTCPHO_MAX) { netif_warn(tp, tx_err, tp->netdev, "Invalid transport offset 0x%x for TSO\n", @@ -2197,6 +2199,7 @@ static int r8152_tx_csum(struct r8152 *tp, struct tx_desc *desc, opts1 |= transport_offset << GTTCPHO_SHIFT; opts2 |= min(mss, MSS_MAX) << MSS_SHIFT; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + u32 transport_offset = (u32)skb_transport_offset(skb); u8 ip_protocol; if (transport_offset > TCPHO_MAX) { @@ -2260,7 +2263,6 @@ static int r8152_tx_agg_fill(struct r8152 *tp, struct tx_agg *agg) struct tx_desc *tx_desc; struct sk_buff *skb; unsigned int len; - u32 offset; skb = __skb_dequeue(&skb_head); if (!skb) @@ -2276,9 +2278,7 @@ static int r8152_tx_agg_fill(struct r8152 *tp, struct tx_agg *agg) tx_data = tx_agg_align(tx_data); tx_desc = (struct tx_desc *)tx_data; - offset = (u32)skb_transport_offset(skb); - - if (r8152_tx_csum(tp, tx_desc, skb, skb->len, offset)) { + if (r8152_tx_csum(tp, tx_desc, skb, skb->len)) { r8152_csum_workaround(tp, skb, &skb_head); continue; } @@ -2759,9 +2759,9 @@ rtl8152_features_check(struct sk_buff *skb, struct net_device *dev, { u32 mss = skb_shinfo(skb)->gso_size; int max_offset = mss ? GTTCPHO_MAX : TCPHO_MAX; - int offset = skb_transport_offset(skb); - if ((mss || skb->ip_summed == CHECKSUM_PARTIAL) && offset > max_offset) + if ((mss || skb->ip_summed == CHECKSUM_PARTIAL) && + skb_transport_offset(skb) > max_offset) features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); else if ((skb->len + sizeof(struct tx_desc)) > agg_buf_sz) features &= ~NETIF_F_GSO_MASK; @@ -5917,7 +5917,8 @@ static void r8153_enter_oob(struct r8152 *tp) wait_oob_link_list_ready(tp); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, mtu_to_size(tp->netdev->mtu)); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, 1522); + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_MTPS, MTPS_DEFAULT); switch (tp->version) { case RTL_VER_03: @@ -5953,6 +5954,10 @@ static void r8153_enter_oob(struct r8152 *tp) ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB; ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data); + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_SFF_STS_7); + ocp_data |= MCU_BORW_EN; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_SFF_STS_7, ocp_data); + rxdy_gated_en(tp, false); ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR); @@ -6555,6 +6560,9 @@ static void rtl8156_down(struct r8152 *tp) rtl_disable(tp); rtl_reset_bmu(tp); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, 1522); + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_MTPS, MTPS_DEFAULT); + /* Clear teredo wake event. bit[15:8] is the teredo wakeup * type. Set it to zero. bits[7:0] are the W1C bits about * the events. Set them to all 1 to clear them. @@ -6565,6 +6573,10 @@ static void rtl8156_down(struct r8152 *tp) ocp_data |= NOW_IS_OOB; ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data); + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_SFF_STS_7); + ocp_data |= MCU_BORW_EN; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_SFF_STS_7, ocp_data); + rtl_rx_vlan_en(tp, true); rxdy_gated_en(tp, false); diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index 84d1c7054013..7b1dc19c565e 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -3822,7 +3822,8 @@ ath11k_wmi_obss_color_collision_event(struct ath11k_base *ab, struct sk_buff *sk switch (ev->evt_type) { case WMI_BSS_COLOR_COLLISION_DETECTION: - ieeee80211_obss_color_collision_notify(arvif->vif, ev->obss_color_bitmap); + ieeee80211_obss_color_collision_notify(arvif->vif, ev->obss_color_bitmap, + GFP_KERNEL); ath11k_dbg(ab, ATH11K_DBG_WMI, "OBSS color collision detected vdev:%d, event:%d, bitmap:%08llx\n", ev->vdev_id, ev->evt_type, ev->obss_color_bitmap); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 2f746eb64507..6f83af849f2e 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -4912,6 +4912,8 @@ static int hwsim_virtio_probe(struct virtio_device *vdev) if (err) return err; + virtio_device_ready(vdev); + err = fill_vq(hwsim_vqs[HWSIM_VQ_RX]); if (err) goto out_remove; diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h index c02be4ac159e..7db627fc26be 100644 --- a/drivers/net/wireless/realtek/rtw88/main.h +++ b/drivers/net/wireless/realtek/rtw88/main.h @@ -1233,9 +1233,6 @@ struct rtw_chip_info { const struct wiphy_wowlan_support *wowlan_stub; const u8 max_sched_scan_ssids; - /* for 8821c set channel */ - u32 ch_param[3]; - /* coex paras */ u32 coex_para_ver; u8 bt_desired_ver; @@ -1937,6 +1934,9 @@ struct rtw_hal { enum rtw_sar_bands sar_band; struct rtw_sar sar; + + /* for 8821c set channel */ + u32 ch_param[3]; }; struct rtw_path_div { diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c index ffee39ea5df6..488a7ddd507c 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c @@ -125,6 +125,7 @@ static void rtw8821c_phy_bf_init(struct rtw_dev *rtwdev) static void rtw8821c_phy_set_param(struct rtw_dev *rtwdev) { + struct rtw_hal *hal = &rtwdev->hal; u8 crystal_cap, val; /* power on BB/RF domain */ @@ -159,9 +160,9 @@ static void rtw8821c_phy_set_param(struct rtw_dev *rtwdev) /* post init after header files config */ rtw_write32_set(rtwdev, REG_RXPSEL, BIT_RX_PSEL_RST); - rtwdev->chip->ch_param[0] = rtw_read32_mask(rtwdev, REG_TXSF2, MASKDWORD); - rtwdev->chip->ch_param[1] = rtw_read32_mask(rtwdev, REG_TXSF6, MASKDWORD); - rtwdev->chip->ch_param[2] = rtw_read32_mask(rtwdev, REG_TXFILTER, MASKDWORD); + hal->ch_param[0] = rtw_read32_mask(rtwdev, REG_TXSF2, MASKDWORD); + hal->ch_param[1] = rtw_read32_mask(rtwdev, REG_TXSF6, MASKDWORD); + hal->ch_param[2] = rtw_read32_mask(rtwdev, REG_TXFILTER, MASKDWORD); rtw_phy_init(rtwdev); rtwdev->dm_info.cck_pd_default = rtw_read8(rtwdev, REG_CSRATIO) & 0x1f; @@ -351,6 +352,7 @@ static void rtw8821c_set_channel_rxdfir(struct rtw_dev *rtwdev, u8 bw) static void rtw8821c_set_channel_bb(struct rtw_dev *rtwdev, u8 channel, u8 bw, u8 primary_ch_idx) { + struct rtw_hal *hal = &rtwdev->hal; u32 val32; if (channel <= 14) { @@ -367,11 +369,11 @@ static void rtw8821c_set_channel_bb(struct rtw_dev *rtwdev, u8 channel, u8 bw, rtw_write32_mask(rtwdev, REG_TXFILTER, MASKDWORD, 0x00003667); } else { rtw_write32_mask(rtwdev, REG_TXSF2, MASKDWORD, - rtwdev->chip->ch_param[0]); + hal->ch_param[0]); rtw_write32_mask(rtwdev, REG_TXSF6, MASKLWORD, - rtwdev->chip->ch_param[1] & MASKLWORD); + hal->ch_param[1] & MASKLWORD); rtw_write32_mask(rtwdev, REG_TXFILTER, MASKDWORD, - rtwdev->chip->ch_param[2]); + hal->ch_param[2]); } } else if (channel > 35) { rtw_write32_mask(rtwdev, REG_ENTXCCK, BIT(18), 0x1); diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c index dbac4c03d21a..a0335407be42 100644 --- a/drivers/net/xen-netback/rx.c +++ b/drivers/net/xen-netback/rx.c @@ -495,6 +495,7 @@ void xenvif_rx_action(struct xenvif_queue *queue) queue->rx_copy.completed = &completed_skbs; while (xenvif_rx_ring_slots_available(queue) && + !skb_queue_empty(&queue->rx_queue) && work_done < RX_BATCH_SIZE) { xenvif_rx_skb(queue); work_done++; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ec6ac298d8de..6a12a906a11e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3786,7 +3786,7 @@ static int nvme_add_ns_cdev(struct nvme_ns *ns) } static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, - unsigned nsid, struct nvme_ns_ids *ids) + unsigned nsid, struct nvme_ns_ids *ids, bool is_shared) { struct nvme_ns_head *head; size_t size = sizeof(*head); @@ -3810,6 +3810,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, head->subsys = ctrl->subsys; head->ns_id = nsid; head->ids = *ids; + head->shared = is_shared; kref_init(&head->ref); if (head->ids.csi) { @@ -3891,12 +3892,11 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid, nsid); goto out_unlock; } - head = nvme_alloc_ns_head(ctrl, nsid, ids); + head = nvme_alloc_ns_head(ctrl, nsid, ids, is_shared); if (IS_ERR(head)) { ret = PTR_ERR(head); goto out_unlock; } - head->shared = is_shared; } else { ret = -EINVAL; if (!is_shared || !head->shared) { diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 193b44755662..58c72d55769a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2690,8 +2690,13 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) struct pci_dev *pdev = to_pci_dev(dev->dev); mutex_lock(&dev->shutdown_lock); - if (pci_device_is_present(pdev) && pci_is_enabled(pdev)) { - u32 csts = readl(dev->bar + NVME_REG_CSTS); + if (pci_is_enabled(pdev)) { + u32 csts; + + if (pci_device_is_present(pdev)) + csts = readl(dev->bar + NVME_REG_CSTS); + else + csts = ~0; if (dev->ctrl.state == NVME_CTRL_LIVE || dev->ctrl.state == NVME_CTRL_RESETTING) { diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index f52960d2dfbe..bff144c97e66 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -32,7 +32,7 @@ config DEBUG_PINCTRL Say Y here to add some extra checks and diagnostics to PINCTRL calls. config PINCTRL_AMD - tristate "AMD GPIO pin control" + bool "AMD GPIO pin control" depends on HAS_IOMEM depends on ACPI || COMPILE_TEST select GPIOLIB diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c index a140b6bfbfaa..bcde042d29dc 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c @@ -102,7 +102,7 @@ struct armada_37xx_pinctrl { struct device *dev; struct gpio_chip gpio_chip; struct irq_chip irq_chip; - spinlock_t irq_lock; + raw_spinlock_t irq_lock; struct pinctrl_desc pctl; struct pinctrl_dev *pctl_dev; struct armada_37xx_pin_group *groups; @@ -523,9 +523,9 @@ static void armada_37xx_irq_ack(struct irq_data *d) unsigned long flags; armada_37xx_irq_update_reg(®, d); - spin_lock_irqsave(&info->irq_lock, flags); + raw_spin_lock_irqsave(&info->irq_lock, flags); writel(d->mask, info->base + reg); - spin_unlock_irqrestore(&info->irq_lock, flags); + raw_spin_unlock_irqrestore(&info->irq_lock, flags); } static void armada_37xx_irq_mask(struct irq_data *d) @@ -536,10 +536,10 @@ static void armada_37xx_irq_mask(struct irq_data *d) unsigned long flags; armada_37xx_irq_update_reg(®, d); - spin_lock_irqsave(&info->irq_lock, flags); + raw_spin_lock_irqsave(&info->irq_lock, flags); val = readl(info->base + reg); writel(val & ~d->mask, info->base + reg); - spin_unlock_irqrestore(&info->irq_lock, flags); + raw_spin_unlock_irqrestore(&info->irq_lock, flags); } static void armada_37xx_irq_unmask(struct irq_data *d) @@ -550,10 +550,10 @@ static void armada_37xx_irq_unmask(struct irq_data *d) unsigned long flags; armada_37xx_irq_update_reg(®, d); - spin_lock_irqsave(&info->irq_lock, flags); + raw_spin_lock_irqsave(&info->irq_lock, flags); val = readl(info->base + reg); writel(val | d->mask, info->base + reg); - spin_unlock_irqrestore(&info->irq_lock, flags); + raw_spin_unlock_irqrestore(&info->irq_lock, flags); } static int armada_37xx_irq_set_wake(struct irq_data *d, unsigned int on) @@ -564,14 +564,14 @@ static int armada_37xx_irq_set_wake(struct irq_data *d, unsigned int on) unsigned long flags; armada_37xx_irq_update_reg(®, d); - spin_lock_irqsave(&info->irq_lock, flags); + raw_spin_lock_irqsave(&info->irq_lock, flags); val = readl(info->base + reg); if (on) val |= (BIT(d->hwirq % GPIO_PER_REG)); else val &= ~(BIT(d->hwirq % GPIO_PER_REG)); writel(val, info->base + reg); - spin_unlock_irqrestore(&info->irq_lock, flags); + raw_spin_unlock_irqrestore(&info->irq_lock, flags); return 0; } @@ -583,7 +583,7 @@ static int armada_37xx_irq_set_type(struct irq_data *d, unsigned int type) u32 val, reg = IRQ_POL; unsigned long flags; - spin_lock_irqsave(&info->irq_lock, flags); + raw_spin_lock_irqsave(&info->irq_lock, flags); armada_37xx_irq_update_reg(®, d); val = readl(info->base + reg); switch (type) { @@ -607,11 +607,11 @@ static int armada_37xx_irq_set_type(struct irq_data *d, unsigned int type) break; } default: - spin_unlock_irqrestore(&info->irq_lock, flags); + raw_spin_unlock_irqrestore(&info->irq_lock, flags); return -EINVAL; } writel(val, info->base + reg); - spin_unlock_irqrestore(&info->irq_lock, flags); + raw_spin_unlock_irqrestore(&info->irq_lock, flags); return 0; } @@ -626,7 +626,7 @@ static int armada_37xx_edge_both_irq_swap_pol(struct armada_37xx_pinctrl *info, regmap_read(info->regmap, INPUT_VAL + 4*reg_idx, &l); - spin_lock_irqsave(&info->irq_lock, flags); + raw_spin_lock_irqsave(&info->irq_lock, flags); p = readl(info->base + IRQ_POL + 4 * reg_idx); if ((p ^ l) & (1 << bit_num)) { /* @@ -647,7 +647,7 @@ static int armada_37xx_edge_both_irq_swap_pol(struct armada_37xx_pinctrl *info, ret = -1; } - spin_unlock_irqrestore(&info->irq_lock, flags); + raw_spin_unlock_irqrestore(&info->irq_lock, flags); return ret; } @@ -664,11 +664,11 @@ static void armada_37xx_irq_handler(struct irq_desc *desc) u32 status; unsigned long flags; - spin_lock_irqsave(&info->irq_lock, flags); + raw_spin_lock_irqsave(&info->irq_lock, flags); status = readl_relaxed(info->base + IRQ_STATUS + 4 * i); /* Manage only the interrupt that was enabled */ status &= readl_relaxed(info->base + IRQ_EN + 4 * i); - spin_unlock_irqrestore(&info->irq_lock, flags); + raw_spin_unlock_irqrestore(&info->irq_lock, flags); while (status) { u32 hwirq = ffs(status) - 1; u32 virq = irq_find_mapping(d, hwirq + @@ -695,12 +695,12 @@ static void armada_37xx_irq_handler(struct irq_desc *desc) update_status: /* Update status in case a new IRQ appears */ - spin_lock_irqsave(&info->irq_lock, flags); + raw_spin_lock_irqsave(&info->irq_lock, flags); status = readl_relaxed(info->base + IRQ_STATUS + 4 * i); /* Manage only the interrupt that was enabled */ status &= readl_relaxed(info->base + IRQ_EN + 4 * i); - spin_unlock_irqrestore(&info->irq_lock, flags); + raw_spin_unlock_irqrestore(&info->irq_lock, flags); } } chained_irq_exit(chip, desc); @@ -731,7 +731,7 @@ static int armada_37xx_irqchip_register(struct platform_device *pdev, struct device *dev = &pdev->dev; unsigned int i, nr_irq_parent; - spin_lock_init(&info->irq_lock); + raw_spin_lock_init(&info->irq_lock); nr_irq_parent = of_irq_count(np); if (!nr_irq_parent) { @@ -1107,25 +1107,40 @@ static const struct of_device_id armada_37xx_pinctrl_of_match[] = { { }, }; +static const struct regmap_config armada_37xx_pinctrl_regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, + .use_raw_spinlock = true, +}; + static int __init armada_37xx_pinctrl_probe(struct platform_device *pdev) { struct armada_37xx_pinctrl *info; struct device *dev = &pdev->dev; - struct device_node *np = dev->of_node; struct regmap *regmap; + void __iomem *base; int ret; + base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); + if (IS_ERR(base)) { + dev_err(dev, "failed to ioremap base address: %pe\n", base); + return PTR_ERR(base); + } + + regmap = devm_regmap_init_mmio(dev, base, + &armada_37xx_pinctrl_regmap_config); + if (IS_ERR(regmap)) { + dev_err(dev, "failed to create regmap: %pe\n", regmap); + return PTR_ERR(regmap); + } + info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; info->dev = dev; - - regmap = syscon_node_to_regmap(np); - if (IS_ERR(regmap)) - return dev_err_probe(dev, PTR_ERR(regmap), "cannot get regmap\n"); info->regmap = regmap; - info->data = of_device_get_match_data(dev); ret = armada_37xx_pinctrl_register(pdev, info); diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c index 5f4a8c5c6650..dfc8ea9f3843 100644 --- a/drivers/pinctrl/pinctrl-ocelot.c +++ b/drivers/pinctrl/pinctrl-ocelot.c @@ -29,19 +29,12 @@ #define ocelot_clrsetbits(addr, clear, set) \ writel((readl(addr) & ~(clear)) | (set), (addr)) -/* PINCONFIG bits (sparx5 only) */ enum { PINCONF_BIAS, PINCONF_SCHMITT, PINCONF_DRIVE_STRENGTH, }; -#define BIAS_PD_BIT BIT(4) -#define BIAS_PU_BIT BIT(3) -#define BIAS_BITS (BIAS_PD_BIT|BIAS_PU_BIT) -#define SCHMITT_BIT BIT(2) -#define DRIVE_BITS GENMASK(1, 0) - /* GPIO standard registers */ #define OCELOT_GPIO_OUT_SET 0x0 #define OCELOT_GPIO_OUT_CLR 0x4 @@ -321,6 +314,13 @@ struct ocelot_pin_caps { unsigned char a_functions[OCELOT_FUNC_PER_PIN]; /* Additional functions */ }; +struct ocelot_pincfg_data { + u8 pd_bit; + u8 pu_bit; + u8 drive_bits; + u8 schmitt_bit; +}; + struct ocelot_pinctrl { struct device *dev; struct pinctrl_dev *pctl; @@ -328,10 +328,16 @@ struct ocelot_pinctrl { struct regmap *map; struct regmap *pincfg; struct pinctrl_desc *desc; + const struct ocelot_pincfg_data *pincfg_data; struct ocelot_pmx_func func[FUNC_MAX]; u8 stride; }; +struct ocelot_match_data { + struct pinctrl_desc desc; + struct ocelot_pincfg_data pincfg_data; +}; + #define LUTON_P(p, f0, f1) \ static struct ocelot_pin_caps luton_pin_##p = { \ .pin = p, \ @@ -1325,24 +1331,27 @@ static int ocelot_hw_get_value(struct ocelot_pinctrl *info, int ret = -EOPNOTSUPP; if (info->pincfg) { + const struct ocelot_pincfg_data *opd = info->pincfg_data; u32 regcfg; - ret = regmap_read(info->pincfg, pin, ®cfg); + ret = regmap_read(info->pincfg, + pin * regmap_get_reg_stride(info->pincfg), + ®cfg); if (ret) return ret; ret = 0; switch (reg) { case PINCONF_BIAS: - *val = regcfg & BIAS_BITS; + *val = regcfg & (opd->pd_bit | opd->pu_bit); break; case PINCONF_SCHMITT: - *val = regcfg & SCHMITT_BIT; + *val = regcfg & opd->schmitt_bit; break; case PINCONF_DRIVE_STRENGTH: - *val = regcfg & DRIVE_BITS; + *val = regcfg & opd->drive_bits; break; default: @@ -1359,14 +1368,18 @@ static int ocelot_pincfg_clrsetbits(struct ocelot_pinctrl *info, u32 regaddr, u32 val; int ret; - ret = regmap_read(info->pincfg, regaddr, &val); + ret = regmap_read(info->pincfg, + regaddr * regmap_get_reg_stride(info->pincfg), + &val); if (ret) return ret; val &= ~clrbits; val |= setbits; - ret = regmap_write(info->pincfg, regaddr, val); + ret = regmap_write(info->pincfg, + regaddr * regmap_get_reg_stride(info->pincfg), + val); return ret; } @@ -1379,23 +1392,27 @@ static int ocelot_hw_set_value(struct ocelot_pinctrl *info, int ret = -EOPNOTSUPP; if (info->pincfg) { + const struct ocelot_pincfg_data *opd = info->pincfg_data; ret = 0; switch (reg) { case PINCONF_BIAS: - ret = ocelot_pincfg_clrsetbits(info, pin, BIAS_BITS, + ret = ocelot_pincfg_clrsetbits(info, pin, + opd->pd_bit | opd->pu_bit, val); break; case PINCONF_SCHMITT: - ret = ocelot_pincfg_clrsetbits(info, pin, SCHMITT_BIT, + ret = ocelot_pincfg_clrsetbits(info, pin, + opd->schmitt_bit, val); break; case PINCONF_DRIVE_STRENGTH: if (val <= 3) ret = ocelot_pincfg_clrsetbits(info, pin, - DRIVE_BITS, val); + opd->drive_bits, + val); else ret = -EINVAL; break; @@ -1425,17 +1442,20 @@ static int ocelot_pinconf_get(struct pinctrl_dev *pctldev, if (param == PIN_CONFIG_BIAS_DISABLE) val = (val == 0); else if (param == PIN_CONFIG_BIAS_PULL_DOWN) - val = (val & BIAS_PD_BIT ? true : false); + val = !!(val & info->pincfg_data->pd_bit); else /* PIN_CONFIG_BIAS_PULL_UP */ - val = (val & BIAS_PU_BIT ? true : false); + val = !!(val & info->pincfg_data->pu_bit); break; case PIN_CONFIG_INPUT_SCHMITT_ENABLE: + if (!info->pincfg_data->schmitt_bit) + return -EOPNOTSUPP; + err = ocelot_hw_get_value(info, pin, PINCONF_SCHMITT, &val); if (err) return err; - val = (val & SCHMITT_BIT ? true : false); + val = !!(val & info->pincfg_data->schmitt_bit); break; case PIN_CONFIG_DRIVE_STRENGTH: @@ -1479,6 +1499,7 @@ static int ocelot_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, unsigned long *configs, unsigned int num_configs) { struct ocelot_pinctrl *info = pinctrl_dev_get_drvdata(pctldev); + const struct ocelot_pincfg_data *opd = info->pincfg_data; u32 param, arg, p; int cfg, err = 0; @@ -1491,8 +1512,8 @@ static int ocelot_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, case PIN_CONFIG_BIAS_PULL_UP: case PIN_CONFIG_BIAS_PULL_DOWN: arg = (param == PIN_CONFIG_BIAS_DISABLE) ? 0 : - (param == PIN_CONFIG_BIAS_PULL_UP) ? BIAS_PU_BIT : - BIAS_PD_BIT; + (param == PIN_CONFIG_BIAS_PULL_UP) ? + opd->pu_bit : opd->pd_bit; err = ocelot_hw_set_value(info, pin, PINCONF_BIAS, arg); if (err) @@ -1501,7 +1522,10 @@ static int ocelot_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, break; case PIN_CONFIG_INPUT_SCHMITT_ENABLE: - arg = arg ? SCHMITT_BIT : 0; + if (!opd->schmitt_bit) + return -EOPNOTSUPP; + + arg = arg ? opd->schmitt_bit : 0; err = ocelot_hw_set_value(info, pin, PINCONF_SCHMITT, arg); if (err) @@ -1562,69 +1586,94 @@ static const struct pinctrl_ops ocelot_pctl_ops = { .dt_free_map = pinconf_generic_dt_free_map, }; -static struct pinctrl_desc luton_desc = { - .name = "luton-pinctrl", - .pins = luton_pins, - .npins = ARRAY_SIZE(luton_pins), - .pctlops = &ocelot_pctl_ops, - .pmxops = &ocelot_pmx_ops, - .owner = THIS_MODULE, +static struct ocelot_match_data luton_desc = { + .desc = { + .name = "luton-pinctrl", + .pins = luton_pins, + .npins = ARRAY_SIZE(luton_pins), + .pctlops = &ocelot_pctl_ops, + .pmxops = &ocelot_pmx_ops, + .owner = THIS_MODULE, + }, }; -static struct pinctrl_desc serval_desc = { - .name = "serval-pinctrl", - .pins = serval_pins, - .npins = ARRAY_SIZE(serval_pins), - .pctlops = &ocelot_pctl_ops, - .pmxops = &ocelot_pmx_ops, - .owner = THIS_MODULE, +static struct ocelot_match_data serval_desc = { + .desc = { + .name = "serval-pinctrl", + .pins = serval_pins, + .npins = ARRAY_SIZE(serval_pins), + .pctlops = &ocelot_pctl_ops, + .pmxops = &ocelot_pmx_ops, + .owner = THIS_MODULE, + }, }; -static struct pinctrl_desc ocelot_desc = { - .name = "ocelot-pinctrl", - .pins = ocelot_pins, - .npins = ARRAY_SIZE(ocelot_pins), - .pctlops = &ocelot_pctl_ops, - .pmxops = &ocelot_pmx_ops, - .owner = THIS_MODULE, +static struct ocelot_match_data ocelot_desc = { + .desc = { + .name = "ocelot-pinctrl", + .pins = ocelot_pins, + .npins = ARRAY_SIZE(ocelot_pins), + .pctlops = &ocelot_pctl_ops, + .pmxops = &ocelot_pmx_ops, + .owner = THIS_MODULE, + }, }; -static struct pinctrl_desc jaguar2_desc = { - .name = "jaguar2-pinctrl", - .pins = jaguar2_pins, - .npins = ARRAY_SIZE(jaguar2_pins), - .pctlops = &ocelot_pctl_ops, - .pmxops = &ocelot_pmx_ops, - .owner = THIS_MODULE, +static struct ocelot_match_data jaguar2_desc = { + .desc = { + .name = "jaguar2-pinctrl", + .pins = jaguar2_pins, + .npins = ARRAY_SIZE(jaguar2_pins), + .pctlops = &ocelot_pctl_ops, + .pmxops = &ocelot_pmx_ops, + .owner = THIS_MODULE, + }, }; -static struct pinctrl_desc servalt_desc = { - .name = "servalt-pinctrl", - .pins = servalt_pins, - .npins = ARRAY_SIZE(servalt_pins), - .pctlops = &ocelot_pctl_ops, - .pmxops = &ocelot_pmx_ops, - .owner = THIS_MODULE, +static struct ocelot_match_data servalt_desc = { + .desc = { + .name = "servalt-pinctrl", + .pins = servalt_pins, + .npins = ARRAY_SIZE(servalt_pins), + .pctlops = &ocelot_pctl_ops, + .pmxops = &ocelot_pmx_ops, + .owner = THIS_MODULE, + }, }; -static struct pinctrl_desc sparx5_desc = { - .name = "sparx5-pinctrl", - .pins = sparx5_pins, - .npins = ARRAY_SIZE(sparx5_pins), - .pctlops = &ocelot_pctl_ops, - .pmxops = &ocelot_pmx_ops, - .confops = &ocelot_confops, - .owner = THIS_MODULE, +static struct ocelot_match_data sparx5_desc = { + .desc = { + .name = "sparx5-pinctrl", + .pins = sparx5_pins, + .npins = ARRAY_SIZE(sparx5_pins), + .pctlops = &ocelot_pctl_ops, + .pmxops = &ocelot_pmx_ops, + .confops = &ocelot_confops, + .owner = THIS_MODULE, + }, + .pincfg_data = { + .pd_bit = BIT(4), + .pu_bit = BIT(3), + .drive_bits = GENMASK(1, 0), + .schmitt_bit = BIT(2), + }, }; -static struct pinctrl_desc lan966x_desc = { - .name = "lan966x-pinctrl", - .pins = lan966x_pins, - .npins = ARRAY_SIZE(lan966x_pins), - .pctlops = &ocelot_pctl_ops, - .pmxops = &lan966x_pmx_ops, - .confops = &ocelot_confops, - .owner = THIS_MODULE, +static struct ocelot_match_data lan966x_desc = { + .desc = { + .name = "lan966x-pinctrl", + .pins = lan966x_pins, + .npins = ARRAY_SIZE(lan966x_pins), + .pctlops = &ocelot_pctl_ops, + .pmxops = &lan966x_pmx_ops, + .confops = &ocelot_confops, + .owner = THIS_MODULE, + }, + .pincfg_data = { + .pd_bit = BIT(3), + .pu_bit = BIT(2), + .drive_bits = GENMASK(1, 0), + }, }; static int ocelot_create_group_func_map(struct device *dev, @@ -1890,7 +1939,8 @@ static const struct of_device_id ocelot_pinctrl_of_match[] = { {}, }; -static struct regmap *ocelot_pinctrl_create_pincfg(struct platform_device *pdev) +static struct regmap *ocelot_pinctrl_create_pincfg(struct platform_device *pdev, + const struct ocelot_pinctrl *info) { void __iomem *base; @@ -1898,7 +1948,7 @@ static struct regmap *ocelot_pinctrl_create_pincfg(struct platform_device *pdev) .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = 32, + .max_register = info->desc->npins * 4, .name = "pincfg", }; @@ -1913,6 +1963,7 @@ static struct regmap *ocelot_pinctrl_create_pincfg(struct platform_device *pdev) static int ocelot_pinctrl_probe(struct platform_device *pdev) { + const struct ocelot_match_data *data; struct device *dev = &pdev->dev; struct ocelot_pinctrl *info; struct reset_control *reset; @@ -1929,7 +1980,16 @@ static int ocelot_pinctrl_probe(struct platform_device *pdev) if (!info) return -ENOMEM; - info->desc = (struct pinctrl_desc *)device_get_match_data(dev); + data = device_get_match_data(dev); + if (!data) + return -EINVAL; + + info->desc = devm_kmemdup(dev, &data->desc, sizeof(*info->desc), + GFP_KERNEL); + if (!info->desc) + return -ENOMEM; + + info->pincfg_data = &data->pincfg_data; reset = devm_reset_control_get_optional_shared(dev, "switch"); if (IS_ERR(reset)) @@ -1956,7 +2016,7 @@ static int ocelot_pinctrl_probe(struct platform_device *pdev) /* Pinconf registers */ if (info->desc->confops) { - pincfg = ocelot_pinctrl_create_pincfg(pdev); + pincfg = ocelot_pinctrl_create_pincfg(pdev, info); if (IS_ERR(pincfg)) dev_dbg(dev, "Failed to create pincfg regmap\n"); else diff --git a/drivers/pinctrl/ralink/pinctrl-ralink.c b/drivers/pinctrl/ralink/pinctrl-ralink.c index 63429a287434..770862f45b3f 100644 --- a/drivers/pinctrl/ralink/pinctrl-ralink.c +++ b/drivers/pinctrl/ralink/pinctrl-ralink.c @@ -266,6 +266,8 @@ static int ralink_pinctrl_pins(struct ralink_priv *p) p->func[i]->pin_count, sizeof(int), GFP_KERNEL); + if (!p->func[i]->pins) + return -ENOMEM; for (j = 0; j < p->func[i]->pin_count; j++) p->func[i]->pins[j] = p->func[i]->pin_first + j; diff --git a/drivers/pinctrl/sunplus/sppctl.c b/drivers/pinctrl/sunplus/sppctl.c index 3ba47040ac42..2b3335ab56c6 100644 --- a/drivers/pinctrl/sunplus/sppctl.c +++ b/drivers/pinctrl/sunplus/sppctl.c @@ -871,6 +871,9 @@ static int sppctl_dt_node_to_map(struct pinctrl_dev *pctldev, struct device_node } *map = kcalloc(*num_maps + nmG, sizeof(**map), GFP_KERNEL); + if (*map == NULL) + return -ENOMEM; + for (i = 0; i < (*num_maps); i++) { dt_pin = be32_to_cpu(list[i]); pin_num = FIELD_GET(GENMASK(31, 24), dt_pin); diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index f11d18beac18..700eb19e8450 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -91,6 +91,8 @@ #define AMD_CPU_ID_PCO AMD_CPU_ID_RV #define AMD_CPU_ID_CZN AMD_CPU_ID_RN #define AMD_CPU_ID_YC 0x14B5 +#define AMD_CPU_ID_CB 0x14D8 +#define AMD_CPU_ID_PS 0x14E8 #define PMC_MSG_DELAY_MIN_US 50 #define RESPONSE_REGISTER_LOOP_MAX 20000 @@ -318,6 +320,8 @@ static int amd_pmc_idlemask_read(struct amd_pmc_dev *pdev, struct device *dev, val = amd_pmc_reg_read(pdev, AMD_PMC_SCRATCH_REG_CZN); break; case AMD_CPU_ID_YC: + case AMD_CPU_ID_CB: + case AMD_CPU_ID_PS: val = amd_pmc_reg_read(pdev, AMD_PMC_SCRATCH_REG_YC); break; default: @@ -491,7 +495,8 @@ static void amd_pmc_dbgfs_register(struct amd_pmc_dev *dev) &amd_pmc_idlemask_fops); /* Enable STB only when the module_param is set */ if (enable_stb) { - if (dev->cpu_id == AMD_CPU_ID_YC) + if (dev->cpu_id == AMD_CPU_ID_YC || dev->cpu_id == AMD_CPU_ID_CB || + dev->cpu_id == AMD_CPU_ID_PS) debugfs_create_file("stb_read", 0644, dev->dbgfs_dir, dev, &amd_pmc_stb_debugfs_fops_v2); else @@ -615,6 +620,8 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) return MSG_OS_HINT_PCO; case AMD_CPU_ID_RN: case AMD_CPU_ID_YC: + case AMD_CPU_ID_CB: + case AMD_CPU_ID_PS: return MSG_OS_HINT_RN; } return -EINVAL; @@ -735,6 +742,8 @@ static struct acpi_s2idle_dev_ops amd_pmc_s2idle_dev_ops = { #endif static const struct pci_device_id pmc_pci_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_PS) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_CB) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_YC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_CZN) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_RN) }, @@ -877,7 +886,7 @@ static int amd_pmc_probe(struct platform_device *pdev) mutex_init(&dev->lock); - if (enable_stb && dev->cpu_id == AMD_CPU_ID_YC) { + if (enable_stb && (dev->cpu_id == AMD_CPU_ID_YC || dev->cpu_id == AMD_CPU_ID_CB)) { err = amd_pmc_s2d_init(dev); if (err) return err; @@ -915,6 +924,7 @@ static const struct acpi_device_id amd_pmc_acpi_ids[] = { {"AMDI0005", 0}, {"AMDI0006", 0}, {"AMDI0007", 0}, + {"AMDI0008", 0}, {"AMD0004", 0}, {"AMD0005", 0}, { } diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 57a07db659cb..478dd300b9c9 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -522,6 +522,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0x31, { KEY_VOLUMEDOWN } }, { KE_KEY, 0x32, { KEY_MUTE } }, { KE_KEY, 0x35, { KEY_SCREENLOCK } }, + { KE_KEY, 0x38, { KEY_PROG3 } }, /* Armoury Crate */ { KE_KEY, 0x40, { KEY_PREVIOUSSONG } }, { KE_KEY, 0x41, { KEY_NEXTSONG } }, { KE_KEY, 0x43, { KEY_STOPCD } }, /* Stop/Eject */ @@ -574,6 +575,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0xA5, { KEY_SWITCHVIDEOMODE } }, /* SDSP LCD + TV + HDMI */ { KE_KEY, 0xA6, { KEY_SWITCHVIDEOMODE } }, /* SDSP CRT + TV + HDMI */ { KE_KEY, 0xA7, { KEY_SWITCHVIDEOMODE } }, /* SDSP LCD + CRT + TV + HDMI */ + { KE_KEY, 0xB3, { KEY_PROG4 } }, /* AURA */ { KE_KEY, 0xB5, { KEY_CALC } }, { KE_KEY, 0xC4, { KEY_KBDILLUMUP } }, { KE_KEY, 0xC5, { KEY_KBDILLUMDOWN } }, diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index 497ad2f64a51..5e7e6659a849 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -150,6 +150,7 @@ static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M AORUS PRO-P"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M DS3H"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B660 GAMING X DDR4"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B660I AORUS PRO DDR4"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("Z390 I AORUS PRO WIFI-CF"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("Z490 AORUS ELITE AC"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 AORUS ELITE"), diff --git a/drivers/platform/x86/intel/atomisp2/led.c b/drivers/platform/x86/intel/atomisp2/led.c index 5935dfca166f..10077a61d8c5 100644 --- a/drivers/platform/x86/intel/atomisp2/led.c +++ b/drivers/platform/x86/intel/atomisp2/led.c @@ -50,7 +50,8 @@ static const struct dmi_system_id atomisp2_led_systems[] __initconst = { { .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"), + /* Non exact match to also match T100TAF */ + DMI_MATCH(DMI_PRODUCT_NAME, "T100TA"), }, .driver_data = &asus_t100ta_lookup, }, diff --git a/drivers/platform/x86/intel/ifs/Kconfig b/drivers/platform/x86/intel/ifs/Kconfig index 7ce896434b8f..c341a27cc1a3 100644 --- a/drivers/platform/x86/intel/ifs/Kconfig +++ b/drivers/platform/x86/intel/ifs/Kconfig @@ -1,6 +1,9 @@ config INTEL_IFS tristate "Intel In Field Scan" depends on X86 && CPU_SUP_INTEL && 64BIT && SMP + # Discussion on the list has shown that the sysfs API needs a bit + # more work, mark this as broken for now + depends on BROKEN select INTEL_IFS_DEVICE help Enable support for the In Field Scan capability in select diff --git a/drivers/platform/x86/x86-android-tablets.c b/drivers/platform/x86/x86-android-tablets.c index f446be72e539..480375977435 100644 --- a/drivers/platform/x86/x86-android-tablets.c +++ b/drivers/platform/x86/x86-android-tablets.c @@ -27,8 +27,8 @@ #include <linux/pinctrl/machine.h> #include <linux/platform_data/lp855x.h> #include <linux/platform_device.h> -#include <linux/pm.h> #include <linux/power/bq24190_charger.h> +#include <linux/reboot.h> #include <linux/rmi.h> #include <linux/serdev.h> #include <linux/spi/spi.h> @@ -889,6 +889,7 @@ static const struct pinctrl_map lenovo_yoga_tab2_830_1050_codec_pinctrl_map = "INT33FC:02", "pmu_clk2_grp", "pmu_clk"); static struct pinctrl *lenovo_yoga_tab2_830_1050_codec_pinctrl; +static struct sys_off_handler *lenovo_yoga_tab2_830_1050_sys_off_handler; static int __init lenovo_yoga_tab2_830_1050_init_codec(void) { @@ -933,9 +934,11 @@ err_put_device: * followed by a normal 3 second press to recover. Avoid this by doing an EFI * poweroff instead. */ -static void lenovo_yoga_tab2_830_1050_power_off(void) +static int lenovo_yoga_tab2_830_1050_power_off(struct sys_off_data *data) { efi.reset_system(EFI_RESET_SHUTDOWN, EFI_SUCCESS, 0, NULL); + + return NOTIFY_DONE; } static int __init lenovo_yoga_tab2_830_1050_init(void) @@ -950,13 +953,19 @@ static int __init lenovo_yoga_tab2_830_1050_init(void) if (ret) return ret; - pm_power_off = lenovo_yoga_tab2_830_1050_power_off; + /* SYS_OFF_PRIO_FIRMWARE + 1 so that it runs before acpi_power_off */ + lenovo_yoga_tab2_830_1050_sys_off_handler = + register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, SYS_OFF_PRIO_FIRMWARE + 1, + lenovo_yoga_tab2_830_1050_power_off, NULL); + if (IS_ERR(lenovo_yoga_tab2_830_1050_sys_off_handler)) + return PTR_ERR(lenovo_yoga_tab2_830_1050_sys_off_handler); + return 0; } static void lenovo_yoga_tab2_830_1050_exit(void) { - pm_power_off = NULL; /* Just turn poweroff into halt on module unload */ + unregister_sys_off_handler(lenovo_yoga_tab2_830_1050_sys_off_handler); if (lenovo_yoga_tab2_830_1050_codec_pinctrl) { pinctrl_put(lenovo_yoga_tab2_830_1050_codec_pinctrl); diff --git a/drivers/power/reset/arm-versatile-reboot.c b/drivers/power/reset/arm-versatile-reboot.c index 08d0a07b58ef..c7624d7611a7 100644 --- a/drivers/power/reset/arm-versatile-reboot.c +++ b/drivers/power/reset/arm-versatile-reboot.c @@ -146,6 +146,7 @@ static int __init versatile_reboot_probe(void) versatile_reboot_type = (enum versatile_reboot)reboot_id->data; syscon_regmap = syscon_node_to_regmap(np); + of_node_put(np); if (IS_ERR(syscon_regmap)) return PTR_ERR(syscon_regmap); diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c index ec8a404d71b4..4339fa9ff009 100644 --- a/drivers/power/supply/ab8500_fg.c +++ b/drivers/power/supply/ab8500_fg.c @@ -3148,6 +3148,7 @@ static int ab8500_fg_probe(struct platform_device *pdev) ret = ab8500_fg_init_hw_registers(di); if (ret) { dev_err(dev, "failed to initialize registers\n"); + destroy_workqueue(di->fg_wq); return ret; } @@ -3159,6 +3160,7 @@ static int ab8500_fg_probe(struct platform_device *pdev) di->fg_psy = devm_power_supply_register(dev, &ab8500_fg_desc, &psy_cfg); if (IS_ERR(di->fg_psy)) { dev_err(dev, "failed to register FG psy\n"); + destroy_workqueue(di->fg_wq); return PTR_ERR(di->fg_psy); } @@ -3174,8 +3176,10 @@ static int ab8500_fg_probe(struct platform_device *pdev) /* Register primary interrupt handlers */ for (i = 0; i < ARRAY_SIZE(ab8500_fg_irq); i++) { irq = platform_get_irq_byname(pdev, ab8500_fg_irq[i].name); - if (irq < 0) + if (irq < 0) { + destroy_workqueue(di->fg_wq); return irq; + } ret = devm_request_threaded_irq(dev, irq, NULL, ab8500_fg_irq[i].isr, @@ -3185,6 +3189,7 @@ static int ab8500_fg_probe(struct platform_device *pdev) if (ret != 0) { dev_err(dev, "failed to request %s IRQ %d: %d\n", ab8500_fg_irq[i].name, irq, ret); + destroy_workqueue(di->fg_wq); return ret; } dev_dbg(dev, "Requested %s IRQ %d: %d\n", @@ -3200,6 +3205,7 @@ static int ab8500_fg_probe(struct platform_device *pdev) ret = ab8500_fg_sysfs_init(di); if (ret) { dev_err(dev, "failed to create sysfs entry\n"); + destroy_workqueue(di->fg_wq); return ret; } @@ -3207,6 +3213,7 @@ static int ab8500_fg_probe(struct platform_device *pdev) if (ret) { dev_err(dev, "failed to create FG psy\n"); ab8500_fg_sysfs_exit(di); + destroy_workqueue(di->fg_wq); return ret; } diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index fad5890c899e..470253c337c7 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -846,17 +846,17 @@ int power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *t { int i, high, low; - /* Break loop at table_len - 1 because that is the highest index */ - for (i = 0; i < table_len - 1; i++) + for (i = 0; i < table_len; i++) if (temp > table[i].temp) break; /* The library function will deal with high == low */ - if ((i == 0) || (i == (table_len - 1))) - high = i; + if (i == 0) + high = low = i; + else if (i == table_len) + high = low = i - 1; else - high = i - 1; - low = i; + high = (low = i) - 1; return fixp_linear_interpolate(table[low].temp, table[low].resistance, @@ -958,17 +958,17 @@ int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table, { int i, high, low; - /* Break loop at table_len - 1 because that is the highest index */ - for (i = 0; i < table_len - 1; i++) + for (i = 0; i < table_len; i++) if (ocv > table[i].ocv) break; /* The library function will deal with high == low */ - if ((i == 0) || (i == (table_len - 1))) - high = i - 1; + if (i == 0) + high = low = i; + else if (i == table_len) + high = low = i - 1; else - high = i; /* i.e. i == 0 */ - low = i; + high = (low = i) - 1; return fixp_linear_interpolate(table[low].ocv, table[low].capacity, diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 5c13d2079d96..0a9045b49c50 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -1435,7 +1435,7 @@ static int __verify_queue_reservations(struct device_driver *drv, void *data) if (ap_drv->in_use) { rc = ap_drv->in_use(ap_perms.apm, newaqm); if (rc) - return -EBUSY; + rc = -EBUSY; } /* release the driver's module */ diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index c95360a3c186..0917b05059b4 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3195,6 +3195,9 @@ static int megasas_map_queues(struct Scsi_Host *shost) qoff += map->nr_queues; offset += map->nr_queues; + /* we never use READ queue, so can't cheat blk-mq */ + shost->tag_set.map[HCTX_TYPE_READ].nr_queues = 0; + /* Setup Poll hctx */ map = &shost->tag_set.map[HCTX_TYPE_POLL]; map->nr_queues = instance->iopoll_q_count; diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index f7466a895d3b..991eb01bb1e0 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -3145,15 +3145,6 @@ void pm8001_bytes_dmaed(struct pm8001_hba_info *pm8001_ha, int i) if (!phy->phy_attached) return; - if (sas_phy->phy) { - struct sas_phy *sphy = sas_phy->phy; - sphy->negotiated_linkrate = sas_phy->linkrate; - sphy->minimum_linkrate = phy->minimum_linkrate; - sphy->minimum_linkrate_hw = SAS_LINK_RATE_1_5_GBPS; - sphy->maximum_linkrate = phy->maximum_linkrate; - sphy->maximum_linkrate_hw = phy->maximum_linkrate; - } - if (phy->phy_type & PORT_TYPE_SAS) { struct sas_identify_frame *id; id = (struct sas_identify_frame *)phy->frame_rcvd; @@ -3177,26 +3168,22 @@ void pm8001_get_lrate_mode(struct pm8001_phy *phy, u8 link_rate) switch (link_rate) { case PHY_SPEED_120: phy->sas_phy.linkrate = SAS_LINK_RATE_12_0_GBPS; - phy->sas_phy.phy->negotiated_linkrate = SAS_LINK_RATE_12_0_GBPS; break; case PHY_SPEED_60: phy->sas_phy.linkrate = SAS_LINK_RATE_6_0_GBPS; - phy->sas_phy.phy->negotiated_linkrate = SAS_LINK_RATE_6_0_GBPS; break; case PHY_SPEED_30: phy->sas_phy.linkrate = SAS_LINK_RATE_3_0_GBPS; - phy->sas_phy.phy->negotiated_linkrate = SAS_LINK_RATE_3_0_GBPS; break; case PHY_SPEED_15: phy->sas_phy.linkrate = SAS_LINK_RATE_1_5_GBPS; - phy->sas_phy.phy->negotiated_linkrate = SAS_LINK_RATE_1_5_GBPS; break; } sas_phy->negotiated_linkrate = phy->sas_phy.linkrate; - sas_phy->maximum_linkrate_hw = SAS_LINK_RATE_6_0_GBPS; + sas_phy->maximum_linkrate_hw = phy->maximum_linkrate; sas_phy->minimum_linkrate_hw = SAS_LINK_RATE_1_5_GBPS; - sas_phy->maximum_linkrate = SAS_LINK_RATE_6_0_GBPS; - sas_phy->minimum_linkrate = SAS_LINK_RATE_1_5_GBPS; + sas_phy->maximum_linkrate = phy->maximum_linkrate; + sas_phy->minimum_linkrate = phy->minimum_linkrate; } /** diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index 9b04f1a6a67d..01f2f41928eb 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -143,6 +143,8 @@ static void pm8001_phy_init(struct pm8001_hba_info *pm8001_ha, int phy_id) struct asd_sas_phy *sas_phy = &phy->sas_phy; phy->phy_state = PHY_LINK_DISABLE; phy->pm8001_ha = pm8001_ha; + phy->minimum_linkrate = SAS_LINK_RATE_1_5_GBPS; + phy->maximum_linkrate = SAS_LINK_RATE_6_0_GBPS; sas_phy->enabled = (phy_id < pm8001_ha->chip->n_phy) ? 1 : 0; sas_phy->class = SAS; sas_phy->iproto = SAS_PROTOCOL_ALL; diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index 01c5e8ff4cc5..303cd05fec50 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -3723,8 +3723,12 @@ static int mpi_phy_stop_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) pm8001_dbg(pm8001_ha, MSG, "phy:0x%x status:0x%x\n", phyid, status); if (status == PHY_STOP_SUCCESS || - status == PHY_STOP_ERR_DEVICE_ATTACHED) + status == PHY_STOP_ERR_DEVICE_ATTACHED) { phy->phy_state = PHY_LINK_DISABLE; + phy->sas_phy.phy->negotiated_linkrate = SAS_PHY_DISABLED; + phy->sas_phy.linkrate = SAS_PHY_DISABLED; + } + return 0; } diff --git a/drivers/spi/spi-amd.c b/drivers/spi/spi-amd.c index cba6a4486c24..efdcbe6c4c26 100644 --- a/drivers/spi/spi-amd.c +++ b/drivers/spi/spi-amd.c @@ -33,6 +33,7 @@ #define AMD_SPI_RX_COUNT_REG 0x4B #define AMD_SPI_STATUS_REG 0x4C +#define AMD_SPI_FIFO_SIZE 70 #define AMD_SPI_MEM_SIZE 200 /* M_CMD OP codes for SPI */ @@ -270,6 +271,11 @@ static int amd_spi_master_transfer(struct spi_master *master, return 0; } +static size_t amd_spi_max_transfer_size(struct spi_device *spi) +{ + return AMD_SPI_FIFO_SIZE; +} + static int amd_spi_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -302,6 +308,8 @@ static int amd_spi_probe(struct platform_device *pdev) master->flags = SPI_MASTER_HALF_DUPLEX; master->setup = amd_spi_master_setup; master->transfer_one_message = amd_spi_master_transfer; + master->max_transfer_size = amd_spi_max_transfer_size; + master->max_message_size = amd_spi_max_transfer_size; /* Register the controller with SPI framework */ err = devm_spi_register_master(dev, master); diff --git a/drivers/spi/spi-aspeed-smc.c b/drivers/spi/spi-aspeed-smc.c index 496f3e1e9079..3e891bf22470 100644 --- a/drivers/spi/spi-aspeed-smc.c +++ b/drivers/spi/spi-aspeed-smc.c @@ -558,6 +558,14 @@ static int aspeed_spi_dirmap_create(struct spi_mem_dirmap_desc *desc) u32 ctl_val; int ret = 0; + dev_dbg(aspi->dev, + "CE%d %s dirmap [ 0x%.8llx - 0x%.8llx ] OP %#x mode:%d.%d.%d.%d naddr:%#x ndummies:%#x\n", + chip->cs, op->data.dir == SPI_MEM_DATA_IN ? "read" : "write", + desc->info.offset, desc->info.offset + desc->info.length, + op->cmd.opcode, op->cmd.buswidth, op->addr.buswidth, + op->dummy.buswidth, op->data.buswidth, + op->addr.nbytes, op->dummy.nbytes); + chip->clk_freq = desc->mem->spi->max_speed_hz; /* Only for reads */ @@ -574,9 +582,11 @@ static int aspeed_spi_dirmap_create(struct spi_mem_dirmap_desc *desc) ctl_val = readl(chip->ctl) & ~CTRL_IO_CMD_MASK; ctl_val |= aspeed_spi_get_io_mode(op) | op->cmd.opcode << CTRL_COMMAND_SHIFT | - CTRL_IO_DUMMY_SET(op->dummy.nbytes / op->dummy.buswidth) | CTRL_IO_MODE_READ; + if (op->dummy.nbytes) + ctl_val |= CTRL_IO_DUMMY_SET(op->dummy.nbytes / op->dummy.buswidth); + /* Tune 4BYTE address mode */ if (op->addr.nbytes) { u32 addr_mode = readl(aspi->regs + CE_CTRL_REG); diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index 775c0bf2f923..0933948d7df3 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -1138,10 +1138,14 @@ static void bcm2835_spi_handle_err(struct spi_controller *ctlr, struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr); /* if an error occurred and we have an active dma, then terminate */ - dmaengine_terminate_sync(ctlr->dma_tx); - bs->tx_dma_active = false; - dmaengine_terminate_sync(ctlr->dma_rx); - bs->rx_dma_active = false; + if (ctlr->dma_tx) { + dmaengine_terminate_sync(ctlr->dma_tx); + bs->tx_dma_active = false; + } + if (ctlr->dma_rx) { + dmaengine_terminate_sync(ctlr->dma_rx); + bs->rx_dma_active = false; + } bcm2835_spi_undo_prologue(bs); /* and reset */ diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 2b9fc8449a62..72b1a5a2298c 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1578,8 +1578,7 @@ static int cqspi_probe(struct platform_device *pdev) ret = cqspi_of_get_pdata(cqspi); if (ret) { dev_err(dev, "Cannot get mandatory OF data.\n"); - ret = -ENODEV; - goto probe_master_put; + return -ENODEV; } /* Obtain QSPI clock. */ @@ -1587,7 +1586,7 @@ static int cqspi_probe(struct platform_device *pdev) if (IS_ERR(cqspi->clk)) { dev_err(dev, "Cannot claim QSPI clock.\n"); ret = PTR_ERR(cqspi->clk); - goto probe_master_put; + return ret; } /* Obtain and remap controller address. */ @@ -1596,7 +1595,7 @@ static int cqspi_probe(struct platform_device *pdev) if (IS_ERR(cqspi->iobase)) { dev_err(dev, "Cannot remap controller address.\n"); ret = PTR_ERR(cqspi->iobase); - goto probe_master_put; + return ret; } /* Obtain and remap AHB address. */ @@ -1605,7 +1604,7 @@ static int cqspi_probe(struct platform_device *pdev) if (IS_ERR(cqspi->ahb_base)) { dev_err(dev, "Cannot remap AHB address.\n"); ret = PTR_ERR(cqspi->ahb_base); - goto probe_master_put; + return ret; } cqspi->mmap_phys_base = (dma_addr_t)res_ahb->start; cqspi->ahb_size = resource_size(res_ahb); @@ -1614,15 +1613,13 @@ static int cqspi_probe(struct platform_device *pdev) /* Obtain IRQ line. */ irq = platform_get_irq(pdev, 0); - if (irq < 0) { - ret = -ENXIO; - goto probe_master_put; - } + if (irq < 0) + return -ENXIO; pm_runtime_enable(dev); ret = pm_runtime_resume_and_get(dev); if (ret < 0) - goto probe_master_put; + return ret; ret = clk_prepare_enable(cqspi->clk); if (ret) { @@ -1716,8 +1713,6 @@ probe_reset_failed: probe_clk_failed: pm_runtime_put_sync(dev); pm_runtime_disable(dev); -probe_master_put: - spi_master_put(master); return ret; } diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index 31d778e9d255..6a7f7df1e776 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -69,7 +69,7 @@ #define CDNS_SPI_BAUD_DIV_SHIFT 3 /* Baud rate divisor shift in CR */ #define CDNS_SPI_SS_SHIFT 10 /* Slave Select field shift in CR */ #define CDNS_SPI_SS0 0x1 /* Slave Select zero */ -#define CDNS_SPI_NOSS 0x3C /* No Slave select */ +#define CDNS_SPI_NOSS 0xF /* No Slave select */ /* * SPI Interrupt Registers bit Masks diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c index 7a014eeec2d0..411b1307b7fd 100644 --- a/drivers/spi/spi-rspi.c +++ b/drivers/spi/spi-rspi.c @@ -613,6 +613,10 @@ static int rspi_dma_transfer(struct rspi_data *rspi, struct sg_table *tx, rspi->dma_callbacked, HZ); if (ret > 0 && rspi->dma_callbacked) { ret = 0; + if (tx) + dmaengine_synchronize(rspi->ctlr->dma_tx); + if (rx) + dmaengine_synchronize(rspi->ctlr->dma_rx); } else { if (!ret) { dev_err(&rspi->ctlr->dev, "DMA timeout\n"); diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index e68f1cc8ef98..6c8d8b051bfd 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -448,6 +448,9 @@ fd_execute_write_same(struct se_cmd *cmd) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } + if (!cmd->t_data_nents) + return TCM_INVALID_CDB_FIELD; + if (cmd->t_data_nents > 1 || cmd->t_data_sg[0].length != cmd->se_dev->dev_attrib.block_size) { pr_err("WRITE_SAME: Illegal SGL t_data_nents: %u length: %u" diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 378c80313a0f..1ed9381751e6 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -494,6 +494,10 @@ iblock_execute_write_same(struct se_cmd *cmd) " backends not supported\n"); return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } + + if (!cmd->t_data_nents) + return TCM_INVALID_CDB_FIELD; + sg = &cmd->t_data_sg[0]; if (cmd->t_data_nents > 1 || diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index ca1b2312d6e7..f6132836eb38 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -312,6 +312,12 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char flags, struct sbc_ops *op pr_warn("WRITE SAME with ANCHOR not supported\n"); return TCM_INVALID_CDB_FIELD; } + + if (flags & 0x01) { + pr_warn("WRITE SAME with NDOB not supported\n"); + return TCM_INVALID_CDB_FIELD; + } + /* * Special case for WRITE_SAME w/ UNMAP=1 that ends up getting * translated into block discard requests within backend code. diff --git a/drivers/tee/optee/optee_smc.h b/drivers/tee/optee/optee_smc.h index c60896cf71cb..73b5e7760d10 100644 --- a/drivers/tee/optee/optee_smc.h +++ b/drivers/tee/optee/optee_smc.h @@ -189,7 +189,7 @@ struct optee_smc_call_get_os_revision_result { * Have config return register usage: * a0 OPTEE_SMC_RETURN_OK * a1 Physical address of start of SHM - * a2 Size of of SHM + * a2 Size of SHM * a3 Cache settings of memory, as defined by the * OPTEE_SMC_SHM_* values above * a4-7 Preserved diff --git a/drivers/tee/optee/smc_abi.c b/drivers/tee/optee/smc_abi.c index 385cb0aee610..a1c1fa1a9c28 100644 --- a/drivers/tee/optee/smc_abi.c +++ b/drivers/tee/optee/smc_abi.c @@ -884,8 +884,8 @@ static int optee_smc_do_call_with_arg(struct tee_context *ctx, rpc_arg_offs = OPTEE_MSG_GET_ARG_SIZE(arg->num_params); rpc_arg = tee_shm_get_va(shm, offs + rpc_arg_offs); - if (IS_ERR(arg)) - return PTR_ERR(arg); + if (IS_ERR(rpc_arg)) + return PTR_ERR(rpc_arg); } if (rpc_arg && tee_shm_is_dynamic(shm)) { diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index af0f7c603fa4..98da206cd761 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -1073,7 +1073,7 @@ EXPORT_SYMBOL_GPL(tee_device_unregister); /** * tee_get_drvdata() - Return driver_data pointer * @teedev: Device containing the driver_data pointer - * @returns the driver_data pointer supplied to tee_register(). + * @returns the driver_data pointer supplied to tee_device_alloc(). */ void *tee_get_drvdata(struct tee_device *teedev) { diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 74bfabe5b453..752dab3356d7 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -111,21 +111,11 @@ static void pty_unthrottle(struct tty_struct *tty) static int pty_write(struct tty_struct *tty, const unsigned char *buf, int c) { struct tty_struct *to = tty->link; - unsigned long flags; - if (tty->flow.stopped) + if (tty->flow.stopped || !c) return 0; - if (c > 0) { - spin_lock_irqsave(&to->port->lock, flags); - /* Stuff the data into the input queue of the other end */ - c = tty_insert_flip_string(to->port, buf, c); - spin_unlock_irqrestore(&to->port->lock, flags); - /* And shovel */ - if (c) - tty_flip_buffer_push(to->port); - } - return c; + return tty_insert_flip_string_and_push_buffer(to->port, buf, c); } /** diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index cfbd2de0ca6e..3f56dbc9432b 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -23,6 +23,7 @@ #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/tty.h> #include <linux/ratelimit.h> #include <linux/tty_flip.h> @@ -559,6 +560,9 @@ serial8250_register_ports(struct uart_driver *drv, struct device *dev) up->port.dev = dev; + if (uart_console_enabled(&up->port)) + pm_runtime_get_sync(up->port.dev); + serial8250_apply_quirks(up); uart_add_one_port(drv, &up->port); } diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index 7133fceed35e..a8dba4a0a8fb 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -106,10 +106,10 @@ int serial8250_tx_dma(struct uart_8250_port *p) UART_XMIT_SIZE, DMA_TO_DEVICE); dma_async_issue_pending(dma->txchan); - if (dma->tx_err) { + serial8250_clear_THRI(p); + if (dma->tx_err) dma->tx_err = 0; - serial8250_clear_THRI(p); - } + return 0; err: dma->tx_err = 1; diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index f57bbd32ef11..bb6aca07ab56 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -47,7 +47,7 @@ #define RZN1_UART_xDMACR_DMA_EN BIT(0) #define RZN1_UART_xDMACR_1_WORD_BURST (0 << 1) #define RZN1_UART_xDMACR_4_WORD_BURST (1 << 1) -#define RZN1_UART_xDMACR_8_WORD_BURST (3 << 1) +#define RZN1_UART_xDMACR_8_WORD_BURST (2 << 1) #define RZN1_UART_xDMACR_BLK_SZ(x) ((x) << 3) /* Quirks */ @@ -773,18 +773,18 @@ static const struct of_device_id dw8250_of_match[] = { MODULE_DEVICE_TABLE(of, dw8250_of_match); static const struct acpi_device_id dw8250_acpi_match[] = { - { "INT33C4", 0 }, - { "INT33C5", 0 }, - { "INT3434", 0 }, - { "INT3435", 0 }, - { "80860F0A", 0 }, - { "8086228A", 0 }, - { "APMC0D08", 0}, - { "AMD0020", 0 }, - { "AMDI0020", 0 }, - { "AMDI0022", 0 }, - { "BRCM2032", 0 }, - { "HISI0031", 0 }, + { "80860F0A", (kernel_ulong_t)&dw8250_dw_apb }, + { "8086228A", (kernel_ulong_t)&dw8250_dw_apb }, + { "AMD0020", (kernel_ulong_t)&dw8250_dw_apb }, + { "AMDI0020", (kernel_ulong_t)&dw8250_dw_apb }, + { "AMDI0022", (kernel_ulong_t)&dw8250_dw_apb }, + { "APMC0D08", (kernel_ulong_t)&dw8250_dw_apb}, + { "BRCM2032", (kernel_ulong_t)&dw8250_dw_apb }, + { "HISI0031", (kernel_ulong_t)&dw8250_dw_apb }, + { "INT33C4", (kernel_ulong_t)&dw8250_dw_apb }, + { "INT33C5", (kernel_ulong_t)&dw8250_dw_apb }, + { "INT3434", (kernel_ulong_t)&dw8250_dw_apb }, + { "INT3435", (kernel_ulong_t)&dw8250_dw_apb }, { }, }; MODULE_DEVICE_TABLE(acpi, dw8250_acpi_match); diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 8f32fe9e149e..3c36a06a20b0 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1949,7 +1949,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) if ((status & UART_LSR_THRE) && (up->ier & UART_IER_THRI)) { if (!up->dma || up->dma->tx_err) serial8250_tx_chars(up); - else + else if (!up->dma->tx_running) __stop_tx(up); } @@ -2975,8 +2975,10 @@ static int serial8250_request_std_resource(struct uart_8250_port *up) case UPIO_MEM32BE: case UPIO_MEM16: case UPIO_MEM: - if (!port->mapbase) + if (!port->mapbase) { + ret = -EINVAL; break; + } if (!request_mem_region(port->mapbase, size, "serial")) { ret = -EBUSY; diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 97ef41cb2721..16a21422ddce 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1367,6 +1367,15 @@ static void pl011_stop_rx(struct uart_port *port) pl011_dma_rx_stop(uap); } +static void pl011_throttle_rx(struct uart_port *port) +{ + unsigned long flags; + + spin_lock_irqsave(&port->lock, flags); + pl011_stop_rx(port); + spin_unlock_irqrestore(&port->lock, flags); +} + static void pl011_enable_ms(struct uart_port *port) { struct uart_amba_port *uap = @@ -1788,9 +1797,10 @@ static int pl011_allocate_irq(struct uart_amba_port *uap) */ static void pl011_enable_interrupts(struct uart_amba_port *uap) { + unsigned long flags; unsigned int i; - spin_lock_irq(&uap->port.lock); + spin_lock_irqsave(&uap->port.lock, flags); /* Clear out any spuriously appearing RX interrupts */ pl011_write(UART011_RTIS | UART011_RXIS, uap, REG_ICR); @@ -1812,7 +1822,14 @@ static void pl011_enable_interrupts(struct uart_amba_port *uap) if (!pl011_dma_rx_running(uap)) uap->im |= UART011_RXIM; pl011_write(uap->im, uap, REG_IMSC); - spin_unlock_irq(&uap->port.lock); + spin_unlock_irqrestore(&uap->port.lock, flags); +} + +static void pl011_unthrottle_rx(struct uart_port *port) +{ + struct uart_amba_port *uap = container_of(port, struct uart_amba_port, port); + + pl011_enable_interrupts(uap); } static int pl011_startup(struct uart_port *port) @@ -2225,6 +2242,8 @@ static const struct uart_ops amba_pl011_pops = { .stop_tx = pl011_stop_tx, .start_tx = pl011_start_tx, .stop_rx = pl011_stop_rx, + .throttle = pl011_throttle_rx, + .unthrottle = pl011_unthrottle_rx, .enable_ms = pl011_enable_ms, .break_ctl = pl011_break_ctl, .startup = pl011_startup, diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c index 0429c2a54290..93489fe334d0 100644 --- a/drivers/tty/serial/mvebu-uart.c +++ b/drivers/tty/serial/mvebu-uart.c @@ -470,14 +470,14 @@ static void mvebu_uart_shutdown(struct uart_port *port) } } -static int mvebu_uart_baud_rate_set(struct uart_port *port, unsigned int baud) +static unsigned int mvebu_uart_baud_rate_set(struct uart_port *port, unsigned int baud) { unsigned int d_divisor, m_divisor; unsigned long flags; u32 brdv, osamp; if (!port->uartclk) - return -EOPNOTSUPP; + return 0; /* * The baudrate is derived from the UART clock thanks to divisors: @@ -548,7 +548,7 @@ static int mvebu_uart_baud_rate_set(struct uart_port *port, unsigned int baud) (m_divisor << 16) | (m_divisor << 24); writel(osamp, port->membase + UART_OSAMP); - return 0; + return DIV_ROUND_CLOSEST(port->uartclk, d_divisor * m_divisor); } static void mvebu_uart_set_termios(struct uart_port *port, @@ -587,15 +587,11 @@ static void mvebu_uart_set_termios(struct uart_port *port, max_baud = port->uartclk / 80; baud = uart_get_baud_rate(port, termios, old, min_baud, max_baud); - if (mvebu_uart_baud_rate_set(port, baud)) { - /* No clock available, baudrate cannot be changed */ - if (old) - baud = uart_get_baud_rate(port, old, NULL, - min_baud, max_baud); - } else { - tty_termios_encode_baud_rate(termios, baud, baud); - uart_update_timeout(port, termios->c_cflag, baud); - } + baud = mvebu_uart_baud_rate_set(port, baud); + + /* In case baudrate cannot be changed, report previous old value */ + if (baud == 0 && old) + baud = tty_termios_baud_rate(old); /* Only the following flag changes are supported */ if (old) { @@ -606,6 +602,11 @@ static void mvebu_uart_set_termios(struct uart_port *port, termios->c_cflag |= CS8; } + if (baud != 0) { + tty_termios_encode_baud_rate(termios, baud, baud); + uart_update_timeout(port, termios->c_cflag, baud); + } + spin_unlock_irqrestore(&port->lock, flags); } diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c index d5ca904def34..1afe47b62ad5 100644 --- a/drivers/tty/serial/samsung_tty.c +++ b/drivers/tty/serial/samsung_tty.c @@ -377,8 +377,7 @@ static void enable_tx_dma(struct s3c24xx_uart_port *ourport) /* Enable tx dma mode */ ucon = rd_regl(port, S3C2410_UCON); ucon &= ~(S3C64XX_UCON_TXBURST_MASK | S3C64XX_UCON_TXMODE_MASK); - ucon |= (dma_get_cache_alignment() >= 16) ? - S3C64XX_UCON_TXBURST_16 : S3C64XX_UCON_TXBURST_1; + ucon |= S3C64XX_UCON_TXBURST_1; ucon |= S3C64XX_UCON_TXMODE_DMA; wr_regl(port, S3C2410_UCON, ucon); @@ -674,7 +673,7 @@ static void enable_rx_dma(struct s3c24xx_uart_port *ourport) S3C64XX_UCON_DMASUS_EN | S3C64XX_UCON_TIMEOUT_EN | S3C64XX_UCON_RXMODE_MASK); - ucon |= S3C64XX_UCON_RXBURST_16 | + ucon |= S3C64XX_UCON_RXBURST_1 | 0xf << S3C64XX_UCON_TIMEOUT_SHIFT | S3C64XX_UCON_EMPTYINT_EN | S3C64XX_UCON_TIMEOUT_EN | diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 338ebadfd44b..3dc926d6c00a 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1941,11 +1941,6 @@ static int uart_proc_show(struct seq_file *m, void *v) } #endif -static inline bool uart_console_enabled(struct uart_port *port) -{ - return uart_console(port) && (port->cons->flags & CON_ENABLED); -} - static void uart_port_spin_lock_init(struct uart_port *port) { spin_lock_init(&port->lock); diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index b7b44f4050d4..0973b03eeeaa 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -72,6 +72,8 @@ static void stm32_usart_config_reg_rs485(u32 *cr1, u32 *cr3, u32 delay_ADE, *cr3 |= USART_CR3_DEM; over8 = *cr1 & USART_CR1_OVER8; + *cr1 &= ~(USART_CR1_DEDT_MASK | USART_CR1_DEAT_MASK); + if (over8) rs485_deat_dedt = delay_ADE * baud * 8; else diff --git a/drivers/tty/tty.h b/drivers/tty/tty.h index b710c5ef89ab..f310a8274df1 100644 --- a/drivers/tty/tty.h +++ b/drivers/tty/tty.h @@ -111,4 +111,7 @@ static inline void tty_audit_tiocsti(struct tty_struct *tty, char ch) ssize_t redirected_tty_write(struct kiocb *, struct iov_iter *); +int tty_insert_flip_string_and_push_buffer(struct tty_port *port, + const unsigned char *chars, size_t cnt); + #endif diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index bfa431a8e690..595d8b49c745 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -532,6 +532,15 @@ static void flush_to_ldisc(struct work_struct *work) } +static inline void tty_flip_buffer_commit(struct tty_buffer *tail) +{ + /* + * Paired w/ acquire in flush_to_ldisc(); ensures flush_to_ldisc() sees + * buffer data. + */ + smp_store_release(&tail->commit, tail->used); +} + /** * tty_flip_buffer_push - push terminal buffers * @port: tty port to push @@ -546,16 +555,43 @@ void tty_flip_buffer_push(struct tty_port *port) { struct tty_bufhead *buf = &port->buf; - /* - * Paired w/ acquire in flush_to_ldisc(); ensures flush_to_ldisc() sees - * buffer data. - */ - smp_store_release(&buf->tail->commit, buf->tail->used); + tty_flip_buffer_commit(buf->tail); queue_work(system_unbound_wq, &buf->work); } EXPORT_SYMBOL(tty_flip_buffer_push); /** + * tty_insert_flip_string_and_push_buffer - add characters to the tty buffer and + * push + * @port: tty port + * @chars: characters + * @size: size + * + * The function combines tty_insert_flip_string() and tty_flip_buffer_push() + * with the exception of properly holding the @port->lock. + * + * To be used only internally (by pty currently). + * + * Returns: the number added. + */ +int tty_insert_flip_string_and_push_buffer(struct tty_port *port, + const unsigned char *chars, size_t size) +{ + struct tty_bufhead *buf = &port->buf; + unsigned long flags; + + spin_lock_irqsave(&port->lock, flags); + size = tty_insert_flip_string(port, chars, size); + if (size) + tty_flip_buffer_commit(buf->tail); + spin_unlock_irqrestore(&port->lock, flags); + + queue_work(system_unbound_wq, &buf->work); + + return size; +} + +/** * tty_buffer_init - prepare a tty buffer structure * @port: tty port to initialise * diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index f8c87c4d7399..dfc1f4b445f3 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -855,7 +855,7 @@ static void delete_char(struct vc_data *vc, unsigned int nr) unsigned short *p = (unsigned short *) vc->vc_pos; vc_uniscr_delete(vc, nr); - scr_memcpyw(p, p + nr, (vc->vc_cols - vc->state.x - nr) * 2); + scr_memmovew(p, p + nr, (vc->vc_cols - vc->state.x - nr) * 2); scr_memsetw(p + vc->vc_cols - vc->state.x - nr, vc->vc_video_erase_char, nr * 2); vc->vc_need_wrap = 0; diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index ce86d1b790c0..c7b337480e3e 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -5738,7 +5738,7 @@ int ufshcd_wb_toggle(struct ufs_hba *hba, bool enable) } hba->dev_info.wb_enabled = enable; - dev_info(hba->dev, "%s Write Booster %s\n", + dev_dbg(hba->dev, "%s Write Booster %s\n", __func__, enable ? "enabled" : "disabled"); return ret; @@ -7253,7 +7253,7 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba) hba->silence_err_logs = false; /* scale up clocks to max frequency before full reinitialization */ - ufshcd_set_clk_freq(hba, true); + ufshcd_scale_clks(hba, true); err = ufshcd_hba_enable(hba); diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c index fea7aca35dc8..173cf3579c55 100644 --- a/drivers/usb/dwc3/dwc3-am62.c +++ b/drivers/usb/dwc3/dwc3-am62.c @@ -195,8 +195,7 @@ static int dwc3_ti_probe(struct platform_device *pdev) if (i == ARRAY_SIZE(dwc3_ti_rate_table)) { dev_err(dev, "unsupported usb2_refclk rate: %lu KHz\n", rate); - ret = -EINVAL; - goto err_clk_disable; + return -EINVAL; } data->rate_code = i; @@ -204,7 +203,7 @@ static int dwc3_ti_probe(struct platform_device *pdev) /* Read the syscon property and set the rate code */ ret = phy_syscon_pll_refclk(data); if (ret) - goto err_clk_disable; + return ret; /* VBUS divider select */ data->vbus_divider = device_property_read_bool(dev, "ti,vbus-divider"); @@ -245,8 +244,6 @@ err_pm_disable: clk_disable_unprepare(data->usb2_refclk); pm_runtime_disable(dev); pm_runtime_set_suspended(dev); -err_clk_disable: - clk_put(data->usb2_refclk); return ret; } @@ -276,7 +273,6 @@ static int dwc3_ti_remove(struct platform_device *pdev) pm_runtime_disable(dev); pm_runtime_set_suspended(dev); - clk_put(data->usb2_refclk); platform_set_drvdata(pdev, NULL); return 0; } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 8716bece1072..0d89dfa6eef5 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4249,7 +4249,6 @@ static irqreturn_t dwc3_process_event_buf(struct dwc3_event_buffer *evt) } evt->count = 0; - evt->flags &= ~DWC3_EVENT_PENDING; ret = IRQ_HANDLED; /* Unmask interrupt */ @@ -4261,6 +4260,9 @@ static irqreturn_t dwc3_process_event_buf(struct dwc3_event_buffer *evt) dwc3_writel(dwc->regs, DWC3_DEV_IMOD(0), dwc->imod_interval); } + /* Keep the clearing of DWC3_EVENT_PENDING at the end */ + evt->flags &= ~DWC3_EVENT_PENDING; + return ret; } diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index e5a6b6e36b3d..4303a3283ba0 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -2371,6 +2371,7 @@ static ssize_t f_uvc_opts_string_##cname##_store(struct config_item *item,\ const char *page, size_t len) \ { \ struct f_uvc_opts *opts = to_f_uvc_opts(item); \ + int size = min(sizeof(opts->aname), len + 1); \ int ret = 0; \ \ mutex_lock(&opts->lock); \ @@ -2379,8 +2380,9 @@ static ssize_t f_uvc_opts_string_##cname##_store(struct config_item *item,\ goto end; \ } \ \ - ret = snprintf(opts->aname, min(sizeof(opts->aname), len), \ - "%s", page); \ + ret = strscpy(opts->aname, page, size); \ + if (ret == -E2BIG) \ + ret = size - 1; \ \ end: \ mutex_unlock(&opts->lock); \ diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c index 385be30baad3..896c0d107f72 100644 --- a/drivers/usb/host/ehci-fsl.c +++ b/drivers/usb/host/ehci-fsl.c @@ -76,14 +76,9 @@ static int fsl_ehci_drv_probe(struct platform_device *pdev) return -ENODEV; } - res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (!res) { - dev_err(&pdev->dev, - "Found HC with no IRQ. Check %s setup!\n", - dev_name(&pdev->dev)); - return -ENODEV; - } - irq = res->start; + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; hcd = __usb_create_hcd(&fsl_ehci_hc_driver, pdev->dev.parent, &pdev->dev, dev_name(&pdev->dev), NULL); diff --git a/drivers/usb/host/fsl-mph-dr-of.c b/drivers/usb/host/fsl-mph-dr-of.c index 44a7e58a26e3..e5df17522892 100644 --- a/drivers/usb/host/fsl-mph-dr-of.c +++ b/drivers/usb/host/fsl-mph-dr-of.c @@ -112,6 +112,9 @@ static struct platform_device *fsl_usb2_device_register( goto error; } + pdev->dev.of_node = ofdev->dev.of_node; + pdev->dev.of_node_reused = true; + retval = platform_device_add(pdev); if (retval) goto error; diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index b440d338a895..d5a3986dfee7 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1023,6 +1023,9 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_DISPLAY_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_LITE_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_ANALOG_PID) }, + /* Belimo Automation devices */ + { USB_DEVICE(FTDI_VID, BELIMO_ZTH_PID) }, + { USB_DEVICE(FTDI_VID, BELIMO_ZIP_PID) }, /* ICP DAS I-756xU devices */ { USB_DEVICE(ICPDAS_VID, ICPDAS_I7560U_PID) }, { USB_DEVICE(ICPDAS_VID, ICPDAS_I7561U_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index d1a9564697a4..4e92c165c86b 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1569,6 +1569,12 @@ #define CHETCO_SEASMART_ANALOG_PID 0xA5AF /* SeaSmart Analog Adapter */ /* + * Belimo Automation + */ +#define BELIMO_ZTH_PID 0x8050 +#define BELIMO_ZIP_PID 0xC811 + +/* * Unjo AB */ #define UNJO_VID 0x22B7 diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index ee0e520707dd..c4724750c81a 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1718,6 +1718,7 @@ void typec_set_pwr_opmode(struct typec_port *port, partner->usb_pd = 1; sysfs_notify(&partner_dev->kobj, NULL, "supports_usb_power_delivery"); + kobject_uevent(&partner_dev->kobj, KOBJ_CHANGE); } put_device(partner_dev); } diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 61e71c1154be..e60b06f2ac22 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -549,6 +549,16 @@ static struct vfio_group *vfio_group_find_or_alloc(struct device *dev) if (!iommu_group) return ERR_PTR(-EINVAL); + /* + * VFIO always sets IOMMU_CACHE because we offer no way for userspace to + * restore cache coherency. It has to be checked here because it is only + * valid for cases where we are using iommu groups. + */ + if (!iommu_capable(dev->bus, IOMMU_CAP_CACHE_COHERENCY)) { + iommu_group_put(iommu_group); + return ERR_PTR(-EINVAL); + } + group = vfio_group_get_from_iommu(iommu_group); if (!group) group = vfio_create_group(iommu_group, VFIO_IOMMU); @@ -601,13 +611,6 @@ static int __vfio_register_dev(struct vfio_device *device, int vfio_register_group_dev(struct vfio_device *device) { - /* - * VFIO always sets IOMMU_CACHE because we offer no way for userspace to - * restore cache coherency. - */ - if (!iommu_capable(device->dev->bus, IOMMU_CAP_CACHE_COHERENCY)) - return -EINVAL; - return __vfio_register_dev(device, vfio_group_find_or_alloc(device->dev)); } diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index 90ce16b6e05f..f422f9c58ba7 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -632,16 +632,19 @@ static int __init sev_guest_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct snp_guest_dev *snp_dev; struct miscdevice *misc; + void __iomem *mapping; int ret; if (!dev->platform_data) return -ENODEV; data = (struct sev_guest_platform_data *)dev->platform_data; - layout = (__force void *)ioremap_encrypted(data->secrets_gpa, PAGE_SIZE); - if (!layout) + mapping = ioremap_encrypted(data->secrets_gpa, PAGE_SIZE); + if (!mapping) return -ENODEV; + layout = (__force void *)mapping; + ret = -ENOMEM; snp_dev = devm_kzalloc(&pdev->dev, sizeof(struct snp_guest_dev), GFP_KERNEL); if (!snp_dev) @@ -706,7 +709,7 @@ e_free_response: e_free_request: free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg)); e_unmap: - iounmap(layout); + iounmap(mapping); return ret; } diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 4b56c39f766d..84b143eef395 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -396,13 +396,15 @@ static void __unmap_grant_pages_done(int result, unsigned int offset = data->unmap_ops - map->unmap_ops; for (i = 0; i < data->count; i++) { - WARN_ON(map->unmap_ops[offset+i].status); + WARN_ON(map->unmap_ops[offset + i].status != GNTST_okay && + map->unmap_ops[offset + i].handle != INVALID_GRANT_HANDLE); pr_debug("unmap handle=%d st=%d\n", map->unmap_ops[offset+i].handle, map->unmap_ops[offset+i].status); map->unmap_ops[offset+i].handle = INVALID_GRANT_HANDLE; if (use_ptemod) { - WARN_ON(map->kunmap_ops[offset+i].status); + WARN_ON(map->kunmap_ops[offset + i].status != GNTST_okay && + map->kunmap_ops[offset + i].handle != INVALID_GRANT_HANDLE); pr_debug("kunmap handle=%u st=%d\n", map->kunmap_ops[offset+i].handle, map->kunmap_ops[offset+i].status); diff --git a/fs/Makefile b/fs/Makefile index 208a74e0b00e..93b80529f8e8 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -34,8 +34,6 @@ obj-$(CONFIG_TIMERFD) += timerfd.o obj-$(CONFIG_EVENTFD) += eventfd.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_AIO) += aio.o -obj-$(CONFIG_IO_URING) += io_uring.o -obj-$(CONFIG_IO_WQ) += io-wq.o obj-$(CONFIG_FS_DAX) += dax.o obj-$(CONFIG_FS_ENCRYPTION) += crypto/ obj-$(CONFIG_FS_VERITY) += verity/ diff --git a/fs/afs/file.c b/fs/afs/file.c index 42118a4f3383..d1cfb235c4b9 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -375,7 +375,7 @@ static int afs_begin_cache_operation(struct netfs_io_request *rreq) } static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len, - struct folio *folio, void **_fsdata) + struct folio **foliop, void **_fsdata) { struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 415bf1823fb3..9c21e214d29e 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -675,9 +675,8 @@ struct btrfs_fs_info { rwlock_t global_root_lock; struct rb_root global_root_tree; - /* The xarray that holds all the FS roots */ - spinlock_t fs_roots_lock; - struct xarray fs_roots; + spinlock_t fs_roots_radix_lock; + struct radix_tree_root fs_roots_radix; /* block group cache stuff */ rwlock_t block_group_cache_lock; @@ -995,10 +994,10 @@ struct btrfs_fs_info { struct btrfs_delayed_root *delayed_root; - /* Extent buffer xarray */ + /* Extent buffer radix tree */ spinlock_t buffer_lock; /* Entries are eb->start / sectorsize */ - struct xarray extent_buffers; + struct radix_tree_root buffer_radix; /* next backup root to be overwritten */ int backup_root_index; @@ -1119,8 +1118,7 @@ enum { */ BTRFS_ROOT_SHAREABLE, BTRFS_ROOT_TRACK_DIRTY, - /* The root is tracked in fs_info::fs_roots */ - BTRFS_ROOT_REGISTERED, + BTRFS_ROOT_IN_RADIX, BTRFS_ROOT_ORPHAN_ITEM_INSERTED, BTRFS_ROOT_DEFRAG_RUNNING, BTRFS_ROOT_FORCE_COW, @@ -1224,10 +1222,10 @@ struct btrfs_root { struct rb_root inode_tree; /* - * Xarray that keeps track of delayed nodes of every inode, protected - * by inode_lock + * radix tree that keeps track of delayed nodes of every inode, + * protected by inode_lock */ - struct xarray delayed_nodes; + struct radix_tree_root delayed_nodes_tree; /* * right now this just gets used so that a root has its own devid * for stat. It may be used for more later diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 66779ab3ed4a..748bf6b0d860 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -78,7 +78,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node( } spin_lock(&root->inode_lock); - node = xa_load(&root->delayed_nodes, ino); + node = radix_tree_lookup(&root->delayed_nodes_tree, ino); if (node) { if (btrfs_inode->delayed_node) { @@ -90,9 +90,9 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node( /* * It's possible that we're racing into the middle of removing - * this node from the xarray. In this case, the refcount + * this node from the radix tree. In this case, the refcount * was zero and it should never go back to one. Just return - * NULL like it was never in the xarray at all; our release + * NULL like it was never in the radix at all; our release * function is in the process of removing it. * * Some implementations of refcount_inc refuse to bump the @@ -100,7 +100,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node( * here, refcount_inc() may decide to just WARN_ONCE() instead * of actually bumping the refcount. * - * If this node is properly in the xarray, we want to bump the + * If this node is properly in the radix, we want to bump the * refcount twice, once for the inode and once for this get * operation. */ @@ -128,30 +128,36 @@ static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node( u64 ino = btrfs_ino(btrfs_inode); int ret; - do { - node = btrfs_get_delayed_node(btrfs_inode); - if (node) - return node; +again: + node = btrfs_get_delayed_node(btrfs_inode); + if (node) + return node; - node = kmem_cache_zalloc(delayed_node_cache, GFP_NOFS); - if (!node) - return ERR_PTR(-ENOMEM); - btrfs_init_delayed_node(node, root, ino); + node = kmem_cache_zalloc(delayed_node_cache, GFP_NOFS); + if (!node) + return ERR_PTR(-ENOMEM); + btrfs_init_delayed_node(node, root, ino); - /* Cached in the inode and can be accessed */ - refcount_set(&node->refs, 2); + /* cached in the btrfs inode and can be accessed */ + refcount_set(&node->refs, 2); - spin_lock(&root->inode_lock); - ret = xa_insert(&root->delayed_nodes, ino, node, GFP_NOFS); - if (ret) { - spin_unlock(&root->inode_lock); - kmem_cache_free(delayed_node_cache, node); - if (ret != -EBUSY) - return ERR_PTR(ret); - } - } while (ret); + ret = radix_tree_preload(GFP_NOFS); + if (ret) { + kmem_cache_free(delayed_node_cache, node); + return ERR_PTR(ret); + } + + spin_lock(&root->inode_lock); + ret = radix_tree_insert(&root->delayed_nodes_tree, ino, node); + if (ret == -EEXIST) { + spin_unlock(&root->inode_lock); + kmem_cache_free(delayed_node_cache, node); + radix_tree_preload_end(); + goto again; + } btrfs_inode->delayed_node = node; spin_unlock(&root->inode_lock); + radix_tree_preload_end(); return node; } @@ -270,7 +276,8 @@ static void __btrfs_release_delayed_node( * back up. We can delete it now. */ ASSERT(refcount_read(&delayed_node->refs) == 0); - xa_erase(&root->delayed_nodes, delayed_node->inode_id); + radix_tree_delete(&root->delayed_nodes_tree, + delayed_node->inode_id); spin_unlock(&root->inode_lock); kmem_cache_free(delayed_node_cache, delayed_node); } @@ -1863,35 +1870,34 @@ void btrfs_kill_delayed_inode_items(struct btrfs_inode *inode) void btrfs_kill_all_delayed_nodes(struct btrfs_root *root) { - unsigned long index = 0; - struct btrfs_delayed_node *delayed_node; + u64 inode_id = 0; struct btrfs_delayed_node *delayed_nodes[8]; + int i, n; while (1) { - int n = 0; - spin_lock(&root->inode_lock); - if (xa_empty(&root->delayed_nodes)) { + n = radix_tree_gang_lookup(&root->delayed_nodes_tree, + (void **)delayed_nodes, inode_id, + ARRAY_SIZE(delayed_nodes)); + if (!n) { spin_unlock(&root->inode_lock); - return; + break; } - xa_for_each_start(&root->delayed_nodes, index, delayed_node, index) { + inode_id = delayed_nodes[n - 1]->inode_id + 1; + for (i = 0; i < n; i++) { /* * Don't increase refs in case the node is dead and * about to be removed from the tree in the loop below */ - if (refcount_inc_not_zero(&delayed_node->refs)) { - delayed_nodes[n] = delayed_node; - n++; - } - if (n >= ARRAY_SIZE(delayed_nodes)) - break; + if (!refcount_inc_not_zero(&delayed_nodes[i]->refs)) + delayed_nodes[i] = NULL; } - index++; spin_unlock(&root->inode_lock); - for (int i = 0; i < n; i++) { + for (i = 0; i < n; i++) { + if (!delayed_nodes[i]) + continue; __btrfs_kill_delayed_node(delayed_nodes[i]); btrfs_release_delayed_node(delayed_nodes[i]); } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4ba005c41983..de440ebf5648 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -5,6 +5,7 @@ #include <linux/fs.h> #include <linux/blkdev.h> +#include <linux/radix-tree.h> #include <linux/writeback.h> #include <linux/workqueue.h> #include <linux/kthread.h> @@ -485,7 +486,7 @@ static int csum_dirty_subpage_buffers(struct btrfs_fs_info *fs_info, uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur, fs_info->nodesize); - /* A dirty eb shouldn't disappear from extent_buffers */ + /* A dirty eb shouldn't disappear from buffer_radix */ if (WARN_ON(!eb)) return -EUCLEAN; @@ -1158,7 +1159,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, root->nr_delalloc_inodes = 0; root->nr_ordered_extents = 0; root->inode_tree = RB_ROOT; - xa_init_flags(&root->delayed_nodes, GFP_ATOMIC); + INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC); btrfs_init_root_block_rsv(root); @@ -1210,9 +1211,9 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks); #ifdef CONFIG_BTRFS_DEBUG INIT_LIST_HEAD(&root->leak_list); - spin_lock(&fs_info->fs_roots_lock); + spin_lock(&fs_info->fs_roots_radix_lock); list_add_tail(&root->leak_list, &fs_info->allocated_roots); - spin_unlock(&fs_info->fs_roots_lock); + spin_unlock(&fs_info->fs_roots_radix_lock); #endif } @@ -1659,11 +1660,12 @@ static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, { struct btrfs_root *root; - spin_lock(&fs_info->fs_roots_lock); - root = xa_load(&fs_info->fs_roots, (unsigned long)root_id); + spin_lock(&fs_info->fs_roots_radix_lock); + root = radix_tree_lookup(&fs_info->fs_roots_radix, + (unsigned long)root_id); if (root) root = btrfs_grab_root(root); - spin_unlock(&fs_info->fs_roots_lock); + spin_unlock(&fs_info->fs_roots_radix_lock); return root; } @@ -1705,14 +1707,20 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, { int ret; - spin_lock(&fs_info->fs_roots_lock); - ret = xa_insert(&fs_info->fs_roots, (unsigned long)root->root_key.objectid, - root, GFP_NOFS); + ret = radix_tree_preload(GFP_NOFS); + if (ret) + return ret; + + spin_lock(&fs_info->fs_roots_radix_lock); + ret = radix_tree_insert(&fs_info->fs_roots_radix, + (unsigned long)root->root_key.objectid, + root); if (ret == 0) { btrfs_grab_root(root); - set_bit(BTRFS_ROOT_REGISTERED, &root->state); + set_bit(BTRFS_ROOT_IN_RADIX, &root->state); } - spin_unlock(&fs_info->fs_roots_lock); + spin_unlock(&fs_info->fs_roots_radix_lock); + radix_tree_preload_end(); return ret; } @@ -2342,9 +2350,9 @@ void btrfs_put_root(struct btrfs_root *root) btrfs_drew_lock_destroy(&root->snapshot_lock); free_root_extent_buffers(root); #ifdef CONFIG_BTRFS_DEBUG - spin_lock(&root->fs_info->fs_roots_lock); + spin_lock(&root->fs_info->fs_roots_radix_lock); list_del_init(&root->leak_list); - spin_unlock(&root->fs_info->fs_roots_lock); + spin_unlock(&root->fs_info->fs_roots_radix_lock); #endif kfree(root); } @@ -2352,21 +2360,28 @@ void btrfs_put_root(struct btrfs_root *root) void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info) { - struct btrfs_root *root; - unsigned long index = 0; + int ret; + struct btrfs_root *gang[8]; + int i; while (!list_empty(&fs_info->dead_roots)) { - root = list_entry(fs_info->dead_roots.next, - struct btrfs_root, root_list); - list_del(&root->root_list); + gang[0] = list_entry(fs_info->dead_roots.next, + struct btrfs_root, root_list); + list_del(&gang[0]->root_list); - if (test_bit(BTRFS_ROOT_REGISTERED, &root->state)) - btrfs_drop_and_free_fs_root(fs_info, root); - btrfs_put_root(root); + if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state)) + btrfs_drop_and_free_fs_root(fs_info, gang[0]); + btrfs_put_root(gang[0]); } - xa_for_each(&fs_info->fs_roots, index, root) { - btrfs_drop_and_free_fs_root(fs_info, root); + while (1) { + ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, + (void **)gang, 0, + ARRAY_SIZE(gang)); + if (!ret) + break; + for (i = 0; i < ret; i++) + btrfs_drop_and_free_fs_root(fs_info, gang[i]); } } @@ -3134,8 +3149,8 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) { - xa_init_flags(&fs_info->fs_roots, GFP_ATOMIC); - xa_init_flags(&fs_info->extent_buffers, GFP_ATOMIC); + INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC); + INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC); INIT_LIST_HEAD(&fs_info->trans_list); INIT_LIST_HEAD(&fs_info->dead_roots); INIT_LIST_HEAD(&fs_info->delayed_iputs); @@ -3143,7 +3158,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) INIT_LIST_HEAD(&fs_info->caching_block_groups); spin_lock_init(&fs_info->delalloc_root_lock); spin_lock_init(&fs_info->trans_lock); - spin_lock_init(&fs_info->fs_roots_lock); + spin_lock_init(&fs_info->fs_roots_radix_lock); spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); spin_lock_init(&fs_info->super_lock); @@ -3374,7 +3389,7 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) /* * btrfs_find_orphan_roots() is responsible for finding all the dead * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load - * them into the fs_info->fs_roots. This must be done before + * them into the fs_info->fs_roots_radix tree. This must be done before * calling btrfs_orphan_cleanup() on the tree root. If we don't do it * first, then btrfs_orphan_cleanup() will delete a dead root's orphan * item before the root's tree is deleted - this means that if we unmount @@ -4499,11 +4514,12 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, { bool drop_ref = false; - spin_lock(&fs_info->fs_roots_lock); - xa_erase(&fs_info->fs_roots, (unsigned long)root->root_key.objectid); - if (test_and_clear_bit(BTRFS_ROOT_REGISTERED, &root->state)) + spin_lock(&fs_info->fs_roots_radix_lock); + radix_tree_delete(&fs_info->fs_roots_radix, + (unsigned long)root->root_key.objectid); + if (test_and_clear_bit(BTRFS_ROOT_IN_RADIX, &root->state)) drop_ref = true; - spin_unlock(&fs_info->fs_roots_lock); + spin_unlock(&fs_info->fs_roots_radix_lock); if (BTRFS_FS_ERROR(fs_info)) { ASSERT(root->log_root == NULL); @@ -4519,48 +4535,50 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) { - struct btrfs_root *roots[8]; - unsigned long index = 0; - int i; + u64 root_objectid = 0; + struct btrfs_root *gang[8]; + int i = 0; int err = 0; - int grabbed; + unsigned int ret = 0; while (1) { - struct btrfs_root *root; - - spin_lock(&fs_info->fs_roots_lock); - if (!xa_find(&fs_info->fs_roots, &index, ULONG_MAX, XA_PRESENT)) { - spin_unlock(&fs_info->fs_roots_lock); - return err; + spin_lock(&fs_info->fs_roots_radix_lock); + ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, + (void **)gang, root_objectid, + ARRAY_SIZE(gang)); + if (!ret) { + spin_unlock(&fs_info->fs_roots_radix_lock); + break; } + root_objectid = gang[ret - 1]->root_key.objectid + 1; - grabbed = 0; - xa_for_each_start(&fs_info->fs_roots, index, root, index) { - /* Avoid grabbing roots in dead_roots */ - if (btrfs_root_refs(&root->root_item) > 0) - roots[grabbed++] = btrfs_grab_root(root); - if (grabbed >= ARRAY_SIZE(roots)) - break; + for (i = 0; i < ret; i++) { + /* Avoid to grab roots in dead_roots */ + if (btrfs_root_refs(&gang[i]->root_item) == 0) { + gang[i] = NULL; + continue; + } + /* grab all the search result for later use */ + gang[i] = btrfs_grab_root(gang[i]); } - spin_unlock(&fs_info->fs_roots_lock); + spin_unlock(&fs_info->fs_roots_radix_lock); - for (i = 0; i < grabbed; i++) { - if (!roots[i]) + for (i = 0; i < ret; i++) { + if (!gang[i]) continue; - index = roots[i]->root_key.objectid; - err = btrfs_orphan_cleanup(roots[i]); + root_objectid = gang[i]->root_key.objectid; + err = btrfs_orphan_cleanup(gang[i]); if (err) - goto out; - btrfs_put_root(roots[i]); + break; + btrfs_put_root(gang[i]); } - index++; + root_objectid++; } -out: - /* Release the roots that remain uncleaned due to error */ - for (; i < grabbed; i++) { - if (roots[i]) - btrfs_put_root(roots[i]); + /* release the uncleaned roots due to error */ + for (; i < ret; i++) { + if (gang[i]) + btrfs_put_root(gang[i]); } return err; } @@ -4879,28 +4897,31 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info) static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info) { - unsigned long index = 0; - int grabbed = 0; - struct btrfs_root *roots[8]; + struct btrfs_root *gang[8]; + u64 root_objectid = 0; + int ret; + + spin_lock(&fs_info->fs_roots_radix_lock); + while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, + (void **)gang, root_objectid, + ARRAY_SIZE(gang))) != 0) { + int i; - spin_lock(&fs_info->fs_roots_lock); - while ((grabbed = xa_extract(&fs_info->fs_roots, (void **)roots, index, - ULONG_MAX, 8, XA_PRESENT))) { - for (int i = 0; i < grabbed; i++) - roots[i] = btrfs_grab_root(roots[i]); - spin_unlock(&fs_info->fs_roots_lock); + for (i = 0; i < ret; i++) + gang[i] = btrfs_grab_root(gang[i]); + spin_unlock(&fs_info->fs_roots_radix_lock); - for (int i = 0; i < grabbed; i++) { - if (!roots[i]) + for (i = 0; i < ret; i++) { + if (!gang[i]) continue; - index = roots[i]->root_key.objectid; - btrfs_free_log(NULL, roots[i]); - btrfs_put_root(roots[i]); + root_objectid = gang[i]->root_key.objectid; + btrfs_free_log(NULL, gang[i]); + btrfs_put_root(gang[i]); } - index++; - spin_lock(&fs_info->fs_roots_lock); + root_objectid++; + spin_lock(&fs_info->fs_roots_radix_lock); } - spin_unlock(&fs_info->fs_roots_lock); + spin_unlock(&fs_info->fs_roots_radix_lock); btrfs_free_log_root_tree(NULL, fs_info); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4157ecc27d4b..a3afc15430ce 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5829,7 +5829,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) btrfs_qgroup_convert_reserved_meta(root, INT_MAX); btrfs_qgroup_free_meta_all_pertrans(root); - if (test_bit(BTRFS_ROOT_REGISTERED, &root->state)) + if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state)) btrfs_add_dropped_root(trans, root); else btrfs_put_root(root); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 04e36343da3a..f03ab5dbda7a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2966,7 +2966,7 @@ static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page) } /* - * Find extent buffer for a given bytenr. + * Find extent buffer for a givne bytenr. * * This is for end_bio_extent_readpage(), thus we can't do any unsafe locking * in endio context. @@ -2985,9 +2985,11 @@ static struct extent_buffer *find_extent_buffer_readpage( return (struct extent_buffer *)page->private; } - /* For subpage case, we need to lookup extent buffer xarray */ - eb = xa_load(&fs_info->extent_buffers, - bytenr >> fs_info->sectorsize_bits); + /* For subpage case, we need to lookup buffer radix tree */ + rcu_read_lock(); + eb = radix_tree_lookup(&fs_info->buffer_radix, + bytenr >> fs_info->sectorsize_bits); + rcu_read_unlock(); ASSERT(eb); return eb; } @@ -4435,8 +4437,8 @@ static struct extent_buffer *find_extent_buffer_nolock( struct extent_buffer *eb; rcu_read_lock(); - eb = xa_load(&fs_info->extent_buffers, - start >> fs_info->sectorsize_bits); + eb = radix_tree_lookup(&fs_info->buffer_radix, + start >> fs_info->sectorsize_bits); if (eb && atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); return eb; @@ -6129,22 +6131,24 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, if (!eb) return ERR_PTR(-ENOMEM); eb->fs_info = fs_info; - - do { - ret = xa_insert(&fs_info->extent_buffers, - start >> fs_info->sectorsize_bits, - eb, GFP_NOFS); - if (ret == -ENOMEM) { - exists = ERR_PTR(ret); +again: + ret = radix_tree_preload(GFP_NOFS); + if (ret) { + exists = ERR_PTR(ret); + goto free_eb; + } + spin_lock(&fs_info->buffer_lock); + ret = radix_tree_insert(&fs_info->buffer_radix, + start >> fs_info->sectorsize_bits, eb); + spin_unlock(&fs_info->buffer_lock); + radix_tree_preload_end(); + if (ret == -EEXIST) { + exists = find_extent_buffer(fs_info, start); + if (exists) goto free_eb; - } - if (ret == -EBUSY) { - exists = find_extent_buffer(fs_info, start); - if (exists) - goto free_eb; - } - } while (ret); - + else + goto again; + } check_buffer_tree_ref(eb); set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags); @@ -6319,22 +6323,25 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, } if (uptodate) set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); - - do { - ret = xa_insert(&fs_info->extent_buffers, - start >> fs_info->sectorsize_bits, - eb, GFP_NOFS); - if (ret == -ENOMEM) { - exists = ERR_PTR(ret); +again: + ret = radix_tree_preload(GFP_NOFS); + if (ret) { + exists = ERR_PTR(ret); + goto free_eb; + } + + spin_lock(&fs_info->buffer_lock); + ret = radix_tree_insert(&fs_info->buffer_radix, + start >> fs_info->sectorsize_bits, eb); + spin_unlock(&fs_info->buffer_lock); + radix_tree_preload_end(); + if (ret == -EEXIST) { + exists = find_extent_buffer(fs_info, start); + if (exists) goto free_eb; - } - if (ret == -EBUSY) { - exists = find_extent_buffer(fs_info, start); - if (exists) - goto free_eb; - } - } while (ret); - + else + goto again; + } /* add one reference for the tree */ check_buffer_tree_ref(eb); set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags); @@ -6379,8 +6386,10 @@ static int release_extent_buffer(struct extent_buffer *eb) spin_unlock(&eb->refs_lock); - xa_erase(&fs_info->extent_buffers, - eb->start >> fs_info->sectorsize_bits); + spin_lock(&fs_info->buffer_lock); + radix_tree_delete(&fs_info->buffer_radix, + eb->start >> fs_info->sectorsize_bits); + spin_unlock(&fs_info->buffer_lock); } else { spin_unlock(&eb->refs_lock); } @@ -7325,25 +7334,42 @@ void memmove_extent_buffer(const struct extent_buffer *dst, } } +#define GANG_LOOKUP_SIZE 16 static struct extent_buffer *get_next_extent_buffer( struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr) { - struct extent_buffer *eb; - unsigned long index; + struct extent_buffer *gang[GANG_LOOKUP_SIZE]; + struct extent_buffer *found = NULL; u64 page_start = page_offset(page); + u64 cur = page_start; ASSERT(in_range(bytenr, page_start, PAGE_SIZE)); lockdep_assert_held(&fs_info->buffer_lock); - xa_for_each_start(&fs_info->extent_buffers, index, eb, - page_start >> fs_info->sectorsize_bits) { - if (in_range(eb->start, page_start, PAGE_SIZE)) - return eb; - else if (eb->start >= page_start + PAGE_SIZE) - /* Already beyond page end */ - return NULL; + while (cur < page_start + PAGE_SIZE) { + int ret; + int i; + + ret = radix_tree_gang_lookup(&fs_info->buffer_radix, + (void **)gang, cur >> fs_info->sectorsize_bits, + min_t(unsigned int, GANG_LOOKUP_SIZE, + PAGE_SIZE / fs_info->nodesize)); + if (ret == 0) + goto out; + for (i = 0; i < ret; i++) { + /* Already beyond page end */ + if (gang[i]->start >= page_start + PAGE_SIZE) + goto out; + /* Found one */ + if (gang[i]->start >= bytenr) { + found = gang[i]; + goto out; + } + } + cur = gang[ret - 1]->start + gang[ret - 1]->len; } - return NULL; +out: + return found; } static int try_release_subpage_extent_buffer(struct page *page) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 05e0c4a5affd..d50448bf8eed 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3578,7 +3578,6 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) u64 last_objectid = 0; int ret = 0, nr_unlink = 0; - /* Bail out if the cleanup is already running. */ if (test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP, &root->state)) return 0; @@ -3661,17 +3660,17 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) * * btrfs_find_orphan_roots() ran before us, which has * found all deleted roots and loaded them into - * fs_info->fs_roots. So here we can find if an + * fs_info->fs_roots_radix. So here we can find if an * orphan item corresponds to a deleted root by looking - * up the root from that xarray. + * up the root from that radix tree. */ - spin_lock(&fs_info->fs_roots_lock); - dead_root = xa_load(&fs_info->fs_roots, - (unsigned long)found_key.objectid); + spin_lock(&fs_info->fs_roots_radix_lock); + dead_root = radix_tree_lookup(&fs_info->fs_roots_radix, + (unsigned long)found_key.objectid); if (dead_root && btrfs_root_refs(&dead_root->root_item) == 0) is_dead_root = 1; - spin_unlock(&fs_info->fs_roots_lock); + spin_unlock(&fs_info->fs_roots_radix_lock); if (is_dead_root) { /* prevent this orphan from being found again */ @@ -3911,7 +3910,7 @@ cache_index: * cache. * * This is required for both inode re-read from disk and delayed inode - * in the delayed_nodes xarray. + * in delayed_nodes_tree. */ if (BTRFS_I(inode)->last_trans == fs_info->generation) set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, @@ -7681,7 +7680,19 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) || em->block_start == EXTENT_MAP_INLINE) { free_extent_map(em); - ret = -ENOTBLK; + /* + * If we are in a NOWAIT context, return -EAGAIN in order to + * fallback to buffered IO. This is not only because we can + * block with buffered IO (no support for NOWAIT semantics at + * the moment) but also to avoid returning short reads to user + * space - this happens if we were able to read some data from + * previous non-compressed extents and then when we fallback to + * buffered IO, at btrfs_file_read_iter() by calling + * filemap_read(), we fail to fault in pages for the read buffer, + * in which case filemap_read() returns a short read (the number + * of bytes previously read is > 0, so it does not return -EFAULT). + */ + ret = (flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOTBLK; goto unlock_err; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index fa56890ff81f..c7dea639a56f 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -10,6 +10,7 @@ #include <linux/mount.h> #include <linux/xattr.h> #include <linux/posix_acl_xattr.h> +#include <linux/radix-tree.h> #include <linux/vmalloc.h> #include <linux/string.h> #include <linux/compat.h> @@ -127,7 +128,7 @@ struct send_ctx { struct list_head new_refs; struct list_head deleted_refs; - struct xarray name_cache; + struct radix_tree_root name_cache; struct list_head name_cache_list; int name_cache_size; @@ -268,13 +269,14 @@ struct orphan_dir_info { struct name_cache_entry { struct list_head list; /* - * On 32bit kernels, xarray has only 32bit indices, but we need to - * handle 64bit inums. We use the lower 32bit of the 64bit inum to store - * it in the tree. If more than one inum would fall into the same entry, - * we use inum_aliases to store the additional entries. inum_aliases is - * also used to store entries with the same inum but different generations. + * radix_tree has only 32bit entries but we need to handle 64bit inums. + * We use the lower 32bit of the 64bit inum to store it in the tree. If + * more then one inum would fall into the same entry, we use radix_list + * to store the additional entries. radix_list is also used to store + * entries where two entries have the same inum but different + * generations. */ - struct list_head inum_aliases; + struct list_head radix_list; u64 ino; u64 gen; u64 parent_ino; @@ -2024,9 +2026,9 @@ out: } /* - * Insert a name cache entry. On 32bit kernels the xarray index is 32bit, + * Insert a name cache entry. On 32bit kernels the radix tree index is 32bit, * so we need to do some special handling in case we have clashes. This function - * takes care of this with the help of name_cache_entry::inum_aliases. + * takes care of this with the help of name_cache_entry::radix_list. * In case of error, nce is kfreed. */ static int name_cache_insert(struct send_ctx *sctx, @@ -2035,7 +2037,8 @@ static int name_cache_insert(struct send_ctx *sctx, int ret = 0; struct list_head *nce_head; - nce_head = xa_load(&sctx->name_cache, (unsigned long)nce->ino); + nce_head = radix_tree_lookup(&sctx->name_cache, + (unsigned long)nce->ino); if (!nce_head) { nce_head = kmalloc(sizeof(*nce_head), GFP_KERNEL); if (!nce_head) { @@ -2044,14 +2047,14 @@ static int name_cache_insert(struct send_ctx *sctx, } INIT_LIST_HEAD(nce_head); - ret = xa_insert(&sctx->name_cache, nce->ino, nce_head, GFP_KERNEL); + ret = radix_tree_insert(&sctx->name_cache, nce->ino, nce_head); if (ret < 0) { kfree(nce_head); kfree(nce); return ret; } } - list_add_tail(&nce->inum_aliases, nce_head); + list_add_tail(&nce->radix_list, nce_head); list_add_tail(&nce->list, &sctx->name_cache_list); sctx->name_cache_size++; @@ -2063,14 +2066,15 @@ static void name_cache_delete(struct send_ctx *sctx, { struct list_head *nce_head; - nce_head = xa_load(&sctx->name_cache, (unsigned long)nce->ino); + nce_head = radix_tree_lookup(&sctx->name_cache, + (unsigned long)nce->ino); if (!nce_head) { btrfs_err(sctx->send_root->fs_info, "name_cache_delete lookup failed ino %llu cache size %d, leaking memory", nce->ino, sctx->name_cache_size); } - list_del(&nce->inum_aliases); + list_del(&nce->radix_list); list_del(&nce->list); sctx->name_cache_size--; @@ -2078,7 +2082,7 @@ static void name_cache_delete(struct send_ctx *sctx, * We may not get to the final release of nce_head if the lookup fails */ if (nce_head && list_empty(nce_head)) { - xa_erase(&sctx->name_cache, (unsigned long)nce->ino); + radix_tree_delete(&sctx->name_cache, (unsigned long)nce->ino); kfree(nce_head); } } @@ -2089,11 +2093,11 @@ static struct name_cache_entry *name_cache_search(struct send_ctx *sctx, struct list_head *nce_head; struct name_cache_entry *cur; - nce_head = xa_load(&sctx->name_cache, (unsigned long)ino); + nce_head = radix_tree_lookup(&sctx->name_cache, (unsigned long)ino); if (!nce_head) return NULL; - list_for_each_entry(cur, nce_head, inum_aliases) { + list_for_each_entry(cur, nce_head, radix_list) { if (cur->ino == ino && cur->gen == gen) return cur; } @@ -7518,7 +7522,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) INIT_LIST_HEAD(&sctx->new_refs); INIT_LIST_HEAD(&sctx->deleted_refs); - xa_init_flags(&sctx->name_cache, GFP_KERNEL); + INIT_RADIX_TREE(&sctx->name_cache, GFP_KERNEL); INIT_LIST_HEAD(&sctx->name_cache_list); sctx->flags = arg->flags; diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 1591bfa55bcc..d8e56edd6991 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -150,8 +150,8 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize) void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info) { - unsigned long index; - struct extent_buffer *eb; + struct radix_tree_iter iter; + void **slot; struct btrfs_device *dev, *tmp; if (!fs_info) @@ -163,9 +163,25 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info) test_mnt->mnt_sb->s_fs_info = NULL; - xa_for_each(&fs_info->extent_buffers, index, eb) { + spin_lock(&fs_info->buffer_lock); + radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, 0) { + struct extent_buffer *eb; + + eb = radix_tree_deref_slot_protected(slot, &fs_info->buffer_lock); + if (!eb) + continue; + /* Shouldn't happen but that kind of thinking creates CVE's */ + if (radix_tree_exception(eb)) { + if (radix_tree_deref_retry(eb)) + slot = radix_tree_iter_retry(&iter); + continue; + } + slot = radix_tree_iter_resume(slot, &iter); + spin_unlock(&fs_info->buffer_lock); free_extent_buffer_stale(eb); + spin_lock(&fs_info->buffer_lock); } + spin_unlock(&fs_info->buffer_lock); btrfs_mapping_tree_free(&fs_info->mapping_tree); list_for_each_entry_safe(dev, tmp, &fs_info->fs_devices->devices, @@ -186,7 +202,7 @@ void btrfs_free_dummy_root(struct btrfs_root *root) if (!root) return; /* Will be freed by btrfs_free_fs_roots */ - if (WARN_ON(test_bit(BTRFS_ROOT_REGISTERED, &root->state))) + if (WARN_ON(test_bit(BTRFS_ROOT_IN_RADIX, &root->state))) return; btrfs_global_root_delete(root); btrfs_put_root(root); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 06c0a958d114..875b801ab3d7 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -23,7 +23,7 @@ #include "space-info.h" #include "zoned.h" -#define BTRFS_ROOT_TRANS_TAG XA_MARK_0 +#define BTRFS_ROOT_TRANS_TAG 0 /* * Transaction states and transitions @@ -437,15 +437,15 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans, */ smp_wmb(); - spin_lock(&fs_info->fs_roots_lock); + spin_lock(&fs_info->fs_roots_radix_lock); if (root->last_trans == trans->transid && !force) { - spin_unlock(&fs_info->fs_roots_lock); + spin_unlock(&fs_info->fs_roots_radix_lock); return 0; } - xa_set_mark(&fs_info->fs_roots, - (unsigned long)root->root_key.objectid, - BTRFS_ROOT_TRANS_TAG); - spin_unlock(&fs_info->fs_roots_lock); + radix_tree_tag_set(&fs_info->fs_roots_radix, + (unsigned long)root->root_key.objectid, + BTRFS_ROOT_TRANS_TAG); + spin_unlock(&fs_info->fs_roots_radix_lock); root->last_trans = trans->transid; /* this is pretty tricky. We don't want to @@ -487,9 +487,11 @@ void btrfs_add_dropped_root(struct btrfs_trans_handle *trans, spin_unlock(&cur_trans->dropped_roots_lock); /* Make sure we don't try to update the root at commit time */ - xa_clear_mark(&fs_info->fs_roots, - (unsigned long)root->root_key.objectid, - BTRFS_ROOT_TRANS_TAG); + spin_lock(&fs_info->fs_roots_radix_lock); + radix_tree_tag_clear(&fs_info->fs_roots_radix, + (unsigned long)root->root_key.objectid, + BTRFS_ROOT_TRANS_TAG); + spin_unlock(&fs_info->fs_roots_radix_lock); } int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, @@ -1402,8 +1404,9 @@ void btrfs_add_dead_root(struct btrfs_root *root) static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_root *root; - unsigned long index; + struct btrfs_root *gang[8]; + int i; + int ret; /* * At this point no one can be using this transaction to modify any tree @@ -1411,46 +1414,57 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) */ ASSERT(trans->transaction->state == TRANS_STATE_COMMIT_DOING); - spin_lock(&fs_info->fs_roots_lock); - xa_for_each_marked(&fs_info->fs_roots, index, root, BTRFS_ROOT_TRANS_TAG) { - int ret; - - /* - * At this point we can neither have tasks logging inodes - * from a root nor trying to commit a log tree. - */ - ASSERT(atomic_read(&root->log_writers) == 0); - ASSERT(atomic_read(&root->log_commit[0]) == 0); - ASSERT(atomic_read(&root->log_commit[1]) == 0); - - xa_clear_mark(&fs_info->fs_roots, - (unsigned long)root->root_key.objectid, - BTRFS_ROOT_TRANS_TAG); - spin_unlock(&fs_info->fs_roots_lock); - - btrfs_free_log(trans, root); - ret = btrfs_update_reloc_root(trans, root); - if (ret) - return ret; - - /* See comments in should_cow_block() */ - clear_bit(BTRFS_ROOT_FORCE_COW, &root->state); - smp_mb__after_atomic(); + spin_lock(&fs_info->fs_roots_radix_lock); + while (1) { + ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix, + (void **)gang, 0, + ARRAY_SIZE(gang), + BTRFS_ROOT_TRANS_TAG); + if (ret == 0) + break; + for (i = 0; i < ret; i++) { + struct btrfs_root *root = gang[i]; + int ret2; + + /* + * At this point we can neither have tasks logging inodes + * from a root nor trying to commit a log tree. + */ + ASSERT(atomic_read(&root->log_writers) == 0); + ASSERT(atomic_read(&root->log_commit[0]) == 0); + ASSERT(atomic_read(&root->log_commit[1]) == 0); + + radix_tree_tag_clear(&fs_info->fs_roots_radix, + (unsigned long)root->root_key.objectid, + BTRFS_ROOT_TRANS_TAG); + spin_unlock(&fs_info->fs_roots_radix_lock); + + btrfs_free_log(trans, root); + ret2 = btrfs_update_reloc_root(trans, root); + if (ret2) + return ret2; + + /* see comments in should_cow_block() */ + clear_bit(BTRFS_ROOT_FORCE_COW, &root->state); + smp_mb__after_atomic(); + + if (root->commit_root != root->node) { + list_add_tail(&root->dirty_list, + &trans->transaction->switch_commits); + btrfs_set_root_node(&root->root_item, + root->node); + } - if (root->commit_root != root->node) { - list_add_tail(&root->dirty_list, - &trans->transaction->switch_commits); - btrfs_set_root_node(&root->root_item, root->node); + ret2 = btrfs_update_root(trans, fs_info->tree_root, + &root->root_key, + &root->root_item); + if (ret2) + return ret2; + spin_lock(&fs_info->fs_roots_radix_lock); + btrfs_qgroup_free_meta_all_pertrans(root); } - - ret = btrfs_update_root(trans, fs_info->tree_root, - &root->root_key, &root->root_item); - if (ret) - return ret; - spin_lock(&fs_info->fs_roots_lock); - btrfs_qgroup_free_meta_all_pertrans(root); } - spin_unlock(&fs_info->fs_roots_lock); + spin_unlock(&fs_info->fs_roots_radix_lock); return 0; } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 79e8c8cd75ed..d99026df6f67 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1735,12 +1735,14 @@ static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical, ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical, &mapped_length, &bioc); if (ret || !bioc || mapped_length < PAGE_SIZE) { - btrfs_put_bioc(bioc); - return -EIO; + ret = -EIO; + goto out_put_bioc; } - if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) - return -EINVAL; + if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) { + ret = -EINVAL; + goto out_put_bioc; + } nofs_flag = memalloc_nofs_save(); nmirrors = (int)bioc->num_stripes; @@ -1759,7 +1761,8 @@ static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical, break; } memalloc_nofs_restore(nofs_flag); - +out_put_bioc: + btrfs_put_bioc(bioc); return ret; } @@ -1885,7 +1888,6 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ { struct btrfs_fs_info *fs_info = block_group->fs_info; struct map_lookup *map; - bool need_zone_finish; int ret = 0; int i; @@ -1942,12 +1944,6 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ } } - /* - * The block group is not fully allocated, so not fully written yet. We - * need to send ZONE_FINISH command to free up an active zone. - */ - need_zone_finish = !btrfs_zoned_bg_is_full(block_group); - block_group->zone_is_active = 0; block_group->alloc_offset = block_group->zone_capacity; block_group->free_space_ctl->free_space = 0; @@ -1963,15 +1959,13 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ if (device->zone_info->max_active_zones == 0) continue; - if (need_zone_finish) { - ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, - physical >> SECTOR_SHIFT, - device->zone_info->zone_size >> SECTOR_SHIFT, - GFP_NOFS); + ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, + physical >> SECTOR_SHIFT, + device->zone_info->zone_size >> SECTOR_SHIFT, + GFP_NOFS); - if (ret) - return ret; - } + if (ret) + return ret; btrfs_dev_clear_active_zone(device, physical); } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 6dee88815491..d6e5916138e4 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -63,7 +63,7 @@ (CONGESTION_ON_THRESH(congestion_kb) >> 2)) static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len, - struct folio *folio, void **_fsdata); + struct folio **foliop, void **_fsdata); static inline struct ceph_snap_context *page_snap_context(struct page *page) { @@ -1288,18 +1288,19 @@ ceph_find_incompatible(struct page *page) } static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len, - struct folio *folio, void **_fsdata) + struct folio **foliop, void **_fsdata) { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_snap_context *snapc; - snapc = ceph_find_incompatible(folio_page(folio, 0)); + snapc = ceph_find_incompatible(folio_page(*foliop, 0)); if (snapc) { int r; - folio_unlock(folio); - folio_put(folio); + folio_unlock(*foliop); + folio_put(*foliop); + *foliop = NULL; if (IS_ERR(snapc)) return PTR_ERR(snapc); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index fa29c9aae24b..386bb523c69e 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1918,7 +1918,6 @@ void cifs_put_smb_ses(struct cifs_ses *ses) list_del_init(&ses->smb_ses_list); spin_unlock(&cifs_tcp_ses_lock); - spin_lock(&ses->chan_lock); chan_count = ses->chan_count; /* close any extra channels */ @@ -1934,7 +1933,6 @@ void cifs_put_smb_ses(struct cifs_ses *ses) ses->chans[i].server = NULL; } } - spin_unlock(&ses->chan_lock); sesInfoFree(ses); cifs_put_tcp_session(server, 0); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index b85718f32b53..02c8b2906196 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -474,6 +474,14 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, out: if (rc && chan->server) { + /* + * we should avoid race with these delayed works before we + * remove this channel + */ + cancel_delayed_work_sync(&chan->server->echo); + cancel_delayed_work_sync(&chan->server->resolve); + cancel_delayed_work_sync(&chan->server->reconnect); + spin_lock(&ses->chan_lock); /* we rely on all bits beyond chan_count to be clear */ cifs_chan_clear_need_reconnect(ses, chan->server); @@ -484,10 +492,9 @@ out: */ WARN_ON(ses->chan_count < 1); spin_unlock(&ses->chan_lock); - } - if (rc && chan->server) cifs_put_tcp_session(chan->server, 0); + } return rc; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 12b4dddaedb0..c705de32e225 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -571,10 +571,6 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, *total_len += ctxt_len; pneg_ctxt += ctxt_len; - build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt); - *total_len += sizeof(struct smb2_posix_neg_context); - pneg_ctxt += sizeof(struct smb2_posix_neg_context); - /* * secondary channels don't have the hostname field populated * use the hostname field in the primary channel instead @@ -586,9 +582,14 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, hostname); *total_len += ctxt_len; pneg_ctxt += ctxt_len; - neg_context_count = 4; - } else /* second channels do not have a hostname */ neg_context_count = 3; + } else + neg_context_count = 2; + + build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt); + *total_len += sizeof(struct smb2_posix_neg_context); + pneg_ctxt += sizeof(struct smb2_posix_neg_context); + neg_context_count++; if (server->compress_algorithm) { build_compression_ctxt((struct smb2_compression_capabilities_context *) diff --git a/fs/exec.c b/fs/exec.c index 0989fb8472a1..778123259e42 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1301,7 +1301,7 @@ int begin_new_exec(struct linux_binprm * bprm) bprm->mm = NULL; #ifdef CONFIG_POSIX_TIMERS - exit_itimers(me->signal); + exit_itimers(me); flush_itimer_signals(); #endif diff --git a/fs/io_uring.c b/fs/io_uring.c deleted file mode 100644 index a01ea49f3017..000000000000 --- a/fs/io_uring.c +++ /dev/null @@ -1,13265 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Shared application/kernel submission and completion ring pairs, for - * supporting fast/efficient IO. - * - * A note on the read/write ordering memory barriers that are matched between - * the application and kernel side. - * - * After the application reads the CQ ring tail, it must use an - * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses - * before writing the tail (using smp_load_acquire to read the tail will - * do). It also needs a smp_mb() before updating CQ head (ordering the - * entry load(s) with the head store), pairing with an implicit barrier - * through a control-dependency in io_get_cqe (smp_store_release to - * store head will do). Failure to do so could lead to reading invalid - * CQ entries. - * - * Likewise, the application must use an appropriate smp_wmb() before - * writing the SQ tail (ordering SQ entry stores with the tail store), - * which pairs with smp_load_acquire in io_get_sqring (smp_store_release - * to store the tail will do). And it needs a barrier ordering the SQ - * head load before writing new SQ entries (smp_load_acquire to read - * head will do). - * - * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application - * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after* - * updating the SQ tail; a full memory barrier smp_mb() is needed - * between. - * - * Also see the examples in the liburing library: - * - * git://git.kernel.dk/liburing - * - * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens - * from data shared between the kernel and application. This is done both - * for ordering purposes, but also to ensure that once a value is loaded from - * data that the application could potentially modify, it remains stable. - * - * Copyright (C) 2018-2019 Jens Axboe - * Copyright (c) 2018-2019 Christoph Hellwig - */ -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/errno.h> -#include <linux/syscalls.h> -#include <linux/compat.h> -#include <net/compat.h> -#include <linux/refcount.h> -#include <linux/uio.h> -#include <linux/bits.h> - -#include <linux/sched/signal.h> -#include <linux/fs.h> -#include <linux/file.h> -#include <linux/fdtable.h> -#include <linux/mm.h> -#include <linux/mman.h> -#include <linux/percpu.h> -#include <linux/slab.h> -#include <linux/blk-mq.h> -#include <linux/bvec.h> -#include <linux/net.h> -#include <net/sock.h> -#include <net/af_unix.h> -#include <net/scm.h> -#include <linux/anon_inodes.h> -#include <linux/sched/mm.h> -#include <linux/uaccess.h> -#include <linux/nospec.h> -#include <linux/sizes.h> -#include <linux/hugetlb.h> -#include <linux/highmem.h> -#include <linux/namei.h> -#include <linux/fsnotify.h> -#include <linux/fadvise.h> -#include <linux/eventpoll.h> -#include <linux/splice.h> -#include <linux/task_work.h> -#include <linux/pagemap.h> -#include <linux/io_uring.h> -#include <linux/audit.h> -#include <linux/security.h> -#include <linux/xattr.h> - -#define CREATE_TRACE_POINTS -#include <trace/events/io_uring.h> - -#include <uapi/linux/io_uring.h> - -#include "internal.h" -#include "io-wq.h" - -#define IORING_MAX_ENTRIES 32768 -#define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES) -#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 - -/* only define max */ -#define IORING_MAX_FIXED_FILES (1U << 20) -#define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ - IORING_REGISTER_LAST + IORING_OP_LAST) - -#define IO_RSRC_TAG_TABLE_SHIFT (PAGE_SHIFT - 3) -#define IO_RSRC_TAG_TABLE_MAX (1U << IO_RSRC_TAG_TABLE_SHIFT) -#define IO_RSRC_TAG_TABLE_MASK (IO_RSRC_TAG_TABLE_MAX - 1) - -#define IORING_MAX_REG_BUFFERS (1U << 14) - -#define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \ - IOSQE_IO_HARDLINK | IOSQE_ASYNC) - -#define SQE_VALID_FLAGS (SQE_COMMON_FLAGS | IOSQE_BUFFER_SELECT | \ - IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS) - -#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ - REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \ - REQ_F_ASYNC_DATA) - -#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\ - IO_REQ_CLEAN_FLAGS) - -#define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED) - -#define IO_TCTX_REFS_CACHE_NR (1U << 10) - -struct io_uring { - u32 head ____cacheline_aligned_in_smp; - u32 tail ____cacheline_aligned_in_smp; -}; - -/* - * This data is shared with the application through the mmap at offsets - * IORING_OFF_SQ_RING and IORING_OFF_CQ_RING. - * - * The offsets to the member fields are published through struct - * io_sqring_offsets when calling io_uring_setup. - */ -struct io_rings { - /* - * Head and tail offsets into the ring; the offsets need to be - * masked to get valid indices. - * - * The kernel controls head of the sq ring and the tail of the cq ring, - * and the application controls tail of the sq ring and the head of the - * cq ring. - */ - struct io_uring sq, cq; - /* - * Bitmasks to apply to head and tail offsets (constant, equals - * ring_entries - 1) - */ - u32 sq_ring_mask, cq_ring_mask; - /* Ring sizes (constant, power of 2) */ - u32 sq_ring_entries, cq_ring_entries; - /* - * Number of invalid entries dropped by the kernel due to - * invalid index stored in array - * - * Written by the kernel, shouldn't be modified by the - * application (i.e. get number of "new events" by comparing to - * cached value). - * - * After a new SQ head value was read by the application this - * counter includes all submissions that were dropped reaching - * the new SQ head (and possibly more). - */ - u32 sq_dropped; - /* - * Runtime SQ flags - * - * Written by the kernel, shouldn't be modified by the - * application. - * - * The application needs a full memory barrier before checking - * for IORING_SQ_NEED_WAKEUP after updating the sq tail. - */ - atomic_t sq_flags; - /* - * Runtime CQ flags - * - * Written by the application, shouldn't be modified by the - * kernel. - */ - u32 cq_flags; - /* - * Number of completion events lost because the queue was full; - * this should be avoided by the application by making sure - * there are not more requests pending than there is space in - * the completion queue. - * - * Written by the kernel, shouldn't be modified by the - * application (i.e. get number of "new events" by comparing to - * cached value). - * - * As completion events come in out of order this counter is not - * ordered with any other data. - */ - u32 cq_overflow; - /* - * Ring buffer of completion events. - * - * The kernel writes completion events fresh every time they are - * produced, so the application is allowed to modify pending - * entries. - */ - struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp; -}; - -struct io_mapped_ubuf { - u64 ubuf; - u64 ubuf_end; - unsigned int nr_bvecs; - unsigned long acct_pages; - struct bio_vec bvec[]; -}; - -struct io_ring_ctx; - -struct io_overflow_cqe { - struct list_head list; - struct io_uring_cqe cqe; -}; - -/* - * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0 - * and define IO_URING_SCM_ALL. For this case, we use SCM for all files as we - * can't safely always dereference the file when the task has exited and ring - * cleanup is done. If a file is tracked and part of SCM, then unix gc on - * process exit may reap it before __io_sqe_files_unregister() is run. - */ -#define FFS_NOWAIT 0x1UL -#define FFS_ISREG 0x2UL -#if defined(CONFIG_64BIT) -#define FFS_SCM 0x4UL -#else -#define IO_URING_SCM_ALL -#define FFS_SCM 0x0UL -#endif -#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG|FFS_SCM) - -struct io_fixed_file { - /* file * with additional FFS_* flags */ - unsigned long file_ptr; -}; - -struct io_rsrc_put { - struct list_head list; - u64 tag; - union { - void *rsrc; - struct file *file; - struct io_mapped_ubuf *buf; - }; -}; - -struct io_file_table { - struct io_fixed_file *files; - unsigned long *bitmap; - unsigned int alloc_hint; -}; - -struct io_rsrc_node { - struct percpu_ref refs; - struct list_head node; - struct list_head rsrc_list; - struct io_rsrc_data *rsrc_data; - struct llist_node llist; - bool done; -}; - -typedef void (rsrc_put_fn)(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc); - -struct io_rsrc_data { - struct io_ring_ctx *ctx; - - u64 **tags; - unsigned int nr; - rsrc_put_fn *do_put; - atomic_t refs; - struct completion done; - bool quiesce; -}; - -#define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf)) -struct io_buffer_list { - /* - * If ->buf_nr_pages is set, then buf_pages/buf_ring are used. If not, - * then these are classic provided buffers and ->buf_list is used. - */ - union { - struct list_head buf_list; - struct { - struct page **buf_pages; - struct io_uring_buf_ring *buf_ring; - }; - }; - __u16 bgid; - - /* below is for ring provided buffers */ - __u16 buf_nr_pages; - __u16 nr_entries; - __u16 head; - __u16 mask; -}; - -struct io_buffer { - struct list_head list; - __u64 addr; - __u32 len; - __u16 bid; - __u16 bgid; -}; - -struct io_restriction { - DECLARE_BITMAP(register_op, IORING_REGISTER_LAST); - DECLARE_BITMAP(sqe_op, IORING_OP_LAST); - u8 sqe_flags_allowed; - u8 sqe_flags_required; - bool registered; -}; - -enum { - IO_SQ_THREAD_SHOULD_STOP = 0, - IO_SQ_THREAD_SHOULD_PARK, -}; - -struct io_sq_data { - refcount_t refs; - atomic_t park_pending; - struct mutex lock; - - /* ctx's that are using this sqd */ - struct list_head ctx_list; - - struct task_struct *thread; - struct wait_queue_head wait; - - unsigned sq_thread_idle; - int sq_cpu; - pid_t task_pid; - pid_t task_tgid; - - unsigned long state; - struct completion exited; -}; - -#define IO_COMPL_BATCH 32 -#define IO_REQ_CACHE_SIZE 32 -#define IO_REQ_ALLOC_BATCH 8 - -struct io_submit_link { - struct io_kiocb *head; - struct io_kiocb *last; -}; - -struct io_submit_state { - /* inline/task_work completion list, under ->uring_lock */ - struct io_wq_work_node free_list; - /* batch completion logic */ - struct io_wq_work_list compl_reqs; - struct io_submit_link link; - - bool plug_started; - bool need_plug; - bool flush_cqes; - unsigned short submit_nr; - struct blk_plug plug; -}; - -struct io_ev_fd { - struct eventfd_ctx *cq_ev_fd; - unsigned int eventfd_async: 1; - struct rcu_head rcu; -}; - -#define BGID_ARRAY 64 - -struct io_ring_ctx { - /* const or read-mostly hot data */ - struct { - struct percpu_ref refs; - - struct io_rings *rings; - unsigned int flags; - enum task_work_notify_mode notify_method; - unsigned int compat: 1; - unsigned int drain_next: 1; - unsigned int restricted: 1; - unsigned int off_timeout_used: 1; - unsigned int drain_active: 1; - unsigned int drain_disabled: 1; - unsigned int has_evfd: 1; - unsigned int syscall_iopoll: 1; - } ____cacheline_aligned_in_smp; - - /* submission data */ - struct { - struct mutex uring_lock; - - /* - * Ring buffer of indices into array of io_uring_sqe, which is - * mmapped by the application using the IORING_OFF_SQES offset. - * - * This indirection could e.g. be used to assign fixed - * io_uring_sqe entries to operations and only submit them to - * the queue when needed. - * - * The kernel modifies neither the indices array nor the entries - * array. - */ - u32 *sq_array; - struct io_uring_sqe *sq_sqes; - unsigned cached_sq_head; - unsigned sq_entries; - struct list_head defer_list; - - /* - * Fixed resources fast path, should be accessed only under - * uring_lock, and updated through io_uring_register(2) - */ - struct io_rsrc_node *rsrc_node; - int rsrc_cached_refs; - atomic_t cancel_seq; - struct io_file_table file_table; - unsigned nr_user_files; - unsigned nr_user_bufs; - struct io_mapped_ubuf **user_bufs; - - struct io_submit_state submit_state; - - struct io_buffer_list *io_bl; - struct xarray io_bl_xa; - struct list_head io_buffers_cache; - - struct list_head timeout_list; - struct list_head ltimeout_list; - struct list_head cq_overflow_list; - struct list_head apoll_cache; - struct xarray personalities; - u32 pers_next; - unsigned sq_thread_idle; - } ____cacheline_aligned_in_smp; - - /* IRQ completion list, under ->completion_lock */ - struct io_wq_work_list locked_free_list; - unsigned int locked_free_nr; - - const struct cred *sq_creds; /* cred used for __io_sq_thread() */ - struct io_sq_data *sq_data; /* if using sq thread polling */ - - struct wait_queue_head sqo_sq_wait; - struct list_head sqd_list; - - unsigned long check_cq; - - struct { - /* - * We cache a range of free CQEs we can use, once exhausted it - * should go through a slower range setup, see __io_get_cqe() - */ - struct io_uring_cqe *cqe_cached; - struct io_uring_cqe *cqe_sentinel; - - unsigned cached_cq_tail; - unsigned cq_entries; - struct io_ev_fd __rcu *io_ev_fd; - struct wait_queue_head cq_wait; - unsigned cq_extra; - atomic_t cq_timeouts; - unsigned cq_last_tm_flush; - } ____cacheline_aligned_in_smp; - - struct { - spinlock_t completion_lock; - - spinlock_t timeout_lock; - - /* - * ->iopoll_list is protected by the ctx->uring_lock for - * io_uring instances that don't use IORING_SETUP_SQPOLL. - * For SQPOLL, only the single threaded io_sq_thread() will - * manipulate the list, hence no extra locking is needed there. - */ - struct io_wq_work_list iopoll_list; - struct hlist_head *cancel_hash; - unsigned cancel_hash_bits; - bool poll_multi_queue; - - struct list_head io_buffers_comp; - } ____cacheline_aligned_in_smp; - - struct io_restriction restrictions; - - /* slow path rsrc auxilary data, used by update/register */ - struct { - struct io_rsrc_node *rsrc_backup_node; - struct io_mapped_ubuf *dummy_ubuf; - struct io_rsrc_data *file_data; - struct io_rsrc_data *buf_data; - - struct delayed_work rsrc_put_work; - struct llist_head rsrc_put_llist; - struct list_head rsrc_ref_list; - spinlock_t rsrc_ref_lock; - - struct list_head io_buffers_pages; - }; - - /* Keep this last, we don't need it for the fast path */ - struct { - #if defined(CONFIG_UNIX) - struct socket *ring_sock; - #endif - /* hashed buffered write serialization */ - struct io_wq_hash *hash_map; - - /* Only used for accounting purposes */ - struct user_struct *user; - struct mm_struct *mm_account; - - /* ctx exit and cancelation */ - struct llist_head fallback_llist; - struct delayed_work fallback_work; - struct work_struct exit_work; - struct list_head tctx_list; - struct completion ref_comp; - u32 iowq_limits[2]; - bool iowq_limits_set; - }; -}; - -/* - * Arbitrary limit, can be raised if need be - */ -#define IO_RINGFD_REG_MAX 16 - -struct io_uring_task { - /* submission side */ - int cached_refs; - struct xarray xa; - struct wait_queue_head wait; - const struct io_ring_ctx *last; - struct io_wq *io_wq; - struct percpu_counter inflight; - atomic_t inflight_tracked; - atomic_t in_idle; - - spinlock_t task_lock; - struct io_wq_work_list task_list; - struct io_wq_work_list prio_task_list; - struct callback_head task_work; - struct file **registered_rings; - bool task_running; -}; - -/* - * First field must be the file pointer in all the - * iocb unions! See also 'struct kiocb' in <linux/fs.h> - */ -struct io_poll_iocb { - struct file *file; - struct wait_queue_head *head; - __poll_t events; - struct wait_queue_entry wait; -}; - -struct io_poll_update { - struct file *file; - u64 old_user_data; - u64 new_user_data; - __poll_t events; - bool update_events; - bool update_user_data; -}; - -struct io_close { - struct file *file; - int fd; - u32 file_slot; -}; - -struct io_timeout_data { - struct io_kiocb *req; - struct hrtimer timer; - struct timespec64 ts; - enum hrtimer_mode mode; - u32 flags; -}; - -struct io_accept { - struct file *file; - struct sockaddr __user *addr; - int __user *addr_len; - int flags; - u32 file_slot; - unsigned long nofile; -}; - -struct io_socket { - struct file *file; - int domain; - int type; - int protocol; - int flags; - u32 file_slot; - unsigned long nofile; -}; - -struct io_sync { - struct file *file; - loff_t len; - loff_t off; - int flags; - int mode; -}; - -struct io_cancel { - struct file *file; - u64 addr; - u32 flags; - s32 fd; -}; - -struct io_timeout { - struct file *file; - u32 off; - u32 target_seq; - struct list_head list; - /* head of the link, used by linked timeouts only */ - struct io_kiocb *head; - /* for linked completions */ - struct io_kiocb *prev; -}; - -struct io_timeout_rem { - struct file *file; - u64 addr; - - /* timeout update */ - struct timespec64 ts; - u32 flags; - bool ltimeout; -}; - -struct io_rw { - /* NOTE: kiocb has the file as the first member, so don't do it here */ - struct kiocb kiocb; - u64 addr; - u32 len; - rwf_t flags; -}; - -struct io_connect { - struct file *file; - struct sockaddr __user *addr; - int addr_len; -}; - -struct io_sr_msg { - struct file *file; - union { - struct compat_msghdr __user *umsg_compat; - struct user_msghdr __user *umsg; - void __user *buf; - }; - int msg_flags; - size_t len; - size_t done_io; - unsigned int flags; -}; - -struct io_open { - struct file *file; - int dfd; - u32 file_slot; - struct filename *filename; - struct open_how how; - unsigned long nofile; -}; - -struct io_rsrc_update { - struct file *file; - u64 arg; - u32 nr_args; - u32 offset; -}; - -struct io_fadvise { - struct file *file; - u64 offset; - u32 len; - u32 advice; -}; - -struct io_madvise { - struct file *file; - u64 addr; - u32 len; - u32 advice; -}; - -struct io_epoll { - struct file *file; - int epfd; - int op; - int fd; - struct epoll_event event; -}; - -struct io_splice { - struct file *file_out; - loff_t off_out; - loff_t off_in; - u64 len; - int splice_fd_in; - unsigned int flags; -}; - -struct io_provide_buf { - struct file *file; - __u64 addr; - __u32 len; - __u32 bgid; - __u16 nbufs; - __u16 bid; -}; - -struct io_statx { - struct file *file; - int dfd; - unsigned int mask; - unsigned int flags; - struct filename *filename; - struct statx __user *buffer; -}; - -struct io_shutdown { - struct file *file; - int how; -}; - -struct io_rename { - struct file *file; - int old_dfd; - int new_dfd; - struct filename *oldpath; - struct filename *newpath; - int flags; -}; - -struct io_unlink { - struct file *file; - int dfd; - int flags; - struct filename *filename; -}; - -struct io_mkdir { - struct file *file; - int dfd; - umode_t mode; - struct filename *filename; -}; - -struct io_symlink { - struct file *file; - int new_dfd; - struct filename *oldpath; - struct filename *newpath; -}; - -struct io_hardlink { - struct file *file; - int old_dfd; - int new_dfd; - struct filename *oldpath; - struct filename *newpath; - int flags; -}; - -struct io_msg { - struct file *file; - u64 user_data; - u32 len; -}; - -struct io_async_connect { - struct sockaddr_storage address; -}; - -struct io_async_msghdr { - struct iovec fast_iov[UIO_FASTIOV]; - /* points to an allocated iov, if NULL we use fast_iov instead */ - struct iovec *free_iov; - struct sockaddr __user *uaddr; - struct msghdr msg; - struct sockaddr_storage addr; -}; - -struct io_rw_state { - struct iov_iter iter; - struct iov_iter_state iter_state; - struct iovec fast_iov[UIO_FASTIOV]; -}; - -struct io_async_rw { - struct io_rw_state s; - const struct iovec *free_iovec; - size_t bytes_done; - struct wait_page_queue wpq; -}; - -struct io_xattr { - struct file *file; - struct xattr_ctx ctx; - struct filename *filename; -}; - -enum { - REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, - REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT, - REQ_F_LINK_BIT = IOSQE_IO_LINK_BIT, - REQ_F_HARDLINK_BIT = IOSQE_IO_HARDLINK_BIT, - REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT, - REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT, - REQ_F_CQE_SKIP_BIT = IOSQE_CQE_SKIP_SUCCESS_BIT, - - /* first byte is taken by user flags, shift it to not overlap */ - REQ_F_FAIL_BIT = 8, - REQ_F_INFLIGHT_BIT, - REQ_F_CUR_POS_BIT, - REQ_F_NOWAIT_BIT, - REQ_F_LINK_TIMEOUT_BIT, - REQ_F_NEED_CLEANUP_BIT, - REQ_F_POLLED_BIT, - REQ_F_BUFFER_SELECTED_BIT, - REQ_F_BUFFER_RING_BIT, - REQ_F_COMPLETE_INLINE_BIT, - REQ_F_REISSUE_BIT, - REQ_F_CREDS_BIT, - REQ_F_REFCOUNT_BIT, - REQ_F_ARM_LTIMEOUT_BIT, - REQ_F_ASYNC_DATA_BIT, - REQ_F_SKIP_LINK_CQES_BIT, - REQ_F_SINGLE_POLL_BIT, - REQ_F_DOUBLE_POLL_BIT, - REQ_F_PARTIAL_IO_BIT, - REQ_F_CQE32_INIT_BIT, - REQ_F_APOLL_MULTISHOT_BIT, - /* keep async read/write and isreg together and in order */ - REQ_F_SUPPORT_NOWAIT_BIT, - REQ_F_ISREG_BIT, - - /* not a real bit, just to check we're not overflowing the space */ - __REQ_F_LAST_BIT, -}; - -enum { - /* ctx owns file */ - REQ_F_FIXED_FILE = BIT(REQ_F_FIXED_FILE_BIT), - /* drain existing IO first */ - REQ_F_IO_DRAIN = BIT(REQ_F_IO_DRAIN_BIT), - /* linked sqes */ - REQ_F_LINK = BIT(REQ_F_LINK_BIT), - /* doesn't sever on completion < 0 */ - REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT), - /* IOSQE_ASYNC */ - REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT), - /* IOSQE_BUFFER_SELECT */ - REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT), - /* IOSQE_CQE_SKIP_SUCCESS */ - REQ_F_CQE_SKIP = BIT(REQ_F_CQE_SKIP_BIT), - - /* fail rest of links */ - REQ_F_FAIL = BIT(REQ_F_FAIL_BIT), - /* on inflight list, should be cancelled and waited on exit reliably */ - REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT), - /* read/write uses file position */ - REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT), - /* must not punt to workers */ - REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT), - /* has or had linked timeout */ - REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT), - /* needs cleanup */ - REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), - /* already went through poll handler */ - REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), - /* buffer already selected */ - REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT), - /* buffer selected from ring, needs commit */ - REQ_F_BUFFER_RING = BIT(REQ_F_BUFFER_RING_BIT), - /* completion is deferred through io_comp_state */ - REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), - /* caller should reissue async */ - REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), - /* supports async reads/writes */ - REQ_F_SUPPORT_NOWAIT = BIT(REQ_F_SUPPORT_NOWAIT_BIT), - /* regular file */ - REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), - /* has creds assigned */ - REQ_F_CREDS = BIT(REQ_F_CREDS_BIT), - /* skip refcounting if not set */ - REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT), - /* there is a linked timeout that has to be armed */ - REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), - /* ->async_data allocated */ - REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT), - /* don't post CQEs while failing linked requests */ - REQ_F_SKIP_LINK_CQES = BIT(REQ_F_SKIP_LINK_CQES_BIT), - /* single poll may be active */ - REQ_F_SINGLE_POLL = BIT(REQ_F_SINGLE_POLL_BIT), - /* double poll may active */ - REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT), - /* request has already done partial IO */ - REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT), - /* fast poll multishot mode */ - REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT), - /* ->extra1 and ->extra2 are initialised */ - REQ_F_CQE32_INIT = BIT(REQ_F_CQE32_INIT_BIT), -}; - -struct async_poll { - struct io_poll_iocb poll; - struct io_poll_iocb *double_poll; -}; - -typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked); - -struct io_task_work { - union { - struct io_wq_work_node node; - struct llist_node fallback_node; - }; - io_req_tw_func_t func; -}; - -enum { - IORING_RSRC_FILE = 0, - IORING_RSRC_BUFFER = 1, -}; - -struct io_cqe { - __u64 user_data; - __s32 res; - /* fd initially, then cflags for completion */ - union { - __u32 flags; - int fd; - }; -}; - -enum { - IO_CHECK_CQ_OVERFLOW_BIT, - IO_CHECK_CQ_DROPPED_BIT, -}; - -/* - * NOTE! Each of the iocb union members has the file pointer - * as the first entry in their struct definition. So you can - * access the file pointer through any of the sub-structs, - * or directly as just 'file' in this struct. - */ -struct io_kiocb { - union { - struct file *file; - struct io_rw rw; - struct io_poll_iocb poll; - struct io_poll_update poll_update; - struct io_accept accept; - struct io_sync sync; - struct io_cancel cancel; - struct io_timeout timeout; - struct io_timeout_rem timeout_rem; - struct io_connect connect; - struct io_sr_msg sr_msg; - struct io_open open; - struct io_close close; - struct io_rsrc_update rsrc_update; - struct io_fadvise fadvise; - struct io_madvise madvise; - struct io_epoll epoll; - struct io_splice splice; - struct io_provide_buf pbuf; - struct io_statx statx; - struct io_shutdown shutdown; - struct io_rename rename; - struct io_unlink unlink; - struct io_mkdir mkdir; - struct io_symlink symlink; - struct io_hardlink hardlink; - struct io_msg msg; - struct io_xattr xattr; - struct io_socket sock; - struct io_uring_cmd uring_cmd; - }; - - u8 opcode; - /* polled IO has completed */ - u8 iopoll_completed; - /* - * Can be either a fixed buffer index, or used with provided buffers. - * For the latter, before issue it points to the buffer group ID, - * and after selection it points to the buffer ID itself. - */ - u16 buf_index; - unsigned int flags; - - struct io_cqe cqe; - - struct io_ring_ctx *ctx; - struct task_struct *task; - - struct io_rsrc_node *rsrc_node; - - union { - /* store used ubuf, so we can prevent reloading */ - struct io_mapped_ubuf *imu; - - /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ - struct io_buffer *kbuf; - - /* - * stores buffer ID for ring provided buffers, valid IFF - * REQ_F_BUFFER_RING is set. - */ - struct io_buffer_list *buf_list; - }; - - union { - /* used by request caches, completion batching and iopoll */ - struct io_wq_work_node comp_list; - /* cache ->apoll->events */ - __poll_t apoll_events; - }; - atomic_t refs; - atomic_t poll_refs; - struct io_task_work io_task_work; - /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ - union { - struct hlist_node hash_node; - struct { - u64 extra1; - u64 extra2; - }; - }; - /* internal polling, see IORING_FEAT_FAST_POLL */ - struct async_poll *apoll; - /* opcode allocated if it needs to store data for async defer */ - void *async_data; - /* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */ - struct io_kiocb *link; - /* custom credentials, valid IFF REQ_F_CREDS is set */ - const struct cred *creds; - struct io_wq_work work; -}; - -struct io_tctx_node { - struct list_head ctx_node; - struct task_struct *task; - struct io_ring_ctx *ctx; -}; - -struct io_defer_entry { - struct list_head list; - struct io_kiocb *req; - u32 seq; -}; - -struct io_cancel_data { - struct io_ring_ctx *ctx; - union { - u64 data; - struct file *file; - }; - u32 flags; - int seq; -}; - -/* - * The URING_CMD payload starts at 'cmd' in the first sqe, and continues into - * the following sqe if SQE128 is used. - */ -#define uring_cmd_pdu_size(is_sqe128) \ - ((1 + !!(is_sqe128)) * sizeof(struct io_uring_sqe) - \ - offsetof(struct io_uring_sqe, cmd)) - -struct io_op_def { - /* needs req->file assigned */ - unsigned needs_file : 1; - /* should block plug */ - unsigned plug : 1; - /* hash wq insertion if file is a regular file */ - unsigned hash_reg_file : 1; - /* unbound wq insertion if file is a non-regular file */ - unsigned unbound_nonreg_file : 1; - /* set if opcode supports polled "wait" */ - unsigned pollin : 1; - unsigned pollout : 1; - unsigned poll_exclusive : 1; - /* op supports buffer selection */ - unsigned buffer_select : 1; - /* do prep async if is going to be punted */ - unsigned needs_async_setup : 1; - /* opcode is not supported by this kernel */ - unsigned not_supported : 1; - /* skip auditing */ - unsigned audit_skip : 1; - /* supports ioprio */ - unsigned ioprio : 1; - /* supports iopoll */ - unsigned iopoll : 1; - /* size of async data needed, if any */ - unsigned short async_size; -}; - -static const struct io_op_def io_op_defs[] = { - [IORING_OP_NOP] = { - .audit_skip = 1, - .iopoll = 1, - }, - [IORING_OP_READV] = { - .needs_file = 1, - .unbound_nonreg_file = 1, - .pollin = 1, - .buffer_select = 1, - .needs_async_setup = 1, - .plug = 1, - .audit_skip = 1, - .ioprio = 1, - .iopoll = 1, - .async_size = sizeof(struct io_async_rw), - }, - [IORING_OP_WRITEV] = { - .needs_file = 1, - .hash_reg_file = 1, - .unbound_nonreg_file = 1, - .pollout = 1, - .needs_async_setup = 1, - .plug = 1, - .audit_skip = 1, - .ioprio = 1, - .iopoll = 1, - .async_size = sizeof(struct io_async_rw), - }, - [IORING_OP_FSYNC] = { - .needs_file = 1, - .audit_skip = 1, - }, - [IORING_OP_READ_FIXED] = { - .needs_file = 1, - .unbound_nonreg_file = 1, - .pollin = 1, - .plug = 1, - .audit_skip = 1, - .ioprio = 1, - .iopoll = 1, - .async_size = sizeof(struct io_async_rw), - }, - [IORING_OP_WRITE_FIXED] = { - .needs_file = 1, - .hash_reg_file = 1, - .unbound_nonreg_file = 1, - .pollout = 1, - .plug = 1, - .audit_skip = 1, - .ioprio = 1, - .iopoll = 1, - .async_size = sizeof(struct io_async_rw), - }, - [IORING_OP_POLL_ADD] = { - .needs_file = 1, - .unbound_nonreg_file = 1, - .audit_skip = 1, - }, - [IORING_OP_POLL_REMOVE] = { - .audit_skip = 1, - }, - [IORING_OP_SYNC_FILE_RANGE] = { - .needs_file = 1, - .audit_skip = 1, - }, - [IORING_OP_SENDMSG] = { - .needs_file = 1, - .unbound_nonreg_file = 1, - .pollout = 1, - .needs_async_setup = 1, - .ioprio = 1, - .async_size = sizeof(struct io_async_msghdr), - }, - [IORING_OP_RECVMSG] = { - .needs_file = 1, - .unbound_nonreg_file = 1, - .pollin = 1, - .buffer_select = 1, - .needs_async_setup = 1, - .ioprio = 1, - .async_size = sizeof(struct io_async_msghdr), - }, - [IORING_OP_TIMEOUT] = { - .audit_skip = 1, - .async_size = sizeof(struct io_timeout_data), - }, - [IORING_OP_TIMEOUT_REMOVE] = { - /* used by timeout updates' prep() */ - .audit_skip = 1, - }, - [IORING_OP_ACCEPT] = { - .needs_file = 1, - .unbound_nonreg_file = 1, - .pollin = 1, - .poll_exclusive = 1, - .ioprio = 1, /* used for flags */ - }, - [IORING_OP_ASYNC_CANCEL] = { - .audit_skip = 1, - }, - [IORING_OP_LINK_TIMEOUT] = { - .audit_skip = 1, - .async_size = sizeof(struct io_timeout_data), - }, - [IORING_OP_CONNECT] = { - .needs_file = 1, - .unbound_nonreg_file = 1, - .pollout = 1, - .needs_async_setup = 1, - .async_size = sizeof(struct io_async_connect), - }, - [IORING_OP_FALLOCATE] = { - .needs_file = 1, - }, - [IORING_OP_OPENAT] = {}, - [IORING_OP_CLOSE] = {}, - [IORING_OP_FILES_UPDATE] = { - .audit_skip = 1, - .iopoll = 1, - }, - [IORING_OP_STATX] = { - .audit_skip = 1, - }, - [IORING_OP_READ] = { - .needs_file = 1, - .unbound_nonreg_file = 1, - .pollin = 1, - .buffer_select = 1, - .plug = 1, - .audit_skip = 1, - .ioprio = 1, - .iopoll = 1, - .async_size = sizeof(struct io_async_rw), - }, - [IORING_OP_WRITE] = { - .needs_file = 1, - .hash_reg_file = 1, - .unbound_nonreg_file = 1, - .pollout = 1, - .plug = 1, - .audit_skip = 1, - .ioprio = 1, - .iopoll = 1, - .async_size = sizeof(struct io_async_rw), - }, - [IORING_OP_FADVISE] = { - .needs_file = 1, - .audit_skip = 1, - }, - [IORING_OP_MADVISE] = {}, - [IORING_OP_SEND] = { - .needs_file = 1, - .unbound_nonreg_file = 1, - .pollout = 1, - .audit_skip = 1, - .ioprio = 1, - }, - [IORING_OP_RECV] = { - .needs_file = 1, - .unbound_nonreg_file = 1, - .pollin = 1, - .buffer_select = 1, - .audit_skip = 1, - .ioprio = 1, - }, - [IORING_OP_OPENAT2] = { - }, - [IORING_OP_EPOLL_CTL] = { - .unbound_nonreg_file = 1, - .audit_skip = 1, - }, - [IORING_OP_SPLICE] = { - .needs_file = 1, - .hash_reg_file = 1, - .unbound_nonreg_file = 1, - .audit_skip = 1, - }, - [IORING_OP_PROVIDE_BUFFERS] = { - .audit_skip = 1, - .iopoll = 1, - }, - [IORING_OP_REMOVE_BUFFERS] = { - .audit_skip = 1, - .iopoll = 1, - }, - [IORING_OP_TEE] = { - .needs_file = 1, - .hash_reg_file = 1, - .unbound_nonreg_file = 1, - .audit_skip = 1, - }, - [IORING_OP_SHUTDOWN] = { - .needs_file = 1, - }, - [IORING_OP_RENAMEAT] = {}, - [IORING_OP_UNLINKAT] = {}, - [IORING_OP_MKDIRAT] = {}, - [IORING_OP_SYMLINKAT] = {}, - [IORING_OP_LINKAT] = {}, - [IORING_OP_MSG_RING] = { - .needs_file = 1, - .iopoll = 1, - }, - [IORING_OP_FSETXATTR] = { - .needs_file = 1 - }, - [IORING_OP_SETXATTR] = {}, - [IORING_OP_FGETXATTR] = { - .needs_file = 1 - }, - [IORING_OP_GETXATTR] = {}, - [IORING_OP_SOCKET] = { - .audit_skip = 1, - }, - [IORING_OP_URING_CMD] = { - .needs_file = 1, - .plug = 1, - .needs_async_setup = 1, - .async_size = uring_cmd_pdu_size(1), - }, -}; - -/* requests with any of those set should undergo io_disarm_next() */ -#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL) -#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK) - -static bool io_disarm_next(struct io_kiocb *req); -static void io_uring_del_tctx_node(unsigned long index); -static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, - struct task_struct *task, - bool cancel_all); -static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); - -static void __io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags); -static void io_dismantle_req(struct io_kiocb *req); -static void io_queue_linked_timeout(struct io_kiocb *req); -static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, - struct io_uring_rsrc_update2 *up, - unsigned nr_args); -static void io_clean_op(struct io_kiocb *req); -static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, - unsigned issue_flags); -static struct file *io_file_get_normal(struct io_kiocb *req, int fd); -static void io_queue_sqe(struct io_kiocb *req); -static void io_rsrc_put_work(struct work_struct *work); - -static void io_req_task_queue(struct io_kiocb *req); -static void __io_submit_flush_completions(struct io_ring_ctx *ctx); -static int io_req_prep_async(struct io_kiocb *req); - -static int io_install_fixed_file(struct io_kiocb *req, struct file *file, - unsigned int issue_flags, u32 slot_index); -static int __io_close_fixed(struct io_kiocb *req, unsigned int issue_flags, - unsigned int offset); -static inline int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags); - -static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer); -static void io_eventfd_signal(struct io_ring_ctx *ctx); -static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags); - -static struct kmem_cache *req_cachep; - -static const struct file_operations io_uring_fops; - -const char *io_uring_get_opcode(u8 opcode) -{ - switch ((enum io_uring_op)opcode) { - case IORING_OP_NOP: - return "NOP"; - case IORING_OP_READV: - return "READV"; - case IORING_OP_WRITEV: - return "WRITEV"; - case IORING_OP_FSYNC: - return "FSYNC"; - case IORING_OP_READ_FIXED: - return "READ_FIXED"; - case IORING_OP_WRITE_FIXED: - return "WRITE_FIXED"; - case IORING_OP_POLL_ADD: - return "POLL_ADD"; - case IORING_OP_POLL_REMOVE: - return "POLL_REMOVE"; - case IORING_OP_SYNC_FILE_RANGE: - return "SYNC_FILE_RANGE"; - case IORING_OP_SENDMSG: - return "SENDMSG"; - case IORING_OP_RECVMSG: - return "RECVMSG"; - case IORING_OP_TIMEOUT: - return "TIMEOUT"; - case IORING_OP_TIMEOUT_REMOVE: - return "TIMEOUT_REMOVE"; - case IORING_OP_ACCEPT: - return "ACCEPT"; - case IORING_OP_ASYNC_CANCEL: - return "ASYNC_CANCEL"; - case IORING_OP_LINK_TIMEOUT: - return "LINK_TIMEOUT"; - case IORING_OP_CONNECT: - return "CONNECT"; - case IORING_OP_FALLOCATE: - return "FALLOCATE"; - case IORING_OP_OPENAT: - return "OPENAT"; - case IORING_OP_CLOSE: - return "CLOSE"; - case IORING_OP_FILES_UPDATE: - return "FILES_UPDATE"; - case IORING_OP_STATX: - return "STATX"; - case IORING_OP_READ: - return "READ"; - case IORING_OP_WRITE: - return "WRITE"; - case IORING_OP_FADVISE: - return "FADVISE"; - case IORING_OP_MADVISE: - return "MADVISE"; - case IORING_OP_SEND: - return "SEND"; - case IORING_OP_RECV: - return "RECV"; - case IORING_OP_OPENAT2: - return "OPENAT2"; - case IORING_OP_EPOLL_CTL: - return "EPOLL_CTL"; - case IORING_OP_SPLICE: - return "SPLICE"; - case IORING_OP_PROVIDE_BUFFERS: - return "PROVIDE_BUFFERS"; - case IORING_OP_REMOVE_BUFFERS: - return "REMOVE_BUFFERS"; - case IORING_OP_TEE: - return "TEE"; - case IORING_OP_SHUTDOWN: - return "SHUTDOWN"; - case IORING_OP_RENAMEAT: - return "RENAMEAT"; - case IORING_OP_UNLINKAT: - return "UNLINKAT"; - case IORING_OP_MKDIRAT: - return "MKDIRAT"; - case IORING_OP_SYMLINKAT: - return "SYMLINKAT"; - case IORING_OP_LINKAT: - return "LINKAT"; - case IORING_OP_MSG_RING: - return "MSG_RING"; - case IORING_OP_FSETXATTR: - return "FSETXATTR"; - case IORING_OP_SETXATTR: - return "SETXATTR"; - case IORING_OP_FGETXATTR: - return "FGETXATTR"; - case IORING_OP_GETXATTR: - return "GETXATTR"; - case IORING_OP_SOCKET: - return "SOCKET"; - case IORING_OP_URING_CMD: - return "URING_CMD"; - case IORING_OP_LAST: - return "INVALID"; - } - return "INVALID"; -} - -struct sock *io_uring_get_socket(struct file *file) -{ -#if defined(CONFIG_UNIX) - if (file->f_op == &io_uring_fops) { - struct io_ring_ctx *ctx = file->private_data; - - return ctx->ring_sock->sk; - } -#endif - return NULL; -} -EXPORT_SYMBOL(io_uring_get_socket); - -#if defined(CONFIG_UNIX) -static inline bool io_file_need_scm(struct file *filp) -{ -#if defined(IO_URING_SCM_ALL) - return true; -#else - return !!unix_get_socket(filp); -#endif -} -#else -static inline bool io_file_need_scm(struct file *filp) -{ - return false; -} -#endif - -static void io_ring_submit_unlock(struct io_ring_ctx *ctx, unsigned issue_flags) -{ - lockdep_assert_held(&ctx->uring_lock); - if (issue_flags & IO_URING_F_UNLOCKED) - mutex_unlock(&ctx->uring_lock); -} - -static void io_ring_submit_lock(struct io_ring_ctx *ctx, unsigned issue_flags) -{ - /* - * "Normal" inline submissions always hold the uring_lock, since we - * grab it from the system call. Same is true for the SQPOLL offload. - * The only exception is when we've detached the request and issue it - * from an async worker thread, grab the lock for that case. - */ - if (issue_flags & IO_URING_F_UNLOCKED) - mutex_lock(&ctx->uring_lock); - lockdep_assert_held(&ctx->uring_lock); -} - -static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked) -{ - if (!*locked) { - mutex_lock(&ctx->uring_lock); - *locked = true; - } -} - -#define io_for_each_link(pos, head) \ - for (pos = (head); pos; pos = pos->link) - -/* - * Shamelessly stolen from the mm implementation of page reference checking, - * see commit f958d7b528b1 for details. - */ -#define req_ref_zero_or_close_to_overflow(req) \ - ((unsigned int) atomic_read(&(req->refs)) + 127u <= 127u) - -static inline bool req_ref_inc_not_zero(struct io_kiocb *req) -{ - WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); - return atomic_inc_not_zero(&req->refs); -} - -static inline bool req_ref_put_and_test(struct io_kiocb *req) -{ - if (likely(!(req->flags & REQ_F_REFCOUNT))) - return true; - - WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); - return atomic_dec_and_test(&req->refs); -} - -static inline void req_ref_get(struct io_kiocb *req) -{ - WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); - WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); - atomic_inc(&req->refs); -} - -static inline void io_submit_flush_completions(struct io_ring_ctx *ctx) -{ - if (!wq_list_empty(&ctx->submit_state.compl_reqs)) - __io_submit_flush_completions(ctx); -} - -static inline void __io_req_set_refcount(struct io_kiocb *req, int nr) -{ - if (!(req->flags & REQ_F_REFCOUNT)) { - req->flags |= REQ_F_REFCOUNT; - atomic_set(&req->refs, nr); - } -} - -static inline void io_req_set_refcount(struct io_kiocb *req) -{ - __io_req_set_refcount(req, 1); -} - -#define IO_RSRC_REF_BATCH 100 - -static void io_rsrc_put_node(struct io_rsrc_node *node, int nr) -{ - percpu_ref_put_many(&node->refs, nr); -} - -static inline void io_req_put_rsrc_locked(struct io_kiocb *req, - struct io_ring_ctx *ctx) - __must_hold(&ctx->uring_lock) -{ - struct io_rsrc_node *node = req->rsrc_node; - - if (node) { - if (node == ctx->rsrc_node) - ctx->rsrc_cached_refs++; - else - io_rsrc_put_node(node, 1); - } -} - -static inline void io_req_put_rsrc(struct io_kiocb *req) -{ - if (req->rsrc_node) - io_rsrc_put_node(req->rsrc_node, 1); -} - -static __cold void io_rsrc_refs_drop(struct io_ring_ctx *ctx) - __must_hold(&ctx->uring_lock) -{ - if (ctx->rsrc_cached_refs) { - io_rsrc_put_node(ctx->rsrc_node, ctx->rsrc_cached_refs); - ctx->rsrc_cached_refs = 0; - } -} - -static void io_rsrc_refs_refill(struct io_ring_ctx *ctx) - __must_hold(&ctx->uring_lock) -{ - ctx->rsrc_cached_refs += IO_RSRC_REF_BATCH; - percpu_ref_get_many(&ctx->rsrc_node->refs, IO_RSRC_REF_BATCH); -} - -static inline void io_req_set_rsrc_node(struct io_kiocb *req, - struct io_ring_ctx *ctx, - unsigned int issue_flags) -{ - if (!req->rsrc_node) { - req->rsrc_node = ctx->rsrc_node; - - if (!(issue_flags & IO_URING_F_UNLOCKED)) { - lockdep_assert_held(&ctx->uring_lock); - ctx->rsrc_cached_refs--; - if (unlikely(ctx->rsrc_cached_refs < 0)) - io_rsrc_refs_refill(ctx); - } else { - percpu_ref_get(&req->rsrc_node->refs); - } - } -} - -static unsigned int __io_put_kbuf(struct io_kiocb *req, struct list_head *list) -{ - if (req->flags & REQ_F_BUFFER_RING) { - if (req->buf_list) - req->buf_list->head++; - req->flags &= ~REQ_F_BUFFER_RING; - } else { - list_add(&req->kbuf->list, list); - req->flags &= ~REQ_F_BUFFER_SELECTED; - } - - return IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT); -} - -static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req) -{ - lockdep_assert_held(&req->ctx->completion_lock); - - if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING))) - return 0; - return __io_put_kbuf(req, &req->ctx->io_buffers_comp); -} - -static inline unsigned int io_put_kbuf(struct io_kiocb *req, - unsigned issue_flags) -{ - unsigned int cflags; - - if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING))) - return 0; - - /* - * We can add this buffer back to two lists: - * - * 1) The io_buffers_cache list. This one is protected by the - * ctx->uring_lock. If we already hold this lock, add back to this - * list as we can grab it from issue as well. - * 2) The io_buffers_comp list. This one is protected by the - * ctx->completion_lock. - * - * We migrate buffers from the comp_list to the issue cache list - * when we need one. - */ - if (req->flags & REQ_F_BUFFER_RING) { - /* no buffers to recycle for this case */ - cflags = __io_put_kbuf(req, NULL); - } else if (issue_flags & IO_URING_F_UNLOCKED) { - struct io_ring_ctx *ctx = req->ctx; - - spin_lock(&ctx->completion_lock); - cflags = __io_put_kbuf(req, &ctx->io_buffers_comp); - spin_unlock(&ctx->completion_lock); - } else { - lockdep_assert_held(&req->ctx->uring_lock); - - cflags = __io_put_kbuf(req, &req->ctx->io_buffers_cache); - } - - return cflags; -} - -static struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, - unsigned int bgid) -{ - if (ctx->io_bl && bgid < BGID_ARRAY) - return &ctx->io_bl[bgid]; - - return xa_load(&ctx->io_bl_xa, bgid); -} - -static void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_buffer_list *bl; - struct io_buffer *buf; - - if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING))) - return; - /* - * For legacy provided buffer mode, don't recycle if we already did - * IO to this buffer. For ring-mapped provided buffer mode, we should - * increment ring->head to explicitly monopolize the buffer to avoid - * multiple use. - */ - if ((req->flags & REQ_F_BUFFER_SELECTED) && - (req->flags & REQ_F_PARTIAL_IO)) - return; - - /* - * We don't need to recycle for REQ_F_BUFFER_RING, we can just clear - * the flag and hence ensure that bl->head doesn't get incremented. - * If the tail has already been incremented, hang on to it. - */ - if (req->flags & REQ_F_BUFFER_RING) { - if (req->buf_list) { - if (req->flags & REQ_F_PARTIAL_IO) { - req->buf_list->head++; - req->buf_list = NULL; - } else { - req->buf_index = req->buf_list->bgid; - req->flags &= ~REQ_F_BUFFER_RING; - } - } - return; - } - - io_ring_submit_lock(ctx, issue_flags); - - buf = req->kbuf; - bl = io_buffer_get_list(ctx, buf->bgid); - list_add(&buf->list, &bl->buf_list); - req->flags &= ~REQ_F_BUFFER_SELECTED; - req->buf_index = buf->bgid; - - io_ring_submit_unlock(ctx, issue_flags); -} - -static bool io_match_task(struct io_kiocb *head, struct task_struct *task, - bool cancel_all) - __must_hold(&req->ctx->timeout_lock) -{ - struct io_kiocb *req; - - if (task && head->task != task) - return false; - if (cancel_all) - return true; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; -} - -static bool io_match_linked(struct io_kiocb *head) -{ - struct io_kiocb *req; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; -} - -/* - * As io_match_task() but protected against racing with linked timeouts. - * User must not hold timeout_lock. - */ -static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, - bool cancel_all) -{ - bool matched; - - if (task && head->task != task) - return false; - if (cancel_all) - return true; - - if (head->flags & REQ_F_LINK_TIMEOUT) { - struct io_ring_ctx *ctx = head->ctx; - - /* protect against races with linked timeouts */ - spin_lock_irq(&ctx->timeout_lock); - matched = io_match_linked(head); - spin_unlock_irq(&ctx->timeout_lock); - } else { - matched = io_match_linked(head); - } - return matched; -} - -static inline bool req_has_async_data(struct io_kiocb *req) -{ - return req->flags & REQ_F_ASYNC_DATA; -} - -static inline void req_set_fail(struct io_kiocb *req) -{ - req->flags |= REQ_F_FAIL; - if (req->flags & REQ_F_CQE_SKIP) { - req->flags &= ~REQ_F_CQE_SKIP; - req->flags |= REQ_F_SKIP_LINK_CQES; - } -} - -static inline void req_fail_link_node(struct io_kiocb *req, int res) -{ - req_set_fail(req); - req->cqe.res = res; -} - -static inline void io_req_add_to_cache(struct io_kiocb *req, struct io_ring_ctx *ctx) -{ - wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list); -} - -static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref) -{ - struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); - - complete(&ctx->ref_comp); -} - -static inline bool io_is_timeout_noseq(struct io_kiocb *req) -{ - return !req->timeout.off; -} - -static __cold void io_fallback_req_func(struct work_struct *work) -{ - struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, - fallback_work.work); - struct llist_node *node = llist_del_all(&ctx->fallback_llist); - struct io_kiocb *req, *tmp; - bool locked = false; - - percpu_ref_get(&ctx->refs); - llist_for_each_entry_safe(req, tmp, node, io_task_work.fallback_node) - req->io_task_work.func(req, &locked); - - if (locked) { - io_submit_flush_completions(ctx); - mutex_unlock(&ctx->uring_lock); - } - percpu_ref_put(&ctx->refs); -} - -static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) -{ - struct io_ring_ctx *ctx; - int hash_bits; - - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) - return NULL; - - xa_init(&ctx->io_bl_xa); - - /* - * Use 5 bits less than the max cq entries, that should give us around - * 32 entries per hash list if totally full and uniformly spread. - */ - hash_bits = ilog2(p->cq_entries); - hash_bits -= 5; - if (hash_bits <= 0) - hash_bits = 1; - ctx->cancel_hash_bits = hash_bits; - ctx->cancel_hash = kmalloc((1U << hash_bits) * sizeof(struct hlist_head), - GFP_KERNEL); - if (!ctx->cancel_hash) - goto err; - __hash_init(ctx->cancel_hash, 1U << hash_bits); - - ctx->dummy_ubuf = kzalloc(sizeof(*ctx->dummy_ubuf), GFP_KERNEL); - if (!ctx->dummy_ubuf) - goto err; - /* set invalid range, so io_import_fixed() fails meeting it */ - ctx->dummy_ubuf->ubuf = -1UL; - - if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, - PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) - goto err; - - ctx->flags = p->flags; - init_waitqueue_head(&ctx->sqo_sq_wait); - INIT_LIST_HEAD(&ctx->sqd_list); - INIT_LIST_HEAD(&ctx->cq_overflow_list); - INIT_LIST_HEAD(&ctx->io_buffers_cache); - INIT_LIST_HEAD(&ctx->apoll_cache); - init_completion(&ctx->ref_comp); - xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); - mutex_init(&ctx->uring_lock); - init_waitqueue_head(&ctx->cq_wait); - spin_lock_init(&ctx->completion_lock); - spin_lock_init(&ctx->timeout_lock); - INIT_WQ_LIST(&ctx->iopoll_list); - INIT_LIST_HEAD(&ctx->io_buffers_pages); - INIT_LIST_HEAD(&ctx->io_buffers_comp); - INIT_LIST_HEAD(&ctx->defer_list); - INIT_LIST_HEAD(&ctx->timeout_list); - INIT_LIST_HEAD(&ctx->ltimeout_list); - spin_lock_init(&ctx->rsrc_ref_lock); - INIT_LIST_HEAD(&ctx->rsrc_ref_list); - INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work); - init_llist_head(&ctx->rsrc_put_llist); - INIT_LIST_HEAD(&ctx->tctx_list); - ctx->submit_state.free_list.next = NULL; - INIT_WQ_LIST(&ctx->locked_free_list); - INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); - INIT_WQ_LIST(&ctx->submit_state.compl_reqs); - return ctx; -err: - kfree(ctx->dummy_ubuf); - kfree(ctx->cancel_hash); - kfree(ctx->io_bl); - xa_destroy(&ctx->io_bl_xa); - kfree(ctx); - return NULL; -} - -static void io_account_cq_overflow(struct io_ring_ctx *ctx) -{ - struct io_rings *r = ctx->rings; - - WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1); - ctx->cq_extra--; -} - -static bool req_need_defer(struct io_kiocb *req, u32 seq) -{ - if (unlikely(req->flags & REQ_F_IO_DRAIN)) { - struct io_ring_ctx *ctx = req->ctx; - - return seq + READ_ONCE(ctx->cq_extra) != ctx->cached_cq_tail; - } - - return false; -} - -static inline bool io_req_ffs_set(struct io_kiocb *req) -{ - return req->flags & REQ_F_FIXED_FILE; -} - -static inline void io_req_track_inflight(struct io_kiocb *req) -{ - if (!(req->flags & REQ_F_INFLIGHT)) { - req->flags |= REQ_F_INFLIGHT; - atomic_inc(&req->task->io_uring->inflight_tracked); - } -} - -static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) -{ - if (WARN_ON_ONCE(!req->link)) - return NULL; - - req->flags &= ~REQ_F_ARM_LTIMEOUT; - req->flags |= REQ_F_LINK_TIMEOUT; - - /* linked timeouts should have two refs once prep'ed */ - io_req_set_refcount(req); - __io_req_set_refcount(req->link, 2); - return req->link; -} - -static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) -{ - if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT))) - return NULL; - return __io_prep_linked_timeout(req); -} - -static noinline void __io_arm_ltimeout(struct io_kiocb *req) -{ - io_queue_linked_timeout(__io_prep_linked_timeout(req)); -} - -static inline void io_arm_ltimeout(struct io_kiocb *req) -{ - if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT)) - __io_arm_ltimeout(req); -} - -static void io_prep_async_work(struct io_kiocb *req) -{ - const struct io_op_def *def = &io_op_defs[req->opcode]; - struct io_ring_ctx *ctx = req->ctx; - - if (!(req->flags & REQ_F_CREDS)) { - req->flags |= REQ_F_CREDS; - req->creds = get_current_cred(); - } - - req->work.list.next = NULL; - req->work.flags = 0; - req->work.cancel_seq = atomic_read(&ctx->cancel_seq); - if (req->flags & REQ_F_FORCE_ASYNC) - req->work.flags |= IO_WQ_WORK_CONCURRENT; - - if (req->flags & REQ_F_ISREG) { - if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL)) - io_wq_hash_work(&req->work, file_inode(req->file)); - } else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) { - if (def->unbound_nonreg_file) - req->work.flags |= IO_WQ_WORK_UNBOUND; - } -} - -static void io_prep_async_link(struct io_kiocb *req) -{ - struct io_kiocb *cur; - - if (req->flags & REQ_F_LINK_TIMEOUT) { - struct io_ring_ctx *ctx = req->ctx; - - spin_lock_irq(&ctx->timeout_lock); - io_for_each_link(cur, req) - io_prep_async_work(cur); - spin_unlock_irq(&ctx->timeout_lock); - } else { - io_for_each_link(cur, req) - io_prep_async_work(cur); - } -} - -static inline void io_req_add_compl_list(struct io_kiocb *req) -{ - struct io_submit_state *state = &req->ctx->submit_state; - - if (!(req->flags & REQ_F_CQE_SKIP)) - state->flush_cqes = true; - wq_list_add_tail(&req->comp_list, &state->compl_reqs); -} - -static void io_queue_iowq(struct io_kiocb *req, bool *dont_use) -{ - struct io_kiocb *link = io_prep_linked_timeout(req); - struct io_uring_task *tctx = req->task->io_uring; - - BUG_ON(!tctx); - BUG_ON(!tctx->io_wq); - - /* init ->work of the whole link before punting */ - io_prep_async_link(req); - - /* - * Not expected to happen, but if we do have a bug where this _can_ - * happen, catch it here and ensure the request is marked as - * canceled. That will make io-wq go through the usual work cancel - * procedure rather than attempt to run this request (or create a new - * worker for it). - */ - if (WARN_ON_ONCE(!same_thread_group(req->task, current))) - req->work.flags |= IO_WQ_WORK_CANCEL; - - trace_io_uring_queue_async_work(req->ctx, req, req->cqe.user_data, - req->opcode, req->flags, &req->work, - io_wq_is_hashed(&req->work)); - io_wq_enqueue(tctx->io_wq, &req->work); - if (link) - io_queue_linked_timeout(link); -} - -static void io_kill_timeout(struct io_kiocb *req, int status) - __must_hold(&req->ctx->completion_lock) - __must_hold(&req->ctx->timeout_lock) -{ - struct io_timeout_data *io = req->async_data; - - if (hrtimer_try_to_cancel(&io->timer) != -1) { - if (status) - req_set_fail(req); - atomic_set(&req->ctx->cq_timeouts, - atomic_read(&req->ctx->cq_timeouts) + 1); - list_del_init(&req->timeout.list); - io_req_tw_post_queue(req, status, 0); - } -} - -static __cold void io_queue_deferred(struct io_ring_ctx *ctx) -{ - while (!list_empty(&ctx->defer_list)) { - struct io_defer_entry *de = list_first_entry(&ctx->defer_list, - struct io_defer_entry, list); - - if (req_need_defer(de->req, de->seq)) - break; - list_del_init(&de->list); - io_req_task_queue(de->req); - kfree(de); - } -} - -static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) - __must_hold(&ctx->completion_lock) -{ - u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); - struct io_kiocb *req, *tmp; - - spin_lock_irq(&ctx->timeout_lock); - list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { - u32 events_needed, events_got; - - if (io_is_timeout_noseq(req)) - break; - - /* - * Since seq can easily wrap around over time, subtract - * the last seq at which timeouts were flushed before comparing. - * Assuming not more than 2^31-1 events have happened since, - * these subtractions won't have wrapped, so we can check if - * target is in [last_seq, current_seq] by comparing the two. - */ - events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush; - events_got = seq - ctx->cq_last_tm_flush; - if (events_got < events_needed) - break; - - io_kill_timeout(req, 0); - } - ctx->cq_last_tm_flush = seq; - spin_unlock_irq(&ctx->timeout_lock); -} - -static inline void io_commit_cqring(struct io_ring_ctx *ctx) -{ - /* order cqe stores with ring update */ - smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail); -} - -static void __io_commit_cqring_flush(struct io_ring_ctx *ctx) -{ - if (ctx->off_timeout_used || ctx->drain_active) { - spin_lock(&ctx->completion_lock); - if (ctx->off_timeout_used) - io_flush_timeouts(ctx); - if (ctx->drain_active) - io_queue_deferred(ctx); - io_commit_cqring(ctx); - spin_unlock(&ctx->completion_lock); - } - if (ctx->has_evfd) - io_eventfd_signal(ctx); -} - -static inline bool io_sqring_full(struct io_ring_ctx *ctx) -{ - struct io_rings *r = ctx->rings; - - return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == ctx->sq_entries; -} - -static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) -{ - return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); -} - -/* - * writes to the cq entry need to come after reading head; the - * control dependency is enough as we're using WRITE_ONCE to - * fill the cq entry - */ -static noinline struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx) -{ - struct io_rings *rings = ctx->rings; - unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1); - unsigned int shift = 0; - unsigned int free, queued, len; - - if (ctx->flags & IORING_SETUP_CQE32) - shift = 1; - - /* userspace may cheat modifying the tail, be safe and do min */ - queued = min(__io_cqring_events(ctx), ctx->cq_entries); - free = ctx->cq_entries - queued; - /* we need a contiguous range, limit based on the current array offset */ - len = min(free, ctx->cq_entries - off); - if (!len) - return NULL; - - ctx->cached_cq_tail++; - ctx->cqe_cached = &rings->cqes[off]; - ctx->cqe_sentinel = ctx->cqe_cached + len; - ctx->cqe_cached++; - return &rings->cqes[off << shift]; -} - -static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) -{ - if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) { - struct io_uring_cqe *cqe = ctx->cqe_cached; - - if (ctx->flags & IORING_SETUP_CQE32) { - unsigned int off = ctx->cqe_cached - ctx->rings->cqes; - - cqe += off; - } - - ctx->cached_cq_tail++; - ctx->cqe_cached++; - return cqe; - } - - return __io_get_cqe(ctx); -} - -static void io_eventfd_signal(struct io_ring_ctx *ctx) -{ - struct io_ev_fd *ev_fd; - - rcu_read_lock(); - /* - * rcu_dereference ctx->io_ev_fd once and use it for both for checking - * and eventfd_signal - */ - ev_fd = rcu_dereference(ctx->io_ev_fd); - - /* - * Check again if ev_fd exists incase an io_eventfd_unregister call - * completed between the NULL check of ctx->io_ev_fd at the start of - * the function and rcu_read_lock. - */ - if (unlikely(!ev_fd)) - goto out; - if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) - goto out; - - if (!ev_fd->eventfd_async || io_wq_current_is_worker()) - eventfd_signal(ev_fd->cq_ev_fd, 1); -out: - rcu_read_unlock(); -} - -static inline void io_cqring_wake(struct io_ring_ctx *ctx) -{ - /* - * wake_up_all() may seem excessive, but io_wake_function() and - * io_should_wake() handle the termination of the loop and only - * wake as many waiters as we need to. - */ - if (wq_has_sleeper(&ctx->cq_wait)) - wake_up_all(&ctx->cq_wait); -} - -/* - * This should only get called when at least one event has been posted. - * Some applications rely on the eventfd notification count only changing - * IFF a new CQE has been added to the CQ ring. There's no depedency on - * 1:1 relationship between how many times this function is called (and - * hence the eventfd count) and number of CQEs posted to the CQ ring. - */ -static inline void io_cqring_ev_posted(struct io_ring_ctx *ctx) -{ - if (unlikely(ctx->off_timeout_used || ctx->drain_active || - ctx->has_evfd)) - __io_commit_cqring_flush(ctx); - - io_cqring_wake(ctx); -} - -static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) -{ - if (unlikely(ctx->off_timeout_used || ctx->drain_active || - ctx->has_evfd)) - __io_commit_cqring_flush(ctx); - - if (ctx->flags & IORING_SETUP_SQPOLL) - io_cqring_wake(ctx); -} - -/* Returns true if there are no backlogged entries after the flush */ -static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) -{ - bool all_flushed, posted; - size_t cqe_size = sizeof(struct io_uring_cqe); - - if (!force && __io_cqring_events(ctx) == ctx->cq_entries) - return false; - - if (ctx->flags & IORING_SETUP_CQE32) - cqe_size <<= 1; - - posted = false; - spin_lock(&ctx->completion_lock); - while (!list_empty(&ctx->cq_overflow_list)) { - struct io_uring_cqe *cqe = io_get_cqe(ctx); - struct io_overflow_cqe *ocqe; - - if (!cqe && !force) - break; - ocqe = list_first_entry(&ctx->cq_overflow_list, - struct io_overflow_cqe, list); - if (cqe) - memcpy(cqe, &ocqe->cqe, cqe_size); - else - io_account_cq_overflow(ctx); - - posted = true; - list_del(&ocqe->list); - kfree(ocqe); - } - - all_flushed = list_empty(&ctx->cq_overflow_list); - if (all_flushed) { - clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq); - atomic_andnot(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags); - } - - io_commit_cqring(ctx); - spin_unlock(&ctx->completion_lock); - if (posted) - io_cqring_ev_posted(ctx); - return all_flushed; -} - -static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx) -{ - bool ret = true; - - if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) { - /* iopoll syncs against uring_lock, not completion_lock */ - if (ctx->flags & IORING_SETUP_IOPOLL) - mutex_lock(&ctx->uring_lock); - ret = __io_cqring_overflow_flush(ctx, false); - if (ctx->flags & IORING_SETUP_IOPOLL) - mutex_unlock(&ctx->uring_lock); - } - - return ret; -} - -static void __io_put_task(struct task_struct *task, int nr) -{ - struct io_uring_task *tctx = task->io_uring; - - percpu_counter_sub(&tctx->inflight, nr); - if (unlikely(atomic_read(&tctx->in_idle))) - wake_up(&tctx->wait); - put_task_struct_many(task, nr); -} - -/* must to be called somewhat shortly after putting a request */ -static inline void io_put_task(struct task_struct *task, int nr) -{ - if (likely(task == current)) - task->io_uring->cached_refs += nr; - else - __io_put_task(task, nr); -} - -static void io_task_refs_refill(struct io_uring_task *tctx) -{ - unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR; - - percpu_counter_add(&tctx->inflight, refill); - refcount_add(refill, ¤t->usage); - tctx->cached_refs += refill; -} - -static inline void io_get_task_refs(int nr) -{ - struct io_uring_task *tctx = current->io_uring; - - tctx->cached_refs -= nr; - if (unlikely(tctx->cached_refs < 0)) - io_task_refs_refill(tctx); -} - -static __cold void io_uring_drop_tctx_refs(struct task_struct *task) -{ - struct io_uring_task *tctx = task->io_uring; - unsigned int refs = tctx->cached_refs; - - if (refs) { - tctx->cached_refs = 0; - percpu_counter_sub(&tctx->inflight, refs); - put_task_struct_many(task, refs); - } -} - -static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, - s32 res, u32 cflags, u64 extra1, - u64 extra2) -{ - struct io_overflow_cqe *ocqe; - size_t ocq_size = sizeof(struct io_overflow_cqe); - bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32); - - if (is_cqe32) - ocq_size += sizeof(struct io_uring_cqe); - - ocqe = kmalloc(ocq_size, GFP_ATOMIC | __GFP_ACCOUNT); - trace_io_uring_cqe_overflow(ctx, user_data, res, cflags, ocqe); - if (!ocqe) { - /* - * If we're in ring overflow flush mode, or in task cancel mode, - * or cannot allocate an overflow entry, then we need to drop it - * on the floor. - */ - io_account_cq_overflow(ctx); - set_bit(IO_CHECK_CQ_DROPPED_BIT, &ctx->check_cq); - return false; - } - if (list_empty(&ctx->cq_overflow_list)) { - set_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq); - atomic_or(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags); - - } - ocqe->cqe.user_data = user_data; - ocqe->cqe.res = res; - ocqe->cqe.flags = cflags; - if (is_cqe32) { - ocqe->cqe.big_cqe[0] = extra1; - ocqe->cqe.big_cqe[1] = extra2; - } - list_add_tail(&ocqe->list, &ctx->cq_overflow_list); - return true; -} - -static inline bool __io_fill_cqe_req(struct io_ring_ctx *ctx, - struct io_kiocb *req) -{ - struct io_uring_cqe *cqe; - - if (!(ctx->flags & IORING_SETUP_CQE32)) { - trace_io_uring_complete(req->ctx, req, req->cqe.user_data, - req->cqe.res, req->cqe.flags, 0, 0); - - /* - * If we can't get a cq entry, userspace overflowed the - * submission (by quite a lot). Increment the overflow count in - * the ring. - */ - cqe = io_get_cqe(ctx); - if (likely(cqe)) { - memcpy(cqe, &req->cqe, sizeof(*cqe)); - return true; - } - - return io_cqring_event_overflow(ctx, req->cqe.user_data, - req->cqe.res, req->cqe.flags, - 0, 0); - } else { - u64 extra1 = 0, extra2 = 0; - - if (req->flags & REQ_F_CQE32_INIT) { - extra1 = req->extra1; - extra2 = req->extra2; - } - - trace_io_uring_complete(req->ctx, req, req->cqe.user_data, - req->cqe.res, req->cqe.flags, extra1, extra2); - - /* - * If we can't get a cq entry, userspace overflowed the - * submission (by quite a lot). Increment the overflow count in - * the ring. - */ - cqe = io_get_cqe(ctx); - if (likely(cqe)) { - memcpy(cqe, &req->cqe, sizeof(struct io_uring_cqe)); - WRITE_ONCE(cqe->big_cqe[0], extra1); - WRITE_ONCE(cqe->big_cqe[1], extra2); - return true; - } - - return io_cqring_event_overflow(ctx, req->cqe.user_data, - req->cqe.res, req->cqe.flags, - extra1, extra2); - } -} - -static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, - s32 res, u32 cflags) -{ - struct io_uring_cqe *cqe; - - ctx->cq_extra++; - trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0); - - /* - * If we can't get a cq entry, userspace overflowed the - * submission (by quite a lot). Increment the overflow count in - * the ring. - */ - cqe = io_get_cqe(ctx); - if (likely(cqe)) { - WRITE_ONCE(cqe->user_data, user_data); - WRITE_ONCE(cqe->res, res); - WRITE_ONCE(cqe->flags, cflags); - - if (ctx->flags & IORING_SETUP_CQE32) { - WRITE_ONCE(cqe->big_cqe[0], 0); - WRITE_ONCE(cqe->big_cqe[1], 0); - } - return true; - } - return io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0); -} - -static void __io_req_complete_put(struct io_kiocb *req) -{ - /* - * If we're the last reference to this request, add to our locked - * free_list cache. - */ - if (req_ref_put_and_test(req)) { - struct io_ring_ctx *ctx = req->ctx; - - if (req->flags & IO_REQ_LINK_FLAGS) { - if (req->flags & IO_DISARM_MASK) - io_disarm_next(req); - if (req->link) { - io_req_task_queue(req->link); - req->link = NULL; - } - } - io_req_put_rsrc(req); - /* - * Selected buffer deallocation in io_clean_op() assumes that - * we don't hold ->completion_lock. Clean them here to avoid - * deadlocks. - */ - io_put_kbuf_comp(req); - io_dismantle_req(req); - io_put_task(req->task, 1); - wq_list_add_head(&req->comp_list, &ctx->locked_free_list); - ctx->locked_free_nr++; - } -} - -static void __io_req_complete_post(struct io_kiocb *req, s32 res, - u32 cflags) -{ - if (!(req->flags & REQ_F_CQE_SKIP)) { - req->cqe.res = res; - req->cqe.flags = cflags; - __io_fill_cqe_req(req->ctx, req); - } - __io_req_complete_put(req); -} - -static void io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags) -{ - struct io_ring_ctx *ctx = req->ctx; - - spin_lock(&ctx->completion_lock); - __io_req_complete_post(req, res, cflags); - io_commit_cqring(ctx); - spin_unlock(&ctx->completion_lock); - io_cqring_ev_posted(ctx); -} - -static inline void io_req_complete_state(struct io_kiocb *req, s32 res, - u32 cflags) -{ - req->cqe.res = res; - req->cqe.flags = cflags; - req->flags |= REQ_F_COMPLETE_INLINE; -} - -static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags, - s32 res, u32 cflags) -{ - if (issue_flags & IO_URING_F_COMPLETE_DEFER) - io_req_complete_state(req, res, cflags); - else - io_req_complete_post(req, res, cflags); -} - -static inline void io_req_complete(struct io_kiocb *req, s32 res) -{ - if (res < 0) - req_set_fail(req); - __io_req_complete(req, 0, res, 0); -} - -static void io_req_complete_failed(struct io_kiocb *req, s32 res) -{ - req_set_fail(req); - io_req_complete_post(req, res, io_put_kbuf(req, IO_URING_F_UNLOCKED)); -} - -/* - * Don't initialise the fields below on every allocation, but do that in - * advance and keep them valid across allocations. - */ -static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx) -{ - req->ctx = ctx; - req->link = NULL; - req->async_data = NULL; - /* not necessary, but safer to zero */ - req->cqe.res = 0; -} - -static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, - struct io_submit_state *state) -{ - spin_lock(&ctx->completion_lock); - wq_list_splice(&ctx->locked_free_list, &state->free_list); - ctx->locked_free_nr = 0; - spin_unlock(&ctx->completion_lock); -} - -static inline bool io_req_cache_empty(struct io_ring_ctx *ctx) -{ - return !ctx->submit_state.free_list.next; -} - -/* - * A request might get retired back into the request caches even before opcode - * handlers and io_issue_sqe() are done with it, e.g. inline completion path. - * Because of that, io_alloc_req() should be called only under ->uring_lock - * and with extra caution to not get a request that is still worked on. - */ -static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx) - __must_hold(&ctx->uring_lock) -{ - gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; - void *reqs[IO_REQ_ALLOC_BATCH]; - int ret, i; - - /* - * If we have more than a batch's worth of requests in our IRQ side - * locked cache, grab the lock and move them over to our submission - * side cache. - */ - if (data_race(ctx->locked_free_nr) > IO_COMPL_BATCH) { - io_flush_cached_locked_reqs(ctx, &ctx->submit_state); - if (!io_req_cache_empty(ctx)) - return true; - } - - ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), reqs); - - /* - * Bulk alloc is all-or-nothing. If we fail to get a batch, - * retry single alloc to be on the safe side. - */ - if (unlikely(ret <= 0)) { - reqs[0] = kmem_cache_alloc(req_cachep, gfp); - if (!reqs[0]) - return false; - ret = 1; - } - - percpu_ref_get_many(&ctx->refs, ret); - for (i = 0; i < ret; i++) { - struct io_kiocb *req = reqs[i]; - - io_preinit_req(req, ctx); - io_req_add_to_cache(req, ctx); - } - return true; -} - -static inline bool io_alloc_req_refill(struct io_ring_ctx *ctx) -{ - if (unlikely(io_req_cache_empty(ctx))) - return __io_alloc_req_refill(ctx); - return true; -} - -static inline struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) -{ - struct io_wq_work_node *node; - - node = wq_stack_extract(&ctx->submit_state.free_list); - return container_of(node, struct io_kiocb, comp_list); -} - -static inline void io_put_file(struct file *file) -{ - if (file) - fput(file); -} - -static inline void io_dismantle_req(struct io_kiocb *req) -{ - unsigned int flags = req->flags; - - if (unlikely(flags & IO_REQ_CLEAN_FLAGS)) - io_clean_op(req); - if (!(flags & REQ_F_FIXED_FILE)) - io_put_file(req->file); -} - -static __cold void io_free_req(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - - io_req_put_rsrc(req); - io_dismantle_req(req); - io_put_task(req->task, 1); - - spin_lock(&ctx->completion_lock); - wq_list_add_head(&req->comp_list, &ctx->locked_free_list); - ctx->locked_free_nr++; - spin_unlock(&ctx->completion_lock); -} - -static inline void io_remove_next_linked(struct io_kiocb *req) -{ - struct io_kiocb *nxt = req->link; - - req->link = nxt->link; - nxt->link = NULL; -} - -static struct io_kiocb *io_disarm_linked_timeout(struct io_kiocb *req) - __must_hold(&req->ctx->completion_lock) - __must_hold(&req->ctx->timeout_lock) -{ - struct io_kiocb *link = req->link; - - if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { - struct io_timeout_data *io = link->async_data; - - io_remove_next_linked(req); - link->timeout.head = NULL; - if (hrtimer_try_to_cancel(&io->timer) != -1) { - list_del(&link->timeout.list); - return link; - } - } - return NULL; -} - -static void io_fail_links(struct io_kiocb *req) - __must_hold(&req->ctx->completion_lock) -{ - struct io_kiocb *nxt, *link = req->link; - bool ignore_cqes = req->flags & REQ_F_SKIP_LINK_CQES; - - req->link = NULL; - while (link) { - long res = -ECANCELED; - - if (link->flags & REQ_F_FAIL) - res = link->cqe.res; - - nxt = link->link; - link->link = NULL; - - trace_io_uring_fail_link(req->ctx, req, req->cqe.user_data, - req->opcode, link); - - if (ignore_cqes) - link->flags |= REQ_F_CQE_SKIP; - else - link->flags &= ~REQ_F_CQE_SKIP; - __io_req_complete_post(link, res, 0); - link = nxt; - } -} - -static bool io_disarm_next(struct io_kiocb *req) - __must_hold(&req->ctx->completion_lock) -{ - struct io_kiocb *link = NULL; - bool posted = false; - - if (req->flags & REQ_F_ARM_LTIMEOUT) { - link = req->link; - req->flags &= ~REQ_F_ARM_LTIMEOUT; - if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { - io_remove_next_linked(req); - io_req_tw_post_queue(link, -ECANCELED, 0); - posted = true; - } - } else if (req->flags & REQ_F_LINK_TIMEOUT) { - struct io_ring_ctx *ctx = req->ctx; - - spin_lock_irq(&ctx->timeout_lock); - link = io_disarm_linked_timeout(req); - spin_unlock_irq(&ctx->timeout_lock); - if (link) { - posted = true; - io_req_tw_post_queue(link, -ECANCELED, 0); - } - } - if (unlikely((req->flags & REQ_F_FAIL) && - !(req->flags & REQ_F_HARDLINK))) { - posted |= (req->link != NULL); - io_fail_links(req); - } - return posted; -} - -static void __io_req_find_next_prep(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - bool posted; - - spin_lock(&ctx->completion_lock); - posted = io_disarm_next(req); - io_commit_cqring(ctx); - spin_unlock(&ctx->completion_lock); - if (posted) - io_cqring_ev_posted(ctx); -} - -static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) -{ - struct io_kiocb *nxt; - - /* - * If LINK is set, we have dependent requests in this chain. If we - * didn't fail this request, queue the first one up, moving any other - * dependencies to the next request. In case of failure, fail the rest - * of the chain. - */ - if (unlikely(req->flags & IO_DISARM_MASK)) - __io_req_find_next_prep(req); - nxt = req->link; - req->link = NULL; - return nxt; -} - -static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked) -{ - if (!ctx) - return; - if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) - atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); - if (*locked) { - io_submit_flush_completions(ctx); - mutex_unlock(&ctx->uring_lock); - *locked = false; - } - percpu_ref_put(&ctx->refs); -} - -static inline void ctx_commit_and_unlock(struct io_ring_ctx *ctx) -{ - io_commit_cqring(ctx); - spin_unlock(&ctx->completion_lock); - io_cqring_ev_posted(ctx); -} - -static void handle_prev_tw_list(struct io_wq_work_node *node, - struct io_ring_ctx **ctx, bool *uring_locked) -{ - if (*ctx && !*uring_locked) - spin_lock(&(*ctx)->completion_lock); - - do { - struct io_wq_work_node *next = node->next; - struct io_kiocb *req = container_of(node, struct io_kiocb, - io_task_work.node); - - prefetch(container_of(next, struct io_kiocb, io_task_work.node)); - - if (req->ctx != *ctx) { - if (unlikely(!*uring_locked && *ctx)) - ctx_commit_and_unlock(*ctx); - - ctx_flush_and_put(*ctx, uring_locked); - *ctx = req->ctx; - /* if not contended, grab and improve batching */ - *uring_locked = mutex_trylock(&(*ctx)->uring_lock); - percpu_ref_get(&(*ctx)->refs); - if (unlikely(!*uring_locked)) - spin_lock(&(*ctx)->completion_lock); - } - if (likely(*uring_locked)) - req->io_task_work.func(req, uring_locked); - else - __io_req_complete_post(req, req->cqe.res, - io_put_kbuf_comp(req)); - node = next; - } while (node); - - if (unlikely(!*uring_locked)) - ctx_commit_and_unlock(*ctx); -} - -static void handle_tw_list(struct io_wq_work_node *node, - struct io_ring_ctx **ctx, bool *locked) -{ - do { - struct io_wq_work_node *next = node->next; - struct io_kiocb *req = container_of(node, struct io_kiocb, - io_task_work.node); - - prefetch(container_of(next, struct io_kiocb, io_task_work.node)); - - if (req->ctx != *ctx) { - ctx_flush_and_put(*ctx, locked); - *ctx = req->ctx; - /* if not contended, grab and improve batching */ - *locked = mutex_trylock(&(*ctx)->uring_lock); - percpu_ref_get(&(*ctx)->refs); - } - req->io_task_work.func(req, locked); - node = next; - } while (node); -} - -static void tctx_task_work(struct callback_head *cb) -{ - bool uring_locked = false; - struct io_ring_ctx *ctx = NULL; - struct io_uring_task *tctx = container_of(cb, struct io_uring_task, - task_work); - - while (1) { - struct io_wq_work_node *node1, *node2; - - spin_lock_irq(&tctx->task_lock); - node1 = tctx->prio_task_list.first; - node2 = tctx->task_list.first; - INIT_WQ_LIST(&tctx->task_list); - INIT_WQ_LIST(&tctx->prio_task_list); - if (!node2 && !node1) - tctx->task_running = false; - spin_unlock_irq(&tctx->task_lock); - if (!node2 && !node1) - break; - - if (node1) - handle_prev_tw_list(node1, &ctx, &uring_locked); - if (node2) - handle_tw_list(node2, &ctx, &uring_locked); - cond_resched(); - - if (data_race(!tctx->task_list.first) && - data_race(!tctx->prio_task_list.first) && uring_locked) - io_submit_flush_completions(ctx); - } - - ctx_flush_and_put(ctx, &uring_locked); - - /* relaxed read is enough as only the task itself sets ->in_idle */ - if (unlikely(atomic_read(&tctx->in_idle))) - io_uring_drop_tctx_refs(current); -} - -static void __io_req_task_work_add(struct io_kiocb *req, - struct io_uring_task *tctx, - struct io_wq_work_list *list) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_wq_work_node *node; - unsigned long flags; - bool running; - - spin_lock_irqsave(&tctx->task_lock, flags); - wq_list_add_tail(&req->io_task_work.node, list); - running = tctx->task_running; - if (!running) - tctx->task_running = true; - spin_unlock_irqrestore(&tctx->task_lock, flags); - - /* task_work already pending, we're done */ - if (running) - return; - - if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) - atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); - - if (likely(!task_work_add(req->task, &tctx->task_work, ctx->notify_method))) - return; - - spin_lock_irqsave(&tctx->task_lock, flags); - tctx->task_running = false; - node = wq_list_merge(&tctx->prio_task_list, &tctx->task_list); - spin_unlock_irqrestore(&tctx->task_lock, flags); - - while (node) { - req = container_of(node, struct io_kiocb, io_task_work.node); - node = node->next; - if (llist_add(&req->io_task_work.fallback_node, - &req->ctx->fallback_llist)) - schedule_delayed_work(&req->ctx->fallback_work, 1); - } -} - -static void io_req_task_work_add(struct io_kiocb *req) -{ - struct io_uring_task *tctx = req->task->io_uring; - - __io_req_task_work_add(req, tctx, &tctx->task_list); -} - -static void io_req_task_prio_work_add(struct io_kiocb *req) -{ - struct io_uring_task *tctx = req->task->io_uring; - - if (req->ctx->flags & IORING_SETUP_SQPOLL) - __io_req_task_work_add(req, tctx, &tctx->prio_task_list); - else - __io_req_task_work_add(req, tctx, &tctx->task_list); -} - -static void io_req_tw_post(struct io_kiocb *req, bool *locked) -{ - io_req_complete_post(req, req->cqe.res, req->cqe.flags); -} - -static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags) -{ - req->cqe.res = res; - req->cqe.flags = cflags; - req->io_task_work.func = io_req_tw_post; - io_req_task_work_add(req); -} - -static void io_req_task_cancel(struct io_kiocb *req, bool *locked) -{ - /* not needed for normal modes, but SQPOLL depends on it */ - io_tw_lock(req->ctx, locked); - io_req_complete_failed(req, req->cqe.res); -} - -static void io_req_task_submit(struct io_kiocb *req, bool *locked) -{ - io_tw_lock(req->ctx, locked); - /* req->task == current here, checking PF_EXITING is safe */ - if (likely(!(req->task->flags & PF_EXITING))) - io_queue_sqe(req); - else - io_req_complete_failed(req, -EFAULT); -} - -static void io_req_task_queue_fail(struct io_kiocb *req, int ret) -{ - req->cqe.res = ret; - req->io_task_work.func = io_req_task_cancel; - io_req_task_work_add(req); -} - -static void io_req_task_queue(struct io_kiocb *req) -{ - req->io_task_work.func = io_req_task_submit; - io_req_task_work_add(req); -} - -static void io_req_task_queue_reissue(struct io_kiocb *req) -{ - req->io_task_work.func = io_queue_iowq; - io_req_task_work_add(req); -} - -static void io_queue_next(struct io_kiocb *req) -{ - struct io_kiocb *nxt = io_req_find_next(req); - - if (nxt) - io_req_task_queue(nxt); -} - -static void io_free_batch_list(struct io_ring_ctx *ctx, - struct io_wq_work_node *node) - __must_hold(&ctx->uring_lock) -{ - struct task_struct *task = NULL; - int task_refs = 0; - - do { - struct io_kiocb *req = container_of(node, struct io_kiocb, - comp_list); - - if (unlikely(req->flags & IO_REQ_CLEAN_SLOW_FLAGS)) { - if (req->flags & REQ_F_REFCOUNT) { - node = req->comp_list.next; - if (!req_ref_put_and_test(req)) - continue; - } - if ((req->flags & REQ_F_POLLED) && req->apoll) { - struct async_poll *apoll = req->apoll; - - if (apoll->double_poll) - kfree(apoll->double_poll); - list_add(&apoll->poll.wait.entry, - &ctx->apoll_cache); - req->flags &= ~REQ_F_POLLED; - } - if (req->flags & IO_REQ_LINK_FLAGS) - io_queue_next(req); - if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS)) - io_clean_op(req); - } - if (!(req->flags & REQ_F_FIXED_FILE)) - io_put_file(req->file); - - io_req_put_rsrc_locked(req, ctx); - - if (req->task != task) { - if (task) - io_put_task(task, task_refs); - task = req->task; - task_refs = 0; - } - task_refs++; - node = req->comp_list.next; - io_req_add_to_cache(req, ctx); - } while (node); - - if (task) - io_put_task(task, task_refs); -} - -static void __io_submit_flush_completions(struct io_ring_ctx *ctx) - __must_hold(&ctx->uring_lock) -{ - struct io_wq_work_node *node, *prev; - struct io_submit_state *state = &ctx->submit_state; - - if (state->flush_cqes) { - spin_lock(&ctx->completion_lock); - wq_list_for_each(node, prev, &state->compl_reqs) { - struct io_kiocb *req = container_of(node, struct io_kiocb, - comp_list); - - if (!(req->flags & REQ_F_CQE_SKIP)) - __io_fill_cqe_req(ctx, req); - } - - io_commit_cqring(ctx); - spin_unlock(&ctx->completion_lock); - io_cqring_ev_posted(ctx); - state->flush_cqes = false; - } - - io_free_batch_list(ctx, state->compl_reqs.first); - INIT_WQ_LIST(&state->compl_reqs); -} - -/* - * Drop reference to request, return next in chain (if there is one) if this - * was the last reference to this request. - */ -static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req) -{ - struct io_kiocb *nxt = NULL; - - if (req_ref_put_and_test(req)) { - if (unlikely(req->flags & IO_REQ_LINK_FLAGS)) - nxt = io_req_find_next(req); - io_free_req(req); - } - return nxt; -} - -static inline void io_put_req(struct io_kiocb *req) -{ - if (req_ref_put_and_test(req)) { - io_queue_next(req); - io_free_req(req); - } -} - -static unsigned io_cqring_events(struct io_ring_ctx *ctx) -{ - /* See comment at the top of this file */ - smp_rmb(); - return __io_cqring_events(ctx); -} - -static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) -{ - struct io_rings *rings = ctx->rings; - - /* make sure SQ entry isn't read before tail */ - return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head; -} - -static inline bool io_run_task_work(void) -{ - if (test_thread_flag(TIF_NOTIFY_SIGNAL) || task_work_pending(current)) { - __set_current_state(TASK_RUNNING); - clear_notify_signal(); - if (task_work_pending(current)) - task_work_run(); - return true; - } - - return false; -} - -static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) -{ - struct io_wq_work_node *pos, *start, *prev; - unsigned int poll_flags = BLK_POLL_NOSLEEP; - DEFINE_IO_COMP_BATCH(iob); - int nr_events = 0; - - /* - * Only spin for completions if we don't have multiple devices hanging - * off our complete list. - */ - if (ctx->poll_multi_queue || force_nonspin) - poll_flags |= BLK_POLL_ONESHOT; - - wq_list_for_each(pos, start, &ctx->iopoll_list) { - struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list); - struct kiocb *kiocb = &req->rw.kiocb; - int ret; - - /* - * Move completed and retryable entries to our local lists. - * If we find a request that requires polling, break out - * and complete those lists first, if we have entries there. - */ - if (READ_ONCE(req->iopoll_completed)) - break; - - ret = kiocb->ki_filp->f_op->iopoll(kiocb, &iob, poll_flags); - if (unlikely(ret < 0)) - return ret; - else if (ret) - poll_flags |= BLK_POLL_ONESHOT; - - /* iopoll may have completed current req */ - if (!rq_list_empty(iob.req_list) || - READ_ONCE(req->iopoll_completed)) - break; - } - - if (!rq_list_empty(iob.req_list)) - iob.complete(&iob); - else if (!pos) - return 0; - - prev = start; - wq_list_for_each_resume(pos, prev) { - struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list); - - /* order with io_complete_rw_iopoll(), e.g. ->result updates */ - if (!smp_load_acquire(&req->iopoll_completed)) - break; - nr_events++; - if (unlikely(req->flags & REQ_F_CQE_SKIP)) - continue; - - req->cqe.flags = io_put_kbuf(req, 0); - __io_fill_cqe_req(req->ctx, req); - } - - if (unlikely(!nr_events)) - return 0; - - io_commit_cqring(ctx); - io_cqring_ev_posted_iopoll(ctx); - pos = start ? start->next : ctx->iopoll_list.first; - wq_list_cut(&ctx->iopoll_list, prev, start); - io_free_batch_list(ctx, pos); - return nr_events; -} - -/* - * We can't just wait for polled events to come to us, we have to actively - * find and complete them. - */ -static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx) -{ - if (!(ctx->flags & IORING_SETUP_IOPOLL)) - return; - - mutex_lock(&ctx->uring_lock); - while (!wq_list_empty(&ctx->iopoll_list)) { - /* let it sleep and repeat later if can't complete a request */ - if (io_do_iopoll(ctx, true) == 0) - break; - /* - * Ensure we allow local-to-the-cpu processing to take place, - * in this case we need to ensure that we reap all events. - * Also let task_work, etc. to progress by releasing the mutex - */ - if (need_resched()) { - mutex_unlock(&ctx->uring_lock); - cond_resched(); - mutex_lock(&ctx->uring_lock); - } - } - mutex_unlock(&ctx->uring_lock); -} - -static int io_iopoll_check(struct io_ring_ctx *ctx, long min) -{ - unsigned int nr_events = 0; - int ret = 0; - unsigned long check_cq; - - /* - * Don't enter poll loop if we already have events pending. - * If we do, we can potentially be spinning for commands that - * already triggered a CQE (eg in error). - */ - check_cq = READ_ONCE(ctx->check_cq); - if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) - __io_cqring_overflow_flush(ctx, false); - if (io_cqring_events(ctx)) - return 0; - - /* - * Similarly do not spin if we have not informed the user of any - * dropped CQE. - */ - if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))) - return -EBADR; - - do { - /* - * If a submit got punted to a workqueue, we can have the - * application entering polling for a command before it gets - * issued. That app will hold the uring_lock for the duration - * of the poll right here, so we need to take a breather every - * now and then to ensure that the issue has a chance to add - * the poll to the issued list. Otherwise we can spin here - * forever, while the workqueue is stuck trying to acquire the - * very same mutex. - */ - if (wq_list_empty(&ctx->iopoll_list)) { - u32 tail = ctx->cached_cq_tail; - - mutex_unlock(&ctx->uring_lock); - io_run_task_work(); - mutex_lock(&ctx->uring_lock); - - /* some requests don't go through iopoll_list */ - if (tail != ctx->cached_cq_tail || - wq_list_empty(&ctx->iopoll_list)) - break; - } - ret = io_do_iopoll(ctx, !min); - if (ret < 0) - break; - nr_events += ret; - ret = 0; - } while (nr_events < min && !need_resched()); - - return ret; -} - -static void kiocb_end_write(struct io_kiocb *req) -{ - /* - * Tell lockdep we inherited freeze protection from submission - * thread. - */ - if (req->flags & REQ_F_ISREG) { - struct super_block *sb = file_inode(req->file)->i_sb; - - __sb_writers_acquired(sb, SB_FREEZE_WRITE); - sb_end_write(sb); - } -} - -#ifdef CONFIG_BLOCK -static bool io_resubmit_prep(struct io_kiocb *req) -{ - struct io_async_rw *rw = req->async_data; - - if (!req_has_async_data(req)) - return !io_req_prep_async(req); - iov_iter_restore(&rw->s.iter, &rw->s.iter_state); - return true; -} - -static bool io_rw_should_reissue(struct io_kiocb *req) -{ - umode_t mode = file_inode(req->file)->i_mode; - struct io_ring_ctx *ctx = req->ctx; - - if (!S_ISBLK(mode) && !S_ISREG(mode)) - return false; - if ((req->flags & REQ_F_NOWAIT) || (io_wq_current_is_worker() && - !(ctx->flags & IORING_SETUP_IOPOLL))) - return false; - /* - * If ref is dying, we might be running poll reap from the exit work. - * Don't attempt to reissue from that path, just let it fail with - * -EAGAIN. - */ - if (percpu_ref_is_dying(&ctx->refs)) - return false; - /* - * Play it safe and assume not safe to re-import and reissue if we're - * not in the original thread group (or in task context). - */ - if (!same_thread_group(req->task, current) || !in_task()) - return false; - return true; -} -#else -static bool io_resubmit_prep(struct io_kiocb *req) -{ - return false; -} -static bool io_rw_should_reissue(struct io_kiocb *req) -{ - return false; -} -#endif - -static bool __io_complete_rw_common(struct io_kiocb *req, long res) -{ - if (req->rw.kiocb.ki_flags & IOCB_WRITE) { - kiocb_end_write(req); - fsnotify_modify(req->file); - } else { - fsnotify_access(req->file); - } - if (unlikely(res != req->cqe.res)) { - if ((res == -EAGAIN || res == -EOPNOTSUPP) && - io_rw_should_reissue(req)) { - req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO; - return true; - } - req_set_fail(req); - req->cqe.res = res; - } - return false; -} - -static inline void io_req_task_complete(struct io_kiocb *req, bool *locked) -{ - int res = req->cqe.res; - - if (*locked) { - io_req_complete_state(req, res, io_put_kbuf(req, 0)); - io_req_add_compl_list(req); - } else { - io_req_complete_post(req, res, - io_put_kbuf(req, IO_URING_F_UNLOCKED)); - } -} - -static void __io_complete_rw(struct io_kiocb *req, long res, - unsigned int issue_flags) -{ - if (__io_complete_rw_common(req, res)) - return; - __io_req_complete(req, issue_flags, req->cqe.res, - io_put_kbuf(req, issue_flags)); -} - -static void io_complete_rw(struct kiocb *kiocb, long res) -{ - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); - - if (__io_complete_rw_common(req, res)) - return; - req->cqe.res = res; - req->io_task_work.func = io_req_task_complete; - io_req_task_prio_work_add(req); -} - -static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) -{ - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); - - if (kiocb->ki_flags & IOCB_WRITE) - kiocb_end_write(req); - if (unlikely(res != req->cqe.res)) { - if (res == -EAGAIN && io_rw_should_reissue(req)) { - req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO; - return; - } - req->cqe.res = res; - } - - /* order with io_iopoll_complete() checking ->iopoll_completed */ - smp_store_release(&req->iopoll_completed, 1); -} - -/* - * After the iocb has been issued, it's safe to be found on the poll list. - * Adding the kiocb to the list AFTER submission ensures that we don't - * find it from a io_do_iopoll() thread before the issuer is done - * accessing the kiocb cookie. - */ -static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_ring_ctx *ctx = req->ctx; - const bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; - - /* workqueue context doesn't hold uring_lock, grab it now */ - if (unlikely(needs_lock)) - mutex_lock(&ctx->uring_lock); - - /* - * Track whether we have multiple files in our lists. This will impact - * how we do polling eventually, not spinning if we're on potentially - * different devices. - */ - if (wq_list_empty(&ctx->iopoll_list)) { - ctx->poll_multi_queue = false; - } else if (!ctx->poll_multi_queue) { - struct io_kiocb *list_req; - - list_req = container_of(ctx->iopoll_list.first, struct io_kiocb, - comp_list); - if (list_req->file != req->file) - ctx->poll_multi_queue = true; - } - - /* - * For fast devices, IO may have already completed. If it has, add - * it to the front so we find it first. - */ - if (READ_ONCE(req->iopoll_completed)) - wq_list_add_head(&req->comp_list, &ctx->iopoll_list); - else - wq_list_add_tail(&req->comp_list, &ctx->iopoll_list); - - if (unlikely(needs_lock)) { - /* - * If IORING_SETUP_SQPOLL is enabled, sqes are either handle - * in sq thread task context or in io worker task context. If - * current task context is sq thread, we don't need to check - * whether should wake up sq thread. - */ - if ((ctx->flags & IORING_SETUP_SQPOLL) && - wq_has_sleeper(&ctx->sq_data->wait)) - wake_up(&ctx->sq_data->wait); - - mutex_unlock(&ctx->uring_lock); - } -} - -static bool io_bdev_nowait(struct block_device *bdev) -{ - return !bdev || blk_queue_nowait(bdev_get_queue(bdev)); -} - -/* - * If we tracked the file through the SCM inflight mechanism, we could support - * any file. For now, just ensure that anything potentially problematic is done - * inline. - */ -static bool __io_file_supports_nowait(struct file *file, umode_t mode) -{ - if (S_ISBLK(mode)) { - if (IS_ENABLED(CONFIG_BLOCK) && - io_bdev_nowait(I_BDEV(file->f_mapping->host))) - return true; - return false; - } - if (S_ISSOCK(mode)) - return true; - if (S_ISREG(mode)) { - if (IS_ENABLED(CONFIG_BLOCK) && - io_bdev_nowait(file->f_inode->i_sb->s_bdev) && - file->f_op != &io_uring_fops) - return true; - return false; - } - - /* any ->read/write should understand O_NONBLOCK */ - if (file->f_flags & O_NONBLOCK) - return true; - return file->f_mode & FMODE_NOWAIT; -} - -/* - * If we tracked the file through the SCM inflight mechanism, we could support - * any file. For now, just ensure that anything potentially problematic is done - * inline. - */ -static unsigned int io_file_get_flags(struct file *file) -{ - umode_t mode = file_inode(file)->i_mode; - unsigned int res = 0; - - if (S_ISREG(mode)) - res |= FFS_ISREG; - if (__io_file_supports_nowait(file, mode)) - res |= FFS_NOWAIT; - if (io_file_need_scm(file)) - res |= FFS_SCM; - return res; -} - -static inline bool io_file_supports_nowait(struct io_kiocb *req) -{ - return req->flags & REQ_F_SUPPORT_NOWAIT; -} - -static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - struct kiocb *kiocb = &req->rw.kiocb; - unsigned ioprio; - int ret; - - kiocb->ki_pos = READ_ONCE(sqe->off); - /* used for fixed read/write too - just read unconditionally */ - req->buf_index = READ_ONCE(sqe->buf_index); - - if (req->opcode == IORING_OP_READ_FIXED || - req->opcode == IORING_OP_WRITE_FIXED) { - struct io_ring_ctx *ctx = req->ctx; - u16 index; - - if (unlikely(req->buf_index >= ctx->nr_user_bufs)) - return -EFAULT; - index = array_index_nospec(req->buf_index, ctx->nr_user_bufs); - req->imu = ctx->user_bufs[index]; - io_req_set_rsrc_node(req, ctx, 0); - } - - ioprio = READ_ONCE(sqe->ioprio); - if (ioprio) { - ret = ioprio_check_cap(ioprio); - if (ret) - return ret; - - kiocb->ki_ioprio = ioprio; - } else { - kiocb->ki_ioprio = get_current_ioprio(); - } - - req->rw.addr = READ_ONCE(sqe->addr); - req->rw.len = READ_ONCE(sqe->len); - req->rw.flags = READ_ONCE(sqe->rw_flags); - return 0; -} - -static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) -{ - switch (ret) { - case -EIOCBQUEUED: - break; - case -ERESTARTSYS: - case -ERESTARTNOINTR: - case -ERESTARTNOHAND: - case -ERESTART_RESTARTBLOCK: - /* - * We can't just restart the syscall, since previously - * submitted sqes may already be in progress. Just fail this - * IO with EINTR. - */ - ret = -EINTR; - fallthrough; - default: - kiocb->ki_complete(kiocb, ret); - } -} - -static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) -{ - struct kiocb *kiocb = &req->rw.kiocb; - - if (kiocb->ki_pos != -1) - return &kiocb->ki_pos; - - if (!(req->file->f_mode & FMODE_STREAM)) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = req->file->f_pos; - return &kiocb->ki_pos; - } - - kiocb->ki_pos = 0; - return NULL; -} - -static void kiocb_done(struct io_kiocb *req, ssize_t ret, - unsigned int issue_flags) -{ - struct io_async_rw *io = req->async_data; - - /* add previously done IO, if any */ - if (req_has_async_data(req) && io->bytes_done > 0) { - if (ret < 0) - ret = io->bytes_done; - else - ret += io->bytes_done; - } - - if (req->flags & REQ_F_CUR_POS) - req->file->f_pos = req->rw.kiocb.ki_pos; - if (ret >= 0 && (req->rw.kiocb.ki_complete == io_complete_rw)) - __io_complete_rw(req, ret, issue_flags); - else - io_rw_done(&req->rw.kiocb, ret); - - if (req->flags & REQ_F_REISSUE) { - req->flags &= ~REQ_F_REISSUE; - if (io_resubmit_prep(req)) - io_req_task_queue_reissue(req); - else - io_req_task_queue_fail(req, ret); - } -} - -static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, - struct io_mapped_ubuf *imu) -{ - size_t len = req->rw.len; - u64 buf_end, buf_addr = req->rw.addr; - size_t offset; - - if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end))) - return -EFAULT; - /* not inside the mapped region */ - if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end)) - return -EFAULT; - - /* - * May not be a start of buffer, set size appropriately - * and advance us to the beginning. - */ - offset = buf_addr - imu->ubuf; - iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len); - - if (offset) { - /* - * Don't use iov_iter_advance() here, as it's really slow for - * using the latter parts of a big fixed buffer - it iterates - * over each segment manually. We can cheat a bit here, because - * we know that: - * - * 1) it's a BVEC iter, we set it up - * 2) all bvecs are PAGE_SIZE in size, except potentially the - * first and last bvec - * - * So just find our index, and adjust the iterator afterwards. - * If the offset is within the first bvec (or the whole first - * bvec, just use iov_iter_advance(). This makes it easier - * since we can just skip the first segment, which may not - * be PAGE_SIZE aligned. - */ - const struct bio_vec *bvec = imu->bvec; - - if (offset <= bvec->bv_len) { - iov_iter_advance(iter, offset); - } else { - unsigned long seg_skip; - - /* skip first vec */ - offset -= bvec->bv_len; - seg_skip = 1 + (offset >> PAGE_SHIFT); - - iter->bvec = bvec + seg_skip; - iter->nr_segs -= seg_skip; - iter->count -= bvec->bv_len + offset; - iter->iov_offset = offset & ~PAGE_MASK; - } - } - - return 0; -} - -static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, - unsigned int issue_flags) -{ - if (WARN_ON_ONCE(!req->imu)) - return -EFAULT; - return __io_import_fixed(req, rw, iter, req->imu); -} - -static int io_buffer_add_list(struct io_ring_ctx *ctx, - struct io_buffer_list *bl, unsigned int bgid) -{ - bl->bgid = bgid; - if (bgid < BGID_ARRAY) - return 0; - - return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); -} - -static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len, - struct io_buffer_list *bl) -{ - if (!list_empty(&bl->buf_list)) { - struct io_buffer *kbuf; - - kbuf = list_first_entry(&bl->buf_list, struct io_buffer, list); - list_del(&kbuf->list); - if (*len > kbuf->len) - *len = kbuf->len; - req->flags |= REQ_F_BUFFER_SELECTED; - req->kbuf = kbuf; - req->buf_index = kbuf->bid; - return u64_to_user_ptr(kbuf->addr); - } - return NULL; -} - -static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, - struct io_buffer_list *bl, - unsigned int issue_flags) -{ - struct io_uring_buf_ring *br = bl->buf_ring; - struct io_uring_buf *buf; - __u16 head = bl->head; - - if (unlikely(smp_load_acquire(&br->tail) == head)) - return NULL; - - head &= bl->mask; - if (head < IO_BUFFER_LIST_BUF_PER_PAGE) { - buf = &br->bufs[head]; - } else { - int off = head & (IO_BUFFER_LIST_BUF_PER_PAGE - 1); - int index = head / IO_BUFFER_LIST_BUF_PER_PAGE; - buf = page_address(bl->buf_pages[index]); - buf += off; - } - if (*len > buf->len) - *len = buf->len; - req->flags |= REQ_F_BUFFER_RING; - req->buf_list = bl; - req->buf_index = buf->bid; - - if (issue_flags & IO_URING_F_UNLOCKED || !file_can_poll(req->file)) { - /* - * If we came in unlocked, we have no choice but to consume the - * buffer here. This does mean it'll be pinned until the IO - * completes. But coming in unlocked means we're in io-wq - * context, hence there should be no further retry. For the - * locked case, the caller must ensure to call the commit when - * the transfer completes (or if we get -EAGAIN and must poll - * or retry). - */ - req->buf_list = NULL; - bl->head++; - } - return u64_to_user_ptr(buf->addr); -} - -static void __user *io_buffer_select(struct io_kiocb *req, size_t *len, - unsigned int issue_flags) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_buffer_list *bl; - void __user *ret = NULL; - - io_ring_submit_lock(req->ctx, issue_flags); - - bl = io_buffer_get_list(ctx, req->buf_index); - if (likely(bl)) { - if (bl->buf_nr_pages) - ret = io_ring_buffer_select(req, len, bl, issue_flags); - else - ret = io_provided_buffer_select(req, len, bl); - } - io_ring_submit_unlock(req->ctx, issue_flags); - return ret; -} - -#ifdef CONFIG_COMPAT -static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov, - unsigned int issue_flags) -{ - struct compat_iovec __user *uiov; - compat_ssize_t clen; - void __user *buf; - size_t len; - - uiov = u64_to_user_ptr(req->rw.addr); - if (!access_ok(uiov, sizeof(*uiov))) - return -EFAULT; - if (__get_user(clen, &uiov->iov_len)) - return -EFAULT; - if (clen < 0) - return -EINVAL; - - len = clen; - buf = io_buffer_select(req, &len, issue_flags); - if (!buf) - return -ENOBUFS; - req->rw.addr = (unsigned long) buf; - iov[0].iov_base = buf; - req->rw.len = iov[0].iov_len = (compat_size_t) len; - return 0; -} -#endif - -static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, - unsigned int issue_flags) -{ - struct iovec __user *uiov = u64_to_user_ptr(req->rw.addr); - void __user *buf; - ssize_t len; - - if (copy_from_user(iov, uiov, sizeof(*uiov))) - return -EFAULT; - - len = iov[0].iov_len; - if (len < 0) - return -EINVAL; - buf = io_buffer_select(req, &len, issue_flags); - if (!buf) - return -ENOBUFS; - req->rw.addr = (unsigned long) buf; - iov[0].iov_base = buf; - req->rw.len = iov[0].iov_len = len; - return 0; -} - -static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, - unsigned int issue_flags) -{ - if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) { - iov[0].iov_base = u64_to_user_ptr(req->rw.addr); - iov[0].iov_len = req->rw.len; - return 0; - } - if (req->rw.len != 1) - return -EINVAL; - -#ifdef CONFIG_COMPAT - if (req->ctx->compat) - return io_compat_import(req, iov, issue_flags); -#endif - - return __io_iov_buffer_select(req, iov, issue_flags); -} - -static inline bool io_do_buffer_select(struct io_kiocb *req) -{ - if (!(req->flags & REQ_F_BUFFER_SELECT)) - return false; - return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)); -} - -static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req, - struct io_rw_state *s, - unsigned int issue_flags) -{ - struct iov_iter *iter = &s->iter; - u8 opcode = req->opcode; - struct iovec *iovec; - void __user *buf; - size_t sqe_len; - ssize_t ret; - - if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { - ret = io_import_fixed(req, rw, iter, issue_flags); - if (ret) - return ERR_PTR(ret); - return NULL; - } - - buf = u64_to_user_ptr(req->rw.addr); - sqe_len = req->rw.len; - - if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) { - if (io_do_buffer_select(req)) { - buf = io_buffer_select(req, &sqe_len, issue_flags); - if (!buf) - return ERR_PTR(-ENOBUFS); - req->rw.addr = (unsigned long) buf; - req->rw.len = sqe_len; - } - - ret = import_single_range(rw, buf, sqe_len, s->fast_iov, iter); - if (ret) - return ERR_PTR(ret); - return NULL; - } - - iovec = s->fast_iov; - if (req->flags & REQ_F_BUFFER_SELECT) { - ret = io_iov_buffer_select(req, iovec, issue_flags); - if (ret) - return ERR_PTR(ret); - iov_iter_init(iter, rw, iovec, 1, iovec->iov_len); - return NULL; - } - - ret = __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, &iovec, iter, - req->ctx->compat); - if (unlikely(ret < 0)) - return ERR_PTR(ret); - return iovec; -} - -static inline int io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct io_rw_state *s, - unsigned int issue_flags) -{ - *iovec = __io_import_iovec(rw, req, s, issue_flags); - if (unlikely(IS_ERR(*iovec))) - return PTR_ERR(*iovec); - - iov_iter_save_state(&s->iter, &s->iter_state); - return 0; -} - -static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb) -{ - return (kiocb->ki_filp->f_mode & FMODE_STREAM) ? NULL : &kiocb->ki_pos; -} - -/* - * For files that don't have ->read_iter() and ->write_iter(), handle them - * by looping over ->read() or ->write() manually. - */ -static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) -{ - struct kiocb *kiocb = &req->rw.kiocb; - struct file *file = req->file; - ssize_t ret = 0; - loff_t *ppos; - - /* - * Don't support polled IO through this interface, and we can't - * support non-blocking either. For the latter, this just causes - * the kiocb to be handled from an async context. - */ - if (kiocb->ki_flags & IOCB_HIPRI) - return -EOPNOTSUPP; - if ((kiocb->ki_flags & IOCB_NOWAIT) && - !(kiocb->ki_filp->f_flags & O_NONBLOCK)) - return -EAGAIN; - - ppos = io_kiocb_ppos(kiocb); - - while (iov_iter_count(iter)) { - struct iovec iovec; - ssize_t nr; - - if (!iov_iter_is_bvec(iter)) { - iovec = iov_iter_iovec(iter); - } else { - iovec.iov_base = u64_to_user_ptr(req->rw.addr); - iovec.iov_len = req->rw.len; - } - - if (rw == READ) { - nr = file->f_op->read(file, iovec.iov_base, - iovec.iov_len, ppos); - } else { - nr = file->f_op->write(file, iovec.iov_base, - iovec.iov_len, ppos); - } - - if (nr < 0) { - if (!ret) - ret = nr; - break; - } - ret += nr; - if (!iov_iter_is_bvec(iter)) { - iov_iter_advance(iter, nr); - } else { - req->rw.addr += nr; - req->rw.len -= nr; - if (!req->rw.len) - break; - } - if (nr != iovec.iov_len) - break; - } - - return ret; -} - -static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, - const struct iovec *fast_iov, struct iov_iter *iter) -{ - struct io_async_rw *rw = req->async_data; - - memcpy(&rw->s.iter, iter, sizeof(*iter)); - rw->free_iovec = iovec; - rw->bytes_done = 0; - /* can only be fixed buffers, no need to do anything */ - if (iov_iter_is_bvec(iter)) - return; - if (!iovec) { - unsigned iov_off = 0; - - rw->s.iter.iov = rw->s.fast_iov; - if (iter->iov != fast_iov) { - iov_off = iter->iov - fast_iov; - rw->s.iter.iov += iov_off; - } - if (rw->s.fast_iov != fast_iov) - memcpy(rw->s.fast_iov + iov_off, fast_iov + iov_off, - sizeof(struct iovec) * iter->nr_segs); - } else { - req->flags |= REQ_F_NEED_CLEANUP; - } -} - -static inline bool io_alloc_async_data(struct io_kiocb *req) -{ - WARN_ON_ONCE(!io_op_defs[req->opcode].async_size); - req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL); - if (req->async_data) { - req->flags |= REQ_F_ASYNC_DATA; - return false; - } - return true; -} - -static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, - struct io_rw_state *s, bool force) -{ - if (!force && !io_op_defs[req->opcode].needs_async_setup) - return 0; - if (!req_has_async_data(req)) { - struct io_async_rw *iorw; - - if (io_alloc_async_data(req)) { - kfree(iovec); - return -ENOMEM; - } - - io_req_map_rw(req, iovec, s->fast_iov, &s->iter); - iorw = req->async_data; - /* we've copied and mapped the iter, ensure state is saved */ - iov_iter_save_state(&iorw->s.iter, &iorw->s.iter_state); - } - return 0; -} - -static inline int io_rw_prep_async(struct io_kiocb *req, int rw) -{ - struct io_async_rw *iorw = req->async_data; - struct iovec *iov; - int ret; - - /* submission path, ->uring_lock should already be taken */ - ret = io_import_iovec(rw, req, &iov, &iorw->s, 0); - if (unlikely(ret < 0)) - return ret; - - iorw->bytes_done = 0; - iorw->free_iovec = iov; - if (iov) - req->flags |= REQ_F_NEED_CLEANUP; - return 0; -} - -static int io_readv_prep_async(struct io_kiocb *req) -{ - return io_rw_prep_async(req, READ); -} - -static int io_writev_prep_async(struct io_kiocb *req) -{ - return io_rw_prep_async(req, WRITE); -} - -/* - * This is our waitqueue callback handler, registered through __folio_lock_async() - * when we initially tried to do the IO with the iocb armed our waitqueue. - * This gets called when the page is unlocked, and we generally expect that to - * happen when the page IO is completed and the page is now uptodate. This will - * queue a task_work based retry of the operation, attempting to copy the data - * again. If the latter fails because the page was NOT uptodate, then we will - * do a thread based blocking retry of the operation. That's the unexpected - * slow path. - */ -static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, - int sync, void *arg) -{ - struct wait_page_queue *wpq; - struct io_kiocb *req = wait->private; - struct wait_page_key *key = arg; - - wpq = container_of(wait, struct wait_page_queue, wait); - - if (!wake_page_match(wpq, key)) - return 0; - - req->rw.kiocb.ki_flags &= ~IOCB_WAITQ; - list_del_init(&wait->entry); - io_req_task_queue(req); - return 1; -} - -/* - * This controls whether a given IO request should be armed for async page - * based retry. If we return false here, the request is handed to the async - * worker threads for retry. If we're doing buffered reads on a regular file, - * we prepare a private wait_page_queue entry and retry the operation. This - * will either succeed because the page is now uptodate and unlocked, or it - * will register a callback when the page is unlocked at IO completion. Through - * that callback, io_uring uses task_work to setup a retry of the operation. - * That retry will attempt the buffered read again. The retry will generally - * succeed, or in rare cases where it fails, we then fall back to using the - * async worker threads for a blocking retry. - */ -static bool io_rw_should_retry(struct io_kiocb *req) -{ - struct io_async_rw *rw = req->async_data; - struct wait_page_queue *wait = &rw->wpq; - struct kiocb *kiocb = &req->rw.kiocb; - - /* never retry for NOWAIT, we just complete with -EAGAIN */ - if (req->flags & REQ_F_NOWAIT) - return false; - - /* Only for buffered IO */ - if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI)) - return false; - - /* - * just use poll if we can, and don't attempt if the fs doesn't - * support callback based unlocks - */ - if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC)) - return false; - - wait->wait.func = io_async_buf_func; - wait->wait.private = req; - wait->wait.flags = 0; - INIT_LIST_HEAD(&wait->wait.entry); - kiocb->ki_flags |= IOCB_WAITQ; - kiocb->ki_flags &= ~IOCB_NOWAIT; - kiocb->ki_waitq = wait; - return true; -} - -static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) -{ - if (likely(req->file->f_op->read_iter)) - return call_read_iter(req->file, &req->rw.kiocb, iter); - else if (req->file->f_op->read) - return loop_rw_iter(READ, req, iter); - else - return -EINVAL; -} - -static bool need_read_all(struct io_kiocb *req) -{ - return req->flags & REQ_F_ISREG || - S_ISBLK(file_inode(req->file)->i_mode); -} - -static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) -{ - struct kiocb *kiocb = &req->rw.kiocb; - struct io_ring_ctx *ctx = req->ctx; - struct file *file = req->file; - int ret; - - if (unlikely(!file || !(file->f_mode & mode))) - return -EBADF; - - if (!io_req_ffs_set(req)) - req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; - - kiocb->ki_flags = iocb_flags(file); - ret = kiocb_set_rw_flags(kiocb, req->rw.flags); - if (unlikely(ret)) - return ret; - - /* - * If the file is marked O_NONBLOCK, still allow retry for it if it - * supports async. Otherwise it's impossible to use O_NONBLOCK files - * reliably. If not, or it IOCB_NOWAIT is set, don't retry. - */ - if ((kiocb->ki_flags & IOCB_NOWAIT) || - ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) - req->flags |= REQ_F_NOWAIT; - - if (ctx->flags & IORING_SETUP_IOPOLL) { - if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) - return -EOPNOTSUPP; - - kiocb->private = NULL; - kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; - kiocb->ki_complete = io_complete_rw_iopoll; - req->iopoll_completed = 0; - } else { - if (kiocb->ki_flags & IOCB_HIPRI) - return -EINVAL; - kiocb->ki_complete = io_complete_rw; - } - - return 0; -} - -static int io_read(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_rw_state __s, *s = &__s; - struct iovec *iovec; - struct kiocb *kiocb = &req->rw.kiocb; - bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - struct io_async_rw *rw; - ssize_t ret, ret2; - loff_t *ppos; - - if (!req_has_async_data(req)) { - ret = io_import_iovec(READ, req, &iovec, s, issue_flags); - if (unlikely(ret < 0)) - return ret; - } else { - rw = req->async_data; - s = &rw->s; - - /* - * Safe and required to re-import if we're using provided - * buffers, as we dropped the selected one before retry. - */ - if (io_do_buffer_select(req)) { - ret = io_import_iovec(READ, req, &iovec, s, issue_flags); - if (unlikely(ret < 0)) - return ret; - } - - /* - * We come here from an earlier attempt, restore our state to - * match in case it doesn't. It's cheap enough that we don't - * need to make this conditional. - */ - iov_iter_restore(&s->iter, &s->iter_state); - iovec = NULL; - } - ret = io_rw_init_file(req, FMODE_READ); - if (unlikely(ret)) { - kfree(iovec); - return ret; - } - req->cqe.res = iov_iter_count(&s->iter); - - if (force_nonblock) { - /* If the file doesn't support async, just async punt */ - if (unlikely(!io_file_supports_nowait(req))) { - ret = io_setup_async_rw(req, iovec, s, true); - return ret ?: -EAGAIN; - } - kiocb->ki_flags |= IOCB_NOWAIT; - } else { - /* Ensure we clear previously set non-block flag */ - kiocb->ki_flags &= ~IOCB_NOWAIT; - } - - ppos = io_kiocb_update_pos(req); - - ret = rw_verify_area(READ, req->file, ppos, req->cqe.res); - if (unlikely(ret)) { - kfree(iovec); - return ret; - } - - ret = io_iter_do_read(req, &s->iter); - - if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) { - req->flags &= ~REQ_F_REISSUE; - /* if we can poll, just do that */ - if (req->opcode == IORING_OP_READ && file_can_poll(req->file)) - return -EAGAIN; - /* IOPOLL retry should happen for io-wq threads */ - if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) - goto done; - /* no retry on NONBLOCK nor RWF_NOWAIT */ - if (req->flags & REQ_F_NOWAIT) - goto done; - ret = 0; - } else if (ret == -EIOCBQUEUED) { - goto out_free; - } else if (ret == req->cqe.res || ret <= 0 || !force_nonblock || - (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) { - /* read all, failed, already did sync or don't want to retry */ - goto done; - } - - /* - * Don't depend on the iter state matching what was consumed, or being - * untouched in case of error. Restore it and we'll advance it - * manually if we need to. - */ - iov_iter_restore(&s->iter, &s->iter_state); - - ret2 = io_setup_async_rw(req, iovec, s, true); - if (ret2) - return ret2; - - iovec = NULL; - rw = req->async_data; - s = &rw->s; - /* - * Now use our persistent iterator and state, if we aren't already. - * We've restored and mapped the iter to match. - */ - - do { - /* - * We end up here because of a partial read, either from - * above or inside this loop. Advance the iter by the bytes - * that were consumed. - */ - iov_iter_advance(&s->iter, ret); - if (!iov_iter_count(&s->iter)) - break; - rw->bytes_done += ret; - iov_iter_save_state(&s->iter, &s->iter_state); - - /* if we can retry, do so with the callbacks armed */ - if (!io_rw_should_retry(req)) { - kiocb->ki_flags &= ~IOCB_WAITQ; - return -EAGAIN; - } - - /* - * Now retry read with the IOCB_WAITQ parts set in the iocb. If - * we get -EIOCBQUEUED, then we'll get a notification when the - * desired page gets unlocked. We can also get a partial read - * here, and if we do, then just retry at the new offset. - */ - ret = io_iter_do_read(req, &s->iter); - if (ret == -EIOCBQUEUED) - return 0; - /* we got some bytes, but not all. retry. */ - kiocb->ki_flags &= ~IOCB_WAITQ; - iov_iter_restore(&s->iter, &s->iter_state); - } while (ret > 0); -done: - kiocb_done(req, ret, issue_flags); -out_free: - /* it's faster to check here then delegate to kfree */ - if (iovec) - kfree(iovec); - return 0; -} - -static int io_write(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_rw_state __s, *s = &__s; - struct iovec *iovec; - struct kiocb *kiocb = &req->rw.kiocb; - bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - ssize_t ret, ret2; - loff_t *ppos; - - if (!req_has_async_data(req)) { - ret = io_import_iovec(WRITE, req, &iovec, s, issue_flags); - if (unlikely(ret < 0)) - return ret; - } else { - struct io_async_rw *rw = req->async_data; - - s = &rw->s; - iov_iter_restore(&s->iter, &s->iter_state); - iovec = NULL; - } - ret = io_rw_init_file(req, FMODE_WRITE); - if (unlikely(ret)) { - kfree(iovec); - return ret; - } - req->cqe.res = iov_iter_count(&s->iter); - - if (force_nonblock) { - /* If the file doesn't support async, just async punt */ - if (unlikely(!io_file_supports_nowait(req))) - goto copy_iov; - - /* file path doesn't support NOWAIT for non-direct_IO */ - if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) && - (req->flags & REQ_F_ISREG)) - goto copy_iov; - - kiocb->ki_flags |= IOCB_NOWAIT; - } else { - /* Ensure we clear previously set non-block flag */ - kiocb->ki_flags &= ~IOCB_NOWAIT; - } - - ppos = io_kiocb_update_pos(req); - - ret = rw_verify_area(WRITE, req->file, ppos, req->cqe.res); - if (unlikely(ret)) - goto out_free; - - /* - * Open-code file_start_write here to grab freeze protection, - * which will be released by another thread in - * io_complete_rw(). Fool lockdep by telling it the lock got - * released so that it doesn't complain about the held lock when - * we return to userspace. - */ - if (req->flags & REQ_F_ISREG) { - sb_start_write(file_inode(req->file)->i_sb); - __sb_writers_release(file_inode(req->file)->i_sb, - SB_FREEZE_WRITE); - } - kiocb->ki_flags |= IOCB_WRITE; - - if (likely(req->file->f_op->write_iter)) - ret2 = call_write_iter(req->file, kiocb, &s->iter); - else if (req->file->f_op->write) - ret2 = loop_rw_iter(WRITE, req, &s->iter); - else - ret2 = -EINVAL; - - if (req->flags & REQ_F_REISSUE) { - req->flags &= ~REQ_F_REISSUE; - ret2 = -EAGAIN; - } - - /* - * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just - * retry them without IOCB_NOWAIT. - */ - if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT)) - ret2 = -EAGAIN; - /* no retry on NONBLOCK nor RWF_NOWAIT */ - if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT)) - goto done; - if (!force_nonblock || ret2 != -EAGAIN) { - /* IOPOLL retry should happen for io-wq threads */ - if (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL)) - goto copy_iov; -done: - kiocb_done(req, ret2, issue_flags); - } else { -copy_iov: - iov_iter_restore(&s->iter, &s->iter_state); - ret = io_setup_async_rw(req, iovec, s, false); - return ret ?: -EAGAIN; - } -out_free: - /* it's reportedly faster than delegating the null check to kfree() */ - if (iovec) - kfree(iovec); - return ret; -} - -static int io_renameat_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_rename *ren = &req->rename; - const char __user *oldf, *newf; - - if (sqe->buf_index || sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->flags & REQ_F_FIXED_FILE)) - return -EBADF; - - ren->old_dfd = READ_ONCE(sqe->fd); - oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); - newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); - ren->new_dfd = READ_ONCE(sqe->len); - ren->flags = READ_ONCE(sqe->rename_flags); - - ren->oldpath = getname(oldf); - if (IS_ERR(ren->oldpath)) - return PTR_ERR(ren->oldpath); - - ren->newpath = getname(newf); - if (IS_ERR(ren->newpath)) { - putname(ren->oldpath); - return PTR_ERR(ren->newpath); - } - - req->flags |= REQ_F_NEED_CLEANUP; - return 0; -} - -static int io_renameat(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_rename *ren = &req->rename; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd, - ren->newpath, ren->flags); - - req->flags &= ~REQ_F_NEED_CLEANUP; - io_req_complete(req, ret); - return 0; -} - -static inline void __io_xattr_finish(struct io_kiocb *req) -{ - struct io_xattr *ix = &req->xattr; - - if (ix->filename) - putname(ix->filename); - - kfree(ix->ctx.kname); - kvfree(ix->ctx.kvalue); -} - -static void io_xattr_finish(struct io_kiocb *req, int ret) -{ - req->flags &= ~REQ_F_NEED_CLEANUP; - - __io_xattr_finish(req); - io_req_complete(req, ret); -} - -static int __io_getxattr_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_xattr *ix = &req->xattr; - const char __user *name; - int ret; - - if (unlikely(req->flags & REQ_F_FIXED_FILE)) - return -EBADF; - - ix->filename = NULL; - ix->ctx.kvalue = NULL; - name = u64_to_user_ptr(READ_ONCE(sqe->addr)); - ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2)); - ix->ctx.size = READ_ONCE(sqe->len); - ix->ctx.flags = READ_ONCE(sqe->xattr_flags); - - if (ix->ctx.flags) - return -EINVAL; - - ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL); - if (!ix->ctx.kname) - return -ENOMEM; - - ret = strncpy_from_user(ix->ctx.kname->name, name, - sizeof(ix->ctx.kname->name)); - if (!ret || ret == sizeof(ix->ctx.kname->name)) - ret = -ERANGE; - if (ret < 0) { - kfree(ix->ctx.kname); - return ret; - } - - req->flags |= REQ_F_NEED_CLEANUP; - return 0; -} - -static int io_fgetxattr_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - return __io_getxattr_prep(req, sqe); -} - -static int io_getxattr_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_xattr *ix = &req->xattr; - const char __user *path; - int ret; - - ret = __io_getxattr_prep(req, sqe); - if (ret) - return ret; - - path = u64_to_user_ptr(READ_ONCE(sqe->addr3)); - - ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL); - if (IS_ERR(ix->filename)) { - ret = PTR_ERR(ix->filename); - ix->filename = NULL; - } - - return ret; -} - -static int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_xattr *ix = &req->xattr; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - ret = do_getxattr(mnt_user_ns(req->file->f_path.mnt), - req->file->f_path.dentry, - &ix->ctx); - - io_xattr_finish(req, ret); - return 0; -} - -static int io_getxattr(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_xattr *ix = &req->xattr; - unsigned int lookup_flags = LOOKUP_FOLLOW; - struct path path; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - -retry: - ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL); - if (!ret) { - ret = do_getxattr(mnt_user_ns(path.mnt), - path.dentry, - &ix->ctx); - - path_put(&path); - if (retry_estale(ret, lookup_flags)) { - lookup_flags |= LOOKUP_REVAL; - goto retry; - } - } - - io_xattr_finish(req, ret); - return 0; -} - -static int __io_setxattr_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_xattr *ix = &req->xattr; - const char __user *name; - int ret; - - if (unlikely(req->flags & REQ_F_FIXED_FILE)) - return -EBADF; - - ix->filename = NULL; - name = u64_to_user_ptr(READ_ONCE(sqe->addr)); - ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2)); - ix->ctx.kvalue = NULL; - ix->ctx.size = READ_ONCE(sqe->len); - ix->ctx.flags = READ_ONCE(sqe->xattr_flags); - - ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL); - if (!ix->ctx.kname) - return -ENOMEM; - - ret = setxattr_copy(name, &ix->ctx); - if (ret) { - kfree(ix->ctx.kname); - return ret; - } - - req->flags |= REQ_F_NEED_CLEANUP; - return 0; -} - -static int io_setxattr_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_xattr *ix = &req->xattr; - const char __user *path; - int ret; - - ret = __io_setxattr_prep(req, sqe); - if (ret) - return ret; - - path = u64_to_user_ptr(READ_ONCE(sqe->addr3)); - - ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL); - if (IS_ERR(ix->filename)) { - ret = PTR_ERR(ix->filename); - ix->filename = NULL; - } - - return ret; -} - -static int io_fsetxattr_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - return __io_setxattr_prep(req, sqe); -} - -static int __io_setxattr(struct io_kiocb *req, unsigned int issue_flags, - struct path *path) -{ - struct io_xattr *ix = &req->xattr; - int ret; - - ret = mnt_want_write(path->mnt); - if (!ret) { - ret = do_setxattr(mnt_user_ns(path->mnt), path->dentry, &ix->ctx); - mnt_drop_write(path->mnt); - } - - return ret; -} - -static int io_fsetxattr(struct io_kiocb *req, unsigned int issue_flags) -{ - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - ret = __io_setxattr(req, issue_flags, &req->file->f_path); - io_xattr_finish(req, ret); - - return 0; -} - -static int io_setxattr(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_xattr *ix = &req->xattr; - unsigned int lookup_flags = LOOKUP_FOLLOW; - struct path path; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - -retry: - ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL); - if (!ret) { - ret = __io_setxattr(req, issue_flags, &path); - path_put(&path); - if (retry_estale(ret, lookup_flags)) { - lookup_flags |= LOOKUP_REVAL; - goto retry; - } - } - - io_xattr_finish(req, ret); - return 0; -} - -static int io_unlinkat_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_unlink *un = &req->unlink; - const char __user *fname; - - if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->flags & REQ_F_FIXED_FILE)) - return -EBADF; - - un->dfd = READ_ONCE(sqe->fd); - - un->flags = READ_ONCE(sqe->unlink_flags); - if (un->flags & ~AT_REMOVEDIR) - return -EINVAL; - - fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); - un->filename = getname(fname); - if (IS_ERR(un->filename)) - return PTR_ERR(un->filename); - - req->flags |= REQ_F_NEED_CLEANUP; - return 0; -} - -static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_unlink *un = &req->unlink; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - if (un->flags & AT_REMOVEDIR) - ret = do_rmdir(un->dfd, un->filename); - else - ret = do_unlinkat(un->dfd, un->filename); - - req->flags &= ~REQ_F_NEED_CLEANUP; - io_req_complete(req, ret); - return 0; -} - -static int io_mkdirat_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_mkdir *mkd = &req->mkdir; - const char __user *fname; - - if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->flags & REQ_F_FIXED_FILE)) - return -EBADF; - - mkd->dfd = READ_ONCE(sqe->fd); - mkd->mode = READ_ONCE(sqe->len); - - fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); - mkd->filename = getname(fname); - if (IS_ERR(mkd->filename)) - return PTR_ERR(mkd->filename); - - req->flags |= REQ_F_NEED_CLEANUP; - return 0; -} - -static int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_mkdir *mkd = &req->mkdir; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode); - - req->flags &= ~REQ_F_NEED_CLEANUP; - io_req_complete(req, ret); - return 0; -} - -static int io_symlinkat_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_symlink *sl = &req->symlink; - const char __user *oldpath, *newpath; - - if (sqe->len || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->flags & REQ_F_FIXED_FILE)) - return -EBADF; - - sl->new_dfd = READ_ONCE(sqe->fd); - oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr)); - newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2)); - - sl->oldpath = getname(oldpath); - if (IS_ERR(sl->oldpath)) - return PTR_ERR(sl->oldpath); - - sl->newpath = getname(newpath); - if (IS_ERR(sl->newpath)) { - putname(sl->oldpath); - return PTR_ERR(sl->newpath); - } - - req->flags |= REQ_F_NEED_CLEANUP; - return 0; -} - -static int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_symlink *sl = &req->symlink; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath); - - req->flags &= ~REQ_F_NEED_CLEANUP; - io_req_complete(req, ret); - return 0; -} - -static int io_linkat_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_hardlink *lnk = &req->hardlink; - const char __user *oldf, *newf; - - if (sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->flags & REQ_F_FIXED_FILE)) - return -EBADF; - - lnk->old_dfd = READ_ONCE(sqe->fd); - lnk->new_dfd = READ_ONCE(sqe->len); - oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); - newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); - lnk->flags = READ_ONCE(sqe->hardlink_flags); - - lnk->oldpath = getname(oldf); - if (IS_ERR(lnk->oldpath)) - return PTR_ERR(lnk->oldpath); - - lnk->newpath = getname(newf); - if (IS_ERR(lnk->newpath)) { - putname(lnk->oldpath); - return PTR_ERR(lnk->newpath); - } - - req->flags |= REQ_F_NEED_CLEANUP; - return 0; -} - -static int io_linkat(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_hardlink *lnk = &req->hardlink; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - ret = do_linkat(lnk->old_dfd, lnk->oldpath, lnk->new_dfd, - lnk->newpath, lnk->flags); - - req->flags &= ~REQ_F_NEED_CLEANUP; - io_req_complete(req, ret); - return 0; -} - -static void io_uring_cmd_work(struct io_kiocb *req, bool *locked) -{ - req->uring_cmd.task_work_cb(&req->uring_cmd); -} - -void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *)) -{ - struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd); - - req->uring_cmd.task_work_cb = task_work_cb; - req->io_task_work.func = io_uring_cmd_work; - io_req_task_work_add(req); -} -EXPORT_SYMBOL_GPL(io_uring_cmd_complete_in_task); - -static inline void io_req_set_cqe32_extra(struct io_kiocb *req, - u64 extra1, u64 extra2) -{ - req->extra1 = extra1; - req->extra2 = extra2; - req->flags |= REQ_F_CQE32_INIT; -} - -/* - * Called by consumers of io_uring_cmd, if they originally returned - * -EIOCBQUEUED upon receiving the command. - */ -void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2) -{ - struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd); - - if (ret < 0) - req_set_fail(req); - - if (req->ctx->flags & IORING_SETUP_CQE32) - io_req_set_cqe32_extra(req, res2, 0); - io_req_complete(req, ret); -} -EXPORT_SYMBOL_GPL(io_uring_cmd_done); - -static int io_uring_cmd_prep_async(struct io_kiocb *req) -{ - size_t cmd_size; - - cmd_size = uring_cmd_pdu_size(req->ctx->flags & IORING_SETUP_SQE128); - - memcpy(req->async_data, req->uring_cmd.cmd, cmd_size); - return 0; -} - -static int io_uring_cmd_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_uring_cmd *ioucmd = &req->uring_cmd; - - if (sqe->rw_flags || sqe->__pad1) - return -EINVAL; - ioucmd->cmd = sqe->cmd; - ioucmd->cmd_op = READ_ONCE(sqe->cmd_op); - return 0; -} - -static int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_uring_cmd *ioucmd = &req->uring_cmd; - struct io_ring_ctx *ctx = req->ctx; - struct file *file = req->file; - int ret; - - if (!req->file->f_op->uring_cmd) - return -EOPNOTSUPP; - - if (ctx->flags & IORING_SETUP_SQE128) - issue_flags |= IO_URING_F_SQE128; - if (ctx->flags & IORING_SETUP_CQE32) - issue_flags |= IO_URING_F_CQE32; - if (ctx->flags & IORING_SETUP_IOPOLL) - issue_flags |= IO_URING_F_IOPOLL; - - if (req_has_async_data(req)) - ioucmd->cmd = req->async_data; - - ret = file->f_op->uring_cmd(ioucmd, issue_flags); - if (ret == -EAGAIN) { - if (!req_has_async_data(req)) { - if (io_alloc_async_data(req)) - return -ENOMEM; - io_uring_cmd_prep_async(req); - } - return -EAGAIN; - } - - if (ret != -EIOCBQUEUED) - io_uring_cmd_done(ioucmd, ret, 0); - return 0; -} - -static int __io_splice_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_splice *sp = &req->splice; - unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL; - - sp->len = READ_ONCE(sqe->len); - sp->flags = READ_ONCE(sqe->splice_flags); - if (unlikely(sp->flags & ~valid_flags)) - return -EINVAL; - sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); - return 0; -} - -static int io_tee_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - if (READ_ONCE(sqe->splice_off_in) || READ_ONCE(sqe->off)) - return -EINVAL; - return __io_splice_prep(req, sqe); -} - -static int io_tee(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_splice *sp = &req->splice; - struct file *out = sp->file_out; - unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; - struct file *in; - long ret = 0; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - if (sp->flags & SPLICE_F_FD_IN_FIXED) - in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); - else - in = io_file_get_normal(req, sp->splice_fd_in); - if (!in) { - ret = -EBADF; - goto done; - } - - if (sp->len) - ret = do_tee(in, out, sp->len, flags); - - if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) - io_put_file(in); -done: - if (ret != sp->len) - req_set_fail(req); - __io_req_complete(req, 0, ret, 0); - return 0; -} - -static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - struct io_splice *sp = &req->splice; - - sp->off_in = READ_ONCE(sqe->splice_off_in); - sp->off_out = READ_ONCE(sqe->off); - return __io_splice_prep(req, sqe); -} - -static int io_splice(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_splice *sp = &req->splice; - struct file *out = sp->file_out; - unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; - loff_t *poff_in, *poff_out; - struct file *in; - long ret = 0; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - if (sp->flags & SPLICE_F_FD_IN_FIXED) - in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); - else - in = io_file_get_normal(req, sp->splice_fd_in); - if (!in) { - ret = -EBADF; - goto done; - } - - poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; - poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; - - if (sp->len) - ret = do_splice(in, poff_in, out, poff_out, sp->len, flags); - - if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) - io_put_file(in); -done: - if (ret != sp->len) - req_set_fail(req); - __io_req_complete(req, 0, ret, 0); - return 0; -} - -static int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - return 0; -} - -/* - * IORING_OP_NOP just posts a completion event, nothing else. - */ -static int io_nop(struct io_kiocb *req, unsigned int issue_flags) -{ - __io_req_complete(req, issue_flags, 0, 0); - return 0; -} - -static int io_msg_ring_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - if (unlikely(sqe->addr || sqe->rw_flags || sqe->splice_fd_in || - sqe->buf_index || sqe->personality)) - return -EINVAL; - - req->msg.user_data = READ_ONCE(sqe->off); - req->msg.len = READ_ONCE(sqe->len); - return 0; -} - -static int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_ring_ctx *target_ctx; - struct io_msg *msg = &req->msg; - bool filled; - int ret; - - ret = -EBADFD; - if (req->file->f_op != &io_uring_fops) - goto done; - - ret = -EOVERFLOW; - target_ctx = req->file->private_data; - - spin_lock(&target_ctx->completion_lock); - filled = io_fill_cqe_aux(target_ctx, msg->user_data, msg->len, 0); - io_commit_cqring(target_ctx); - spin_unlock(&target_ctx->completion_lock); - - if (filled) { - io_cqring_ev_posted(target_ctx); - ret = 0; - } - -done: - if (ret < 0) - req_set_fail(req); - __io_req_complete(req, issue_flags, ret, 0); - /* put file to avoid an attempt to IOPOLL the req */ - io_put_file(req->file); - req->file = NULL; - return 0; -} - -static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in)) - return -EINVAL; - - req->sync.flags = READ_ONCE(sqe->fsync_flags); - if (unlikely(req->sync.flags & ~IORING_FSYNC_DATASYNC)) - return -EINVAL; - - req->sync.off = READ_ONCE(sqe->off); - req->sync.len = READ_ONCE(sqe->len); - return 0; -} - -static int io_fsync(struct io_kiocb *req, unsigned int issue_flags) -{ - loff_t end = req->sync.off + req->sync.len; - int ret; - - /* fsync always requires a blocking context */ - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - ret = vfs_fsync_range(req->file, req->sync.off, - end > 0 ? end : LLONG_MAX, - req->sync.flags & IORING_FSYNC_DATASYNC); - io_req_complete(req, ret); - return 0; -} - -static int io_fallocate_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - if (sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) - return -EINVAL; - - req->sync.off = READ_ONCE(sqe->off); - req->sync.len = READ_ONCE(sqe->addr); - req->sync.mode = READ_ONCE(sqe->len); - return 0; -} - -static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) -{ - int ret; - - /* fallocate always requiring blocking context */ - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, - req->sync.len); - if (ret >= 0) - fsnotify_modify(req->file); - io_req_complete(req, ret); - return 0; -} - -static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - const char __user *fname; - int ret; - - if (unlikely(sqe->buf_index)) - return -EINVAL; - if (unlikely(req->flags & REQ_F_FIXED_FILE)) - return -EBADF; - - /* open.how should be already initialised */ - if (!(req->open.how.flags & O_PATH) && force_o_largefile()) - req->open.how.flags |= O_LARGEFILE; - - req->open.dfd = READ_ONCE(sqe->fd); - fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); - req->open.filename = getname(fname); - if (IS_ERR(req->open.filename)) { - ret = PTR_ERR(req->open.filename); - req->open.filename = NULL; - return ret; - } - - req->open.file_slot = READ_ONCE(sqe->file_index); - if (req->open.file_slot && (req->open.how.flags & O_CLOEXEC)) - return -EINVAL; - - req->open.nofile = rlimit(RLIMIT_NOFILE); - req->flags |= REQ_F_NEED_CLEANUP; - return 0; -} - -static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - u64 mode = READ_ONCE(sqe->len); - u64 flags = READ_ONCE(sqe->open_flags); - - req->open.how = build_open_how(flags, mode); - return __io_openat_prep(req, sqe); -} - -static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - struct open_how __user *how; - size_t len; - int ret; - - how = u64_to_user_ptr(READ_ONCE(sqe->addr2)); - len = READ_ONCE(sqe->len); - if (len < OPEN_HOW_SIZE_VER0) - return -EINVAL; - - ret = copy_struct_from_user(&req->open.how, sizeof(req->open.how), how, - len); - if (ret) - return ret; - - return __io_openat_prep(req, sqe); -} - -static int io_file_bitmap_get(struct io_ring_ctx *ctx) -{ - struct io_file_table *table = &ctx->file_table; - unsigned long nr = ctx->nr_user_files; - int ret; - - do { - ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint); - if (ret != nr) - return ret; - - if (!table->alloc_hint) - break; - - nr = table->alloc_hint; - table->alloc_hint = 0; - } while (1); - - return -ENFILE; -} - -/* - * Note when io_fixed_fd_install() returns error value, it will ensure - * fput() is called correspondingly. - */ -static int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags, - struct file *file, unsigned int file_slot) -{ - bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC; - struct io_ring_ctx *ctx = req->ctx; - int ret; - - io_ring_submit_lock(ctx, issue_flags); - - if (alloc_slot) { - ret = io_file_bitmap_get(ctx); - if (unlikely(ret < 0)) - goto err; - file_slot = ret; - } else { - file_slot--; - } - - ret = io_install_fixed_file(req, file, issue_flags, file_slot); - if (!ret && alloc_slot) - ret = file_slot; -err: - io_ring_submit_unlock(ctx, issue_flags); - if (unlikely(ret < 0)) - fput(file); - return ret; -} - -static int io_openat2(struct io_kiocb *req, unsigned int issue_flags) -{ - struct open_flags op; - struct file *file; - bool resolve_nonblock, nonblock_set; - bool fixed = !!req->open.file_slot; - int ret; - - ret = build_open_flags(&req->open.how, &op); - if (ret) - goto err; - nonblock_set = op.open_flag & O_NONBLOCK; - resolve_nonblock = req->open.how.resolve & RESOLVE_CACHED; - if (issue_flags & IO_URING_F_NONBLOCK) { - /* - * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open, - * it'll always -EAGAIN - */ - if (req->open.how.flags & (O_TRUNC | O_CREAT | O_TMPFILE)) - return -EAGAIN; - op.lookup_flags |= LOOKUP_CACHED; - op.open_flag |= O_NONBLOCK; - } - - if (!fixed) { - ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile); - if (ret < 0) - goto err; - } - - file = do_filp_open(req->open.dfd, req->open.filename, &op); - if (IS_ERR(file)) { - /* - * We could hang on to this 'fd' on retrying, but seems like - * marginal gain for something that is now known to be a slower - * path. So just put it, and we'll get a new one when we retry. - */ - if (!fixed) - put_unused_fd(ret); - - ret = PTR_ERR(file); - /* only retry if RESOLVE_CACHED wasn't already set by application */ - if (ret == -EAGAIN && - (!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK))) - return -EAGAIN; - goto err; - } - - if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set) - file->f_flags &= ~O_NONBLOCK; - fsnotify_open(file); - - if (!fixed) - fd_install(ret, file); - else - ret = io_fixed_fd_install(req, issue_flags, file, - req->open.file_slot); -err: - putname(req->open.filename); - req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < 0) - req_set_fail(req); - __io_req_complete(req, issue_flags, ret, 0); - return 0; -} - -static int io_openat(struct io_kiocb *req, unsigned int issue_flags) -{ - return io_openat2(req, issue_flags); -} - -static int io_remove_buffers_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_provide_buf *p = &req->pbuf; - u64 tmp; - - if (sqe->rw_flags || sqe->addr || sqe->len || sqe->off || - sqe->splice_fd_in) - return -EINVAL; - - tmp = READ_ONCE(sqe->fd); - if (!tmp || tmp > USHRT_MAX) - return -EINVAL; - - memset(p, 0, sizeof(*p)); - p->nbufs = tmp; - p->bgid = READ_ONCE(sqe->buf_group); - return 0; -} - -static int __io_remove_buffers(struct io_ring_ctx *ctx, - struct io_buffer_list *bl, unsigned nbufs) -{ - unsigned i = 0; - - /* shouldn't happen */ - if (!nbufs) - return 0; - - if (bl->buf_nr_pages) { - int j; - - i = bl->buf_ring->tail - bl->head; - for (j = 0; j < bl->buf_nr_pages; j++) - unpin_user_page(bl->buf_pages[j]); - kvfree(bl->buf_pages); - bl->buf_pages = NULL; - bl->buf_nr_pages = 0; - /* make sure it's seen as empty */ - INIT_LIST_HEAD(&bl->buf_list); - return i; - } - - /* the head kbuf is the list itself */ - while (!list_empty(&bl->buf_list)) { - struct io_buffer *nxt; - - nxt = list_first_entry(&bl->buf_list, struct io_buffer, list); - list_del(&nxt->list); - if (++i == nbufs) - return i; - cond_resched(); - } - i++; - - return i; -} - -static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_provide_buf *p = &req->pbuf; - struct io_ring_ctx *ctx = req->ctx; - struct io_buffer_list *bl; - int ret = 0; - - io_ring_submit_lock(ctx, issue_flags); - - ret = -ENOENT; - bl = io_buffer_get_list(ctx, p->bgid); - if (bl) { - ret = -EINVAL; - /* can't use provide/remove buffers command on mapped buffers */ - if (!bl->buf_nr_pages) - ret = __io_remove_buffers(ctx, bl, p->nbufs); - } - if (ret < 0) - req_set_fail(req); - - /* complete before unlock, IOPOLL may need the lock */ - __io_req_complete(req, issue_flags, ret, 0); - io_ring_submit_unlock(ctx, issue_flags); - return 0; -} - -static int io_provide_buffers_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - unsigned long size, tmp_check; - struct io_provide_buf *p = &req->pbuf; - u64 tmp; - - if (sqe->rw_flags || sqe->splice_fd_in) - return -EINVAL; - - tmp = READ_ONCE(sqe->fd); - if (!tmp || tmp > USHRT_MAX) - return -E2BIG; - p->nbufs = tmp; - p->addr = READ_ONCE(sqe->addr); - p->len = READ_ONCE(sqe->len); - - if (check_mul_overflow((unsigned long)p->len, (unsigned long)p->nbufs, - &size)) - return -EOVERFLOW; - if (check_add_overflow((unsigned long)p->addr, size, &tmp_check)) - return -EOVERFLOW; - - size = (unsigned long)p->len * p->nbufs; - if (!access_ok(u64_to_user_ptr(p->addr), size)) - return -EFAULT; - - p->bgid = READ_ONCE(sqe->buf_group); - tmp = READ_ONCE(sqe->off); - if (tmp > USHRT_MAX) - return -E2BIG; - p->bid = tmp; - return 0; -} - -static int io_refill_buffer_cache(struct io_ring_ctx *ctx) -{ - struct io_buffer *buf; - struct page *page; - int bufs_in_page; - - /* - * Completions that don't happen inline (eg not under uring_lock) will - * add to ->io_buffers_comp. If we don't have any free buffers, check - * the completion list and splice those entries first. - */ - if (!list_empty_careful(&ctx->io_buffers_comp)) { - spin_lock(&ctx->completion_lock); - if (!list_empty(&ctx->io_buffers_comp)) { - list_splice_init(&ctx->io_buffers_comp, - &ctx->io_buffers_cache); - spin_unlock(&ctx->completion_lock); - return 0; - } - spin_unlock(&ctx->completion_lock); - } - - /* - * No free buffers and no completion entries either. Allocate a new - * page worth of buffer entries and add those to our freelist. - */ - page = alloc_page(GFP_KERNEL_ACCOUNT); - if (!page) - return -ENOMEM; - - list_add(&page->lru, &ctx->io_buffers_pages); - - buf = page_address(page); - bufs_in_page = PAGE_SIZE / sizeof(*buf); - while (bufs_in_page) { - list_add_tail(&buf->list, &ctx->io_buffers_cache); - buf++; - bufs_in_page--; - } - - return 0; -} - -static int io_add_buffers(struct io_ring_ctx *ctx, struct io_provide_buf *pbuf, - struct io_buffer_list *bl) -{ - struct io_buffer *buf; - u64 addr = pbuf->addr; - int i, bid = pbuf->bid; - - for (i = 0; i < pbuf->nbufs; i++) { - if (list_empty(&ctx->io_buffers_cache) && - io_refill_buffer_cache(ctx)) - break; - buf = list_first_entry(&ctx->io_buffers_cache, struct io_buffer, - list); - list_move_tail(&buf->list, &bl->buf_list); - buf->addr = addr; - buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT); - buf->bid = bid; - buf->bgid = pbuf->bgid; - addr += pbuf->len; - bid++; - cond_resched(); - } - - return i ? 0 : -ENOMEM; -} - -static __cold int io_init_bl_list(struct io_ring_ctx *ctx) -{ - int i; - - ctx->io_bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), - GFP_KERNEL); - if (!ctx->io_bl) - return -ENOMEM; - - for (i = 0; i < BGID_ARRAY; i++) { - INIT_LIST_HEAD(&ctx->io_bl[i].buf_list); - ctx->io_bl[i].bgid = i; - } - - return 0; -} - -static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_provide_buf *p = &req->pbuf; - struct io_ring_ctx *ctx = req->ctx; - struct io_buffer_list *bl; - int ret = 0; - - io_ring_submit_lock(ctx, issue_flags); - - if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) { - ret = io_init_bl_list(ctx); - if (ret) - goto err; - } - - bl = io_buffer_get_list(ctx, p->bgid); - if (unlikely(!bl)) { - bl = kzalloc(sizeof(*bl), GFP_KERNEL); - if (!bl) { - ret = -ENOMEM; - goto err; - } - INIT_LIST_HEAD(&bl->buf_list); - ret = io_buffer_add_list(ctx, bl, p->bgid); - if (ret) { - kfree(bl); - goto err; - } - } - /* can't add buffers via this command for a mapped buffer ring */ - if (bl->buf_nr_pages) { - ret = -EINVAL; - goto err; - } - - ret = io_add_buffers(ctx, p, bl); -err: - if (ret < 0) - req_set_fail(req); - /* complete before unlock, IOPOLL may need the lock */ - __io_req_complete(req, issue_flags, ret, 0); - io_ring_submit_unlock(ctx, issue_flags); - return 0; -} - -static int io_epoll_ctl_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ -#if defined(CONFIG_EPOLL) - if (sqe->buf_index || sqe->splice_fd_in) - return -EINVAL; - - req->epoll.epfd = READ_ONCE(sqe->fd); - req->epoll.op = READ_ONCE(sqe->len); - req->epoll.fd = READ_ONCE(sqe->off); - - if (ep_op_has_event(req->epoll.op)) { - struct epoll_event __user *ev; - - ev = u64_to_user_ptr(READ_ONCE(sqe->addr)); - if (copy_from_user(&req->epoll.event, ev, sizeof(*ev))) - return -EFAULT; - } - - return 0; -#else - return -EOPNOTSUPP; -#endif -} - -static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags) -{ -#if defined(CONFIG_EPOLL) - struct io_epoll *ie = &req->epoll; - int ret; - bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - - ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock); - if (force_nonblock && ret == -EAGAIN) - return -EAGAIN; - - if (ret < 0) - req_set_fail(req); - __io_req_complete(req, issue_flags, ret, 0); - return 0; -#else - return -EOPNOTSUPP; -#endif -} - -static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ -#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) - if (sqe->buf_index || sqe->off || sqe->splice_fd_in) - return -EINVAL; - - req->madvise.addr = READ_ONCE(sqe->addr); - req->madvise.len = READ_ONCE(sqe->len); - req->madvise.advice = READ_ONCE(sqe->fadvise_advice); - return 0; -#else - return -EOPNOTSUPP; -#endif -} - -static int io_madvise(struct io_kiocb *req, unsigned int issue_flags) -{ -#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) - struct io_madvise *ma = &req->madvise; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice); - io_req_complete(req, ret); - return 0; -#else - return -EOPNOTSUPP; -#endif -} - -static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (sqe->buf_index || sqe->addr || sqe->splice_fd_in) - return -EINVAL; - - req->fadvise.offset = READ_ONCE(sqe->off); - req->fadvise.len = READ_ONCE(sqe->len); - req->fadvise.advice = READ_ONCE(sqe->fadvise_advice); - return 0; -} - -static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_fadvise *fa = &req->fadvise; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) { - switch (fa->advice) { - case POSIX_FADV_NORMAL: - case POSIX_FADV_RANDOM: - case POSIX_FADV_SEQUENTIAL: - break; - default: - return -EAGAIN; - } - } - - ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice); - if (ret < 0) - req_set_fail(req); - __io_req_complete(req, issue_flags, ret, 0); - return 0; -} - -static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - const char __user *path; - - if (sqe->buf_index || sqe->splice_fd_in) - return -EINVAL; - if (req->flags & REQ_F_FIXED_FILE) - return -EBADF; - - req->statx.dfd = READ_ONCE(sqe->fd); - req->statx.mask = READ_ONCE(sqe->len); - path = u64_to_user_ptr(READ_ONCE(sqe->addr)); - req->statx.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2)); - req->statx.flags = READ_ONCE(sqe->statx_flags); - - req->statx.filename = getname_flags(path, - getname_statx_lookup_flags(req->statx.flags), - NULL); - - if (IS_ERR(req->statx.filename)) { - int ret = PTR_ERR(req->statx.filename); - - req->statx.filename = NULL; - return ret; - } - - req->flags |= REQ_F_NEED_CLEANUP; - return 0; -} - -static int io_statx(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_statx *ctx = &req->statx; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask, - ctx->buffer); - io_req_complete(req, ret); - return 0; -} - -static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (sqe->off || sqe->addr || sqe->len || sqe->rw_flags || sqe->buf_index) - return -EINVAL; - if (req->flags & REQ_F_FIXED_FILE) - return -EBADF; - - req->close.fd = READ_ONCE(sqe->fd); - req->close.file_slot = READ_ONCE(sqe->file_index); - if (req->close.file_slot && req->close.fd) - return -EINVAL; - - return 0; -} - -static int io_close(struct io_kiocb *req, unsigned int issue_flags) -{ - struct files_struct *files = current->files; - struct io_close *close = &req->close; - struct fdtable *fdt; - struct file *file; - int ret = -EBADF; - - if (req->close.file_slot) { - ret = io_close_fixed(req, issue_flags); - goto err; - } - - spin_lock(&files->file_lock); - fdt = files_fdtable(files); - if (close->fd >= fdt->max_fds) { - spin_unlock(&files->file_lock); - goto err; - } - file = rcu_dereference_protected(fdt->fd[close->fd], - lockdep_is_held(&files->file_lock)); - if (!file || file->f_op == &io_uring_fops) { - spin_unlock(&files->file_lock); - goto err; - } - - /* if the file has a flush method, be safe and punt to async */ - if (file->f_op->flush && (issue_flags & IO_URING_F_NONBLOCK)) { - spin_unlock(&files->file_lock); - return -EAGAIN; - } - - file = __close_fd_get_file(close->fd); - spin_unlock(&files->file_lock); - if (!file) - goto err; - - /* No ->flush() or already async, safely close from here */ - ret = filp_close(file, current->files); -err: - if (ret < 0) - req_set_fail(req); - __io_req_complete(req, issue_flags, ret, 0); - return 0; -} - -static int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in)) - return -EINVAL; - - req->sync.off = READ_ONCE(sqe->off); - req->sync.len = READ_ONCE(sqe->len); - req->sync.flags = READ_ONCE(sqe->sync_range_flags); - return 0; -} - -static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) -{ - int ret; - - /* sync_file_range always requires a blocking context */ - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - ret = sync_file_range(req->file, req->sync.off, req->sync.len, - req->sync.flags); - io_req_complete(req, ret); - return 0; -} - -#if defined(CONFIG_NET) -static int io_shutdown_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - if (unlikely(sqe->off || sqe->addr || sqe->rw_flags || - sqe->buf_index || sqe->splice_fd_in)) - return -EINVAL; - - req->shutdown.how = READ_ONCE(sqe->len); - return 0; -} - -static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags) -{ - struct socket *sock; - int ret; - - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - - sock = sock_from_file(req->file); - if (unlikely(!sock)) - return -ENOTSOCK; - - ret = __sys_shutdown_sock(sock, req->shutdown.how); - io_req_complete(req, ret); - return 0; -} - -static bool io_net_retry(struct socket *sock, int flags) -{ - if (!(flags & MSG_WAITALL)) - return false; - return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; -} - -static int io_setup_async_msg(struct io_kiocb *req, - struct io_async_msghdr *kmsg) -{ - struct io_async_msghdr *async_msg = req->async_data; - - if (async_msg) - return -EAGAIN; - if (io_alloc_async_data(req)) { - kfree(kmsg->free_iov); - return -ENOMEM; - } - async_msg = req->async_data; - req->flags |= REQ_F_NEED_CLEANUP; - memcpy(async_msg, kmsg, sizeof(*kmsg)); - async_msg->msg.msg_name = &async_msg->addr; - /* if were using fast_iov, set it to the new one */ - if (!async_msg->free_iov) - async_msg->msg.msg_iter.iov = async_msg->fast_iov; - - return -EAGAIN; -} - -static int io_sendmsg_copy_hdr(struct io_kiocb *req, - struct io_async_msghdr *iomsg) -{ - iomsg->msg.msg_name = &iomsg->addr; - iomsg->free_iov = iomsg->fast_iov; - return sendmsg_copy_msghdr(&iomsg->msg, req->sr_msg.umsg, - req->sr_msg.msg_flags, &iomsg->free_iov); -} - -static int io_sendmsg_prep_async(struct io_kiocb *req) -{ - int ret; - - ret = io_sendmsg_copy_hdr(req, req->async_data); - if (!ret) - req->flags |= REQ_F_NEED_CLEANUP; - return ret; -} - -static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - struct io_sr_msg *sr = &req->sr_msg; - - if (unlikely(sqe->file_index || sqe->addr2)) - return -EINVAL; - - sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); - sr->len = READ_ONCE(sqe->len); - sr->flags = READ_ONCE(sqe->ioprio); - if (sr->flags & ~IORING_RECVSEND_POLL_FIRST) - return -EINVAL; - sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; - if (sr->msg_flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - -#ifdef CONFIG_COMPAT - if (req->ctx->compat) - sr->msg_flags |= MSG_CMSG_COMPAT; -#endif - sr->done_io = 0; - return 0; -} - -static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_async_msghdr iomsg, *kmsg; - struct io_sr_msg *sr = &req->sr_msg; - struct socket *sock; - unsigned flags; - int min_ret = 0; - int ret; - - sock = sock_from_file(req->file); - if (unlikely(!sock)) - return -ENOTSOCK; - - if (req_has_async_data(req)) { - kmsg = req->async_data; - } else { - ret = io_sendmsg_copy_hdr(req, &iomsg); - if (ret) - return ret; - kmsg = &iomsg; - } - - if (!(req->flags & REQ_F_POLLED) && - (sr->flags & IORING_RECVSEND_POLL_FIRST)) - return io_setup_async_msg(req, kmsg); - - flags = sr->msg_flags; - if (issue_flags & IO_URING_F_NONBLOCK) - flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) - min_ret = iov_iter_count(&kmsg->msg.msg_iter); - - ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); - - if (ret < min_ret) { - if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) - return io_setup_async_msg(req, kmsg); - if (ret == -ERESTARTSYS) - ret = -EINTR; - if (ret > 0 && io_net_retry(sock, flags)) { - sr->done_io += ret; - req->flags |= REQ_F_PARTIAL_IO; - return io_setup_async_msg(req, kmsg); - } - req_set_fail(req); - } - /* fast path, check for non-NULL to avoid function call */ - if (kmsg->free_iov) - kfree(kmsg->free_iov); - req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret >= 0) - ret += sr->done_io; - else if (sr->done_io) - ret = sr->done_io; - __io_req_complete(req, issue_flags, ret, 0); - return 0; -} - -static int io_send(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_sr_msg *sr = &req->sr_msg; - struct msghdr msg; - struct iovec iov; - struct socket *sock; - unsigned flags; - int min_ret = 0; - int ret; - - if (!(req->flags & REQ_F_POLLED) && - (sr->flags & IORING_RECVSEND_POLL_FIRST)) - return -EAGAIN; - - sock = sock_from_file(req->file); - if (unlikely(!sock)) - return -ENOTSOCK; - - ret = import_single_range(WRITE, sr->buf, sr->len, &iov, &msg.msg_iter); - if (unlikely(ret)) - return ret; - - msg.msg_name = NULL; - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_namelen = 0; - - flags = sr->msg_flags; - if (issue_flags & IO_URING_F_NONBLOCK) - flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) - min_ret = iov_iter_count(&msg.msg_iter); - - msg.msg_flags = flags; - ret = sock_sendmsg(sock, &msg); - if (ret < min_ret) { - if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) - return -EAGAIN; - if (ret == -ERESTARTSYS) - ret = -EINTR; - if (ret > 0 && io_net_retry(sock, flags)) { - sr->len -= ret; - sr->buf += ret; - sr->done_io += ret; - req->flags |= REQ_F_PARTIAL_IO; - return -EAGAIN; - } - req_set_fail(req); - } - if (ret >= 0) - ret += sr->done_io; - else if (sr->done_io) - ret = sr->done_io; - __io_req_complete(req, issue_flags, ret, 0); - return 0; -} - -static int __io_recvmsg_copy_hdr(struct io_kiocb *req, - struct io_async_msghdr *iomsg) -{ - struct io_sr_msg *sr = &req->sr_msg; - struct iovec __user *uiov; - size_t iov_len; - int ret; - - ret = __copy_msghdr_from_user(&iomsg->msg, sr->umsg, - &iomsg->uaddr, &uiov, &iov_len); - if (ret) - return ret; - - if (req->flags & REQ_F_BUFFER_SELECT) { - if (iov_len > 1) - return -EINVAL; - if (copy_from_user(iomsg->fast_iov, uiov, sizeof(*uiov))) - return -EFAULT; - sr->len = iomsg->fast_iov[0].iov_len; - iomsg->free_iov = NULL; - } else { - iomsg->free_iov = iomsg->fast_iov; - ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV, - &iomsg->free_iov, &iomsg->msg.msg_iter, - false); - if (ret > 0) - ret = 0; - } - - return ret; -} - -#ifdef CONFIG_COMPAT -static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, - struct io_async_msghdr *iomsg) -{ - struct io_sr_msg *sr = &req->sr_msg; - struct compat_iovec __user *uiov; - compat_uptr_t ptr; - compat_size_t len; - int ret; - - ret = __get_compat_msghdr(&iomsg->msg, sr->umsg_compat, &iomsg->uaddr, - &ptr, &len); - if (ret) - return ret; - - uiov = compat_ptr(ptr); - if (req->flags & REQ_F_BUFFER_SELECT) { - compat_ssize_t clen; - - if (len > 1) - return -EINVAL; - if (!access_ok(uiov, sizeof(*uiov))) - return -EFAULT; - if (__get_user(clen, &uiov->iov_len)) - return -EFAULT; - if (clen < 0) - return -EINVAL; - sr->len = clen; - iomsg->free_iov = NULL; - } else { - iomsg->free_iov = iomsg->fast_iov; - ret = __import_iovec(READ, (struct iovec __user *)uiov, len, - UIO_FASTIOV, &iomsg->free_iov, - &iomsg->msg.msg_iter, true); - if (ret < 0) - return ret; - } - - return 0; -} -#endif - -static int io_recvmsg_copy_hdr(struct io_kiocb *req, - struct io_async_msghdr *iomsg) -{ - iomsg->msg.msg_name = &iomsg->addr; - -#ifdef CONFIG_COMPAT - if (req->ctx->compat) - return __io_compat_recvmsg_copy_hdr(req, iomsg); -#endif - - return __io_recvmsg_copy_hdr(req, iomsg); -} - -static int io_recvmsg_prep_async(struct io_kiocb *req) -{ - int ret; - - ret = io_recvmsg_copy_hdr(req, req->async_data); - if (!ret) - req->flags |= REQ_F_NEED_CLEANUP; - return ret; -} - -static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - struct io_sr_msg *sr = &req->sr_msg; - - if (unlikely(sqe->file_index || sqe->addr2)) - return -EINVAL; - - sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); - sr->len = READ_ONCE(sqe->len); - sr->flags = READ_ONCE(sqe->ioprio); - if (sr->flags & ~IORING_RECVSEND_POLL_FIRST) - return -EINVAL; - sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; - if (sr->msg_flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - -#ifdef CONFIG_COMPAT - if (req->ctx->compat) - sr->msg_flags |= MSG_CMSG_COMPAT; -#endif - sr->done_io = 0; - return 0; -} - -static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_async_msghdr iomsg, *kmsg; - struct io_sr_msg *sr = &req->sr_msg; - struct socket *sock; - unsigned int cflags; - unsigned flags; - int ret, min_ret = 0; - bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - - sock = sock_from_file(req->file); - if (unlikely(!sock)) - return -ENOTSOCK; - - if (req_has_async_data(req)) { - kmsg = req->async_data; - } else { - ret = io_recvmsg_copy_hdr(req, &iomsg); - if (ret) - return ret; - kmsg = &iomsg; - } - - if (!(req->flags & REQ_F_POLLED) && - (sr->flags & IORING_RECVSEND_POLL_FIRST)) - return io_setup_async_msg(req, kmsg); - - if (io_do_buffer_select(req)) { - void __user *buf; - - buf = io_buffer_select(req, &sr->len, issue_flags); - if (!buf) - return -ENOBUFS; - kmsg->fast_iov[0].iov_base = buf; - kmsg->fast_iov[0].iov_len = sr->len; - iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, - sr->len); - } - - flags = sr->msg_flags; - if (force_nonblock) - flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) - min_ret = iov_iter_count(&kmsg->msg.msg_iter); - - kmsg->msg.msg_get_inq = 1; - ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags); - if (ret < min_ret) { - if (ret == -EAGAIN && force_nonblock) - return io_setup_async_msg(req, kmsg); - if (ret == -ERESTARTSYS) - ret = -EINTR; - if (ret > 0 && io_net_retry(sock, flags)) { - sr->done_io += ret; - req->flags |= REQ_F_PARTIAL_IO; - return io_setup_async_msg(req, kmsg); - } - req_set_fail(req); - } else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { - req_set_fail(req); - } - - /* fast path, check for non-NULL to avoid function call */ - if (kmsg->free_iov) - kfree(kmsg->free_iov); - req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret >= 0) - ret += sr->done_io; - else if (sr->done_io) - ret = sr->done_io; - cflags = io_put_kbuf(req, issue_flags); - if (kmsg->msg.msg_inq) - cflags |= IORING_CQE_F_SOCK_NONEMPTY; - __io_req_complete(req, issue_flags, ret, cflags); - return 0; -} - -static int io_recv(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_sr_msg *sr = &req->sr_msg; - struct msghdr msg; - struct socket *sock; - struct iovec iov; - unsigned int cflags; - unsigned flags; - int ret, min_ret = 0; - bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - - if (!(req->flags & REQ_F_POLLED) && - (sr->flags & IORING_RECVSEND_POLL_FIRST)) - return -EAGAIN; - - sock = sock_from_file(req->file); - if (unlikely(!sock)) - return -ENOTSOCK; - - if (io_do_buffer_select(req)) { - void __user *buf; - - buf = io_buffer_select(req, &sr->len, issue_flags); - if (!buf) - return -ENOBUFS; - sr->buf = buf; - } - - ret = import_single_range(READ, sr->buf, sr->len, &iov, &msg.msg_iter); - if (unlikely(ret)) - goto out_free; - - msg.msg_name = NULL; - msg.msg_namelen = 0; - msg.msg_control = NULL; - msg.msg_get_inq = 1; - msg.msg_flags = 0; - msg.msg_controllen = 0; - msg.msg_iocb = NULL; - - flags = sr->msg_flags; - if (force_nonblock) - flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) - min_ret = iov_iter_count(&msg.msg_iter); - - ret = sock_recvmsg(sock, &msg, flags); - if (ret < min_ret) { - if (ret == -EAGAIN && force_nonblock) - return -EAGAIN; - if (ret == -ERESTARTSYS) - ret = -EINTR; - if (ret > 0 && io_net_retry(sock, flags)) { - sr->len -= ret; - sr->buf += ret; - sr->done_io += ret; - req->flags |= REQ_F_PARTIAL_IO; - return -EAGAIN; - } - req_set_fail(req); - } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { -out_free: - req_set_fail(req); - } - - if (ret >= 0) - ret += sr->done_io; - else if (sr->done_io) - ret = sr->done_io; - cflags = io_put_kbuf(req, issue_flags); - if (msg.msg_inq) - cflags |= IORING_CQE_F_SOCK_NONEMPTY; - __io_req_complete(req, issue_flags, ret, cflags); - return 0; -} - -static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - struct io_accept *accept = &req->accept; - unsigned flags; - - if (sqe->len || sqe->buf_index) - return -EINVAL; - - accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); - accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); - accept->flags = READ_ONCE(sqe->accept_flags); - accept->nofile = rlimit(RLIMIT_NOFILE); - flags = READ_ONCE(sqe->ioprio); - if (flags & ~IORING_ACCEPT_MULTISHOT) - return -EINVAL; - - accept->file_slot = READ_ONCE(sqe->file_index); - if (accept->file_slot) { - if (accept->flags & SOCK_CLOEXEC) - return -EINVAL; - if (flags & IORING_ACCEPT_MULTISHOT && - accept->file_slot != IORING_FILE_INDEX_ALLOC) - return -EINVAL; - } - if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) - return -EINVAL; - if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK)) - accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - if (flags & IORING_ACCEPT_MULTISHOT) - req->flags |= REQ_F_APOLL_MULTISHOT; - return 0; -} - -static int io_accept(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_accept *accept = &req->accept; - bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0; - bool fixed = !!accept->file_slot; - struct file *file; - int ret, fd; - -retry: - if (!fixed) { - fd = __get_unused_fd_flags(accept->flags, accept->nofile); - if (unlikely(fd < 0)) - return fd; - } - file = do_accept(req->file, file_flags, accept->addr, accept->addr_len, - accept->flags); - if (IS_ERR(file)) { - if (!fixed) - put_unused_fd(fd); - ret = PTR_ERR(file); - if (ret == -EAGAIN && force_nonblock) { - /* - * if it's multishot and polled, we don't need to - * return EAGAIN to arm the poll infra since it - * has already been done - */ - if ((req->flags & IO_APOLL_MULTI_POLLED) == - IO_APOLL_MULTI_POLLED) - ret = 0; - return ret; - } - if (ret == -ERESTARTSYS) - ret = -EINTR; - req_set_fail(req); - } else if (!fixed) { - fd_install(fd, file); - ret = fd; - } else { - ret = io_fixed_fd_install(req, issue_flags, file, - accept->file_slot); - } - - if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { - __io_req_complete(req, issue_flags, ret, 0); - return 0; - } - if (ret >= 0) { - bool filled; - - spin_lock(&ctx->completion_lock); - filled = io_fill_cqe_aux(ctx, req->cqe.user_data, ret, - IORING_CQE_F_MORE); - io_commit_cqring(ctx); - spin_unlock(&ctx->completion_lock); - if (filled) { - io_cqring_ev_posted(ctx); - goto retry; - } - ret = -ECANCELED; - } - - return ret; -} - -static int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - struct io_socket *sock = &req->sock; - - if (sqe->addr || sqe->rw_flags || sqe->buf_index) - return -EINVAL; - - sock->domain = READ_ONCE(sqe->fd); - sock->type = READ_ONCE(sqe->off); - sock->protocol = READ_ONCE(sqe->len); - sock->file_slot = READ_ONCE(sqe->file_index); - sock->nofile = rlimit(RLIMIT_NOFILE); - - sock->flags = sock->type & ~SOCK_TYPE_MASK; - if (sock->file_slot && (sock->flags & SOCK_CLOEXEC)) - return -EINVAL; - if (sock->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) - return -EINVAL; - return 0; -} - -static int io_socket(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_socket *sock = &req->sock; - bool fixed = !!sock->file_slot; - struct file *file; - int ret, fd; - - if (!fixed) { - fd = __get_unused_fd_flags(sock->flags, sock->nofile); - if (unlikely(fd < 0)) - return fd; - } - file = __sys_socket_file(sock->domain, sock->type, sock->protocol); - if (IS_ERR(file)) { - if (!fixed) - put_unused_fd(fd); - ret = PTR_ERR(file); - if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) - return -EAGAIN; - if (ret == -ERESTARTSYS) - ret = -EINTR; - req_set_fail(req); - } else if (!fixed) { - fd_install(fd, file); - ret = fd; - } else { - ret = io_fixed_fd_install(req, issue_flags, file, - sock->file_slot); - } - __io_req_complete(req, issue_flags, ret, 0); - return 0; -} - -static int io_connect_prep_async(struct io_kiocb *req) -{ - struct io_async_connect *io = req->async_data; - struct io_connect *conn = &req->connect; - - return move_addr_to_kernel(conn->addr, conn->addr_len, &io->address); -} - -static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - struct io_connect *conn = &req->connect; - - if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) - return -EINVAL; - - conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); - conn->addr_len = READ_ONCE(sqe->addr2); - return 0; -} - -static int io_connect(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_async_connect __io, *io; - unsigned file_flags; - int ret; - bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - - if (req_has_async_data(req)) { - io = req->async_data; - } else { - ret = move_addr_to_kernel(req->connect.addr, - req->connect.addr_len, - &__io.address); - if (ret) - goto out; - io = &__io; - } - - file_flags = force_nonblock ? O_NONBLOCK : 0; - - ret = __sys_connect_file(req->file, &io->address, - req->connect.addr_len, file_flags); - if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) { - if (req_has_async_data(req)) - return -EAGAIN; - if (io_alloc_async_data(req)) { - ret = -ENOMEM; - goto out; - } - memcpy(req->async_data, &__io, sizeof(__io)); - return -EAGAIN; - } - if (ret == -ERESTARTSYS) - ret = -EINTR; -out: - if (ret < 0) - req_set_fail(req); - __io_req_complete(req, issue_flags, ret, 0); - return 0; -} -#else /* !CONFIG_NET */ -#define IO_NETOP_FN(op) \ -static int io_##op(struct io_kiocb *req, unsigned int issue_flags) \ -{ \ - return -EOPNOTSUPP; \ -} - -#define IO_NETOP_PREP(op) \ -IO_NETOP_FN(op) \ -static int io_##op##_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) \ -{ \ - return -EOPNOTSUPP; \ -} \ - -#define IO_NETOP_PREP_ASYNC(op) \ -IO_NETOP_PREP(op) \ -static int io_##op##_prep_async(struct io_kiocb *req) \ -{ \ - return -EOPNOTSUPP; \ -} - -IO_NETOP_PREP_ASYNC(sendmsg); -IO_NETOP_PREP_ASYNC(recvmsg); -IO_NETOP_PREP_ASYNC(connect); -IO_NETOP_PREP(accept); -IO_NETOP_PREP(socket); -IO_NETOP_PREP(shutdown); -IO_NETOP_FN(send); -IO_NETOP_FN(recv); -#endif /* CONFIG_NET */ - -struct io_poll_table { - struct poll_table_struct pt; - struct io_kiocb *req; - int nr_entries; - int error; -}; - -#define IO_POLL_CANCEL_FLAG BIT(31) -#define IO_POLL_REF_MASK GENMASK(30, 0) - -/* - * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can - * bump it and acquire ownership. It's disallowed to modify requests while not - * owning it, that prevents from races for enqueueing task_work's and b/w - * arming poll and wakeups. - */ -static inline bool io_poll_get_ownership(struct io_kiocb *req) -{ - return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); -} - -static void io_poll_mark_cancelled(struct io_kiocb *req) -{ - atomic_or(IO_POLL_CANCEL_FLAG, &req->poll_refs); -} - -static struct io_poll_iocb *io_poll_get_double(struct io_kiocb *req) -{ - /* pure poll stashes this in ->async_data, poll driven retry elsewhere */ - if (req->opcode == IORING_OP_POLL_ADD) - return req->async_data; - return req->apoll->double_poll; -} - -static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req) -{ - if (req->opcode == IORING_OP_POLL_ADD) - return &req->poll; - return &req->apoll->poll; -} - -static void io_poll_req_insert(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - struct hlist_head *list; - - list = &ctx->cancel_hash[hash_long(req->cqe.user_data, ctx->cancel_hash_bits)]; - hlist_add_head(&req->hash_node, list); -} - -static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events, - wait_queue_func_t wake_func) -{ - poll->head = NULL; -#define IO_POLL_UNMASK (EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP) - /* mask in events that we always want/need */ - poll->events = events | IO_POLL_UNMASK; - INIT_LIST_HEAD(&poll->wait.entry); - init_waitqueue_func_entry(&poll->wait, wake_func); -} - -static inline void io_poll_remove_entry(struct io_poll_iocb *poll) -{ - struct wait_queue_head *head = smp_load_acquire(&poll->head); - - if (head) { - spin_lock_irq(&head->lock); - list_del_init(&poll->wait.entry); - poll->head = NULL; - spin_unlock_irq(&head->lock); - } -} - -static void io_poll_remove_entries(struct io_kiocb *req) -{ - /* - * Nothing to do if neither of those flags are set. Avoid dipping - * into the poll/apoll/double cachelines if we can. - */ - if (!(req->flags & (REQ_F_SINGLE_POLL | REQ_F_DOUBLE_POLL))) - return; - - /* - * While we hold the waitqueue lock and the waitqueue is nonempty, - * wake_up_pollfree() will wait for us. However, taking the waitqueue - * lock in the first place can race with the waitqueue being freed. - * - * We solve this as eventpoll does: by taking advantage of the fact that - * all users of wake_up_pollfree() will RCU-delay the actual free. If - * we enter rcu_read_lock() and see that the pointer to the queue is - * non-NULL, we can then lock it without the memory being freed out from - * under us. - * - * Keep holding rcu_read_lock() as long as we hold the queue lock, in - * case the caller deletes the entry from the queue, leaving it empty. - * In that case, only RCU prevents the queue memory from being freed. - */ - rcu_read_lock(); - if (req->flags & REQ_F_SINGLE_POLL) - io_poll_remove_entry(io_poll_get_single(req)); - if (req->flags & REQ_F_DOUBLE_POLL) - io_poll_remove_entry(io_poll_get_double(req)); - rcu_read_unlock(); -} - -static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags); -/* - * All poll tw should go through this. Checks for poll events, manages - * references, does rewait, etc. - * - * Returns a negative error on failure. >0 when no action require, which is - * either spurious wakeup or multishot CQE is served. 0 when it's done with - * the request, then the mask is stored in req->cqe.res. - */ -static int io_poll_check_events(struct io_kiocb *req, bool *locked) -{ - struct io_ring_ctx *ctx = req->ctx; - int v, ret; - - /* req->task == current here, checking PF_EXITING is safe */ - if (unlikely(req->task->flags & PF_EXITING)) - return -ECANCELED; - - do { - v = atomic_read(&req->poll_refs); - - /* tw handler should be the owner, and so have some references */ - if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK))) - return 0; - if (v & IO_POLL_CANCEL_FLAG) - return -ECANCELED; - - if (!req->cqe.res) { - struct poll_table_struct pt = { ._key = req->apoll_events }; - req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events; - } - - if ((unlikely(!req->cqe.res))) - continue; - if (req->apoll_events & EPOLLONESHOT) - return 0; - - /* multishot, just fill a CQE and proceed */ - if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { - __poll_t mask = mangle_poll(req->cqe.res & - req->apoll_events); - bool filled; - - spin_lock(&ctx->completion_lock); - filled = io_fill_cqe_aux(ctx, req->cqe.user_data, - mask, IORING_CQE_F_MORE); - io_commit_cqring(ctx); - spin_unlock(&ctx->completion_lock); - if (filled) { - io_cqring_ev_posted(ctx); - continue; - } - return -ECANCELED; - } - - io_tw_lock(req->ctx, locked); - if (unlikely(req->task->flags & PF_EXITING)) - return -EFAULT; - ret = io_issue_sqe(req, - IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); - if (ret) - return ret; - - /* - * Release all references, retry if someone tried to restart - * task_work while we were executing it. - */ - } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs)); - - return 1; -} - -static void io_poll_task_func(struct io_kiocb *req, bool *locked) -{ - struct io_ring_ctx *ctx = req->ctx; - int ret; - - ret = io_poll_check_events(req, locked); - if (ret > 0) - return; - - if (!ret) { - req->cqe.res = mangle_poll(req->cqe.res & req->poll.events); - } else { - req->cqe.res = ret; - req_set_fail(req); - } - - io_poll_remove_entries(req); - spin_lock(&ctx->completion_lock); - hash_del(&req->hash_node); - __io_req_complete_post(req, req->cqe.res, 0); - io_commit_cqring(ctx); - spin_unlock(&ctx->completion_lock); - io_cqring_ev_posted(ctx); -} - -static void io_apoll_task_func(struct io_kiocb *req, bool *locked) -{ - struct io_ring_ctx *ctx = req->ctx; - int ret; - - ret = io_poll_check_events(req, locked); - if (ret > 0) - return; - - io_poll_remove_entries(req); - spin_lock(&ctx->completion_lock); - hash_del(&req->hash_node); - spin_unlock(&ctx->completion_lock); - - if (!ret) - io_req_task_submit(req, locked); - else - io_req_complete_failed(req, ret); -} - -static void __io_poll_execute(struct io_kiocb *req, int mask, - __poll_t __maybe_unused events) -{ - req->cqe.res = mask; - /* - * This is useful for poll that is armed on behalf of another - * request, and where the wakeup path could be on a different - * CPU. We want to avoid pulling in req->apoll->events for that - * case. - */ - if (req->opcode == IORING_OP_POLL_ADD) - req->io_task_work.func = io_poll_task_func; - else - req->io_task_work.func = io_apoll_task_func; - - trace_io_uring_task_add(req->ctx, req, req->cqe.user_data, req->opcode, mask); - io_req_task_work_add(req); -} - -static inline void io_poll_execute(struct io_kiocb *req, int res, - __poll_t events) -{ - if (io_poll_get_ownership(req)) - __io_poll_execute(req, res, events); -} - -static void io_poll_cancel_req(struct io_kiocb *req) -{ - io_poll_mark_cancelled(req); - /* kick tw, which should complete the request */ - io_poll_execute(req, 0, 0); -} - -#define wqe_to_req(wait) ((void *)((unsigned long) (wait)->private & ~1)) -#define wqe_is_double(wait) ((unsigned long) (wait)->private & 1) -#define IO_ASYNC_POLL_COMMON (EPOLLONESHOT | EPOLLPRI) - -static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, - void *key) -{ - struct io_kiocb *req = wqe_to_req(wait); - struct io_poll_iocb *poll = container_of(wait, struct io_poll_iocb, - wait); - __poll_t mask = key_to_poll(key); - - if (unlikely(mask & POLLFREE)) { - io_poll_mark_cancelled(req); - /* we have to kick tw in case it's not already */ - io_poll_execute(req, 0, poll->events); - - /* - * If the waitqueue is being freed early but someone is already - * holds ownership over it, we have to tear down the request as - * best we can. That means immediately removing the request from - * its waitqueue and preventing all further accesses to the - * waitqueue via the request. - */ - list_del_init(&poll->wait.entry); - - /* - * Careful: this *must* be the last step, since as soon - * as req->head is NULL'ed out, the request can be - * completed and freed, since aio_poll_complete_work() - * will no longer need to take the waitqueue lock. - */ - smp_store_release(&poll->head, NULL); - return 1; - } - - /* for instances that support it check for an event match first */ - if (mask && !(mask & (poll->events & ~IO_ASYNC_POLL_COMMON))) - return 0; - - if (io_poll_get_ownership(req)) { - /* optional, saves extra locking for removal in tw handler */ - if (mask && poll->events & EPOLLONESHOT) { - list_del_init(&poll->wait.entry); - poll->head = NULL; - if (wqe_is_double(wait)) - req->flags &= ~REQ_F_DOUBLE_POLL; - else - req->flags &= ~REQ_F_SINGLE_POLL; - } - __io_poll_execute(req, mask, poll->events); - } - return 1; -} - -static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, - struct wait_queue_head *head, - struct io_poll_iocb **poll_ptr) -{ - struct io_kiocb *req = pt->req; - unsigned long wqe_private = (unsigned long) req; - - /* - * The file being polled uses multiple waitqueues for poll handling - * (e.g. one for read, one for write). Setup a separate io_poll_iocb - * if this happens. - */ - if (unlikely(pt->nr_entries)) { - struct io_poll_iocb *first = poll; - - /* double add on the same waitqueue head, ignore */ - if (first->head == head) - return; - /* already have a 2nd entry, fail a third attempt */ - if (*poll_ptr) { - if ((*poll_ptr)->head == head) - return; - pt->error = -EINVAL; - return; - } - - poll = kmalloc(sizeof(*poll), GFP_ATOMIC); - if (!poll) { - pt->error = -ENOMEM; - return; - } - /* mark as double wq entry */ - wqe_private |= 1; - req->flags |= REQ_F_DOUBLE_POLL; - io_init_poll_iocb(poll, first->events, first->wait.func); - *poll_ptr = poll; - if (req->opcode == IORING_OP_POLL_ADD) - req->flags |= REQ_F_ASYNC_DATA; - } - - req->flags |= REQ_F_SINGLE_POLL; - pt->nr_entries++; - poll->head = head; - poll->wait.private = (void *) wqe_private; - - if (poll->events & EPOLLEXCLUSIVE) - add_wait_queue_exclusive(head, &poll->wait); - else - add_wait_queue(head, &poll->wait); -} - -static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, - struct poll_table_struct *p) -{ - struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); - - __io_queue_proc(&pt->req->poll, pt, head, - (struct io_poll_iocb **) &pt->req->async_data); -} - -static int __io_arm_poll_handler(struct io_kiocb *req, - struct io_poll_iocb *poll, - struct io_poll_table *ipt, __poll_t mask) -{ - struct io_ring_ctx *ctx = req->ctx; - int v; - - INIT_HLIST_NODE(&req->hash_node); - req->work.cancel_seq = atomic_read(&ctx->cancel_seq); - io_init_poll_iocb(poll, mask, io_poll_wake); - poll->file = req->file; - - req->apoll_events = poll->events; - - ipt->pt._key = mask; - ipt->req = req; - ipt->error = 0; - ipt->nr_entries = 0; - - /* - * Take the ownership to delay any tw execution up until we're done - * with poll arming. see io_poll_get_ownership(). - */ - atomic_set(&req->poll_refs, 1); - mask = vfs_poll(req->file, &ipt->pt) & poll->events; - - if (mask && (poll->events & EPOLLONESHOT)) { - io_poll_remove_entries(req); - /* no one else has access to the req, forget about the ref */ - return mask; - } - if (!mask && unlikely(ipt->error || !ipt->nr_entries)) { - io_poll_remove_entries(req); - if (!ipt->error) - ipt->error = -EINVAL; - return 0; - } - - spin_lock(&ctx->completion_lock); - io_poll_req_insert(req); - spin_unlock(&ctx->completion_lock); - - if (mask) { - /* can't multishot if failed, just queue the event we've got */ - if (unlikely(ipt->error || !ipt->nr_entries)) { - poll->events |= EPOLLONESHOT; - req->apoll_events |= EPOLLONESHOT; - ipt->error = 0; - } - __io_poll_execute(req, mask, poll->events); - return 0; - } - - /* - * Release ownership. If someone tried to queue a tw while it was - * locked, kick it off for them. - */ - v = atomic_dec_return(&req->poll_refs); - if (unlikely(v & IO_POLL_REF_MASK)) - __io_poll_execute(req, 0, poll->events); - return 0; -} - -static void io_async_queue_proc(struct file *file, struct wait_queue_head *head, - struct poll_table_struct *p) -{ - struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); - struct async_poll *apoll = pt->req->apoll; - - __io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll); -} - -enum { - IO_APOLL_OK, - IO_APOLL_ABORTED, - IO_APOLL_READY -}; - -static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) -{ - const struct io_op_def *def = &io_op_defs[req->opcode]; - struct io_ring_ctx *ctx = req->ctx; - struct async_poll *apoll; - struct io_poll_table ipt; - __poll_t mask = POLLPRI | POLLERR; - int ret; - - if (!def->pollin && !def->pollout) - return IO_APOLL_ABORTED; - if (!file_can_poll(req->file)) - return IO_APOLL_ABORTED; - if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED) - return IO_APOLL_ABORTED; - if (!(req->flags & REQ_F_APOLL_MULTISHOT)) - mask |= EPOLLONESHOT; - - if (def->pollin) { - mask |= EPOLLIN | EPOLLRDNORM; - - /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ - if ((req->opcode == IORING_OP_RECVMSG) && - (req->sr_msg.msg_flags & MSG_ERRQUEUE)) - mask &= ~EPOLLIN; - } else { - mask |= EPOLLOUT | EPOLLWRNORM; - } - if (def->poll_exclusive) - mask |= EPOLLEXCLUSIVE; - if (req->flags & REQ_F_POLLED) { - apoll = req->apoll; - kfree(apoll->double_poll); - } else if (!(issue_flags & IO_URING_F_UNLOCKED) && - !list_empty(&ctx->apoll_cache)) { - apoll = list_first_entry(&ctx->apoll_cache, struct async_poll, - poll.wait.entry); - list_del_init(&apoll->poll.wait.entry); - } else { - apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); - if (unlikely(!apoll)) - return IO_APOLL_ABORTED; - } - apoll->double_poll = NULL; - req->apoll = apoll; - req->flags |= REQ_F_POLLED; - ipt.pt._qproc = io_async_queue_proc; - - io_kbuf_recycle(req, issue_flags); - - ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask); - if (ret || ipt.error) - return ret ? IO_APOLL_READY : IO_APOLL_ABORTED; - - trace_io_uring_poll_arm(ctx, req, req->cqe.user_data, req->opcode, - mask, apoll->poll.events); - return IO_APOLL_OK; -} - -/* - * Returns true if we found and killed one or more poll requests - */ -static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx, - struct task_struct *tsk, bool cancel_all) -{ - struct hlist_node *tmp; - struct io_kiocb *req; - bool found = false; - int i; - - spin_lock(&ctx->completion_lock); - for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { - struct hlist_head *list; - - list = &ctx->cancel_hash[i]; - hlist_for_each_entry_safe(req, tmp, list, hash_node) { - if (io_match_task_safe(req, tsk, cancel_all)) { - hlist_del_init(&req->hash_node); - io_poll_cancel_req(req); - found = true; - } - } - } - spin_unlock(&ctx->completion_lock); - return found; -} - -static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only, - struct io_cancel_data *cd) - __must_hold(&ctx->completion_lock) -{ - struct hlist_head *list; - struct io_kiocb *req; - - list = &ctx->cancel_hash[hash_long(cd->data, ctx->cancel_hash_bits)]; - hlist_for_each_entry(req, list, hash_node) { - if (cd->data != req->cqe.user_data) - continue; - if (poll_only && req->opcode != IORING_OP_POLL_ADD) - continue; - if (cd->flags & IORING_ASYNC_CANCEL_ALL) { - if (cd->seq == req->work.cancel_seq) - continue; - req->work.cancel_seq = cd->seq; - } - return req; - } - return NULL; -} - -static struct io_kiocb *io_poll_file_find(struct io_ring_ctx *ctx, - struct io_cancel_data *cd) - __must_hold(&ctx->completion_lock) -{ - struct io_kiocb *req; - int i; - - for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { - struct hlist_head *list; - - list = &ctx->cancel_hash[i]; - hlist_for_each_entry(req, list, hash_node) { - if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) && - req->file != cd->file) - continue; - if (cd->seq == req->work.cancel_seq) - continue; - req->work.cancel_seq = cd->seq; - return req; - } - } - return NULL; -} - -static bool io_poll_disarm(struct io_kiocb *req) - __must_hold(&ctx->completion_lock) -{ - if (!io_poll_get_ownership(req)) - return false; - io_poll_remove_entries(req); - hash_del(&req->hash_node); - return true; -} - -static int io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) - __must_hold(&ctx->completion_lock) -{ - struct io_kiocb *req; - - if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_ANY)) - req = io_poll_file_find(ctx, cd); - else - req = io_poll_find(ctx, false, cd); - if (!req) - return -ENOENT; - io_poll_cancel_req(req); - return 0; -} - -static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe, - unsigned int flags) -{ - u32 events; - - events = READ_ONCE(sqe->poll32_events); -#ifdef __BIG_ENDIAN - events = swahw32(events); -#endif - if (!(flags & IORING_POLL_ADD_MULTI)) - events |= EPOLLONESHOT; - return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT)); -} - -static int io_poll_remove_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_poll_update *upd = &req->poll_update; - u32 flags; - - if (sqe->buf_index || sqe->splice_fd_in) - return -EINVAL; - flags = READ_ONCE(sqe->len); - if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA | - IORING_POLL_ADD_MULTI)) - return -EINVAL; - /* meaningless without update */ - if (flags == IORING_POLL_ADD_MULTI) - return -EINVAL; - - upd->old_user_data = READ_ONCE(sqe->addr); - upd->update_events = flags & IORING_POLL_UPDATE_EVENTS; - upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA; - - upd->new_user_data = READ_ONCE(sqe->off); - if (!upd->update_user_data && upd->new_user_data) - return -EINVAL; - if (upd->update_events) - upd->events = io_poll_parse_events(sqe, flags); - else if (sqe->poll32_events) - return -EINVAL; - - return 0; -} - -static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - struct io_poll_iocb *poll = &req->poll; - u32 flags; - - if (sqe->buf_index || sqe->off || sqe->addr) - return -EINVAL; - flags = READ_ONCE(sqe->len); - if (flags & ~IORING_POLL_ADD_MULTI) - return -EINVAL; - if ((flags & IORING_POLL_ADD_MULTI) && (req->flags & REQ_F_CQE_SKIP)) - return -EINVAL; - - io_req_set_refcount(req); - poll->events = io_poll_parse_events(sqe, flags); - return 0; -} - -static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_poll_iocb *poll = &req->poll; - struct io_poll_table ipt; - int ret; - - ipt.pt._qproc = io_poll_queue_proc; - - ret = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events); - if (!ret && ipt.error) - req_set_fail(req); - ret = ret ?: ipt.error; - if (ret) - __io_req_complete(req, issue_flags, ret, 0); - return 0; -} - -static int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_cancel_data cd = { .data = req->poll_update.old_user_data, }; - struct io_ring_ctx *ctx = req->ctx; - struct io_kiocb *preq; - int ret2, ret = 0; - bool locked; - - spin_lock(&ctx->completion_lock); - preq = io_poll_find(ctx, true, &cd); - if (!preq || !io_poll_disarm(preq)) { - spin_unlock(&ctx->completion_lock); - ret = preq ? -EALREADY : -ENOENT; - goto out; - } - spin_unlock(&ctx->completion_lock); - - if (req->poll_update.update_events || req->poll_update.update_user_data) { - /* only mask one event flags, keep behavior flags */ - if (req->poll_update.update_events) { - preq->poll.events &= ~0xffff; - preq->poll.events |= req->poll_update.events & 0xffff; - preq->poll.events |= IO_POLL_UNMASK; - } - if (req->poll_update.update_user_data) - preq->cqe.user_data = req->poll_update.new_user_data; - - ret2 = io_poll_add(preq, issue_flags); - /* successfully updated, don't complete poll request */ - if (!ret2) - goto out; - } - - req_set_fail(preq); - preq->cqe.res = -ECANCELED; - locked = !(issue_flags & IO_URING_F_UNLOCKED); - io_req_task_complete(preq, &locked); -out: - if (ret < 0) - req_set_fail(req); - /* complete update request, we're done with it */ - __io_req_complete(req, issue_flags, ret, 0); - return 0; -} - -static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) -{ - struct io_timeout_data *data = container_of(timer, - struct io_timeout_data, timer); - struct io_kiocb *req = data->req; - struct io_ring_ctx *ctx = req->ctx; - unsigned long flags; - - spin_lock_irqsave(&ctx->timeout_lock, flags); - list_del_init(&req->timeout.list); - atomic_set(&req->ctx->cq_timeouts, - atomic_read(&req->ctx->cq_timeouts) + 1); - spin_unlock_irqrestore(&ctx->timeout_lock, flags); - - if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS)) - req_set_fail(req); - - req->cqe.res = -ETIME; - req->io_task_work.func = io_req_task_complete; - io_req_task_work_add(req); - return HRTIMER_NORESTART; -} - -static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, - struct io_cancel_data *cd) - __must_hold(&ctx->timeout_lock) -{ - struct io_timeout_data *io; - struct io_kiocb *req; - bool found = false; - - list_for_each_entry(req, &ctx->timeout_list, timeout.list) { - if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) && - cd->data != req->cqe.user_data) - continue; - if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) { - if (cd->seq == req->work.cancel_seq) - continue; - req->work.cancel_seq = cd->seq; - } - found = true; - break; - } - if (!found) - return ERR_PTR(-ENOENT); - - io = req->async_data; - if (hrtimer_try_to_cancel(&io->timer) == -1) - return ERR_PTR(-EALREADY); - list_del_init(&req->timeout.list); - return req; -} - -static int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) - __must_hold(&ctx->completion_lock) -{ - struct io_kiocb *req; - - spin_lock_irq(&ctx->timeout_lock); - req = io_timeout_extract(ctx, cd); - spin_unlock_irq(&ctx->timeout_lock); - - if (IS_ERR(req)) - return PTR_ERR(req); - io_req_task_queue_fail(req, -ECANCELED); - return 0; -} - -static clockid_t io_timeout_get_clock(struct io_timeout_data *data) -{ - switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) { - case IORING_TIMEOUT_BOOTTIME: - return CLOCK_BOOTTIME; - case IORING_TIMEOUT_REALTIME: - return CLOCK_REALTIME; - default: - /* can't happen, vetted at prep time */ - WARN_ON_ONCE(1); - fallthrough; - case 0: - return CLOCK_MONOTONIC; - } -} - -static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, - struct timespec64 *ts, enum hrtimer_mode mode) - __must_hold(&ctx->timeout_lock) -{ - struct io_timeout_data *io; - struct io_kiocb *req; - bool found = false; - - list_for_each_entry(req, &ctx->ltimeout_list, timeout.list) { - found = user_data == req->cqe.user_data; - if (found) - break; - } - if (!found) - return -ENOENT; - - io = req->async_data; - if (hrtimer_try_to_cancel(&io->timer) == -1) - return -EALREADY; - hrtimer_init(&io->timer, io_timeout_get_clock(io), mode); - io->timer.function = io_link_timeout_fn; - hrtimer_start(&io->timer, timespec64_to_ktime(*ts), mode); - return 0; -} - -static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, - struct timespec64 *ts, enum hrtimer_mode mode) - __must_hold(&ctx->timeout_lock) -{ - struct io_cancel_data cd = { .data = user_data, }; - struct io_kiocb *req = io_timeout_extract(ctx, &cd); - struct io_timeout_data *data; - - if (IS_ERR(req)) - return PTR_ERR(req); - - req->timeout.off = 0; /* noseq */ - data = req->async_data; - list_add_tail(&req->timeout.list, &ctx->timeout_list); - hrtimer_init(&data->timer, io_timeout_get_clock(data), mode); - data->timer.function = io_timeout_fn; - hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode); - return 0; -} - -static int io_timeout_remove_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - struct io_timeout_rem *tr = &req->timeout_rem; - - if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) - return -EINVAL; - if (sqe->buf_index || sqe->len || sqe->splice_fd_in) - return -EINVAL; - - tr->ltimeout = false; - tr->addr = READ_ONCE(sqe->addr); - tr->flags = READ_ONCE(sqe->timeout_flags); - if (tr->flags & IORING_TIMEOUT_UPDATE_MASK) { - if (hweight32(tr->flags & IORING_TIMEOUT_CLOCK_MASK) > 1) - return -EINVAL; - if (tr->flags & IORING_LINK_TIMEOUT_UPDATE) - tr->ltimeout = true; - if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS)) - return -EINVAL; - if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2))) - return -EFAULT; - if (tr->ts.tv_sec < 0 || tr->ts.tv_nsec < 0) - return -EINVAL; - } else if (tr->flags) { - /* timeout removal doesn't support flags */ - return -EINVAL; - } - - return 0; -} - -static inline enum hrtimer_mode io_translate_timeout_mode(unsigned int flags) -{ - return (flags & IORING_TIMEOUT_ABS) ? HRTIMER_MODE_ABS - : HRTIMER_MODE_REL; -} - -/* - * Remove or update an existing timeout command - */ -static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_timeout_rem *tr = &req->timeout_rem; - struct io_ring_ctx *ctx = req->ctx; - int ret; - - if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE)) { - struct io_cancel_data cd = { .data = tr->addr, }; - - spin_lock(&ctx->completion_lock); - ret = io_timeout_cancel(ctx, &cd); - spin_unlock(&ctx->completion_lock); - } else { - enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags); - - spin_lock_irq(&ctx->timeout_lock); - if (tr->ltimeout) - ret = io_linked_timeout_update(ctx, tr->addr, &tr->ts, mode); - else - ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode); - spin_unlock_irq(&ctx->timeout_lock); - } - - if (ret < 0) - req_set_fail(req); - io_req_complete_post(req, ret, 0); - return 0; -} - -static int __io_timeout_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe, - bool is_timeout_link) -{ - struct io_timeout_data *data; - unsigned flags; - u32 off = READ_ONCE(sqe->off); - - if (sqe->buf_index || sqe->len != 1 || sqe->splice_fd_in) - return -EINVAL; - if (off && is_timeout_link) - return -EINVAL; - flags = READ_ONCE(sqe->timeout_flags); - if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK | - IORING_TIMEOUT_ETIME_SUCCESS)) - return -EINVAL; - /* more than one clock specified is invalid, obviously */ - if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1) - return -EINVAL; - - INIT_LIST_HEAD(&req->timeout.list); - req->timeout.off = off; - if (unlikely(off && !req->ctx->off_timeout_used)) - req->ctx->off_timeout_used = true; - - if (WARN_ON_ONCE(req_has_async_data(req))) - return -EFAULT; - if (io_alloc_async_data(req)) - return -ENOMEM; - - data = req->async_data; - data->req = req; - data->flags = flags; - - if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr))) - return -EFAULT; - - if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0) - return -EINVAL; - - INIT_LIST_HEAD(&req->timeout.list); - data->mode = io_translate_timeout_mode(flags); - hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); - - if (is_timeout_link) { - struct io_submit_link *link = &req->ctx->submit_state.link; - - if (!link->head) - return -EINVAL; - if (link->last->opcode == IORING_OP_LINK_TIMEOUT) - return -EINVAL; - req->timeout.head = link->last; - link->last->flags |= REQ_F_ARM_LTIMEOUT; - } - return 0; -} - -static int io_timeout_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - return __io_timeout_prep(req, sqe, false); -} - -static int io_link_timeout_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - return __io_timeout_prep(req, sqe, true); -} - -static int io_timeout(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_timeout_data *data = req->async_data; - struct list_head *entry; - u32 tail, off = req->timeout.off; - - spin_lock_irq(&ctx->timeout_lock); - - /* - * sqe->off holds how many events that need to occur for this - * timeout event to be satisfied. If it isn't set, then this is - * a pure timeout request, sequence isn't used. - */ - if (io_is_timeout_noseq(req)) { - entry = ctx->timeout_list.prev; - goto add; - } - - tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); - req->timeout.target_seq = tail + off; - - /* Update the last seq here in case io_flush_timeouts() hasn't. - * This is safe because ->completion_lock is held, and submissions - * and completions are never mixed in the same ->completion_lock section. - */ - ctx->cq_last_tm_flush = tail; - - /* - * Insertion sort, ensuring the first entry in the list is always - * the one we need first. - */ - list_for_each_prev(entry, &ctx->timeout_list) { - struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, - timeout.list); - - if (io_is_timeout_noseq(nxt)) - continue; - /* nxt.seq is behind @tail, otherwise would've been completed */ - if (off >= nxt->timeout.target_seq - tail) - break; - } -add: - list_add(&req->timeout.list, entry); - data->timer.function = io_timeout_fn; - hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); - spin_unlock_irq(&ctx->timeout_lock); - return 0; -} - -static bool io_cancel_cb(struct io_wq_work *work, void *data) -{ - struct io_kiocb *req = container_of(work, struct io_kiocb, work); - struct io_cancel_data *cd = data; - - if (req->ctx != cd->ctx) - return false; - if (cd->flags & IORING_ASYNC_CANCEL_ANY) { - ; - } else if (cd->flags & IORING_ASYNC_CANCEL_FD) { - if (req->file != cd->file) - return false; - } else { - if (req->cqe.user_data != cd->data) - return false; - } - if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) { - if (cd->seq == req->work.cancel_seq) - return false; - req->work.cancel_seq = cd->seq; - } - return true; -} - -static int io_async_cancel_one(struct io_uring_task *tctx, - struct io_cancel_data *cd) -{ - enum io_wq_cancel cancel_ret; - int ret = 0; - bool all; - - if (!tctx || !tctx->io_wq) - return -ENOENT; - - all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); - cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, cd, all); - switch (cancel_ret) { - case IO_WQ_CANCEL_OK: - ret = 0; - break; - case IO_WQ_CANCEL_RUNNING: - ret = -EALREADY; - break; - case IO_WQ_CANCEL_NOTFOUND: - ret = -ENOENT; - break; - } - - return ret; -} - -static int io_try_cancel(struct io_kiocb *req, struct io_cancel_data *cd) -{ - struct io_ring_ctx *ctx = req->ctx; - int ret; - - WARN_ON_ONCE(!io_wq_current_is_worker() && req->task != current); - - ret = io_async_cancel_one(req->task->io_uring, cd); - /* - * Fall-through even for -EALREADY, as we may have poll armed - * that need unarming. - */ - if (!ret) - return 0; - - spin_lock(&ctx->completion_lock); - ret = io_poll_cancel(ctx, cd); - if (ret != -ENOENT) - goto out; - if (!(cd->flags & IORING_ASYNC_CANCEL_FD)) - ret = io_timeout_cancel(ctx, cd); -out: - spin_unlock(&ctx->completion_lock); - return ret; -} - -#define CANCEL_FLAGS (IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \ - IORING_ASYNC_CANCEL_ANY) - -static int io_async_cancel_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - if (unlikely(req->flags & REQ_F_BUFFER_SELECT)) - return -EINVAL; - if (sqe->off || sqe->len || sqe->splice_fd_in) - return -EINVAL; - - req->cancel.addr = READ_ONCE(sqe->addr); - req->cancel.flags = READ_ONCE(sqe->cancel_flags); - if (req->cancel.flags & ~CANCEL_FLAGS) - return -EINVAL; - if (req->cancel.flags & IORING_ASYNC_CANCEL_FD) { - if (req->cancel.flags & IORING_ASYNC_CANCEL_ANY) - return -EINVAL; - req->cancel.fd = READ_ONCE(sqe->fd); - } - - return 0; -} - -static int __io_async_cancel(struct io_cancel_data *cd, struct io_kiocb *req, - unsigned int issue_flags) -{ - bool all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); - struct io_ring_ctx *ctx = cd->ctx; - struct io_tctx_node *node; - int ret, nr = 0; - - do { - ret = io_try_cancel(req, cd); - if (ret == -ENOENT) - break; - if (!all) - return ret; - nr++; - } while (1); - - /* slow path, try all io-wq's */ - io_ring_submit_lock(ctx, issue_flags); - ret = -ENOENT; - list_for_each_entry(node, &ctx->tctx_list, ctx_node) { - struct io_uring_task *tctx = node->task->io_uring; - - ret = io_async_cancel_one(tctx, cd); - if (ret != -ENOENT) { - if (!all) - break; - nr++; - } - } - io_ring_submit_unlock(ctx, issue_flags); - return all ? nr : ret; -} - -static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_cancel_data cd = { - .ctx = req->ctx, - .data = req->cancel.addr, - .flags = req->cancel.flags, - .seq = atomic_inc_return(&req->ctx->cancel_seq), - }; - int ret; - - if (cd.flags & IORING_ASYNC_CANCEL_FD) { - if (req->flags & REQ_F_FIXED_FILE) - req->file = io_file_get_fixed(req, req->cancel.fd, - issue_flags); - else - req->file = io_file_get_normal(req, req->cancel.fd); - if (!req->file) { - ret = -EBADF; - goto done; - } - cd.file = req->file; - } - - ret = __io_async_cancel(&cd, req, issue_flags); -done: - if (ret < 0) - req_set_fail(req); - io_req_complete_post(req, ret, 0); - return 0; -} - -static int io_files_update_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) - return -EINVAL; - if (sqe->rw_flags || sqe->splice_fd_in) - return -EINVAL; - - req->rsrc_update.offset = READ_ONCE(sqe->off); - req->rsrc_update.nr_args = READ_ONCE(sqe->len); - if (!req->rsrc_update.nr_args) - return -EINVAL; - req->rsrc_update.arg = READ_ONCE(sqe->addr); - return 0; -} - -static int io_files_update_with_index_alloc(struct io_kiocb *req, - unsigned int issue_flags) -{ - __s32 __user *fds = u64_to_user_ptr(req->rsrc_update.arg); - unsigned int done; - struct file *file; - int ret, fd; - - if (!req->ctx->file_data) - return -ENXIO; - - for (done = 0; done < req->rsrc_update.nr_args; done++) { - if (copy_from_user(&fd, &fds[done], sizeof(fd))) { - ret = -EFAULT; - break; - } - - file = fget(fd); - if (!file) { - ret = -EBADF; - break; - } - ret = io_fixed_fd_install(req, issue_flags, file, - IORING_FILE_INDEX_ALLOC); - if (ret < 0) - break; - if (copy_to_user(&fds[done], &ret, sizeof(ret))) { - __io_close_fixed(req, issue_flags, ret); - ret = -EFAULT; - break; - } - } - - if (done) - return done; - return ret; -} - -static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_uring_rsrc_update2 up; - int ret; - - up.offset = req->rsrc_update.offset; - up.data = req->rsrc_update.arg; - up.nr = 0; - up.tags = 0; - up.resv = 0; - up.resv2 = 0; - - if (req->rsrc_update.offset == IORING_FILE_INDEX_ALLOC) { - ret = io_files_update_with_index_alloc(req, issue_flags); - } else { - io_ring_submit_lock(ctx, issue_flags); - ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, - &up, req->rsrc_update.nr_args); - io_ring_submit_unlock(ctx, issue_flags); - } - - if (ret < 0) - req_set_fail(req); - __io_req_complete(req, issue_flags, ret, 0); - return 0; -} - -static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - switch (req->opcode) { - case IORING_OP_NOP: - return io_nop_prep(req, sqe); - case IORING_OP_READV: - case IORING_OP_READ_FIXED: - case IORING_OP_READ: - case IORING_OP_WRITEV: - case IORING_OP_WRITE_FIXED: - case IORING_OP_WRITE: - return io_prep_rw(req, sqe); - case IORING_OP_POLL_ADD: - return io_poll_add_prep(req, sqe); - case IORING_OP_POLL_REMOVE: - return io_poll_remove_prep(req, sqe); - case IORING_OP_FSYNC: - return io_fsync_prep(req, sqe); - case IORING_OP_SYNC_FILE_RANGE: - return io_sfr_prep(req, sqe); - case IORING_OP_SENDMSG: - case IORING_OP_SEND: - return io_sendmsg_prep(req, sqe); - case IORING_OP_RECVMSG: - case IORING_OP_RECV: - return io_recvmsg_prep(req, sqe); - case IORING_OP_CONNECT: - return io_connect_prep(req, sqe); - case IORING_OP_TIMEOUT: - return io_timeout_prep(req, sqe); - case IORING_OP_TIMEOUT_REMOVE: - return io_timeout_remove_prep(req, sqe); - case IORING_OP_ASYNC_CANCEL: - return io_async_cancel_prep(req, sqe); - case IORING_OP_LINK_TIMEOUT: - return io_link_timeout_prep(req, sqe); - case IORING_OP_ACCEPT: - return io_accept_prep(req, sqe); - case IORING_OP_FALLOCATE: - return io_fallocate_prep(req, sqe); - case IORING_OP_OPENAT: - return io_openat_prep(req, sqe); - case IORING_OP_CLOSE: - return io_close_prep(req, sqe); - case IORING_OP_FILES_UPDATE: - return io_files_update_prep(req, sqe); - case IORING_OP_STATX: - return io_statx_prep(req, sqe); - case IORING_OP_FADVISE: - return io_fadvise_prep(req, sqe); - case IORING_OP_MADVISE: - return io_madvise_prep(req, sqe); - case IORING_OP_OPENAT2: - return io_openat2_prep(req, sqe); - case IORING_OP_EPOLL_CTL: - return io_epoll_ctl_prep(req, sqe); - case IORING_OP_SPLICE: - return io_splice_prep(req, sqe); - case IORING_OP_PROVIDE_BUFFERS: - return io_provide_buffers_prep(req, sqe); - case IORING_OP_REMOVE_BUFFERS: - return io_remove_buffers_prep(req, sqe); - case IORING_OP_TEE: - return io_tee_prep(req, sqe); - case IORING_OP_SHUTDOWN: - return io_shutdown_prep(req, sqe); - case IORING_OP_RENAMEAT: - return io_renameat_prep(req, sqe); - case IORING_OP_UNLINKAT: - return io_unlinkat_prep(req, sqe); - case IORING_OP_MKDIRAT: - return io_mkdirat_prep(req, sqe); - case IORING_OP_SYMLINKAT: - return io_symlinkat_prep(req, sqe); - case IORING_OP_LINKAT: - return io_linkat_prep(req, sqe); - case IORING_OP_MSG_RING: - return io_msg_ring_prep(req, sqe); - case IORING_OP_FSETXATTR: - return io_fsetxattr_prep(req, sqe); - case IORING_OP_SETXATTR: - return io_setxattr_prep(req, sqe); - case IORING_OP_FGETXATTR: - return io_fgetxattr_prep(req, sqe); - case IORING_OP_GETXATTR: - return io_getxattr_prep(req, sqe); - case IORING_OP_SOCKET: - return io_socket_prep(req, sqe); - case IORING_OP_URING_CMD: - return io_uring_cmd_prep(req, sqe); - } - - printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", - req->opcode); - return -EINVAL; -} - -static int io_req_prep_async(struct io_kiocb *req) -{ - const struct io_op_def *def = &io_op_defs[req->opcode]; - - /* assign early for deferred execution for non-fixed file */ - if (def->needs_file && !(req->flags & REQ_F_FIXED_FILE)) - req->file = io_file_get_normal(req, req->cqe.fd); - if (!def->needs_async_setup) - return 0; - if (WARN_ON_ONCE(req_has_async_data(req))) - return -EFAULT; - if (io_alloc_async_data(req)) - return -EAGAIN; - - switch (req->opcode) { - case IORING_OP_READV: - return io_readv_prep_async(req); - case IORING_OP_WRITEV: - return io_writev_prep_async(req); - case IORING_OP_SENDMSG: - return io_sendmsg_prep_async(req); - case IORING_OP_RECVMSG: - return io_recvmsg_prep_async(req); - case IORING_OP_CONNECT: - return io_connect_prep_async(req); - case IORING_OP_URING_CMD: - return io_uring_cmd_prep_async(req); - } - printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n", - req->opcode); - return -EFAULT; -} - -static u32 io_get_sequence(struct io_kiocb *req) -{ - u32 seq = req->ctx->cached_sq_head; - struct io_kiocb *cur; - - /* need original cached_sq_head, but it was increased for each req */ - io_for_each_link(cur, req) - seq--; - return seq; -} - -static __cold void io_drain_req(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_defer_entry *de; - int ret; - u32 seq = io_get_sequence(req); - - /* Still need defer if there is pending req in defer list. */ - spin_lock(&ctx->completion_lock); - if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) { - spin_unlock(&ctx->completion_lock); -queue: - ctx->drain_active = false; - io_req_task_queue(req); - return; - } - spin_unlock(&ctx->completion_lock); - - ret = io_req_prep_async(req); - if (ret) { -fail: - io_req_complete_failed(req, ret); - return; - } - io_prep_async_link(req); - de = kmalloc(sizeof(*de), GFP_KERNEL); - if (!de) { - ret = -ENOMEM; - goto fail; - } - - spin_lock(&ctx->completion_lock); - if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) { - spin_unlock(&ctx->completion_lock); - kfree(de); - goto queue; - } - - trace_io_uring_defer(ctx, req, req->cqe.user_data, req->opcode); - de->req = req; - de->seq = seq; - list_add_tail(&de->list, &ctx->defer_list); - spin_unlock(&ctx->completion_lock); -} - -static void io_clean_op(struct io_kiocb *req) -{ - if (req->flags & REQ_F_BUFFER_SELECTED) { - spin_lock(&req->ctx->completion_lock); - io_put_kbuf_comp(req); - spin_unlock(&req->ctx->completion_lock); - } - - if (req->flags & REQ_F_NEED_CLEANUP) { - switch (req->opcode) { - case IORING_OP_READV: - case IORING_OP_READ_FIXED: - case IORING_OP_READ: - case IORING_OP_WRITEV: - case IORING_OP_WRITE_FIXED: - case IORING_OP_WRITE: { - struct io_async_rw *io = req->async_data; - - kfree(io->free_iovec); - break; - } - case IORING_OP_RECVMSG: - case IORING_OP_SENDMSG: { - struct io_async_msghdr *io = req->async_data; - - kfree(io->free_iov); - break; - } - case IORING_OP_OPENAT: - case IORING_OP_OPENAT2: - if (req->open.filename) - putname(req->open.filename); - break; - case IORING_OP_RENAMEAT: - putname(req->rename.oldpath); - putname(req->rename.newpath); - break; - case IORING_OP_UNLINKAT: - putname(req->unlink.filename); - break; - case IORING_OP_MKDIRAT: - putname(req->mkdir.filename); - break; - case IORING_OP_SYMLINKAT: - putname(req->symlink.oldpath); - putname(req->symlink.newpath); - break; - case IORING_OP_LINKAT: - putname(req->hardlink.oldpath); - putname(req->hardlink.newpath); - break; - case IORING_OP_STATX: - if (req->statx.filename) - putname(req->statx.filename); - break; - case IORING_OP_SETXATTR: - case IORING_OP_FSETXATTR: - case IORING_OP_GETXATTR: - case IORING_OP_FGETXATTR: - __io_xattr_finish(req); - break; - } - } - if ((req->flags & REQ_F_POLLED) && req->apoll) { - kfree(req->apoll->double_poll); - kfree(req->apoll); - req->apoll = NULL; - } - if (req->flags & REQ_F_INFLIGHT) { - struct io_uring_task *tctx = req->task->io_uring; - - atomic_dec(&tctx->inflight_tracked); - } - if (req->flags & REQ_F_CREDS) - put_cred(req->creds); - if (req->flags & REQ_F_ASYNC_DATA) { - kfree(req->async_data); - req->async_data = NULL; - } - req->flags &= ~IO_REQ_CLEAN_FLAGS; -} - -static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags) -{ - if (req->file || !io_op_defs[req->opcode].needs_file) - return true; - - if (req->flags & REQ_F_FIXED_FILE) - req->file = io_file_get_fixed(req, req->cqe.fd, issue_flags); - else - req->file = io_file_get_normal(req, req->cqe.fd); - - return !!req->file; -} - -static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) -{ - const struct io_op_def *def = &io_op_defs[req->opcode]; - const struct cred *creds = NULL; - int ret; - - if (unlikely(!io_assign_file(req, issue_flags))) - return -EBADF; - - if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred())) - creds = override_creds(req->creds); - - if (!def->audit_skip) - audit_uring_entry(req->opcode); - - switch (req->opcode) { - case IORING_OP_NOP: - ret = io_nop(req, issue_flags); - break; - case IORING_OP_READV: - case IORING_OP_READ_FIXED: - case IORING_OP_READ: - ret = io_read(req, issue_flags); - break; - case IORING_OP_WRITEV: - case IORING_OP_WRITE_FIXED: - case IORING_OP_WRITE: - ret = io_write(req, issue_flags); - break; - case IORING_OP_FSYNC: - ret = io_fsync(req, issue_flags); - break; - case IORING_OP_POLL_ADD: - ret = io_poll_add(req, issue_flags); - break; - case IORING_OP_POLL_REMOVE: - ret = io_poll_remove(req, issue_flags); - break; - case IORING_OP_SYNC_FILE_RANGE: - ret = io_sync_file_range(req, issue_flags); - break; - case IORING_OP_SENDMSG: - ret = io_sendmsg(req, issue_flags); - break; - case IORING_OP_SEND: - ret = io_send(req, issue_flags); - break; - case IORING_OP_RECVMSG: - ret = io_recvmsg(req, issue_flags); - break; - case IORING_OP_RECV: - ret = io_recv(req, issue_flags); - break; - case IORING_OP_TIMEOUT: - ret = io_timeout(req, issue_flags); - break; - case IORING_OP_TIMEOUT_REMOVE: - ret = io_timeout_remove(req, issue_flags); - break; - case IORING_OP_ACCEPT: - ret = io_accept(req, issue_flags); - break; - case IORING_OP_CONNECT: - ret = io_connect(req, issue_flags); - break; - case IORING_OP_ASYNC_CANCEL: - ret = io_async_cancel(req, issue_flags); - break; - case IORING_OP_FALLOCATE: - ret = io_fallocate(req, issue_flags); - break; - case IORING_OP_OPENAT: - ret = io_openat(req, issue_flags); - break; - case IORING_OP_CLOSE: - ret = io_close(req, issue_flags); - break; - case IORING_OP_FILES_UPDATE: - ret = io_files_update(req, issue_flags); - break; - case IORING_OP_STATX: - ret = io_statx(req, issue_flags); - break; - case IORING_OP_FADVISE: - ret = io_fadvise(req, issue_flags); - break; - case IORING_OP_MADVISE: - ret = io_madvise(req, issue_flags); - break; - case IORING_OP_OPENAT2: - ret = io_openat2(req, issue_flags); - break; - case IORING_OP_EPOLL_CTL: - ret = io_epoll_ctl(req, issue_flags); - break; - case IORING_OP_SPLICE: - ret = io_splice(req, issue_flags); - break; - case IORING_OP_PROVIDE_BUFFERS: - ret = io_provide_buffers(req, issue_flags); - break; - case IORING_OP_REMOVE_BUFFERS: - ret = io_remove_buffers(req, issue_flags); - break; - case IORING_OP_TEE: - ret = io_tee(req, issue_flags); - break; - case IORING_OP_SHUTDOWN: - ret = io_shutdown(req, issue_flags); - break; - case IORING_OP_RENAMEAT: - ret = io_renameat(req, issue_flags); - break; - case IORING_OP_UNLINKAT: - ret = io_unlinkat(req, issue_flags); - break; - case IORING_OP_MKDIRAT: - ret = io_mkdirat(req, issue_flags); - break; - case IORING_OP_SYMLINKAT: - ret = io_symlinkat(req, issue_flags); - break; - case IORING_OP_LINKAT: - ret = io_linkat(req, issue_flags); - break; - case IORING_OP_MSG_RING: - ret = io_msg_ring(req, issue_flags); - break; - case IORING_OP_FSETXATTR: - ret = io_fsetxattr(req, issue_flags); - break; - case IORING_OP_SETXATTR: - ret = io_setxattr(req, issue_flags); - break; - case IORING_OP_FGETXATTR: - ret = io_fgetxattr(req, issue_flags); - break; - case IORING_OP_GETXATTR: - ret = io_getxattr(req, issue_flags); - break; - case IORING_OP_SOCKET: - ret = io_socket(req, issue_flags); - break; - case IORING_OP_URING_CMD: - ret = io_uring_cmd(req, issue_flags); - break; - default: - ret = -EINVAL; - break; - } - - if (!def->audit_skip) - audit_uring_exit(!ret, ret); - - if (creds) - revert_creds(creds); - if (ret) - return ret; - /* If the op doesn't have a file, we're not polling for it */ - if ((req->ctx->flags & IORING_SETUP_IOPOLL) && req->file) - io_iopoll_req_issued(req, issue_flags); - - return 0; -} - -static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) -{ - struct io_kiocb *req = container_of(work, struct io_kiocb, work); - - req = io_put_req_find_next(req); - return req ? &req->work : NULL; -} - -static void io_wq_submit_work(struct io_wq_work *work) -{ - struct io_kiocb *req = container_of(work, struct io_kiocb, work); - const struct io_op_def *def = &io_op_defs[req->opcode]; - unsigned int issue_flags = IO_URING_F_UNLOCKED; - bool needs_poll = false; - int ret = 0, err = -ECANCELED; - - /* one will be dropped by ->io_free_work() after returning to io-wq */ - if (!(req->flags & REQ_F_REFCOUNT)) - __io_req_set_refcount(req, 2); - else - req_ref_get(req); - - io_arm_ltimeout(req); - - /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ - if (work->flags & IO_WQ_WORK_CANCEL) { -fail: - io_req_task_queue_fail(req, err); - return; - } - if (!io_assign_file(req, issue_flags)) { - err = -EBADF; - work->flags |= IO_WQ_WORK_CANCEL; - goto fail; - } - - if (req->flags & REQ_F_FORCE_ASYNC) { - bool opcode_poll = def->pollin || def->pollout; - - if (opcode_poll && file_can_poll(req->file)) { - needs_poll = true; - issue_flags |= IO_URING_F_NONBLOCK; - } - } - - do { - ret = io_issue_sqe(req, issue_flags); - if (ret != -EAGAIN) - break; - /* - * We can get EAGAIN for iopolled IO even though we're - * forcing a sync submission from here, since we can't - * wait for request slots on the block side. - */ - if (!needs_poll) { - if (!(req->ctx->flags & IORING_SETUP_IOPOLL)) - break; - cond_resched(); - continue; - } - - if (io_arm_poll_handler(req, issue_flags) == IO_APOLL_OK) - return; - /* aborted or ready, in either case retry blocking */ - needs_poll = false; - issue_flags &= ~IO_URING_F_NONBLOCK; - } while (1); - - /* avoid locking problems by failing it from a clean context */ - if (ret) - io_req_task_queue_fail(req, ret); -} - -static inline struct io_fixed_file *io_fixed_file_slot(struct io_file_table *table, - unsigned i) -{ - return &table->files[i]; -} - -static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, - int index) -{ - struct io_fixed_file *slot = io_fixed_file_slot(&ctx->file_table, index); - - return (struct file *) (slot->file_ptr & FFS_MASK); -} - -static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file) -{ - unsigned long file_ptr = (unsigned long) file; - - file_ptr |= io_file_get_flags(file); - file_slot->file_ptr = file_ptr; -} - -static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, - unsigned int issue_flags) -{ - struct io_ring_ctx *ctx = req->ctx; - struct file *file = NULL; - unsigned long file_ptr; - - io_ring_submit_lock(ctx, issue_flags); - - if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - goto out; - fd = array_index_nospec(fd, ctx->nr_user_files); - file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; - file = (struct file *) (file_ptr & FFS_MASK); - file_ptr &= ~FFS_MASK; - /* mask in overlapping REQ_F and FFS bits */ - req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT); - io_req_set_rsrc_node(req, ctx, 0); - WARN_ON_ONCE(file && !test_bit(fd, ctx->file_table.bitmap)); -out: - io_ring_submit_unlock(ctx, issue_flags); - return file; -} - -static struct file *io_file_get_normal(struct io_kiocb *req, int fd) -{ - struct file *file = fget(fd); - - trace_io_uring_file_get(req->ctx, req, req->cqe.user_data, fd); - - /* we don't allow fixed io_uring files */ - if (file && file->f_op == &io_uring_fops) - io_req_track_inflight(req); - return file; -} - -static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) -{ - struct io_kiocb *prev = req->timeout.prev; - int ret = -ENOENT; - - if (prev) { - if (!(req->task->flags & PF_EXITING)) { - struct io_cancel_data cd = { - .ctx = req->ctx, - .data = prev->cqe.user_data, - }; - - ret = io_try_cancel(req, &cd); - } - io_req_complete_post(req, ret ?: -ETIME, 0); - io_put_req(prev); - } else { - io_req_complete_post(req, -ETIME, 0); - } -} - -static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) -{ - struct io_timeout_data *data = container_of(timer, - struct io_timeout_data, timer); - struct io_kiocb *prev, *req = data->req; - struct io_ring_ctx *ctx = req->ctx; - unsigned long flags; - - spin_lock_irqsave(&ctx->timeout_lock, flags); - prev = req->timeout.head; - req->timeout.head = NULL; - - /* - * We don't expect the list to be empty, that will only happen if we - * race with the completion of the linked work. - */ - if (prev) { - io_remove_next_linked(prev); - if (!req_ref_inc_not_zero(prev)) - prev = NULL; - } - list_del(&req->timeout.list); - req->timeout.prev = prev; - spin_unlock_irqrestore(&ctx->timeout_lock, flags); - - req->io_task_work.func = io_req_task_link_timeout; - io_req_task_work_add(req); - return HRTIMER_NORESTART; -} - -static void io_queue_linked_timeout(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - - spin_lock_irq(&ctx->timeout_lock); - /* - * If the back reference is NULL, then our linked request finished - * before we got a chance to setup the timer - */ - if (req->timeout.head) { - struct io_timeout_data *data = req->async_data; - - data->timer.function = io_link_timeout_fn; - hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), - data->mode); - list_add_tail(&req->timeout.list, &ctx->ltimeout_list); - } - spin_unlock_irq(&ctx->timeout_lock); - /* drop submission reference */ - io_put_req(req); -} - -static void io_queue_async(struct io_kiocb *req, int ret) - __must_hold(&req->ctx->uring_lock) -{ - struct io_kiocb *linked_timeout; - - if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) { - io_req_complete_failed(req, ret); - return; - } - - linked_timeout = io_prep_linked_timeout(req); - - switch (io_arm_poll_handler(req, 0)) { - case IO_APOLL_READY: - io_req_task_queue(req); - break; - case IO_APOLL_ABORTED: - /* - * Queued up for async execution, worker will release - * submit reference when the iocb is actually submitted. - */ - io_kbuf_recycle(req, 0); - io_queue_iowq(req, NULL); - break; - case IO_APOLL_OK: - break; - } - - if (linked_timeout) - io_queue_linked_timeout(linked_timeout); -} - -static inline void io_queue_sqe(struct io_kiocb *req) - __must_hold(&req->ctx->uring_lock) -{ - int ret; - - ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); - - if (req->flags & REQ_F_COMPLETE_INLINE) { - io_req_add_compl_list(req); - return; - } - /* - * We async punt it if the file wasn't marked NOWAIT, or if the file - * doesn't support non-blocking read/write attempts - */ - if (likely(!ret)) - io_arm_ltimeout(req); - else - io_queue_async(req, ret); -} - -static void io_queue_sqe_fallback(struct io_kiocb *req) - __must_hold(&req->ctx->uring_lock) -{ - if (unlikely(req->flags & REQ_F_FAIL)) { - /* - * We don't submit, fail them all, for that replace hardlinks - * with normal links. Extra REQ_F_LINK is tolerated. - */ - req->flags &= ~REQ_F_HARDLINK; - req->flags |= REQ_F_LINK; - io_req_complete_failed(req, req->cqe.res); - } else if (unlikely(req->ctx->drain_active)) { - io_drain_req(req); - } else { - int ret = io_req_prep_async(req); - - if (unlikely(ret)) - io_req_complete_failed(req, ret); - else - io_queue_iowq(req, NULL); - } -} - -/* - * Check SQE restrictions (opcode and flags). - * - * Returns 'true' if SQE is allowed, 'false' otherwise. - */ -static inline bool io_check_restriction(struct io_ring_ctx *ctx, - struct io_kiocb *req, - unsigned int sqe_flags) -{ - if (!test_bit(req->opcode, ctx->restrictions.sqe_op)) - return false; - - if ((sqe_flags & ctx->restrictions.sqe_flags_required) != - ctx->restrictions.sqe_flags_required) - return false; - - if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed | - ctx->restrictions.sqe_flags_required)) - return false; - - return true; -} - -static void io_init_req_drain(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_kiocb *head = ctx->submit_state.link.head; - - ctx->drain_active = true; - if (head) { - /* - * If we need to drain a request in the middle of a link, drain - * the head request and the next request/link after the current - * link. Considering sequential execution of links, - * REQ_F_IO_DRAIN will be maintained for every request of our - * link. - */ - head->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC; - ctx->drain_next = true; - } -} - -static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct io_uring_sqe *sqe) - __must_hold(&ctx->uring_lock) -{ - const struct io_op_def *def; - unsigned int sqe_flags; - int personality; - u8 opcode; - - /* req is partially pre-initialised, see io_preinit_req() */ - req->opcode = opcode = READ_ONCE(sqe->opcode); - /* same numerical values with corresponding REQ_F_*, safe to copy */ - req->flags = sqe_flags = READ_ONCE(sqe->flags); - req->cqe.user_data = READ_ONCE(sqe->user_data); - req->file = NULL; - req->rsrc_node = NULL; - req->task = current; - - if (unlikely(opcode >= IORING_OP_LAST)) { - req->opcode = 0; - return -EINVAL; - } - def = &io_op_defs[opcode]; - if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) { - /* enforce forwards compatibility on users */ - if (sqe_flags & ~SQE_VALID_FLAGS) - return -EINVAL; - if (sqe_flags & IOSQE_BUFFER_SELECT) { - if (!def->buffer_select) - return -EOPNOTSUPP; - req->buf_index = READ_ONCE(sqe->buf_group); - } - if (sqe_flags & IOSQE_CQE_SKIP_SUCCESS) - ctx->drain_disabled = true; - if (sqe_flags & IOSQE_IO_DRAIN) { - if (ctx->drain_disabled) - return -EOPNOTSUPP; - io_init_req_drain(req); - } - } - if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) { - if (ctx->restricted && !io_check_restriction(ctx, req, sqe_flags)) - return -EACCES; - /* knock it to the slow queue path, will be drained there */ - if (ctx->drain_active) - req->flags |= REQ_F_FORCE_ASYNC; - /* if there is no link, we're at "next" request and need to drain */ - if (unlikely(ctx->drain_next) && !ctx->submit_state.link.head) { - ctx->drain_next = false; - ctx->drain_active = true; - req->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC; - } - } - - if (!def->ioprio && sqe->ioprio) - return -EINVAL; - if (!def->iopoll && (ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - - if (def->needs_file) { - struct io_submit_state *state = &ctx->submit_state; - - req->cqe.fd = READ_ONCE(sqe->fd); - - /* - * Plug now if we have more than 2 IO left after this, and the - * target is potentially a read/write to block based storage. - */ - if (state->need_plug && def->plug) { - state->plug_started = true; - state->need_plug = false; - blk_start_plug_nr_ios(&state->plug, state->submit_nr); - } - } - - personality = READ_ONCE(sqe->personality); - if (personality) { - int ret; - - req->creds = xa_load(&ctx->personalities, personality); - if (!req->creds) - return -EINVAL; - get_cred(req->creds); - ret = security_uring_override_creds(req->creds); - if (ret) { - put_cred(req->creds); - return ret; - } - req->flags |= REQ_F_CREDS; - } - - return io_req_prep(req, sqe); -} - -static __cold int io_submit_fail_init(const struct io_uring_sqe *sqe, - struct io_kiocb *req, int ret) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_submit_link *link = &ctx->submit_state.link; - struct io_kiocb *head = link->head; - - trace_io_uring_req_failed(sqe, ctx, req, ret); - - /* - * Avoid breaking links in the middle as it renders links with SQPOLL - * unusable. Instead of failing eagerly, continue assembling the link if - * applicable and mark the head with REQ_F_FAIL. The link flushing code - * should find the flag and handle the rest. - */ - req_fail_link_node(req, ret); - if (head && !(head->flags & REQ_F_FAIL)) - req_fail_link_node(head, -ECANCELED); - - if (!(req->flags & IO_REQ_LINK_FLAGS)) { - if (head) { - link->last->link = req; - link->head = NULL; - req = head; - } - io_queue_sqe_fallback(req); - return ret; - } - - if (head) - link->last->link = req; - else - link->head = req; - link->last = req; - return 0; -} - -static inline int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct io_uring_sqe *sqe) - __must_hold(&ctx->uring_lock) -{ - struct io_submit_link *link = &ctx->submit_state.link; - int ret; - - ret = io_init_req(ctx, req, sqe); - if (unlikely(ret)) - return io_submit_fail_init(sqe, req, ret); - - /* don't need @sqe from now on */ - trace_io_uring_submit_sqe(ctx, req, req->cqe.user_data, req->opcode, - req->flags, true, - ctx->flags & IORING_SETUP_SQPOLL); - - /* - * If we already have a head request, queue this one for async - * submittal once the head completes. If we don't have a head but - * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be - * submitted sync once the chain is complete. If none of those - * conditions are true (normal request), then just queue it. - */ - if (unlikely(link->head)) { - ret = io_req_prep_async(req); - if (unlikely(ret)) - return io_submit_fail_init(sqe, req, ret); - - trace_io_uring_link(ctx, req, link->head); - link->last->link = req; - link->last = req; - - if (req->flags & IO_REQ_LINK_FLAGS) - return 0; - /* last request of the link, flush it */ - req = link->head; - link->head = NULL; - if (req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)) - goto fallback; - - } else if (unlikely(req->flags & (IO_REQ_LINK_FLAGS | - REQ_F_FORCE_ASYNC | REQ_F_FAIL))) { - if (req->flags & IO_REQ_LINK_FLAGS) { - link->head = req; - link->last = req; - } else { -fallback: - io_queue_sqe_fallback(req); - } - return 0; - } - - io_queue_sqe(req); - return 0; -} - -/* - * Batched submission is done, ensure local IO is flushed out. - */ -static void io_submit_state_end(struct io_ring_ctx *ctx) -{ - struct io_submit_state *state = &ctx->submit_state; - - if (unlikely(state->link.head)) - io_queue_sqe_fallback(state->link.head); - /* flush only after queuing links as they can generate completions */ - io_submit_flush_completions(ctx); - if (state->plug_started) - blk_finish_plug(&state->plug); -} - -/* - * Start submission side cache. - */ -static void io_submit_state_start(struct io_submit_state *state, - unsigned int max_ios) -{ - state->plug_started = false; - state->need_plug = max_ios > 2; - state->submit_nr = max_ios; - /* set only head, no need to init link_last in advance */ - state->link.head = NULL; -} - -static void io_commit_sqring(struct io_ring_ctx *ctx) -{ - struct io_rings *rings = ctx->rings; - - /* - * Ensure any loads from the SQEs are done at this point, - * since once we write the new head, the application could - * write new data to them. - */ - smp_store_release(&rings->sq.head, ctx->cached_sq_head); -} - -/* - * Fetch an sqe, if one is available. Note this returns a pointer to memory - * that is mapped by userspace. This means that care needs to be taken to - * ensure that reads are stable, as we cannot rely on userspace always - * being a good citizen. If members of the sqe are validated and then later - * used, it's important that those reads are done through READ_ONCE() to - * prevent a re-load down the line. - */ -static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) -{ - unsigned head, mask = ctx->sq_entries - 1; - unsigned sq_idx = ctx->cached_sq_head++ & mask; - - /* - * The cached sq head (or cq tail) serves two purposes: - * - * 1) allows us to batch the cost of updating the user visible - * head updates. - * 2) allows the kernel side to track the head on its own, even - * though the application is the one updating it. - */ - head = READ_ONCE(ctx->sq_array[sq_idx]); - if (likely(head < ctx->sq_entries)) { - /* double index for 128-byte SQEs, twice as long */ - if (ctx->flags & IORING_SETUP_SQE128) - head <<= 1; - return &ctx->sq_sqes[head]; - } - - /* drop invalid entries */ - ctx->cq_extra--; - WRITE_ONCE(ctx->rings->sq_dropped, - READ_ONCE(ctx->rings->sq_dropped) + 1); - return NULL; -} - -static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) - __must_hold(&ctx->uring_lock) -{ - unsigned int entries = io_sqring_entries(ctx); - unsigned int left; - int ret; - - if (unlikely(!entries)) - return 0; - /* make sure SQ entry isn't read before tail */ - ret = left = min3(nr, ctx->sq_entries, entries); - io_get_task_refs(left); - io_submit_state_start(&ctx->submit_state, left); - - do { - const struct io_uring_sqe *sqe; - struct io_kiocb *req; - - if (unlikely(!io_alloc_req_refill(ctx))) - break; - req = io_alloc_req(ctx); - sqe = io_get_sqe(ctx); - if (unlikely(!sqe)) { - io_req_add_to_cache(req, ctx); - break; - } - - /* - * Continue submitting even for sqe failure if the - * ring was setup with IORING_SETUP_SUBMIT_ALL - */ - if (unlikely(io_submit_sqe(ctx, req, sqe)) && - !(ctx->flags & IORING_SETUP_SUBMIT_ALL)) { - left--; - break; - } - } while (--left); - - if (unlikely(left)) { - ret -= left; - /* try again if it submitted nothing and can't allocate a req */ - if (!ret && io_req_cache_empty(ctx)) - ret = -EAGAIN; - current->io_uring->cached_refs += left; - } - - io_submit_state_end(ctx); - /* Commit SQ ring head once we've consumed and submitted all SQEs */ - io_commit_sqring(ctx); - return ret; -} - -static inline bool io_sqd_events_pending(struct io_sq_data *sqd) -{ - return READ_ONCE(sqd->state); -} - -static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) -{ - unsigned int to_submit; - int ret = 0; - - to_submit = io_sqring_entries(ctx); - /* if we're handling multiple rings, cap submit size for fairness */ - if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE) - to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE; - - if (!wq_list_empty(&ctx->iopoll_list) || to_submit) { - const struct cred *creds = NULL; - - if (ctx->sq_creds != current_cred()) - creds = override_creds(ctx->sq_creds); - - mutex_lock(&ctx->uring_lock); - if (!wq_list_empty(&ctx->iopoll_list)) - io_do_iopoll(ctx, true); - - /* - * Don't submit if refs are dying, good for io_uring_register(), - * but also it is relied upon by io_ring_exit_work() - */ - if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) && - !(ctx->flags & IORING_SETUP_R_DISABLED)) - ret = io_submit_sqes(ctx, to_submit); - mutex_unlock(&ctx->uring_lock); - - if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) - wake_up(&ctx->sqo_sq_wait); - if (creds) - revert_creds(creds); - } - - return ret; -} - -static __cold void io_sqd_update_thread_idle(struct io_sq_data *sqd) -{ - struct io_ring_ctx *ctx; - unsigned sq_thread_idle = 0; - - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) - sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle); - sqd->sq_thread_idle = sq_thread_idle; -} - -static bool io_sqd_handle_event(struct io_sq_data *sqd) -{ - bool did_sig = false; - struct ksignal ksig; - - if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) || - signal_pending(current)) { - mutex_unlock(&sqd->lock); - if (signal_pending(current)) - did_sig = get_signal(&ksig); - cond_resched(); - mutex_lock(&sqd->lock); - } - return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); -} - -static int io_sq_thread(void *data) -{ - struct io_sq_data *sqd = data; - struct io_ring_ctx *ctx; - unsigned long timeout = 0; - char buf[TASK_COMM_LEN]; - DEFINE_WAIT(wait); - - snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); - set_task_comm(current, buf); - - if (sqd->sq_cpu != -1) - set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu)); - else - set_cpus_allowed_ptr(current, cpu_online_mask); - current->flags |= PF_NO_SETAFFINITY; - - audit_alloc_kernel(current); - - mutex_lock(&sqd->lock); - while (1) { - bool cap_entries, sqt_spin = false; - - if (io_sqd_events_pending(sqd) || signal_pending(current)) { - if (io_sqd_handle_event(sqd)) - break; - timeout = jiffies + sqd->sq_thread_idle; - } - - cap_entries = !list_is_singular(&sqd->ctx_list); - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { - int ret = __io_sq_thread(ctx, cap_entries); - - if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list))) - sqt_spin = true; - } - if (io_run_task_work()) - sqt_spin = true; - - if (sqt_spin || !time_after(jiffies, timeout)) { - cond_resched(); - if (sqt_spin) - timeout = jiffies + sqd->sq_thread_idle; - continue; - } - - prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE); - if (!io_sqd_events_pending(sqd) && !task_work_pending(current)) { - bool needs_sched = true; - - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { - atomic_or(IORING_SQ_NEED_WAKEUP, - &ctx->rings->sq_flags); - if ((ctx->flags & IORING_SETUP_IOPOLL) && - !wq_list_empty(&ctx->iopoll_list)) { - needs_sched = false; - break; - } - - /* - * Ensure the store of the wakeup flag is not - * reordered with the load of the SQ tail - */ - smp_mb__after_atomic(); - - if (io_sqring_entries(ctx)) { - needs_sched = false; - break; - } - } - - if (needs_sched) { - mutex_unlock(&sqd->lock); - schedule(); - mutex_lock(&sqd->lock); - } - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) - atomic_andnot(IORING_SQ_NEED_WAKEUP, - &ctx->rings->sq_flags); - } - - finish_wait(&sqd->wait, &wait); - timeout = jiffies + sqd->sq_thread_idle; - } - - io_uring_cancel_generic(true, sqd); - sqd->thread = NULL; - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) - atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags); - io_run_task_work(); - mutex_unlock(&sqd->lock); - - audit_free(current); - - complete(&sqd->exited); - do_exit(0); -} - -struct io_wait_queue { - struct wait_queue_entry wq; - struct io_ring_ctx *ctx; - unsigned cq_tail; - unsigned nr_timeouts; -}; - -static inline bool io_should_wake(struct io_wait_queue *iowq) -{ - struct io_ring_ctx *ctx = iowq->ctx; - int dist = ctx->cached_cq_tail - (int) iowq->cq_tail; - - /* - * Wake up if we have enough events, or if a timeout occurred since we - * started waiting. For timeouts, we always want to return to userspace, - * regardless of event count. - */ - return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; -} - -static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, - int wake_flags, void *key) -{ - struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue, - wq); - - /* - * Cannot safely flush overflowed CQEs from here, ensure we wake up - * the task, and the next invocation will do it. - */ - if (io_should_wake(iowq) || - test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &iowq->ctx->check_cq)) - return autoremove_wake_function(curr, mode, wake_flags, key); - return -1; -} - -static int io_run_task_work_sig(void) -{ - if (io_run_task_work()) - return 1; - if (test_thread_flag(TIF_NOTIFY_SIGNAL)) - return -ERESTARTSYS; - if (task_sigpending(current)) - return -EINTR; - return 0; -} - -/* when returns >0, the caller should retry */ -static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, - struct io_wait_queue *iowq, - ktime_t timeout) -{ - int ret; - unsigned long check_cq; - - /* make sure we run task_work before checking for signals */ - ret = io_run_task_work_sig(); - if (ret || io_should_wake(iowq)) - return ret; - check_cq = READ_ONCE(ctx->check_cq); - /* let the caller flush overflows, retry */ - if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) - return 1; - if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))) - return -EBADR; - if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS)) - return -ETIME; - return 1; -} - -/* - * Wait until events become available, if we don't already have some. The - * application must reap them itself, as they reside on the shared cq ring. - */ -static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, - const sigset_t __user *sig, size_t sigsz, - struct __kernel_timespec __user *uts) -{ - struct io_wait_queue iowq; - struct io_rings *rings = ctx->rings; - ktime_t timeout = KTIME_MAX; - int ret; - - do { - io_cqring_overflow_flush(ctx); - if (io_cqring_events(ctx) >= min_events) - return 0; - if (!io_run_task_work()) - break; - } while (1); - - if (sig) { -#ifdef CONFIG_COMPAT - if (in_compat_syscall()) - ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig, - sigsz); - else -#endif - ret = set_user_sigmask(sig, sigsz); - - if (ret) - return ret; - } - - if (uts) { - struct timespec64 ts; - - if (get_timespec64(&ts, uts)) - return -EFAULT; - timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); - } - - init_waitqueue_func_entry(&iowq.wq, io_wake_function); - iowq.wq.private = current; - INIT_LIST_HEAD(&iowq.wq.entry); - iowq.ctx = ctx; - iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); - iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; - - trace_io_uring_cqring_wait(ctx, min_events); - do { - /* if we can't even flush overflow, don't wait for more */ - if (!io_cqring_overflow_flush(ctx)) { - ret = -EBUSY; - break; - } - prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, - TASK_INTERRUPTIBLE); - ret = io_cqring_wait_schedule(ctx, &iowq, timeout); - cond_resched(); - } while (ret > 0); - - finish_wait(&ctx->cq_wait, &iowq.wq); - restore_saved_sigmask_unless(ret == -EINTR); - - return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; -} - -static void io_free_page_table(void **table, size_t size) -{ - unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); - - for (i = 0; i < nr_tables; i++) - kfree(table[i]); - kfree(table); -} - -static __cold void **io_alloc_page_table(size_t size) -{ - unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); - size_t init_size = size; - void **table; - - table = kcalloc(nr_tables, sizeof(*table), GFP_KERNEL_ACCOUNT); - if (!table) - return NULL; - - for (i = 0; i < nr_tables; i++) { - unsigned int this_size = min_t(size_t, size, PAGE_SIZE); - - table[i] = kzalloc(this_size, GFP_KERNEL_ACCOUNT); - if (!table[i]) { - io_free_page_table(table, init_size); - return NULL; - } - size -= this_size; - } - return table; -} - -static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node) -{ - percpu_ref_exit(&ref_node->refs); - kfree(ref_node); -} - -static __cold void io_rsrc_node_ref_zero(struct percpu_ref *ref) -{ - struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs); - struct io_ring_ctx *ctx = node->rsrc_data->ctx; - unsigned long flags; - bool first_add = false; - unsigned long delay = HZ; - - spin_lock_irqsave(&ctx->rsrc_ref_lock, flags); - node->done = true; - - /* if we are mid-quiesce then do not delay */ - if (node->rsrc_data->quiesce) - delay = 0; - - while (!list_empty(&ctx->rsrc_ref_list)) { - node = list_first_entry(&ctx->rsrc_ref_list, - struct io_rsrc_node, node); - /* recycle ref nodes in order */ - if (!node->done) - break; - list_del(&node->node); - first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist); - } - spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags); - - if (first_add) - mod_delayed_work(system_wq, &ctx->rsrc_put_work, delay); -} - -static struct io_rsrc_node *io_rsrc_node_alloc(void) -{ - struct io_rsrc_node *ref_node; - - ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); - if (!ref_node) - return NULL; - - if (percpu_ref_init(&ref_node->refs, io_rsrc_node_ref_zero, - 0, GFP_KERNEL)) { - kfree(ref_node); - return NULL; - } - INIT_LIST_HEAD(&ref_node->node); - INIT_LIST_HEAD(&ref_node->rsrc_list); - ref_node->done = false; - return ref_node; -} - -static void io_rsrc_node_switch(struct io_ring_ctx *ctx, - struct io_rsrc_data *data_to_kill) - __must_hold(&ctx->uring_lock) -{ - WARN_ON_ONCE(!ctx->rsrc_backup_node); - WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node); - - io_rsrc_refs_drop(ctx); - - if (data_to_kill) { - struct io_rsrc_node *rsrc_node = ctx->rsrc_node; - - rsrc_node->rsrc_data = data_to_kill; - spin_lock_irq(&ctx->rsrc_ref_lock); - list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list); - spin_unlock_irq(&ctx->rsrc_ref_lock); - - atomic_inc(&data_to_kill->refs); - percpu_ref_kill(&rsrc_node->refs); - ctx->rsrc_node = NULL; - } - - if (!ctx->rsrc_node) { - ctx->rsrc_node = ctx->rsrc_backup_node; - ctx->rsrc_backup_node = NULL; - } -} - -static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx) -{ - if (ctx->rsrc_backup_node) - return 0; - ctx->rsrc_backup_node = io_rsrc_node_alloc(); - return ctx->rsrc_backup_node ? 0 : -ENOMEM; -} - -static __cold int io_rsrc_ref_quiesce(struct io_rsrc_data *data, - struct io_ring_ctx *ctx) -{ - int ret; - - /* As we may drop ->uring_lock, other task may have started quiesce */ - if (data->quiesce) - return -ENXIO; - - data->quiesce = true; - do { - ret = io_rsrc_node_switch_start(ctx); - if (ret) - break; - io_rsrc_node_switch(ctx, data); - - /* kill initial ref, already quiesced if zero */ - if (atomic_dec_and_test(&data->refs)) - break; - mutex_unlock(&ctx->uring_lock); - flush_delayed_work(&ctx->rsrc_put_work); - ret = wait_for_completion_interruptible(&data->done); - if (!ret) { - mutex_lock(&ctx->uring_lock); - if (atomic_read(&data->refs) > 0) { - /* - * it has been revived by another thread while - * we were unlocked - */ - mutex_unlock(&ctx->uring_lock); - } else { - break; - } - } - - atomic_inc(&data->refs); - /* wait for all works potentially completing data->done */ - flush_delayed_work(&ctx->rsrc_put_work); - reinit_completion(&data->done); - - ret = io_run_task_work_sig(); - mutex_lock(&ctx->uring_lock); - } while (ret >= 0); - data->quiesce = false; - - return ret; -} - -static u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx) -{ - unsigned int off = idx & IO_RSRC_TAG_TABLE_MASK; - unsigned int table_idx = idx >> IO_RSRC_TAG_TABLE_SHIFT; - - return &data->tags[table_idx][off]; -} - -static void io_rsrc_data_free(struct io_rsrc_data *data) -{ - size_t size = data->nr * sizeof(data->tags[0][0]); - - if (data->tags) - io_free_page_table((void **)data->tags, size); - kfree(data); -} - -static __cold int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put, - u64 __user *utags, unsigned nr, - struct io_rsrc_data **pdata) -{ - struct io_rsrc_data *data; - int ret = -ENOMEM; - unsigned i; - - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - return -ENOMEM; - data->tags = (u64 **)io_alloc_page_table(nr * sizeof(data->tags[0][0])); - if (!data->tags) { - kfree(data); - return -ENOMEM; - } - - data->nr = nr; - data->ctx = ctx; - data->do_put = do_put; - if (utags) { - ret = -EFAULT; - for (i = 0; i < nr; i++) { - u64 *tag_slot = io_get_tag_slot(data, i); - - if (copy_from_user(tag_slot, &utags[i], - sizeof(*tag_slot))) - goto fail; - } - } - - atomic_set(&data->refs, 1); - init_completion(&data->done); - *pdata = data; - return 0; -fail: - io_rsrc_data_free(data); - return ret; -} - -static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) -{ - table->files = kvcalloc(nr_files, sizeof(table->files[0]), - GFP_KERNEL_ACCOUNT); - if (unlikely(!table->files)) - return false; - - table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT); - if (unlikely(!table->bitmap)) { - kvfree(table->files); - return false; - } - - return true; -} - -static void io_free_file_tables(struct io_file_table *table) -{ - kvfree(table->files); - bitmap_free(table->bitmap); - table->files = NULL; - table->bitmap = NULL; -} - -static inline void io_file_bitmap_set(struct io_file_table *table, int bit) -{ - WARN_ON_ONCE(test_bit(bit, table->bitmap)); - __set_bit(bit, table->bitmap); - table->alloc_hint = bit + 1; -} - -static inline void io_file_bitmap_clear(struct io_file_table *table, int bit) -{ - __clear_bit(bit, table->bitmap); - table->alloc_hint = bit; -} - -static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) -{ -#if !defined(IO_URING_SCM_ALL) - int i; - - for (i = 0; i < ctx->nr_user_files; i++) { - struct file *file = io_file_from_index(ctx, i); - - if (!file) - continue; - if (io_fixed_file_slot(&ctx->file_table, i)->file_ptr & FFS_SCM) - continue; - io_file_bitmap_clear(&ctx->file_table, i); - fput(file); - } -#endif - -#if defined(CONFIG_UNIX) - if (ctx->ring_sock) { - struct sock *sock = ctx->ring_sock->sk; - struct sk_buff *skb; - - while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL) - kfree_skb(skb); - } -#endif - io_free_file_tables(&ctx->file_table); - io_rsrc_data_free(ctx->file_data); - ctx->file_data = NULL; - ctx->nr_user_files = 0; -} - -static int io_sqe_files_unregister(struct io_ring_ctx *ctx) -{ - unsigned nr = ctx->nr_user_files; - int ret; - - if (!ctx->file_data) - return -ENXIO; - - /* - * Quiesce may unlock ->uring_lock, and while it's not held - * prevent new requests using the table. - */ - ctx->nr_user_files = 0; - ret = io_rsrc_ref_quiesce(ctx->file_data, ctx); - ctx->nr_user_files = nr; - if (!ret) - __io_sqe_files_unregister(ctx); - return ret; -} - -static void io_sq_thread_unpark(struct io_sq_data *sqd) - __releases(&sqd->lock) -{ - WARN_ON_ONCE(sqd->thread == current); - - /* - * Do the dance but not conditional clear_bit() because it'd race with - * other threads incrementing park_pending and setting the bit. - */ - clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); - if (atomic_dec_return(&sqd->park_pending)) - set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); - mutex_unlock(&sqd->lock); -} - -static void io_sq_thread_park(struct io_sq_data *sqd) - __acquires(&sqd->lock) -{ - WARN_ON_ONCE(sqd->thread == current); - - atomic_inc(&sqd->park_pending); - set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); - mutex_lock(&sqd->lock); - if (sqd->thread) - wake_up_process(sqd->thread); -} - -static void io_sq_thread_stop(struct io_sq_data *sqd) -{ - WARN_ON_ONCE(sqd->thread == current); - WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)); - - set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); - mutex_lock(&sqd->lock); - if (sqd->thread) - wake_up_process(sqd->thread); - mutex_unlock(&sqd->lock); - wait_for_completion(&sqd->exited); -} - -static void io_put_sq_data(struct io_sq_data *sqd) -{ - if (refcount_dec_and_test(&sqd->refs)) { - WARN_ON_ONCE(atomic_read(&sqd->park_pending)); - - io_sq_thread_stop(sqd); - kfree(sqd); - } -} - -static void io_sq_thread_finish(struct io_ring_ctx *ctx) -{ - struct io_sq_data *sqd = ctx->sq_data; - - if (sqd) { - io_sq_thread_park(sqd); - list_del_init(&ctx->sqd_list); - io_sqd_update_thread_idle(sqd); - io_sq_thread_unpark(sqd); - - io_put_sq_data(sqd); - ctx->sq_data = NULL; - } -} - -static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p) -{ - struct io_ring_ctx *ctx_attach; - struct io_sq_data *sqd; - struct fd f; - - f = fdget(p->wq_fd); - if (!f.file) - return ERR_PTR(-ENXIO); - if (f.file->f_op != &io_uring_fops) { - fdput(f); - return ERR_PTR(-EINVAL); - } - - ctx_attach = f.file->private_data; - sqd = ctx_attach->sq_data; - if (!sqd) { - fdput(f); - return ERR_PTR(-EINVAL); - } - if (sqd->task_tgid != current->tgid) { - fdput(f); - return ERR_PTR(-EPERM); - } - - refcount_inc(&sqd->refs); - fdput(f); - return sqd; -} - -static struct io_sq_data *io_get_sq_data(struct io_uring_params *p, - bool *attached) -{ - struct io_sq_data *sqd; - - *attached = false; - if (p->flags & IORING_SETUP_ATTACH_WQ) { - sqd = io_attach_sq_data(p); - if (!IS_ERR(sqd)) { - *attached = true; - return sqd; - } - /* fall through for EPERM case, setup new sqd/task */ - if (PTR_ERR(sqd) != -EPERM) - return sqd; - } - - sqd = kzalloc(sizeof(*sqd), GFP_KERNEL); - if (!sqd) - return ERR_PTR(-ENOMEM); - - atomic_set(&sqd->park_pending, 0); - refcount_set(&sqd->refs, 1); - INIT_LIST_HEAD(&sqd->ctx_list); - mutex_init(&sqd->lock); - init_waitqueue_head(&sqd->wait); - init_completion(&sqd->exited); - return sqd; -} - -/* - * Ensure the UNIX gc is aware of our file set, so we are certain that - * the io_uring can be safely unregistered on process exit, even if we have - * loops in the file referencing. We account only files that can hold other - * files because otherwise they can't form a loop and so are not interesting - * for GC. - */ -static int io_scm_file_account(struct io_ring_ctx *ctx, struct file *file) -{ -#if defined(CONFIG_UNIX) - struct sock *sk = ctx->ring_sock->sk; - struct sk_buff_head *head = &sk->sk_receive_queue; - struct scm_fp_list *fpl; - struct sk_buff *skb; - - if (likely(!io_file_need_scm(file))) - return 0; - - /* - * See if we can merge this file into an existing skb SCM_RIGHTS - * file set. If there's no room, fall back to allocating a new skb - * and filling it in. - */ - spin_lock_irq(&head->lock); - skb = skb_peek(head); - if (skb && UNIXCB(skb).fp->count < SCM_MAX_FD) - __skb_unlink(skb, head); - else - skb = NULL; - spin_unlock_irq(&head->lock); - - if (!skb) { - fpl = kzalloc(sizeof(*fpl), GFP_KERNEL); - if (!fpl) - return -ENOMEM; - - skb = alloc_skb(0, GFP_KERNEL); - if (!skb) { - kfree(fpl); - return -ENOMEM; - } - - fpl->user = get_uid(current_user()); - fpl->max = SCM_MAX_FD; - fpl->count = 0; - - UNIXCB(skb).fp = fpl; - skb->sk = sk; - skb->destructor = unix_destruct_scm; - refcount_add(skb->truesize, &sk->sk_wmem_alloc); - } - - fpl = UNIXCB(skb).fp; - fpl->fp[fpl->count++] = get_file(file); - unix_inflight(fpl->user, file); - skb_queue_head(head, skb); - fput(file); -#endif - return 0; -} - -static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) -{ - struct file *file = prsrc->file; -#if defined(CONFIG_UNIX) - struct sock *sock = ctx->ring_sock->sk; - struct sk_buff_head list, *head = &sock->sk_receive_queue; - struct sk_buff *skb; - int i; - - if (!io_file_need_scm(file)) { - fput(file); - return; - } - - __skb_queue_head_init(&list); - - /* - * Find the skb that holds this file in its SCM_RIGHTS. When found, - * remove this entry and rearrange the file array. - */ - skb = skb_dequeue(head); - while (skb) { - struct scm_fp_list *fp; - - fp = UNIXCB(skb).fp; - for (i = 0; i < fp->count; i++) { - int left; - - if (fp->fp[i] != file) - continue; - - unix_notinflight(fp->user, fp->fp[i]); - left = fp->count - 1 - i; - if (left) { - memmove(&fp->fp[i], &fp->fp[i + 1], - left * sizeof(struct file *)); - } - fp->count--; - if (!fp->count) { - kfree_skb(skb); - skb = NULL; - } else { - __skb_queue_tail(&list, skb); - } - fput(file); - file = NULL; - break; - } - - if (!file) - break; - - __skb_queue_tail(&list, skb); - - skb = skb_dequeue(head); - } - - if (skb_peek(&list)) { - spin_lock_irq(&head->lock); - while ((skb = __skb_dequeue(&list)) != NULL) - __skb_queue_tail(head, skb); - spin_unlock_irq(&head->lock); - } -#else - fput(file); -#endif -} - -static void __io_rsrc_put_work(struct io_rsrc_node *ref_node) -{ - struct io_rsrc_data *rsrc_data = ref_node->rsrc_data; - struct io_ring_ctx *ctx = rsrc_data->ctx; - struct io_rsrc_put *prsrc, *tmp; - - list_for_each_entry_safe(prsrc, tmp, &ref_node->rsrc_list, list) { - list_del(&prsrc->list); - - if (prsrc->tag) { - if (ctx->flags & IORING_SETUP_IOPOLL) - mutex_lock(&ctx->uring_lock); - - spin_lock(&ctx->completion_lock); - io_fill_cqe_aux(ctx, prsrc->tag, 0, 0); - io_commit_cqring(ctx); - spin_unlock(&ctx->completion_lock); - io_cqring_ev_posted(ctx); - - if (ctx->flags & IORING_SETUP_IOPOLL) - mutex_unlock(&ctx->uring_lock); - } - - rsrc_data->do_put(ctx, prsrc); - kfree(prsrc); - } - - io_rsrc_node_destroy(ref_node); - if (atomic_dec_and_test(&rsrc_data->refs)) - complete(&rsrc_data->done); -} - -static void io_rsrc_put_work(struct work_struct *work) -{ - struct io_ring_ctx *ctx; - struct llist_node *node; - - ctx = container_of(work, struct io_ring_ctx, rsrc_put_work.work); - node = llist_del_all(&ctx->rsrc_put_llist); - - while (node) { - struct io_rsrc_node *ref_node; - struct llist_node *next = node->next; - - ref_node = llist_entry(node, struct io_rsrc_node, llist); - __io_rsrc_put_work(ref_node); - node = next; - } -} - -static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, - unsigned nr_args, u64 __user *tags) -{ - __s32 __user *fds = (__s32 __user *) arg; - struct file *file; - int fd, ret; - unsigned i; - - if (ctx->file_data) - return -EBUSY; - if (!nr_args) - return -EINVAL; - if (nr_args > IORING_MAX_FIXED_FILES) - return -EMFILE; - if (nr_args > rlimit(RLIMIT_NOFILE)) - return -EMFILE; - ret = io_rsrc_node_switch_start(ctx); - if (ret) - return ret; - ret = io_rsrc_data_alloc(ctx, io_rsrc_file_put, tags, nr_args, - &ctx->file_data); - if (ret) - return ret; - - if (!io_alloc_file_tables(&ctx->file_table, nr_args)) { - io_rsrc_data_free(ctx->file_data); - ctx->file_data = NULL; - return -ENOMEM; - } - - for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { - struct io_fixed_file *file_slot; - - if (fds && copy_from_user(&fd, &fds[i], sizeof(fd))) { - ret = -EFAULT; - goto fail; - } - /* allow sparse sets */ - if (!fds || fd == -1) { - ret = -EINVAL; - if (unlikely(*io_get_tag_slot(ctx->file_data, i))) - goto fail; - continue; - } - - file = fget(fd); - ret = -EBADF; - if (unlikely(!file)) - goto fail; - - /* - * Don't allow io_uring instances to be registered. If UNIX - * isn't enabled, then this causes a reference cycle and this - * instance can never get freed. If UNIX is enabled we'll - * handle it just fine, but there's still no point in allowing - * a ring fd as it doesn't support regular read/write anyway. - */ - if (file->f_op == &io_uring_fops) { - fput(file); - goto fail; - } - ret = io_scm_file_account(ctx, file); - if (ret) { - fput(file); - goto fail; - } - file_slot = io_fixed_file_slot(&ctx->file_table, i); - io_fixed_file_set(file_slot, file); - io_file_bitmap_set(&ctx->file_table, i); - } - - io_rsrc_node_switch(ctx, NULL); - return 0; -fail: - __io_sqe_files_unregister(ctx); - return ret; -} - -static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, - struct io_rsrc_node *node, void *rsrc) -{ - u64 *tag_slot = io_get_tag_slot(data, idx); - struct io_rsrc_put *prsrc; - - prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); - if (!prsrc) - return -ENOMEM; - - prsrc->tag = *tag_slot; - *tag_slot = 0; - prsrc->rsrc = rsrc; - list_add(&prsrc->list, &node->rsrc_list); - return 0; -} - -static int io_install_fixed_file(struct io_kiocb *req, struct file *file, - unsigned int issue_flags, u32 slot_index) - __must_hold(&req->ctx->uring_lock) -{ - struct io_ring_ctx *ctx = req->ctx; - bool needs_switch = false; - struct io_fixed_file *file_slot; - int ret; - - if (file->f_op == &io_uring_fops) - return -EBADF; - if (!ctx->file_data) - return -ENXIO; - if (slot_index >= ctx->nr_user_files) - return -EINVAL; - - slot_index = array_index_nospec(slot_index, ctx->nr_user_files); - file_slot = io_fixed_file_slot(&ctx->file_table, slot_index); - - if (file_slot->file_ptr) { - struct file *old_file; - - ret = io_rsrc_node_switch_start(ctx); - if (ret) - goto err; - - old_file = (struct file *)(file_slot->file_ptr & FFS_MASK); - ret = io_queue_rsrc_removal(ctx->file_data, slot_index, - ctx->rsrc_node, old_file); - if (ret) - goto err; - file_slot->file_ptr = 0; - io_file_bitmap_clear(&ctx->file_table, slot_index); - needs_switch = true; - } - - ret = io_scm_file_account(ctx, file); - if (!ret) { - *io_get_tag_slot(ctx->file_data, slot_index) = 0; - io_fixed_file_set(file_slot, file); - io_file_bitmap_set(&ctx->file_table, slot_index); - } -err: - if (needs_switch) - io_rsrc_node_switch(ctx, ctx->file_data); - if (ret) - fput(file); - return ret; -} - -static int __io_close_fixed(struct io_kiocb *req, unsigned int issue_flags, - unsigned int offset) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_fixed_file *file_slot; - struct file *file; - int ret; - - io_ring_submit_lock(ctx, issue_flags); - ret = -ENXIO; - if (unlikely(!ctx->file_data)) - goto out; - ret = -EINVAL; - if (offset >= ctx->nr_user_files) - goto out; - ret = io_rsrc_node_switch_start(ctx); - if (ret) - goto out; - - offset = array_index_nospec(offset, ctx->nr_user_files); - file_slot = io_fixed_file_slot(&ctx->file_table, offset); - ret = -EBADF; - if (!file_slot->file_ptr) - goto out; - - file = (struct file *)(file_slot->file_ptr & FFS_MASK); - ret = io_queue_rsrc_removal(ctx->file_data, offset, ctx->rsrc_node, file); - if (ret) - goto out; - - file_slot->file_ptr = 0; - io_file_bitmap_clear(&ctx->file_table, offset); - io_rsrc_node_switch(ctx, ctx->file_data); - ret = 0; -out: - io_ring_submit_unlock(ctx, issue_flags); - return ret; -} - -static inline int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) -{ - return __io_close_fixed(req, issue_flags, req->close.file_slot - 1); -} - -static int __io_sqe_files_update(struct io_ring_ctx *ctx, - struct io_uring_rsrc_update2 *up, - unsigned nr_args) -{ - u64 __user *tags = u64_to_user_ptr(up->tags); - __s32 __user *fds = u64_to_user_ptr(up->data); - struct io_rsrc_data *data = ctx->file_data; - struct io_fixed_file *file_slot; - struct file *file; - int fd, i, err = 0; - unsigned int done; - bool needs_switch = false; - - if (!ctx->file_data) - return -ENXIO; - if (up->offset + nr_args > ctx->nr_user_files) - return -EINVAL; - - for (done = 0; done < nr_args; done++) { - u64 tag = 0; - - if ((tags && copy_from_user(&tag, &tags[done], sizeof(tag))) || - copy_from_user(&fd, &fds[done], sizeof(fd))) { - err = -EFAULT; - break; - } - if ((fd == IORING_REGISTER_FILES_SKIP || fd == -1) && tag) { - err = -EINVAL; - break; - } - if (fd == IORING_REGISTER_FILES_SKIP) - continue; - - i = array_index_nospec(up->offset + done, ctx->nr_user_files); - file_slot = io_fixed_file_slot(&ctx->file_table, i); - - if (file_slot->file_ptr) { - file = (struct file *)(file_slot->file_ptr & FFS_MASK); - err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file); - if (err) - break; - file_slot->file_ptr = 0; - io_file_bitmap_clear(&ctx->file_table, i); - needs_switch = true; - } - if (fd != -1) { - file = fget(fd); - if (!file) { - err = -EBADF; - break; - } - /* - * Don't allow io_uring instances to be registered. If - * UNIX isn't enabled, then this causes a reference - * cycle and this instance can never get freed. If UNIX - * is enabled we'll handle it just fine, but there's - * still no point in allowing a ring fd as it doesn't - * support regular read/write anyway. - */ - if (file->f_op == &io_uring_fops) { - fput(file); - err = -EBADF; - break; - } - err = io_scm_file_account(ctx, file); - if (err) { - fput(file); - break; - } - *io_get_tag_slot(data, i) = tag; - io_fixed_file_set(file_slot, file); - io_file_bitmap_set(&ctx->file_table, i); - } - } - - if (needs_switch) - io_rsrc_node_switch(ctx, data); - return done ? done : err; -} - -static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx, - struct task_struct *task) -{ - struct io_wq_hash *hash; - struct io_wq_data data; - unsigned int concurrency; - - mutex_lock(&ctx->uring_lock); - hash = ctx->hash_map; - if (!hash) { - hash = kzalloc(sizeof(*hash), GFP_KERNEL); - if (!hash) { - mutex_unlock(&ctx->uring_lock); - return ERR_PTR(-ENOMEM); - } - refcount_set(&hash->refs, 1); - init_waitqueue_head(&hash->wait); - ctx->hash_map = hash; - } - mutex_unlock(&ctx->uring_lock); - - data.hash = hash; - data.task = task; - data.free_work = io_wq_free_work; - data.do_work = io_wq_submit_work; - - /* Do QD, or 4 * CPUS, whatever is smallest */ - concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); - - return io_wq_create(concurrency, &data); -} - -static __cold int io_uring_alloc_task_context(struct task_struct *task, - struct io_ring_ctx *ctx) -{ - struct io_uring_task *tctx; - int ret; - - tctx = kzalloc(sizeof(*tctx), GFP_KERNEL); - if (unlikely(!tctx)) - return -ENOMEM; - - tctx->registered_rings = kcalloc(IO_RINGFD_REG_MAX, - sizeof(struct file *), GFP_KERNEL); - if (unlikely(!tctx->registered_rings)) { - kfree(tctx); - return -ENOMEM; - } - - ret = percpu_counter_init(&tctx->inflight, 0, GFP_KERNEL); - if (unlikely(ret)) { - kfree(tctx->registered_rings); - kfree(tctx); - return ret; - } - - tctx->io_wq = io_init_wq_offload(ctx, task); - if (IS_ERR(tctx->io_wq)) { - ret = PTR_ERR(tctx->io_wq); - percpu_counter_destroy(&tctx->inflight); - kfree(tctx->registered_rings); - kfree(tctx); - return ret; - } - - xa_init(&tctx->xa); - init_waitqueue_head(&tctx->wait); - atomic_set(&tctx->in_idle, 0); - atomic_set(&tctx->inflight_tracked, 0); - task->io_uring = tctx; - spin_lock_init(&tctx->task_lock); - INIT_WQ_LIST(&tctx->task_list); - INIT_WQ_LIST(&tctx->prio_task_list); - init_task_work(&tctx->task_work, tctx_task_work); - return 0; -} - -void __io_uring_free(struct task_struct *tsk) -{ - struct io_uring_task *tctx = tsk->io_uring; - - WARN_ON_ONCE(!xa_empty(&tctx->xa)); - WARN_ON_ONCE(tctx->io_wq); - WARN_ON_ONCE(tctx->cached_refs); - - kfree(tctx->registered_rings); - percpu_counter_destroy(&tctx->inflight); - kfree(tctx); - tsk->io_uring = NULL; -} - -static __cold int io_sq_offload_create(struct io_ring_ctx *ctx, - struct io_uring_params *p) -{ - int ret; - - /* Retain compatibility with failing for an invalid attach attempt */ - if ((ctx->flags & (IORING_SETUP_ATTACH_WQ | IORING_SETUP_SQPOLL)) == - IORING_SETUP_ATTACH_WQ) { - struct fd f; - - f = fdget(p->wq_fd); - if (!f.file) - return -ENXIO; - if (f.file->f_op != &io_uring_fops) { - fdput(f); - return -EINVAL; - } - fdput(f); - } - if (ctx->flags & IORING_SETUP_SQPOLL) { - struct task_struct *tsk; - struct io_sq_data *sqd; - bool attached; - - ret = security_uring_sqpoll(); - if (ret) - return ret; - - sqd = io_get_sq_data(p, &attached); - if (IS_ERR(sqd)) { - ret = PTR_ERR(sqd); - goto err; - } - - ctx->sq_creds = get_current_cred(); - ctx->sq_data = sqd; - ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); - if (!ctx->sq_thread_idle) - ctx->sq_thread_idle = HZ; - - io_sq_thread_park(sqd); - list_add(&ctx->sqd_list, &sqd->ctx_list); - io_sqd_update_thread_idle(sqd); - /* don't attach to a dying SQPOLL thread, would be racy */ - ret = (attached && !sqd->thread) ? -ENXIO : 0; - io_sq_thread_unpark(sqd); - - if (ret < 0) - goto err; - if (attached) - return 0; - - if (p->flags & IORING_SETUP_SQ_AFF) { - int cpu = p->sq_thread_cpu; - - ret = -EINVAL; - if (cpu >= nr_cpu_ids || !cpu_online(cpu)) - goto err_sqpoll; - sqd->sq_cpu = cpu; - } else { - sqd->sq_cpu = -1; - } - - sqd->task_pid = current->pid; - sqd->task_tgid = current->tgid; - tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE); - if (IS_ERR(tsk)) { - ret = PTR_ERR(tsk); - goto err_sqpoll; - } - - sqd->thread = tsk; - ret = io_uring_alloc_task_context(tsk, ctx); - wake_up_new_task(tsk); - if (ret) - goto err; - } else if (p->flags & IORING_SETUP_SQ_AFF) { - /* Can't have SQ_AFF without SQPOLL */ - ret = -EINVAL; - goto err; - } - - return 0; -err_sqpoll: - complete(&ctx->sq_data->exited); -err: - io_sq_thread_finish(ctx); - return ret; -} - -static inline void __io_unaccount_mem(struct user_struct *user, - unsigned long nr_pages) -{ - atomic_long_sub(nr_pages, &user->locked_vm); -} - -static inline int __io_account_mem(struct user_struct *user, - unsigned long nr_pages) -{ - unsigned long page_limit, cur_pages, new_pages; - - /* Don't allow more pages than we can safely lock */ - page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - - do { - cur_pages = atomic_long_read(&user->locked_vm); - new_pages = cur_pages + nr_pages; - if (new_pages > page_limit) - return -ENOMEM; - } while (atomic_long_cmpxchg(&user->locked_vm, cur_pages, - new_pages) != cur_pages); - - return 0; -} - -static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) -{ - if (ctx->user) - __io_unaccount_mem(ctx->user, nr_pages); - - if (ctx->mm_account) - atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm); -} - -static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) -{ - int ret; - - if (ctx->user) { - ret = __io_account_mem(ctx->user, nr_pages); - if (ret) - return ret; - } - - if (ctx->mm_account) - atomic64_add(nr_pages, &ctx->mm_account->pinned_vm); - - return 0; -} - -static void io_mem_free(void *ptr) -{ - struct page *page; - - if (!ptr) - return; - - page = virt_to_head_page(ptr); - if (put_page_testzero(page)) - free_compound_page(page); -} - -static void *io_mem_alloc(size_t size) -{ - gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP; - - return (void *) __get_free_pages(gfp, get_order(size)); -} - -static unsigned long rings_size(struct io_ring_ctx *ctx, unsigned int sq_entries, - unsigned int cq_entries, size_t *sq_offset) -{ - struct io_rings *rings; - size_t off, sq_array_size; - - off = struct_size(rings, cqes, cq_entries); - if (off == SIZE_MAX) - return SIZE_MAX; - if (ctx->flags & IORING_SETUP_CQE32) { - if (check_shl_overflow(off, 1, &off)) - return SIZE_MAX; - } - -#ifdef CONFIG_SMP - off = ALIGN(off, SMP_CACHE_BYTES); - if (off == 0) - return SIZE_MAX; -#endif - - if (sq_offset) - *sq_offset = off; - - sq_array_size = array_size(sizeof(u32), sq_entries); - if (sq_array_size == SIZE_MAX) - return SIZE_MAX; - - if (check_add_overflow(off, sq_array_size, &off)) - return SIZE_MAX; - - return off; -} - -static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slot) -{ - struct io_mapped_ubuf *imu = *slot; - unsigned int i; - - if (imu != ctx->dummy_ubuf) { - for (i = 0; i < imu->nr_bvecs; i++) - unpin_user_page(imu->bvec[i].bv_page); - if (imu->acct_pages) - io_unaccount_mem(ctx, imu->acct_pages); - kvfree(imu); - } - *slot = NULL; -} - -static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) -{ - io_buffer_unmap(ctx, &prsrc->buf); - prsrc->buf = NULL; -} - -static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx) -{ - unsigned int i; - - for (i = 0; i < ctx->nr_user_bufs; i++) - io_buffer_unmap(ctx, &ctx->user_bufs[i]); - kfree(ctx->user_bufs); - io_rsrc_data_free(ctx->buf_data); - ctx->user_bufs = NULL; - ctx->buf_data = NULL; - ctx->nr_user_bufs = 0; -} - -static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx) -{ - unsigned nr = ctx->nr_user_bufs; - int ret; - - if (!ctx->buf_data) - return -ENXIO; - - /* - * Quiesce may unlock ->uring_lock, and while it's not held - * prevent new requests using the table. - */ - ctx->nr_user_bufs = 0; - ret = io_rsrc_ref_quiesce(ctx->buf_data, ctx); - ctx->nr_user_bufs = nr; - if (!ret) - __io_sqe_buffers_unregister(ctx); - return ret; -} - -static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst, - void __user *arg, unsigned index) -{ - struct iovec __user *src; - -#ifdef CONFIG_COMPAT - if (ctx->compat) { - struct compat_iovec __user *ciovs; - struct compat_iovec ciov; - - ciovs = (struct compat_iovec __user *) arg; - if (copy_from_user(&ciov, &ciovs[index], sizeof(ciov))) - return -EFAULT; - - dst->iov_base = u64_to_user_ptr((u64)ciov.iov_base); - dst->iov_len = ciov.iov_len; - return 0; - } -#endif - src = (struct iovec __user *) arg; - if (copy_from_user(dst, &src[index], sizeof(*dst))) - return -EFAULT; - return 0; -} - -/* - * Not super efficient, but this is just a registration time. And we do cache - * the last compound head, so generally we'll only do a full search if we don't - * match that one. - * - * We check if the given compound head page has already been accounted, to - * avoid double accounting it. This allows us to account the full size of the - * page, not just the constituent pages of a huge page. - */ -static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages, - int nr_pages, struct page *hpage) -{ - int i, j; - - /* check current page array */ - for (i = 0; i < nr_pages; i++) { - if (!PageCompound(pages[i])) - continue; - if (compound_head(pages[i]) == hpage) - return true; - } - - /* check previously registered pages */ - for (i = 0; i < ctx->nr_user_bufs; i++) { - struct io_mapped_ubuf *imu = ctx->user_bufs[i]; - - for (j = 0; j < imu->nr_bvecs; j++) { - if (!PageCompound(imu->bvec[j].bv_page)) - continue; - if (compound_head(imu->bvec[j].bv_page) == hpage) - return true; - } - } - - return false; -} - -static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, - int nr_pages, struct io_mapped_ubuf *imu, - struct page **last_hpage) -{ - int i, ret; - - imu->acct_pages = 0; - for (i = 0; i < nr_pages; i++) { - if (!PageCompound(pages[i])) { - imu->acct_pages++; - } else { - struct page *hpage; - - hpage = compound_head(pages[i]); - if (hpage == *last_hpage) - continue; - *last_hpage = hpage; - if (headpage_already_acct(ctx, pages, i, hpage)) - continue; - imu->acct_pages += page_size(hpage) >> PAGE_SHIFT; - } - } - - if (!imu->acct_pages) - return 0; - - ret = io_account_mem(ctx, imu->acct_pages); - if (ret) - imu->acct_pages = 0; - return ret; -} - -static struct page **io_pin_pages(unsigned long ubuf, unsigned long len, - int *npages) -{ - unsigned long start, end, nr_pages; - struct vm_area_struct **vmas = NULL; - struct page **pages = NULL; - int i, pret, ret = -ENOMEM; - - end = (ubuf + len + PAGE_SIZE - 1) >> PAGE_SHIFT; - start = ubuf >> PAGE_SHIFT; - nr_pages = end - start; - - pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); - if (!pages) - goto done; - - vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *), - GFP_KERNEL); - if (!vmas) - goto done; - - ret = 0; - mmap_read_lock(current->mm); - pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, - pages, vmas); - if (pret == nr_pages) { - /* don't support file backed memory */ - for (i = 0; i < nr_pages; i++) { - struct vm_area_struct *vma = vmas[i]; - - if (vma_is_shmem(vma)) - continue; - if (vma->vm_file && - !is_file_hugepages(vma->vm_file)) { - ret = -EOPNOTSUPP; - break; - } - } - *npages = nr_pages; - } else { - ret = pret < 0 ? pret : -EFAULT; - } - mmap_read_unlock(current->mm); - if (ret) { - /* - * if we did partial map, or found file backed vmas, - * release any pages we did get - */ - if (pret > 0) - unpin_user_pages(pages, pret); - goto done; - } - ret = 0; -done: - kvfree(vmas); - if (ret < 0) { - kvfree(pages); - pages = ERR_PTR(ret); - } - return pages; -} - -static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, - struct io_mapped_ubuf **pimu, - struct page **last_hpage) -{ - struct io_mapped_ubuf *imu = NULL; - struct page **pages = NULL; - unsigned long off; - size_t size; - int ret, nr_pages, i; - - if (!iov->iov_base) { - *pimu = ctx->dummy_ubuf; - return 0; - } - - *pimu = NULL; - ret = -ENOMEM; - - pages = io_pin_pages((unsigned long) iov->iov_base, iov->iov_len, - &nr_pages); - if (IS_ERR(pages)) { - ret = PTR_ERR(pages); - pages = NULL; - goto done; - } - - imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL); - if (!imu) - goto done; - - ret = io_buffer_account_pin(ctx, pages, nr_pages, imu, last_hpage); - if (ret) { - unpin_user_pages(pages, nr_pages); - goto done; - } - - off = (unsigned long) iov->iov_base & ~PAGE_MASK; - size = iov->iov_len; - for (i = 0; i < nr_pages; i++) { - size_t vec_len; - - vec_len = min_t(size_t, size, PAGE_SIZE - off); - imu->bvec[i].bv_page = pages[i]; - imu->bvec[i].bv_len = vec_len; - imu->bvec[i].bv_offset = off; - off = 0; - size -= vec_len; - } - /* store original address for later verification */ - imu->ubuf = (unsigned long) iov->iov_base; - imu->ubuf_end = imu->ubuf + iov->iov_len; - imu->nr_bvecs = nr_pages; - *pimu = imu; - ret = 0; -done: - if (ret) - kvfree(imu); - kvfree(pages); - return ret; -} - -static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args) -{ - ctx->user_bufs = kcalloc(nr_args, sizeof(*ctx->user_bufs), GFP_KERNEL); - return ctx->user_bufs ? 0 : -ENOMEM; -} - -static int io_buffer_validate(struct iovec *iov) -{ - unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1); - - /* - * Don't impose further limits on the size and buffer - * constraints here, we'll -EINVAL later when IO is - * submitted if they are wrong. - */ - if (!iov->iov_base) - return iov->iov_len ? -EFAULT : 0; - if (!iov->iov_len) - return -EFAULT; - - /* arbitrary limit, but we need something */ - if (iov->iov_len > SZ_1G) - return -EFAULT; - - if (check_add_overflow((unsigned long)iov->iov_base, acct_len, &tmp)) - return -EOVERFLOW; - - return 0; -} - -static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, - unsigned int nr_args, u64 __user *tags) -{ - struct page *last_hpage = NULL; - struct io_rsrc_data *data; - int i, ret; - struct iovec iov; - - if (ctx->user_bufs) - return -EBUSY; - if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS) - return -EINVAL; - ret = io_rsrc_node_switch_start(ctx); - if (ret) - return ret; - ret = io_rsrc_data_alloc(ctx, io_rsrc_buf_put, tags, nr_args, &data); - if (ret) - return ret; - ret = io_buffers_map_alloc(ctx, nr_args); - if (ret) { - io_rsrc_data_free(data); - return ret; - } - - for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) { - if (arg) { - ret = io_copy_iov(ctx, &iov, arg, i); - if (ret) - break; - ret = io_buffer_validate(&iov); - if (ret) - break; - } else { - memset(&iov, 0, sizeof(iov)); - } - - if (!iov.iov_base && *io_get_tag_slot(data, i)) { - ret = -EINVAL; - break; - } - - ret = io_sqe_buffer_register(ctx, &iov, &ctx->user_bufs[i], - &last_hpage); - if (ret) - break; - } - - WARN_ON_ONCE(ctx->buf_data); - - ctx->buf_data = data; - if (ret) - __io_sqe_buffers_unregister(ctx); - else - io_rsrc_node_switch(ctx, NULL); - return ret; -} - -static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, - struct io_uring_rsrc_update2 *up, - unsigned int nr_args) -{ - u64 __user *tags = u64_to_user_ptr(up->tags); - struct iovec iov, __user *iovs = u64_to_user_ptr(up->data); - struct page *last_hpage = NULL; - bool needs_switch = false; - __u32 done; - int i, err; - - if (!ctx->buf_data) - return -ENXIO; - if (up->offset + nr_args > ctx->nr_user_bufs) - return -EINVAL; - - for (done = 0; done < nr_args; done++) { - struct io_mapped_ubuf *imu; - int offset = up->offset + done; - u64 tag = 0; - - err = io_copy_iov(ctx, &iov, iovs, done); - if (err) - break; - if (tags && copy_from_user(&tag, &tags[done], sizeof(tag))) { - err = -EFAULT; - break; - } - err = io_buffer_validate(&iov); - if (err) - break; - if (!iov.iov_base && tag) { - err = -EINVAL; - break; - } - err = io_sqe_buffer_register(ctx, &iov, &imu, &last_hpage); - if (err) - break; - - i = array_index_nospec(offset, ctx->nr_user_bufs); - if (ctx->user_bufs[i] != ctx->dummy_ubuf) { - err = io_queue_rsrc_removal(ctx->buf_data, i, - ctx->rsrc_node, ctx->user_bufs[i]); - if (unlikely(err)) { - io_buffer_unmap(ctx, &imu); - break; - } - ctx->user_bufs[i] = NULL; - needs_switch = true; - } - - ctx->user_bufs[i] = imu; - *io_get_tag_slot(ctx->buf_data, offset) = tag; - } - - if (needs_switch) - io_rsrc_node_switch(ctx, ctx->buf_data); - return done ? done : err; -} - -static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg, - unsigned int eventfd_async) -{ - struct io_ev_fd *ev_fd; - __s32 __user *fds = arg; - int fd; - - ev_fd = rcu_dereference_protected(ctx->io_ev_fd, - lockdep_is_held(&ctx->uring_lock)); - if (ev_fd) - return -EBUSY; - - if (copy_from_user(&fd, fds, sizeof(*fds))) - return -EFAULT; - - ev_fd = kmalloc(sizeof(*ev_fd), GFP_KERNEL); - if (!ev_fd) - return -ENOMEM; - - ev_fd->cq_ev_fd = eventfd_ctx_fdget(fd); - if (IS_ERR(ev_fd->cq_ev_fd)) { - int ret = PTR_ERR(ev_fd->cq_ev_fd); - kfree(ev_fd); - return ret; - } - ev_fd->eventfd_async = eventfd_async; - ctx->has_evfd = true; - rcu_assign_pointer(ctx->io_ev_fd, ev_fd); - return 0; -} - -static void io_eventfd_put(struct rcu_head *rcu) -{ - struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); - - eventfd_ctx_put(ev_fd->cq_ev_fd); - kfree(ev_fd); -} - -static int io_eventfd_unregister(struct io_ring_ctx *ctx) -{ - struct io_ev_fd *ev_fd; - - ev_fd = rcu_dereference_protected(ctx->io_ev_fd, - lockdep_is_held(&ctx->uring_lock)); - if (ev_fd) { - ctx->has_evfd = false; - rcu_assign_pointer(ctx->io_ev_fd, NULL); - call_rcu(&ev_fd->rcu, io_eventfd_put); - return 0; - } - - return -ENXIO; -} - -static void io_destroy_buffers(struct io_ring_ctx *ctx) -{ - struct io_buffer_list *bl; - unsigned long index; - int i; - - for (i = 0; i < BGID_ARRAY; i++) { - if (!ctx->io_bl) - break; - __io_remove_buffers(ctx, &ctx->io_bl[i], -1U); - } - - xa_for_each(&ctx->io_bl_xa, index, bl) { - xa_erase(&ctx->io_bl_xa, bl->bgid); - __io_remove_buffers(ctx, bl, -1U); - kfree(bl); - } - - while (!list_empty(&ctx->io_buffers_pages)) { - struct page *page; - - page = list_first_entry(&ctx->io_buffers_pages, struct page, lru); - list_del_init(&page->lru); - __free_page(page); - } -} - -static void io_req_caches_free(struct io_ring_ctx *ctx) -{ - struct io_submit_state *state = &ctx->submit_state; - int nr = 0; - - mutex_lock(&ctx->uring_lock); - io_flush_cached_locked_reqs(ctx, state); - - while (!io_req_cache_empty(ctx)) { - struct io_wq_work_node *node; - struct io_kiocb *req; - - node = wq_stack_extract(&state->free_list); - req = container_of(node, struct io_kiocb, comp_list); - kmem_cache_free(req_cachep, req); - nr++; - } - if (nr) - percpu_ref_put_many(&ctx->refs, nr); - mutex_unlock(&ctx->uring_lock); -} - -static void io_wait_rsrc_data(struct io_rsrc_data *data) -{ - if (data && !atomic_dec_and_test(&data->refs)) - wait_for_completion(&data->done); -} - -static void io_flush_apoll_cache(struct io_ring_ctx *ctx) -{ - struct async_poll *apoll; - - while (!list_empty(&ctx->apoll_cache)) { - apoll = list_first_entry(&ctx->apoll_cache, struct async_poll, - poll.wait.entry); - list_del(&apoll->poll.wait.entry); - kfree(apoll); - } -} - -static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) -{ - io_sq_thread_finish(ctx); - - if (ctx->mm_account) { - mmdrop(ctx->mm_account); - ctx->mm_account = NULL; - } - - io_rsrc_refs_drop(ctx); - /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ - io_wait_rsrc_data(ctx->buf_data); - io_wait_rsrc_data(ctx->file_data); - - mutex_lock(&ctx->uring_lock); - if (ctx->buf_data) - __io_sqe_buffers_unregister(ctx); - if (ctx->file_data) - __io_sqe_files_unregister(ctx); - if (ctx->rings) - __io_cqring_overflow_flush(ctx, true); - io_eventfd_unregister(ctx); - io_flush_apoll_cache(ctx); - mutex_unlock(&ctx->uring_lock); - io_destroy_buffers(ctx); - if (ctx->sq_creds) - put_cred(ctx->sq_creds); - - /* there are no registered resources left, nobody uses it */ - if (ctx->rsrc_node) - io_rsrc_node_destroy(ctx->rsrc_node); - if (ctx->rsrc_backup_node) - io_rsrc_node_destroy(ctx->rsrc_backup_node); - flush_delayed_work(&ctx->rsrc_put_work); - flush_delayed_work(&ctx->fallback_work); - - WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)); - WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist)); - -#if defined(CONFIG_UNIX) - if (ctx->ring_sock) { - ctx->ring_sock->file = NULL; /* so that iput() is called */ - sock_release(ctx->ring_sock); - } -#endif - WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); - - io_mem_free(ctx->rings); - io_mem_free(ctx->sq_sqes); - - percpu_ref_exit(&ctx->refs); - free_uid(ctx->user); - io_req_caches_free(ctx); - if (ctx->hash_map) - io_wq_put_hash(ctx->hash_map); - kfree(ctx->cancel_hash); - kfree(ctx->dummy_ubuf); - kfree(ctx->io_bl); - xa_destroy(&ctx->io_bl_xa); - kfree(ctx); -} - -static __poll_t io_uring_poll(struct file *file, poll_table *wait) -{ - struct io_ring_ctx *ctx = file->private_data; - __poll_t mask = 0; - - poll_wait(file, &ctx->cq_wait, wait); - /* - * synchronizes with barrier from wq_has_sleeper call in - * io_commit_cqring - */ - smp_rmb(); - if (!io_sqring_full(ctx)) - mask |= EPOLLOUT | EPOLLWRNORM; - - /* - * Don't flush cqring overflow list here, just do a simple check. - * Otherwise there could possible be ABBA deadlock: - * CPU0 CPU1 - * ---- ---- - * lock(&ctx->uring_lock); - * lock(&ep->mtx); - * lock(&ctx->uring_lock); - * lock(&ep->mtx); - * - * Users may get EPOLLIN meanwhile seeing nothing in cqring, this - * pushs them to do the flush. - */ - if (io_cqring_events(ctx) || - test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) - mask |= EPOLLIN | EPOLLRDNORM; - - return mask; -} - -static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) -{ - const struct cred *creds; - - creds = xa_erase(&ctx->personalities, id); - if (creds) { - put_cred(creds); - return 0; - } - - return -EINVAL; -} - -struct io_tctx_exit { - struct callback_head task_work; - struct completion completion; - struct io_ring_ctx *ctx; -}; - -static __cold void io_tctx_exit_cb(struct callback_head *cb) -{ - struct io_uring_task *tctx = current->io_uring; - struct io_tctx_exit *work; - - work = container_of(cb, struct io_tctx_exit, task_work); - /* - * When @in_idle, we're in cancellation and it's racy to remove the - * node. It'll be removed by the end of cancellation, just ignore it. - */ - if (!atomic_read(&tctx->in_idle)) - io_uring_del_tctx_node((unsigned long)work->ctx); - complete(&work->completion); -} - -static __cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) -{ - struct io_kiocb *req = container_of(work, struct io_kiocb, work); - - return req->ctx == data; -} - -static __cold void io_ring_exit_work(struct work_struct *work) -{ - struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work); - unsigned long timeout = jiffies + HZ * 60 * 5; - unsigned long interval = HZ / 20; - struct io_tctx_exit exit; - struct io_tctx_node *node; - int ret; - - /* - * If we're doing polled IO and end up having requests being - * submitted async (out-of-line), then completions can come in while - * we're waiting for refs to drop. We need to reap these manually, - * as nobody else will be looking for them. - */ - do { - io_uring_try_cancel_requests(ctx, NULL, true); - if (ctx->sq_data) { - struct io_sq_data *sqd = ctx->sq_data; - struct task_struct *tsk; - - io_sq_thread_park(sqd); - tsk = sqd->thread; - if (tsk && tsk->io_uring && tsk->io_uring->io_wq) - io_wq_cancel_cb(tsk->io_uring->io_wq, - io_cancel_ctx_cb, ctx, true); - io_sq_thread_unpark(sqd); - } - - io_req_caches_free(ctx); - - if (WARN_ON_ONCE(time_after(jiffies, timeout))) { - /* there is little hope left, don't run it too often */ - interval = HZ * 60; - } - } while (!wait_for_completion_timeout(&ctx->ref_comp, interval)); - - init_completion(&exit.completion); - init_task_work(&exit.task_work, io_tctx_exit_cb); - exit.ctx = ctx; - /* - * Some may use context even when all refs and requests have been put, - * and they are free to do so while still holding uring_lock or - * completion_lock, see io_req_task_submit(). Apart from other work, - * this lock/unlock section also waits them to finish. - */ - mutex_lock(&ctx->uring_lock); - while (!list_empty(&ctx->tctx_list)) { - WARN_ON_ONCE(time_after(jiffies, timeout)); - - node = list_first_entry(&ctx->tctx_list, struct io_tctx_node, - ctx_node); - /* don't spin on a single task if cancellation failed */ - list_rotate_left(&ctx->tctx_list); - ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL); - if (WARN_ON_ONCE(ret)) - continue; - - mutex_unlock(&ctx->uring_lock); - wait_for_completion(&exit.completion); - mutex_lock(&ctx->uring_lock); - } - mutex_unlock(&ctx->uring_lock); - spin_lock(&ctx->completion_lock); - spin_unlock(&ctx->completion_lock); - - io_ring_ctx_free(ctx); -} - -/* Returns true if we found and killed one or more timeouts */ -static __cold bool io_kill_timeouts(struct io_ring_ctx *ctx, - struct task_struct *tsk, bool cancel_all) -{ - struct io_kiocb *req, *tmp; - int canceled = 0; - - spin_lock(&ctx->completion_lock); - spin_lock_irq(&ctx->timeout_lock); - list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { - if (io_match_task(req, tsk, cancel_all)) { - io_kill_timeout(req, -ECANCELED); - canceled++; - } - } - spin_unlock_irq(&ctx->timeout_lock); - io_commit_cqring(ctx); - spin_unlock(&ctx->completion_lock); - if (canceled != 0) - io_cqring_ev_posted(ctx); - return canceled != 0; -} - -static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) -{ - unsigned long index; - struct creds *creds; - - mutex_lock(&ctx->uring_lock); - percpu_ref_kill(&ctx->refs); - if (ctx->rings) - __io_cqring_overflow_flush(ctx, true); - xa_for_each(&ctx->personalities, index, creds) - io_unregister_personality(ctx, index); - mutex_unlock(&ctx->uring_lock); - - /* failed during ring init, it couldn't have issued any requests */ - if (ctx->rings) { - io_kill_timeouts(ctx, NULL, true); - io_poll_remove_all(ctx, NULL, true); - /* if we failed setting up the ctx, we might not have any rings */ - io_iopoll_try_reap_events(ctx); - } - - INIT_WORK(&ctx->exit_work, io_ring_exit_work); - /* - * Use system_unbound_wq to avoid spawning tons of event kworkers - * if we're exiting a ton of rings at the same time. It just adds - * noise and overhead, there's no discernable change in runtime - * over using system_wq. - */ - queue_work(system_unbound_wq, &ctx->exit_work); -} - -static int io_uring_release(struct inode *inode, struct file *file) -{ - struct io_ring_ctx *ctx = file->private_data; - - file->private_data = NULL; - io_ring_ctx_wait_and_kill(ctx); - return 0; -} - -struct io_task_cancel { - struct task_struct *task; - bool all; -}; - -static bool io_cancel_task_cb(struct io_wq_work *work, void *data) -{ - struct io_kiocb *req = container_of(work, struct io_kiocb, work); - struct io_task_cancel *cancel = data; - - return io_match_task_safe(req, cancel->task, cancel->all); -} - -static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx, - struct task_struct *task, - bool cancel_all) -{ - struct io_defer_entry *de; - LIST_HEAD(list); - - spin_lock(&ctx->completion_lock); - list_for_each_entry_reverse(de, &ctx->defer_list, list) { - if (io_match_task_safe(de->req, task, cancel_all)) { - list_cut_position(&list, &ctx->defer_list, &de->list); - break; - } - } - spin_unlock(&ctx->completion_lock); - if (list_empty(&list)) - return false; - - while (!list_empty(&list)) { - de = list_first_entry(&list, struct io_defer_entry, list); - list_del_init(&de->list); - io_req_complete_failed(de->req, -ECANCELED); - kfree(de); - } - return true; -} - -static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) -{ - struct io_tctx_node *node; - enum io_wq_cancel cret; - bool ret = false; - - mutex_lock(&ctx->uring_lock); - list_for_each_entry(node, &ctx->tctx_list, ctx_node) { - struct io_uring_task *tctx = node->task->io_uring; - - /* - * io_wq will stay alive while we hold uring_lock, because it's - * killed after ctx nodes, which requires to take the lock. - */ - if (!tctx || !tctx->io_wq) - continue; - cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true); - ret |= (cret != IO_WQ_CANCEL_NOTFOUND); - } - mutex_unlock(&ctx->uring_lock); - - return ret; -} - -static __cold void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, - struct task_struct *task, - bool cancel_all) -{ - struct io_task_cancel cancel = { .task = task, .all = cancel_all, }; - struct io_uring_task *tctx = task ? task->io_uring : NULL; - - /* failed during ring init, it couldn't have issued any requests */ - if (!ctx->rings) - return; - - while (1) { - enum io_wq_cancel cret; - bool ret = false; - - if (!task) { - ret |= io_uring_try_cancel_iowq(ctx); - } else if (tctx && tctx->io_wq) { - /* - * Cancels requests of all rings, not only @ctx, but - * it's fine as the task is in exit/exec. - */ - cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb, - &cancel, true); - ret |= (cret != IO_WQ_CANCEL_NOTFOUND); - } - - /* SQPOLL thread does its own polling */ - if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) || - (ctx->sq_data && ctx->sq_data->thread == current)) { - while (!wq_list_empty(&ctx->iopoll_list)) { - io_iopoll_try_reap_events(ctx); - ret = true; - } - } - - ret |= io_cancel_defer_files(ctx, task, cancel_all); - ret |= io_poll_remove_all(ctx, task, cancel_all); - ret |= io_kill_timeouts(ctx, task, cancel_all); - if (task) - ret |= io_run_task_work(); - if (!ret) - break; - cond_resched(); - } -} - -static int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) -{ - struct io_uring_task *tctx = current->io_uring; - struct io_tctx_node *node; - int ret; - - if (unlikely(!tctx)) { - ret = io_uring_alloc_task_context(current, ctx); - if (unlikely(ret)) - return ret; - - tctx = current->io_uring; - if (ctx->iowq_limits_set) { - unsigned int limits[2] = { ctx->iowq_limits[0], - ctx->iowq_limits[1], }; - - ret = io_wq_max_workers(tctx->io_wq, limits); - if (ret) - return ret; - } - } - if (!xa_load(&tctx->xa, (unsigned long)ctx)) { - node = kmalloc(sizeof(*node), GFP_KERNEL); - if (!node) - return -ENOMEM; - node->ctx = ctx; - node->task = current; - - ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx, - node, GFP_KERNEL)); - if (ret) { - kfree(node); - return ret; - } - - mutex_lock(&ctx->uring_lock); - list_add(&node->ctx_node, &ctx->tctx_list); - mutex_unlock(&ctx->uring_lock); - } - tctx->last = ctx; - return 0; -} - -/* - * Note that this task has used io_uring. We use it for cancelation purposes. - */ -static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) -{ - struct io_uring_task *tctx = current->io_uring; - - if (likely(tctx && tctx->last == ctx)) - return 0; - return __io_uring_add_tctx_node(ctx); -} - -/* - * Remove this io_uring_file -> task mapping. - */ -static __cold void io_uring_del_tctx_node(unsigned long index) -{ - struct io_uring_task *tctx = current->io_uring; - struct io_tctx_node *node; - - if (!tctx) - return; - node = xa_erase(&tctx->xa, index); - if (!node) - return; - - WARN_ON_ONCE(current != node->task); - WARN_ON_ONCE(list_empty(&node->ctx_node)); - - mutex_lock(&node->ctx->uring_lock); - list_del(&node->ctx_node); - mutex_unlock(&node->ctx->uring_lock); - - if (tctx->last == node->ctx) - tctx->last = NULL; - kfree(node); -} - -static __cold void io_uring_clean_tctx(struct io_uring_task *tctx) -{ - struct io_wq *wq = tctx->io_wq; - struct io_tctx_node *node; - unsigned long index; - - xa_for_each(&tctx->xa, index, node) { - io_uring_del_tctx_node(index); - cond_resched(); - } - if (wq) { - /* - * Must be after io_uring_del_tctx_node() (removes nodes under - * uring_lock) to avoid race with io_uring_try_cancel_iowq(). - */ - io_wq_put_and_exit(wq); - tctx->io_wq = NULL; - } -} - -static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) -{ - if (tracked) - return atomic_read(&tctx->inflight_tracked); - return percpu_counter_sum(&tctx->inflight); -} - -/* - * Find any io_uring ctx that this task has registered or done IO on, and cancel - * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation. - */ -static __cold void io_uring_cancel_generic(bool cancel_all, - struct io_sq_data *sqd) -{ - struct io_uring_task *tctx = current->io_uring; - struct io_ring_ctx *ctx; - s64 inflight; - DEFINE_WAIT(wait); - - WARN_ON_ONCE(sqd && sqd->thread != current); - - if (!current->io_uring) - return; - if (tctx->io_wq) - io_wq_exit_start(tctx->io_wq); - - atomic_inc(&tctx->in_idle); - do { - io_uring_drop_tctx_refs(current); - /* read completions before cancelations */ - inflight = tctx_inflight(tctx, !cancel_all); - if (!inflight) - break; - - if (!sqd) { - struct io_tctx_node *node; - unsigned long index; - - xa_for_each(&tctx->xa, index, node) { - /* sqpoll task will cancel all its requests */ - if (node->ctx->sq_data) - continue; - io_uring_try_cancel_requests(node->ctx, current, - cancel_all); - } - } else { - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) - io_uring_try_cancel_requests(ctx, current, - cancel_all); - } - - prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE); - io_run_task_work(); - io_uring_drop_tctx_refs(current); - - /* - * If we've seen completions, retry without waiting. This - * avoids a race where a completion comes in before we did - * prepare_to_wait(). - */ - if (inflight == tctx_inflight(tctx, !cancel_all)) - schedule(); - finish_wait(&tctx->wait, &wait); - } while (1); - - io_uring_clean_tctx(tctx); - if (cancel_all) { - /* - * We shouldn't run task_works after cancel, so just leave - * ->in_idle set for normal exit. - */ - atomic_dec(&tctx->in_idle); - /* for exec all current's requests should be gone, kill tctx */ - __io_uring_free(current); - } -} - -void __io_uring_cancel(bool cancel_all) -{ - io_uring_cancel_generic(cancel_all, NULL); -} - -void io_uring_unreg_ringfd(void) -{ - struct io_uring_task *tctx = current->io_uring; - int i; - - for (i = 0; i < IO_RINGFD_REG_MAX; i++) { - if (tctx->registered_rings[i]) { - fput(tctx->registered_rings[i]); - tctx->registered_rings[i] = NULL; - } - } -} - -static int io_ring_add_registered_fd(struct io_uring_task *tctx, int fd, - int start, int end) -{ - struct file *file; - int offset; - - for (offset = start; offset < end; offset++) { - offset = array_index_nospec(offset, IO_RINGFD_REG_MAX); - if (tctx->registered_rings[offset]) - continue; - - file = fget(fd); - if (!file) { - return -EBADF; - } else if (file->f_op != &io_uring_fops) { - fput(file); - return -EOPNOTSUPP; - } - tctx->registered_rings[offset] = file; - return offset; - } - - return -EBUSY; -} - -/* - * Register a ring fd to avoid fdget/fdput for each io_uring_enter() - * invocation. User passes in an array of struct io_uring_rsrc_update - * with ->data set to the ring_fd, and ->offset given for the desired - * index. If no index is desired, application may set ->offset == -1U - * and we'll find an available index. Returns number of entries - * successfully processed, or < 0 on error if none were processed. - */ -static int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, - unsigned nr_args) -{ - struct io_uring_rsrc_update __user *arg = __arg; - struct io_uring_rsrc_update reg; - struct io_uring_task *tctx; - int ret, i; - - if (!nr_args || nr_args > IO_RINGFD_REG_MAX) - return -EINVAL; - - mutex_unlock(&ctx->uring_lock); - ret = io_uring_add_tctx_node(ctx); - mutex_lock(&ctx->uring_lock); - if (ret) - return ret; - - tctx = current->io_uring; - for (i = 0; i < nr_args; i++) { - int start, end; - - if (copy_from_user(®, &arg[i], sizeof(reg))) { - ret = -EFAULT; - break; - } - - if (reg.resv) { - ret = -EINVAL; - break; - } - - if (reg.offset == -1U) { - start = 0; - end = IO_RINGFD_REG_MAX; - } else { - if (reg.offset >= IO_RINGFD_REG_MAX) { - ret = -EINVAL; - break; - } - start = reg.offset; - end = start + 1; - } - - ret = io_ring_add_registered_fd(tctx, reg.data, start, end); - if (ret < 0) - break; - - reg.offset = ret; - if (copy_to_user(&arg[i], ®, sizeof(reg))) { - fput(tctx->registered_rings[reg.offset]); - tctx->registered_rings[reg.offset] = NULL; - ret = -EFAULT; - break; - } - } - - return i ? i : ret; -} - -static int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg, - unsigned nr_args) -{ - struct io_uring_rsrc_update __user *arg = __arg; - struct io_uring_task *tctx = current->io_uring; - struct io_uring_rsrc_update reg; - int ret = 0, i; - - if (!nr_args || nr_args > IO_RINGFD_REG_MAX) - return -EINVAL; - if (!tctx) - return 0; - - for (i = 0; i < nr_args; i++) { - if (copy_from_user(®, &arg[i], sizeof(reg))) { - ret = -EFAULT; - break; - } - if (reg.resv || reg.data || reg.offset >= IO_RINGFD_REG_MAX) { - ret = -EINVAL; - break; - } - - reg.offset = array_index_nospec(reg.offset, IO_RINGFD_REG_MAX); - if (tctx->registered_rings[reg.offset]) { - fput(tctx->registered_rings[reg.offset]); - tctx->registered_rings[reg.offset] = NULL; - } - } - - return i ? i : ret; -} - -static void *io_uring_validate_mmap_request(struct file *file, - loff_t pgoff, size_t sz) -{ - struct io_ring_ctx *ctx = file->private_data; - loff_t offset = pgoff << PAGE_SHIFT; - struct page *page; - void *ptr; - - switch (offset) { - case IORING_OFF_SQ_RING: - case IORING_OFF_CQ_RING: - ptr = ctx->rings; - break; - case IORING_OFF_SQES: - ptr = ctx->sq_sqes; - break; - default: - return ERR_PTR(-EINVAL); - } - - page = virt_to_head_page(ptr); - if (sz > page_size(page)) - return ERR_PTR(-EINVAL); - - return ptr; -} - -#ifdef CONFIG_MMU - -static __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma) -{ - size_t sz = vma->vm_end - vma->vm_start; - unsigned long pfn; - void *ptr; - - ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff, sz); - if (IS_ERR(ptr)) - return PTR_ERR(ptr); - - pfn = virt_to_phys(ptr) >> PAGE_SHIFT; - return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot); -} - -#else /* !CONFIG_MMU */ - -static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) -{ - return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -EINVAL; -} - -static unsigned int io_uring_nommu_mmap_capabilities(struct file *file) -{ - return NOMMU_MAP_DIRECT | NOMMU_MAP_READ | NOMMU_MAP_WRITE; -} - -static unsigned long io_uring_nommu_get_unmapped_area(struct file *file, - unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags) -{ - void *ptr; - - ptr = io_uring_validate_mmap_request(file, pgoff, len); - if (IS_ERR(ptr)) - return PTR_ERR(ptr); - - return (unsigned long) ptr; -} - -#endif /* !CONFIG_MMU */ - -static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx) -{ - DEFINE_WAIT(wait); - - do { - if (!io_sqring_full(ctx)) - break; - prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE); - - if (!io_sqring_full(ctx)) - break; - schedule(); - } while (!signal_pending(current)); - - finish_wait(&ctx->sqo_sq_wait, &wait); - return 0; -} - -static int io_validate_ext_arg(unsigned flags, const void __user *argp, size_t argsz) -{ - if (flags & IORING_ENTER_EXT_ARG) { - struct io_uring_getevents_arg arg; - - if (argsz != sizeof(arg)) - return -EINVAL; - if (copy_from_user(&arg, argp, sizeof(arg))) - return -EFAULT; - } - return 0; -} - -static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz, - struct __kernel_timespec __user **ts, - const sigset_t __user **sig) -{ - struct io_uring_getevents_arg arg; - - /* - * If EXT_ARG isn't set, then we have no timespec and the argp pointer - * is just a pointer to the sigset_t. - */ - if (!(flags & IORING_ENTER_EXT_ARG)) { - *sig = (const sigset_t __user *) argp; - *ts = NULL; - return 0; - } - - /* - * EXT_ARG is set - ensure we agree on the size of it and copy in our - * timespec and sigset_t pointers if good. - */ - if (*argsz != sizeof(arg)) - return -EINVAL; - if (copy_from_user(&arg, argp, sizeof(arg))) - return -EFAULT; - if (arg.pad) - return -EINVAL; - *sig = u64_to_user_ptr(arg.sigmask); - *argsz = arg.sigmask_sz; - *ts = u64_to_user_ptr(arg.ts); - return 0; -} - -SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, - u32, min_complete, u32, flags, const void __user *, argp, - size_t, argsz) -{ - struct io_ring_ctx *ctx; - struct fd f; - long ret; - - io_run_task_work(); - - if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP | - IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG | - IORING_ENTER_REGISTERED_RING))) - return -EINVAL; - - /* - * Ring fd has been registered via IORING_REGISTER_RING_FDS, we - * need only dereference our task private array to find it. - */ - if (flags & IORING_ENTER_REGISTERED_RING) { - struct io_uring_task *tctx = current->io_uring; - - if (!tctx || fd >= IO_RINGFD_REG_MAX) - return -EINVAL; - fd = array_index_nospec(fd, IO_RINGFD_REG_MAX); - f.file = tctx->registered_rings[fd]; - f.flags = 0; - } else { - f = fdget(fd); - } - - if (unlikely(!f.file)) - return -EBADF; - - ret = -EOPNOTSUPP; - if (unlikely(f.file->f_op != &io_uring_fops)) - goto out_fput; - - ret = -ENXIO; - ctx = f.file->private_data; - if (unlikely(!percpu_ref_tryget(&ctx->refs))) - goto out_fput; - - ret = -EBADFD; - if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED)) - goto out; - - /* - * For SQ polling, the thread will do all submissions and completions. - * Just return the requested submit count, and wake the thread if - * we were asked to. - */ - ret = 0; - if (ctx->flags & IORING_SETUP_SQPOLL) { - io_cqring_overflow_flush(ctx); - - if (unlikely(ctx->sq_data->thread == NULL)) { - ret = -EOWNERDEAD; - goto out; - } - if (flags & IORING_ENTER_SQ_WAKEUP) - wake_up(&ctx->sq_data->wait); - if (flags & IORING_ENTER_SQ_WAIT) { - ret = io_sqpoll_wait_sq(ctx); - if (ret) - goto out; - } - ret = to_submit; - } else if (to_submit) { - ret = io_uring_add_tctx_node(ctx); - if (unlikely(ret)) - goto out; - - mutex_lock(&ctx->uring_lock); - ret = io_submit_sqes(ctx, to_submit); - if (ret != to_submit) { - mutex_unlock(&ctx->uring_lock); - goto out; - } - if ((flags & IORING_ENTER_GETEVENTS) && ctx->syscall_iopoll) - goto iopoll_locked; - mutex_unlock(&ctx->uring_lock); - } - if (flags & IORING_ENTER_GETEVENTS) { - int ret2; - if (ctx->syscall_iopoll) { - /* - * We disallow the app entering submit/complete with - * polling, but we still need to lock the ring to - * prevent racing with polled issue that got punted to - * a workqueue. - */ - mutex_lock(&ctx->uring_lock); -iopoll_locked: - ret2 = io_validate_ext_arg(flags, argp, argsz); - if (likely(!ret2)) { - min_complete = min(min_complete, - ctx->cq_entries); - ret2 = io_iopoll_check(ctx, min_complete); - } - mutex_unlock(&ctx->uring_lock); - } else { - const sigset_t __user *sig; - struct __kernel_timespec __user *ts; - - ret2 = io_get_ext_arg(flags, argp, &argsz, &ts, &sig); - if (likely(!ret2)) { - min_complete = min(min_complete, - ctx->cq_entries); - ret2 = io_cqring_wait(ctx, min_complete, sig, - argsz, ts); - } - } - - if (!ret) { - ret = ret2; - - /* - * EBADR indicates that one or more CQE were dropped. - * Once the user has been informed we can clear the bit - * as they are obviously ok with those drops. - */ - if (unlikely(ret2 == -EBADR)) - clear_bit(IO_CHECK_CQ_DROPPED_BIT, - &ctx->check_cq); - } - } - -out: - percpu_ref_put(&ctx->refs); -out_fput: - fdput(f); - return ret; -} - -#ifdef CONFIG_PROC_FS -static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id, - const struct cred *cred) -{ - struct user_namespace *uns = seq_user_ns(m); - struct group_info *gi; - kernel_cap_t cap; - unsigned __capi; - int g; - - seq_printf(m, "%5d\n", id); - seq_put_decimal_ull(m, "\tUid:\t", from_kuid_munged(uns, cred->uid)); - seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->euid)); - seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->suid)); - seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->fsuid)); - seq_put_decimal_ull(m, "\n\tGid:\t", from_kgid_munged(uns, cred->gid)); - seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->egid)); - seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->sgid)); - seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->fsgid)); - seq_puts(m, "\n\tGroups:\t"); - gi = cred->group_info; - for (g = 0; g < gi->ngroups; g++) { - seq_put_decimal_ull(m, g ? " " : "", - from_kgid_munged(uns, gi->gid[g])); - } - seq_puts(m, "\n\tCapEff:\t"); - cap = cred->cap_effective; - CAP_FOR_EACH_U32(__capi) - seq_put_hex_ll(m, NULL, cap.cap[CAP_LAST_U32 - __capi], 8); - seq_putc(m, '\n'); - return 0; -} - -static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, - struct seq_file *m) -{ - struct io_sq_data *sq = NULL; - struct io_overflow_cqe *ocqe; - struct io_rings *r = ctx->rings; - unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1; - unsigned int sq_head = READ_ONCE(r->sq.head); - unsigned int sq_tail = READ_ONCE(r->sq.tail); - unsigned int cq_head = READ_ONCE(r->cq.head); - unsigned int cq_tail = READ_ONCE(r->cq.tail); - unsigned int cq_shift = 0; - unsigned int sq_entries, cq_entries; - bool has_lock; - bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32); - unsigned int i; - - if (is_cqe32) - cq_shift = 1; - - /* - * we may get imprecise sqe and cqe info if uring is actively running - * since we get cached_sq_head and cached_cq_tail without uring_lock - * and sq_tail and cq_head are changed by userspace. But it's ok since - * we usually use these info when it is stuck. - */ - seq_printf(m, "SqMask:\t0x%x\n", sq_mask); - seq_printf(m, "SqHead:\t%u\n", sq_head); - seq_printf(m, "SqTail:\t%u\n", sq_tail); - seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head); - seq_printf(m, "CqMask:\t0x%x\n", cq_mask); - seq_printf(m, "CqHead:\t%u\n", cq_head); - seq_printf(m, "CqTail:\t%u\n", cq_tail); - seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail); - seq_printf(m, "SQEs:\t%u\n", sq_tail - ctx->cached_sq_head); - sq_entries = min(sq_tail - sq_head, ctx->sq_entries); - for (i = 0; i < sq_entries; i++) { - unsigned int entry = i + sq_head; - unsigned int sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]); - struct io_uring_sqe *sqe; - - if (sq_idx > sq_mask) - continue; - sqe = &ctx->sq_sqes[sq_idx]; - seq_printf(m, "%5u: opcode:%d, fd:%d, flags:%x, user_data:%llu\n", - sq_idx, sqe->opcode, sqe->fd, sqe->flags, - sqe->user_data); - } - seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head); - cq_entries = min(cq_tail - cq_head, ctx->cq_entries); - for (i = 0; i < cq_entries; i++) { - unsigned int entry = i + cq_head; - struct io_uring_cqe *cqe = &r->cqes[(entry & cq_mask) << cq_shift]; - - if (!is_cqe32) { - seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n", - entry & cq_mask, cqe->user_data, cqe->res, - cqe->flags); - } else { - seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x, " - "extra1:%llu, extra2:%llu\n", - entry & cq_mask, cqe->user_data, cqe->res, - cqe->flags, cqe->big_cqe[0], cqe->big_cqe[1]); - } - } - - /* - * Avoid ABBA deadlock between the seq lock and the io_uring mutex, - * since fdinfo case grabs it in the opposite direction of normal use - * cases. If we fail to get the lock, we just don't iterate any - * structures that could be going away outside the io_uring mutex. - */ - has_lock = mutex_trylock(&ctx->uring_lock); - - if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) { - sq = ctx->sq_data; - if (!sq->thread) - sq = NULL; - } - - seq_printf(m, "SqThread:\t%d\n", sq ? task_pid_nr(sq->thread) : -1); - seq_printf(m, "SqThreadCpu:\t%d\n", sq ? task_cpu(sq->thread) : -1); - seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); - for (i = 0; has_lock && i < ctx->nr_user_files; i++) { - struct file *f = io_file_from_index(ctx, i); - - if (f) - seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname); - else - seq_printf(m, "%5u: <none>\n", i); - } - seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); - for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) { - struct io_mapped_ubuf *buf = ctx->user_bufs[i]; - unsigned int len = buf->ubuf_end - buf->ubuf; - - seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len); - } - if (has_lock && !xa_empty(&ctx->personalities)) { - unsigned long index; - const struct cred *cred; - - seq_printf(m, "Personalities:\n"); - xa_for_each(&ctx->personalities, index, cred) - io_uring_show_cred(m, index, cred); - } - if (has_lock) - mutex_unlock(&ctx->uring_lock); - - seq_puts(m, "PollList:\n"); - spin_lock(&ctx->completion_lock); - for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { - struct hlist_head *list = &ctx->cancel_hash[i]; - struct io_kiocb *req; - - hlist_for_each_entry(req, list, hash_node) - seq_printf(m, " op=%d, task_works=%d\n", req->opcode, - task_work_pending(req->task)); - } - - seq_puts(m, "CqOverflowList:\n"); - list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) { - struct io_uring_cqe *cqe = &ocqe->cqe; - - seq_printf(m, " user_data=%llu, res=%d, flags=%x\n", - cqe->user_data, cqe->res, cqe->flags); - - } - - spin_unlock(&ctx->completion_lock); -} - -static __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f) -{ - struct io_ring_ctx *ctx = f->private_data; - - if (percpu_ref_tryget(&ctx->refs)) { - __io_uring_show_fdinfo(ctx, m); - percpu_ref_put(&ctx->refs); - } -} -#endif - -static const struct file_operations io_uring_fops = { - .release = io_uring_release, - .mmap = io_uring_mmap, -#ifndef CONFIG_MMU - .get_unmapped_area = io_uring_nommu_get_unmapped_area, - .mmap_capabilities = io_uring_nommu_mmap_capabilities, -#endif - .poll = io_uring_poll, -#ifdef CONFIG_PROC_FS - .show_fdinfo = io_uring_show_fdinfo, -#endif -}; - -static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, - struct io_uring_params *p) -{ - struct io_rings *rings; - size_t size, sq_array_offset; - - /* make sure these are sane, as we already accounted them */ - ctx->sq_entries = p->sq_entries; - ctx->cq_entries = p->cq_entries; - - size = rings_size(ctx, p->sq_entries, p->cq_entries, &sq_array_offset); - if (size == SIZE_MAX) - return -EOVERFLOW; - - rings = io_mem_alloc(size); - if (!rings) - return -ENOMEM; - - ctx->rings = rings; - ctx->sq_array = (u32 *)((char *)rings + sq_array_offset); - rings->sq_ring_mask = p->sq_entries - 1; - rings->cq_ring_mask = p->cq_entries - 1; - rings->sq_ring_entries = p->sq_entries; - rings->cq_ring_entries = p->cq_entries; - - if (p->flags & IORING_SETUP_SQE128) - size = array_size(2 * sizeof(struct io_uring_sqe), p->sq_entries); - else - size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); - if (size == SIZE_MAX) { - io_mem_free(ctx->rings); - ctx->rings = NULL; - return -EOVERFLOW; - } - - ctx->sq_sqes = io_mem_alloc(size); - if (!ctx->sq_sqes) { - io_mem_free(ctx->rings); - ctx->rings = NULL; - return -ENOMEM; - } - - return 0; -} - -static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) -{ - int ret, fd; - - fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); - if (fd < 0) - return fd; - - ret = io_uring_add_tctx_node(ctx); - if (ret) { - put_unused_fd(fd); - return ret; - } - fd_install(fd, file); - return fd; -} - -/* - * Allocate an anonymous fd, this is what constitutes the application - * visible backing of an io_uring instance. The application mmaps this - * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled, - * we have to tie this fd to a socket for file garbage collection purposes. - */ -static struct file *io_uring_get_file(struct io_ring_ctx *ctx) -{ - struct file *file; -#if defined(CONFIG_UNIX) - int ret; - - ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP, - &ctx->ring_sock); - if (ret) - return ERR_PTR(ret); -#endif - - file = anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx, - O_RDWR | O_CLOEXEC, NULL); -#if defined(CONFIG_UNIX) - if (IS_ERR(file)) { - sock_release(ctx->ring_sock); - ctx->ring_sock = NULL; - } else { - ctx->ring_sock->file = file; - } -#endif - return file; -} - -static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, - struct io_uring_params __user *params) -{ - struct io_ring_ctx *ctx; - struct file *file; - int ret; - - if (!entries) - return -EINVAL; - if (entries > IORING_MAX_ENTRIES) { - if (!(p->flags & IORING_SETUP_CLAMP)) - return -EINVAL; - entries = IORING_MAX_ENTRIES; - } - - /* - * Use twice as many entries for the CQ ring. It's possible for the - * application to drive a higher depth than the size of the SQ ring, - * since the sqes are only used at submission time. This allows for - * some flexibility in overcommitting a bit. If the application has - * set IORING_SETUP_CQSIZE, it will have passed in the desired number - * of CQ ring entries manually. - */ - p->sq_entries = roundup_pow_of_two(entries); - if (p->flags & IORING_SETUP_CQSIZE) { - /* - * If IORING_SETUP_CQSIZE is set, we do the same roundup - * to a power-of-two, if it isn't already. We do NOT impose - * any cq vs sq ring sizing. - */ - if (!p->cq_entries) - return -EINVAL; - if (p->cq_entries > IORING_MAX_CQ_ENTRIES) { - if (!(p->flags & IORING_SETUP_CLAMP)) - return -EINVAL; - p->cq_entries = IORING_MAX_CQ_ENTRIES; - } - p->cq_entries = roundup_pow_of_two(p->cq_entries); - if (p->cq_entries < p->sq_entries) - return -EINVAL; - } else { - p->cq_entries = 2 * p->sq_entries; - } - - ctx = io_ring_ctx_alloc(p); - if (!ctx) - return -ENOMEM; - - /* - * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user - * space applications don't need to do io completion events - * polling again, they can rely on io_sq_thread to do polling - * work, which can reduce cpu usage and uring_lock contention. - */ - if (ctx->flags & IORING_SETUP_IOPOLL && - !(ctx->flags & IORING_SETUP_SQPOLL)) - ctx->syscall_iopoll = 1; - - ctx->compat = in_compat_syscall(); - if (!capable(CAP_IPC_LOCK)) - ctx->user = get_uid(current_user()); - - /* - * For SQPOLL, we just need a wakeup, always. For !SQPOLL, if - * COOP_TASKRUN is set, then IPIs are never needed by the app. - */ - ret = -EINVAL; - if (ctx->flags & IORING_SETUP_SQPOLL) { - /* IPI related flags don't make sense with SQPOLL */ - if (ctx->flags & (IORING_SETUP_COOP_TASKRUN | - IORING_SETUP_TASKRUN_FLAG)) - goto err; - ctx->notify_method = TWA_SIGNAL_NO_IPI; - } else if (ctx->flags & IORING_SETUP_COOP_TASKRUN) { - ctx->notify_method = TWA_SIGNAL_NO_IPI; - } else { - if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) - goto err; - ctx->notify_method = TWA_SIGNAL; - } - - /* - * This is just grabbed for accounting purposes. When a process exits, - * the mm is exited and dropped before the files, hence we need to hang - * on to this mm purely for the purposes of being able to unaccount - * memory (locked/pinned vm). It's not used for anything else. - */ - mmgrab(current->mm); - ctx->mm_account = current->mm; - - ret = io_allocate_scq_urings(ctx, p); - if (ret) - goto err; - - ret = io_sq_offload_create(ctx, p); - if (ret) - goto err; - /* always set a rsrc node */ - ret = io_rsrc_node_switch_start(ctx); - if (ret) - goto err; - io_rsrc_node_switch(ctx, NULL); - - memset(&p->sq_off, 0, sizeof(p->sq_off)); - p->sq_off.head = offsetof(struct io_rings, sq.head); - p->sq_off.tail = offsetof(struct io_rings, sq.tail); - p->sq_off.ring_mask = offsetof(struct io_rings, sq_ring_mask); - p->sq_off.ring_entries = offsetof(struct io_rings, sq_ring_entries); - p->sq_off.flags = offsetof(struct io_rings, sq_flags); - p->sq_off.dropped = offsetof(struct io_rings, sq_dropped); - p->sq_off.array = (char *)ctx->sq_array - (char *)ctx->rings; - - memset(&p->cq_off, 0, sizeof(p->cq_off)); - p->cq_off.head = offsetof(struct io_rings, cq.head); - p->cq_off.tail = offsetof(struct io_rings, cq.tail); - p->cq_off.ring_mask = offsetof(struct io_rings, cq_ring_mask); - p->cq_off.ring_entries = offsetof(struct io_rings, cq_ring_entries); - p->cq_off.overflow = offsetof(struct io_rings, cq_overflow); - p->cq_off.cqes = offsetof(struct io_rings, cqes); - p->cq_off.flags = offsetof(struct io_rings, cq_flags); - - p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | - IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | - IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | - IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | - IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | - IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP | - IORING_FEAT_LINKED_FILE; - - if (copy_to_user(params, p, sizeof(*p))) { - ret = -EFAULT; - goto err; - } - - file = io_uring_get_file(ctx); - if (IS_ERR(file)) { - ret = PTR_ERR(file); - goto err; - } - - /* - * Install ring fd as the very last thing, so we don't risk someone - * having closed it before we finish setup - */ - ret = io_uring_install_fd(ctx, file); - if (ret < 0) { - /* fput will clean it up */ - fput(file); - return ret; - } - - trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); - return ret; -err: - io_ring_ctx_wait_and_kill(ctx); - return ret; -} - -/* - * Sets up an aio uring context, and returns the fd. Applications asks for a - * ring size, we return the actual sq/cq ring sizes (among other things) in the - * params structure passed in. - */ -static long io_uring_setup(u32 entries, struct io_uring_params __user *params) -{ - struct io_uring_params p; - int i; - - if (copy_from_user(&p, params, sizeof(p))) - return -EFAULT; - for (i = 0; i < ARRAY_SIZE(p.resv); i++) { - if (p.resv[i]) - return -EINVAL; - } - - if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL | - IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE | - IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ | - IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL | - IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG | - IORING_SETUP_SQE128 | IORING_SETUP_CQE32)) - return -EINVAL; - - return io_uring_create(entries, &p, params); -} - -SYSCALL_DEFINE2(io_uring_setup, u32, entries, - struct io_uring_params __user *, params) -{ - return io_uring_setup(entries, params); -} - -static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg, - unsigned nr_args) -{ - struct io_uring_probe *p; - size_t size; - int i, ret; - - size = struct_size(p, ops, nr_args); - if (size == SIZE_MAX) - return -EOVERFLOW; - p = kzalloc(size, GFP_KERNEL); - if (!p) - return -ENOMEM; - - ret = -EFAULT; - if (copy_from_user(p, arg, size)) - goto out; - ret = -EINVAL; - if (memchr_inv(p, 0, size)) - goto out; - - p->last_op = IORING_OP_LAST - 1; - if (nr_args > IORING_OP_LAST) - nr_args = IORING_OP_LAST; - - for (i = 0; i < nr_args; i++) { - p->ops[i].op = i; - if (!io_op_defs[i].not_supported) - p->ops[i].flags = IO_URING_OP_SUPPORTED; - } - p->ops_len = i; - - ret = 0; - if (copy_to_user(arg, p, size)) - ret = -EFAULT; -out: - kfree(p); - return ret; -} - -static int io_register_personality(struct io_ring_ctx *ctx) -{ - const struct cred *creds; - u32 id; - int ret; - - creds = get_current_cred(); - - ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds, - XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL); - if (ret < 0) { - put_cred(creds); - return ret; - } - return id; -} - -static __cold int io_register_restrictions(struct io_ring_ctx *ctx, - void __user *arg, unsigned int nr_args) -{ - struct io_uring_restriction *res; - size_t size; - int i, ret; - - /* Restrictions allowed only if rings started disabled */ - if (!(ctx->flags & IORING_SETUP_R_DISABLED)) - return -EBADFD; - - /* We allow only a single restrictions registration */ - if (ctx->restrictions.registered) - return -EBUSY; - - if (!arg || nr_args > IORING_MAX_RESTRICTIONS) - return -EINVAL; - - size = array_size(nr_args, sizeof(*res)); - if (size == SIZE_MAX) - return -EOVERFLOW; - - res = memdup_user(arg, size); - if (IS_ERR(res)) - return PTR_ERR(res); - - ret = 0; - - for (i = 0; i < nr_args; i++) { - switch (res[i].opcode) { - case IORING_RESTRICTION_REGISTER_OP: - if (res[i].register_op >= IORING_REGISTER_LAST) { - ret = -EINVAL; - goto out; - } - - __set_bit(res[i].register_op, - ctx->restrictions.register_op); - break; - case IORING_RESTRICTION_SQE_OP: - if (res[i].sqe_op >= IORING_OP_LAST) { - ret = -EINVAL; - goto out; - } - - __set_bit(res[i].sqe_op, ctx->restrictions.sqe_op); - break; - case IORING_RESTRICTION_SQE_FLAGS_ALLOWED: - ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags; - break; - case IORING_RESTRICTION_SQE_FLAGS_REQUIRED: - ctx->restrictions.sqe_flags_required = res[i].sqe_flags; - break; - default: - ret = -EINVAL; - goto out; - } - } - -out: - /* Reset all restrictions if an error happened */ - if (ret != 0) - memset(&ctx->restrictions, 0, sizeof(ctx->restrictions)); - else - ctx->restrictions.registered = true; - - kfree(res); - return ret; -} - -static int io_register_enable_rings(struct io_ring_ctx *ctx) -{ - if (!(ctx->flags & IORING_SETUP_R_DISABLED)) - return -EBADFD; - - if (ctx->restrictions.registered) - ctx->restricted = 1; - - ctx->flags &= ~IORING_SETUP_R_DISABLED; - if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait)) - wake_up(&ctx->sq_data->wait); - return 0; -} - -static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, - struct io_uring_rsrc_update2 *up, - unsigned nr_args) -{ - __u32 tmp; - int err; - - if (check_add_overflow(up->offset, nr_args, &tmp)) - return -EOVERFLOW; - err = io_rsrc_node_switch_start(ctx); - if (err) - return err; - - switch (type) { - case IORING_RSRC_FILE: - return __io_sqe_files_update(ctx, up, nr_args); - case IORING_RSRC_BUFFER: - return __io_sqe_buffers_update(ctx, up, nr_args); - } - return -EINVAL; -} - -static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, - unsigned nr_args) -{ - struct io_uring_rsrc_update2 up; - - if (!nr_args) - return -EINVAL; - memset(&up, 0, sizeof(up)); - if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update))) - return -EFAULT; - if (up.resv || up.resv2) - return -EINVAL; - return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args); -} - -static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, - unsigned size, unsigned type) -{ - struct io_uring_rsrc_update2 up; - - if (size != sizeof(up)) - return -EINVAL; - if (copy_from_user(&up, arg, sizeof(up))) - return -EFAULT; - if (!up.nr || up.resv || up.resv2) - return -EINVAL; - return __io_register_rsrc_update(ctx, type, &up, up.nr); -} - -static __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, - unsigned int size, unsigned int type) -{ - struct io_uring_rsrc_register rr; - - /* keep it extendible */ - if (size != sizeof(rr)) - return -EINVAL; - - memset(&rr, 0, sizeof(rr)); - if (copy_from_user(&rr, arg, size)) - return -EFAULT; - if (!rr.nr || rr.resv2) - return -EINVAL; - if (rr.flags & ~IORING_RSRC_REGISTER_SPARSE) - return -EINVAL; - - switch (type) { - case IORING_RSRC_FILE: - if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data) - break; - return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data), - rr.nr, u64_to_user_ptr(rr.tags)); - case IORING_RSRC_BUFFER: - if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data) - break; - return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data), - rr.nr, u64_to_user_ptr(rr.tags)); - } - return -EINVAL; -} - -static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, - void __user *arg, unsigned len) -{ - struct io_uring_task *tctx = current->io_uring; - cpumask_var_t new_mask; - int ret; - - if (!tctx || !tctx->io_wq) - return -EINVAL; - - if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) - return -ENOMEM; - - cpumask_clear(new_mask); - if (len > cpumask_size()) - len = cpumask_size(); - - if (in_compat_syscall()) { - ret = compat_get_bitmap(cpumask_bits(new_mask), - (const compat_ulong_t __user *)arg, - len * 8 /* CHAR_BIT */); - } else { - ret = copy_from_user(new_mask, arg, len); - } - - if (ret) { - free_cpumask_var(new_mask); - return -EFAULT; - } - - ret = io_wq_cpu_affinity(tctx->io_wq, new_mask); - free_cpumask_var(new_mask); - return ret; -} - -static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx) -{ - struct io_uring_task *tctx = current->io_uring; - - if (!tctx || !tctx->io_wq) - return -EINVAL; - - return io_wq_cpu_affinity(tctx->io_wq, NULL); -} - -static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx, - void __user *arg) - __must_hold(&ctx->uring_lock) -{ - struct io_tctx_node *node; - struct io_uring_task *tctx = NULL; - struct io_sq_data *sqd = NULL; - __u32 new_count[2]; - int i, ret; - - if (copy_from_user(new_count, arg, sizeof(new_count))) - return -EFAULT; - for (i = 0; i < ARRAY_SIZE(new_count); i++) - if (new_count[i] > INT_MAX) - return -EINVAL; - - if (ctx->flags & IORING_SETUP_SQPOLL) { - sqd = ctx->sq_data; - if (sqd) { - /* - * Observe the correct sqd->lock -> ctx->uring_lock - * ordering. Fine to drop uring_lock here, we hold - * a ref to the ctx. - */ - refcount_inc(&sqd->refs); - mutex_unlock(&ctx->uring_lock); - mutex_lock(&sqd->lock); - mutex_lock(&ctx->uring_lock); - if (sqd->thread) - tctx = sqd->thread->io_uring; - } - } else { - tctx = current->io_uring; - } - - BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits)); - - for (i = 0; i < ARRAY_SIZE(new_count); i++) - if (new_count[i]) - ctx->iowq_limits[i] = new_count[i]; - ctx->iowq_limits_set = true; - - if (tctx && tctx->io_wq) { - ret = io_wq_max_workers(tctx->io_wq, new_count); - if (ret) - goto err; - } else { - memset(new_count, 0, sizeof(new_count)); - } - - if (sqd) { - mutex_unlock(&sqd->lock); - io_put_sq_data(sqd); - } - - if (copy_to_user(arg, new_count, sizeof(new_count))) - return -EFAULT; - - /* that's it for SQPOLL, only the SQPOLL task creates requests */ - if (sqd) - return 0; - - /* now propagate the restriction to all registered users */ - list_for_each_entry(node, &ctx->tctx_list, ctx_node) { - struct io_uring_task *tctx = node->task->io_uring; - - if (WARN_ON_ONCE(!tctx->io_wq)) - continue; - - for (i = 0; i < ARRAY_SIZE(new_count); i++) - new_count[i] = ctx->iowq_limits[i]; - /* ignore errors, it always returns zero anyway */ - (void)io_wq_max_workers(tctx->io_wq, new_count); - } - return 0; -err: - if (sqd) { - mutex_unlock(&sqd->lock); - io_put_sq_data(sqd); - } - return ret; -} - -static int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) -{ - struct io_uring_buf_ring *br; - struct io_uring_buf_reg reg; - struct io_buffer_list *bl; - struct page **pages; - int nr_pages; - - if (copy_from_user(®, arg, sizeof(reg))) - return -EFAULT; - - if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2]) - return -EINVAL; - if (!reg.ring_addr) - return -EFAULT; - if (reg.ring_addr & ~PAGE_MASK) - return -EINVAL; - if (!is_power_of_2(reg.ring_entries)) - return -EINVAL; - - /* cannot disambiguate full vs empty due to head/tail size */ - if (reg.ring_entries >= 65536) - return -EINVAL; - - if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) { - int ret = io_init_bl_list(ctx); - if (ret) - return ret; - } - - bl = io_buffer_get_list(ctx, reg.bgid); - if (bl) { - /* if mapped buffer ring OR classic exists, don't allow */ - if (bl->buf_nr_pages || !list_empty(&bl->buf_list)) - return -EEXIST; - } else { - bl = kzalloc(sizeof(*bl), GFP_KERNEL); - if (!bl) - return -ENOMEM; - } - - pages = io_pin_pages(reg.ring_addr, - struct_size(br, bufs, reg.ring_entries), - &nr_pages); - if (IS_ERR(pages)) { - kfree(bl); - return PTR_ERR(pages); - } - - br = page_address(pages[0]); - bl->buf_pages = pages; - bl->buf_nr_pages = nr_pages; - bl->nr_entries = reg.ring_entries; - bl->buf_ring = br; - bl->mask = reg.ring_entries - 1; - io_buffer_add_list(ctx, bl, reg.bgid); - return 0; -} - -static int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) -{ - struct io_uring_buf_reg reg; - struct io_buffer_list *bl; - - if (copy_from_user(®, arg, sizeof(reg))) - return -EFAULT; - if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2]) - return -EINVAL; - - bl = io_buffer_get_list(ctx, reg.bgid); - if (!bl) - return -ENOENT; - if (!bl->buf_nr_pages) - return -EINVAL; - - __io_remove_buffers(ctx, bl, -1U); - if (bl->bgid >= BGID_ARRAY) { - xa_erase(&ctx->io_bl_xa, bl->bgid); - kfree(bl); - } - return 0; -} - -static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, - void __user *arg, unsigned nr_args) - __releases(ctx->uring_lock) - __acquires(ctx->uring_lock) -{ - int ret; - - /* - * We're inside the ring mutex, if the ref is already dying, then - * someone else killed the ctx or is already going through - * io_uring_register(). - */ - if (percpu_ref_is_dying(&ctx->refs)) - return -ENXIO; - - if (ctx->restricted) { - if (opcode >= IORING_REGISTER_LAST) - return -EINVAL; - opcode = array_index_nospec(opcode, IORING_REGISTER_LAST); - if (!test_bit(opcode, ctx->restrictions.register_op)) - return -EACCES; - } - - switch (opcode) { - case IORING_REGISTER_BUFFERS: - ret = -EFAULT; - if (!arg) - break; - ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL); - break; - case IORING_UNREGISTER_BUFFERS: - ret = -EINVAL; - if (arg || nr_args) - break; - ret = io_sqe_buffers_unregister(ctx); - break; - case IORING_REGISTER_FILES: - ret = -EFAULT; - if (!arg) - break; - ret = io_sqe_files_register(ctx, arg, nr_args, NULL); - break; - case IORING_UNREGISTER_FILES: - ret = -EINVAL; - if (arg || nr_args) - break; - ret = io_sqe_files_unregister(ctx); - break; - case IORING_REGISTER_FILES_UPDATE: - ret = io_register_files_update(ctx, arg, nr_args); - break; - case IORING_REGISTER_EVENTFD: - ret = -EINVAL; - if (nr_args != 1) - break; - ret = io_eventfd_register(ctx, arg, 0); - break; - case IORING_REGISTER_EVENTFD_ASYNC: - ret = -EINVAL; - if (nr_args != 1) - break; - ret = io_eventfd_register(ctx, arg, 1); - break; - case IORING_UNREGISTER_EVENTFD: - ret = -EINVAL; - if (arg || nr_args) - break; - ret = io_eventfd_unregister(ctx); - break; - case IORING_REGISTER_PROBE: - ret = -EINVAL; - if (!arg || nr_args > 256) - break; - ret = io_probe(ctx, arg, nr_args); - break; - case IORING_REGISTER_PERSONALITY: - ret = -EINVAL; - if (arg || nr_args) - break; - ret = io_register_personality(ctx); - break; - case IORING_UNREGISTER_PERSONALITY: - ret = -EINVAL; - if (arg) - break; - ret = io_unregister_personality(ctx, nr_args); - break; - case IORING_REGISTER_ENABLE_RINGS: - ret = -EINVAL; - if (arg || nr_args) - break; - ret = io_register_enable_rings(ctx); - break; - case IORING_REGISTER_RESTRICTIONS: - ret = io_register_restrictions(ctx, arg, nr_args); - break; - case IORING_REGISTER_FILES2: - ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE); - break; - case IORING_REGISTER_FILES_UPDATE2: - ret = io_register_rsrc_update(ctx, arg, nr_args, - IORING_RSRC_FILE); - break; - case IORING_REGISTER_BUFFERS2: - ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER); - break; - case IORING_REGISTER_BUFFERS_UPDATE: - ret = io_register_rsrc_update(ctx, arg, nr_args, - IORING_RSRC_BUFFER); - break; - case IORING_REGISTER_IOWQ_AFF: - ret = -EINVAL; - if (!arg || !nr_args) - break; - ret = io_register_iowq_aff(ctx, arg, nr_args); - break; - case IORING_UNREGISTER_IOWQ_AFF: - ret = -EINVAL; - if (arg || nr_args) - break; - ret = io_unregister_iowq_aff(ctx); - break; - case IORING_REGISTER_IOWQ_MAX_WORKERS: - ret = -EINVAL; - if (!arg || nr_args != 2) - break; - ret = io_register_iowq_max_workers(ctx, arg); - break; - case IORING_REGISTER_RING_FDS: - ret = io_ringfd_register(ctx, arg, nr_args); - break; - case IORING_UNREGISTER_RING_FDS: - ret = io_ringfd_unregister(ctx, arg, nr_args); - break; - case IORING_REGISTER_PBUF_RING: - ret = -EINVAL; - if (!arg || nr_args != 1) - break; - ret = io_register_pbuf_ring(ctx, arg); - break; - case IORING_UNREGISTER_PBUF_RING: - ret = -EINVAL; - if (!arg || nr_args != 1) - break; - ret = io_unregister_pbuf_ring(ctx, arg); - break; - default: - ret = -EINVAL; - break; - } - - return ret; -} - -SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, - void __user *, arg, unsigned int, nr_args) -{ - struct io_ring_ctx *ctx; - long ret = -EBADF; - struct fd f; - - f = fdget(fd); - if (!f.file) - return -EBADF; - - ret = -EOPNOTSUPP; - if (f.file->f_op != &io_uring_fops) - goto out_fput; - - ctx = f.file->private_data; - - io_run_task_work(); - - mutex_lock(&ctx->uring_lock); - ret = __io_uring_register(ctx, opcode, arg, nr_args); - mutex_unlock(&ctx->uring_lock); - trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, ret); -out_fput: - fdput(f); - return ret; -} - -static int __init io_uring_init(void) -{ -#define __BUILD_BUG_VERIFY_ELEMENT(stype, eoffset, etype, ename) do { \ - BUILD_BUG_ON(offsetof(stype, ename) != eoffset); \ - BUILD_BUG_ON(sizeof(etype) != sizeof_field(stype, ename)); \ -} while (0) - -#define BUILD_BUG_SQE_ELEM(eoffset, etype, ename) \ - __BUILD_BUG_VERIFY_ELEMENT(struct io_uring_sqe, eoffset, etype, ename) - BUILD_BUG_ON(sizeof(struct io_uring_sqe) != 64); - BUILD_BUG_SQE_ELEM(0, __u8, opcode); - BUILD_BUG_SQE_ELEM(1, __u8, flags); - BUILD_BUG_SQE_ELEM(2, __u16, ioprio); - BUILD_BUG_SQE_ELEM(4, __s32, fd); - BUILD_BUG_SQE_ELEM(8, __u64, off); - BUILD_BUG_SQE_ELEM(8, __u64, addr2); - BUILD_BUG_SQE_ELEM(16, __u64, addr); - BUILD_BUG_SQE_ELEM(16, __u64, splice_off_in); - BUILD_BUG_SQE_ELEM(24, __u32, len); - BUILD_BUG_SQE_ELEM(28, __kernel_rwf_t, rw_flags); - BUILD_BUG_SQE_ELEM(28, /* compat */ int, rw_flags); - BUILD_BUG_SQE_ELEM(28, /* compat */ __u32, rw_flags); - BUILD_BUG_SQE_ELEM(28, __u32, fsync_flags); - BUILD_BUG_SQE_ELEM(28, /* compat */ __u16, poll_events); - BUILD_BUG_SQE_ELEM(28, __u32, poll32_events); - BUILD_BUG_SQE_ELEM(28, __u32, sync_range_flags); - BUILD_BUG_SQE_ELEM(28, __u32, msg_flags); - BUILD_BUG_SQE_ELEM(28, __u32, timeout_flags); - BUILD_BUG_SQE_ELEM(28, __u32, accept_flags); - BUILD_BUG_SQE_ELEM(28, __u32, cancel_flags); - BUILD_BUG_SQE_ELEM(28, __u32, open_flags); - BUILD_BUG_SQE_ELEM(28, __u32, statx_flags); - BUILD_BUG_SQE_ELEM(28, __u32, fadvise_advice); - BUILD_BUG_SQE_ELEM(28, __u32, splice_flags); - BUILD_BUG_SQE_ELEM(32, __u64, user_data); - BUILD_BUG_SQE_ELEM(40, __u16, buf_index); - BUILD_BUG_SQE_ELEM(40, __u16, buf_group); - BUILD_BUG_SQE_ELEM(42, __u16, personality); - BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); - BUILD_BUG_SQE_ELEM(44, __u32, file_index); - BUILD_BUG_SQE_ELEM(48, __u64, addr3); - - BUILD_BUG_ON(sizeof(struct io_uring_files_update) != - sizeof(struct io_uring_rsrc_update)); - BUILD_BUG_ON(sizeof(struct io_uring_rsrc_update) > - sizeof(struct io_uring_rsrc_update2)); - - /* ->buf_index is u16 */ - BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16)); - BUILD_BUG_ON(BGID_ARRAY * sizeof(struct io_buffer_list) > PAGE_SIZE); - BUILD_BUG_ON(offsetof(struct io_uring_buf_ring, bufs) != 0); - BUILD_BUG_ON(offsetof(struct io_uring_buf, resv) != - offsetof(struct io_uring_buf_ring, tail)); - - /* should fit into one byte */ - BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8)); - BUILD_BUG_ON(SQE_COMMON_FLAGS >= (1 << 8)); - BUILD_BUG_ON((SQE_VALID_FLAGS | SQE_COMMON_FLAGS) != SQE_VALID_FLAGS); - - BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); - BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int)); - - BUILD_BUG_ON(sizeof(atomic_t) != sizeof(u32)); - - BUILD_BUG_ON(sizeof(struct io_uring_cmd) > 64); - - req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC | - SLAB_ACCOUNT); - return 0; -}; -__initcall(io_uring_init); diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 0a22a2faf552..e1c4617de771 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -176,7 +176,7 @@ nlm_delete_file(struct nlm_file *file) } } -static int nlm_unlock_files(struct nlm_file *file) +static int nlm_unlock_files(struct nlm_file *file, fl_owner_t owner) { struct file_lock lock; @@ -184,6 +184,7 @@ static int nlm_unlock_files(struct nlm_file *file) lock.fl_type = F_UNLCK; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; + lock.fl_owner = owner; if (file->f_file[O_RDONLY] && vfs_lock_file(file->f_file[O_RDONLY], F_SETLK, &lock, NULL)) goto out_err; @@ -225,7 +226,7 @@ again: if (match(lockhost, host)) { spin_unlock(&flctx->flc_lock); - if (nlm_unlock_files(file)) + if (nlm_unlock_files(file, fl->fl_owner)) return 1; goto again; } @@ -282,11 +283,10 @@ nlm_file_inuse(struct nlm_file *file) static void nlm_close_files(struct nlm_file *file) { - struct file *f; - - for (f = file->f_file[0]; f <= file->f_file[1]; f++) - if (f) - nlmsvc_ops->fclose(f); + if (file->f_file[O_RDONLY]) + nlmsvc_ops->fclose(file->f_file[O_RDONLY]); + if (file->f_file[O_WRONLY]) + nlmsvc_ops->fclose(file->f_file[O_WRONLY]); } /* diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 42f892c5712e..0ce535852151 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -319,8 +319,9 @@ zero_out: * conflicting writes once the folio is grabbed and locked. It is passed a * pointer to the fsdata cookie that gets returned to the VM to be passed to * write_end. It is permitted to sleep. It should return 0 if the request - * should go ahead; unlock the folio and return -EAGAIN to cause the folio to - * be regot; or return an error. + * should go ahead or it may return an error. It may also unlock and put the + * folio, provided it sets ``*foliop`` to NULL, in which case a return of 0 + * will cause the folio to be re-got and the process to be retried. * * The calling netfs must initialise a netfs context contiguous to the vfs * inode before calling this. @@ -348,13 +349,13 @@ retry: if (ctx->ops->check_write_begin) { /* Allow the netfs (eg. ceph) to flush conflicts. */ - ret = ctx->ops->check_write_begin(file, pos, len, folio, _fsdata); + ret = ctx->ops->check_write_begin(file, pos, len, &folio, _fsdata); if (ret < 0) { trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); - if (ret == -EAGAIN) - goto retry; goto error; } + if (!folio) + goto retry; } if (folio_test_uptodate(folio)) @@ -416,8 +417,10 @@ have_folio_no_wait: error_put: netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); error: - folio_unlock(folio); - folio_put(folio); + if (folio) { + folio_unlock(folio); + folio_put(folio); + } _leave(" = %d", ret); return ret; } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 61b2aae81abb..2acea7792bb2 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -470,6 +470,15 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen, return nfserr_bad_xdr; } } + if (bmval[1] & FATTR4_WORD1_TIME_CREATE) { + struct timespec64 ts; + + /* No Linux filesystem supports setting this attribute. */ + bmval[1] &= ~FATTR4_WORD1_TIME_CREATE; + status = nfsd4_decode_nfstime4(argp, &ts); + if (status) + return status; + } if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) { u32 set_it; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 847b482155ae..9a8b09afc173 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -465,7 +465,8 @@ static inline bool nfsd_attrs_supported(u32 minorversion, const u32 *bmval) (FATTR4_WORD0_SIZE | FATTR4_WORD0_ACL) #define NFSD_WRITEABLE_ATTRS_WORD1 \ (FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP \ - | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) + | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_CREATE \ + | FATTR4_WORD1_TIME_MODIFY_SET) #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #define MAYBE_FATTR4_WORD2_SECURITY_LABEL \ FATTR4_WORD2_SECURITY_LABEL diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 1344f7d475d3..aecda4fc95f5 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -198,6 +198,9 @@ static inline int nilfs_acl_chmod(struct inode *inode) static inline int nilfs_init_acl(struct inode *inode, struct inode *dir) { + if (S_ISLNK(inode->i_mode)) + return 0; + inode->i_mode &= ~current_umask(); return 0; } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index e0a2e0468ee7..1ce5c9698393 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1003,6 +1003,9 @@ ovl_posix_acl_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size) { + if (!IS_POSIXACL(inode)) + return -EOPNOTSUPP; + return ovl_xattr_get(dentry, inode, handler->name, buffer, size); } @@ -1018,6 +1021,9 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler, struct posix_acl *acl = NULL; int err; + if (!IS_POSIXACL(inode)) + return -EOPNOTSUPP; + /* Check that everything is OK before copy-up */ if (value) { acl = posix_acl_from_xattr(&init_user_ns, value, size); @@ -1960,6 +1966,20 @@ static struct dentry *ovl_get_root(struct super_block *sb, return root; } +static bool ovl_has_idmapped_layers(struct ovl_fs *ofs) +{ + + unsigned int i; + const struct vfsmount *mnt; + + for (i = 0; i < ofs->numlayer; i++) { + mnt = ofs->layers[i].mnt; + if (mnt && is_idmapped_mnt(mnt)) + return true; + } + return false; +} + static int ovl_fill_super(struct super_block *sb, void *data, int silent) { struct path upperpath = { }; @@ -2129,7 +2149,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_xattr = ofs->config.userxattr ? ovl_user_xattr_handlers : ovl_trusted_xattr_handlers; sb->s_fs_info = ofs; - sb->s_flags |= SB_POSIXACL; + if (ovl_has_idmapped_layers(ofs)) + pr_warn("POSIX ACLs are not yet supported with idmapped layers, mounting without ACL support.\n"); + else + sb->s_flags |= SB_POSIXACL; sb->s_iflags |= SB_I_SKIP_SYNC; err = -ENOMEM; diff --git a/fs/remap_range.c b/fs/remap_range.c index e112b5424cdb..881a306ee247 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -71,7 +71,8 @@ static int generic_remap_checks(struct file *file_in, loff_t pos_in, * Otherwise, make sure the count is also block-aligned, having * already confirmed the starting offsets' block alignment. */ - if (pos_in + count == size_in) { + if (pos_in + count == size_in && + (!(remap_flags & REMAP_FILE_DEDUP) || pos_out + count == size_out)) { bcount = ALIGN(size_in, bs) - pos_in; } else { if (!IS_ALIGNED(count, bs)) diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index ff3e82553a76..492dce43236e 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -158,9 +158,24 @@ * Useful if your architecture doesn't use IPIs for remote TLB invalidates * and therefore doesn't naturally serialize with software page-table walkers. * + * MMU_GATHER_NO_FLUSH_CACHE + * + * Indicates the architecture has flush_cache_range() but it needs *NOT* be called + * before unmapping a VMA. + * + * NOTE: strictly speaking we shouldn't have this knob and instead rely on + * flush_cache_range() being a NOP, except Sparc64 seems to be + * different here. + * + * MMU_GATHER_MERGE_VMAS + * + * Indicates the architecture wants to merge ranges over VMAs; typical when + * multiple range invalidates are more expensive than a full invalidate. + * * MMU_GATHER_NO_RANGE * - * Use this if your architecture lacks an efficient flush_tlb_range(). + * Use this if your architecture lacks an efficient flush_tlb_range(). This + * option implies MMU_GATHER_MERGE_VMAS above. * * MMU_GATHER_NO_GATHER * @@ -288,6 +303,7 @@ struct mmu_gather { */ unsigned int vma_exec : 1; unsigned int vma_huge : 1; + unsigned int vma_pfn : 1; unsigned int batch_count; @@ -334,8 +350,8 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) #ifdef CONFIG_MMU_GATHER_NO_RANGE -#if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma) -#error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma() +#if defined(tlb_flush) +#error MMU_GATHER_NO_RANGE relies on default tlb_flush() #endif /* @@ -352,20 +368,9 @@ static inline void tlb_flush(struct mmu_gather *tlb) flush_tlb_mm(tlb->mm); } -static inline void -tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } - -#define tlb_end_vma tlb_end_vma -static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { } - #else /* CONFIG_MMU_GATHER_NO_RANGE */ #ifndef tlb_flush - -#if defined(tlb_start_vma) || defined(tlb_end_vma) -#error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma() -#endif - /* * When an architecture does not provide its own tlb_flush() implementation * but does have a reasonably efficient flush_vma_range() implementation @@ -385,6 +390,9 @@ static inline void tlb_flush(struct mmu_gather *tlb) flush_tlb_range(&vma, tlb->start, tlb->end); } } +#endif + +#endif /* CONFIG_MMU_GATHER_NO_RANGE */ static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) @@ -402,17 +410,9 @@ tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) */ tlb->vma_huge = is_vm_hugetlb_page(vma); tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); + tlb->vma_pfn = !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)); } -#else - -static inline void -tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } - -#endif - -#endif /* CONFIG_MMU_GATHER_NO_RANGE */ - static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { /* @@ -486,32 +486,36 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) * case where we're doing a full MM flush. When we're doing a munmap, * the vmas are adjusted to only cover the region to be torn down. */ -#ifndef tlb_start_vma static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; tlb_update_vma_flags(tlb, vma); +#ifndef CONFIG_MMU_GATHER_NO_FLUSH_CACHE flush_cache_range(vma, vma->vm_start, vma->vm_end); -} #endif +} -#ifndef tlb_end_vma static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; /* - * Do a TLB flush and reset the range at VMA boundaries; this avoids - * the ranges growing with the unused space between consecutive VMAs, - * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on - * this. + * VM_PFNMAP is more fragile because the core mm will not track the + * page mapcount -- there might not be page-frames for these PFNs after + * all. Force flush TLBs for such ranges to avoid munmap() vs + * unmap_mapping_range() races. */ - tlb_flush_mmu_tlbonly(tlb); + if (tlb->vma_pfn || !IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS)) { + /* + * Do a TLB flush and reset the range at VMA boundaries; this avoids + * the ranges growing with the unused space between consecutive VMAs. + */ + tlb_flush_mmu_tlbonly(tlb); + } } -#endif /* * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end, diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 0fca8f38bee4..addb135eeea6 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -28,7 +28,7 @@ #include <linux/dma-fence.h> #include <linux/completion.h> #include <linux/xarray.h> -#include <linux/irq_work.h> +#include <linux/workqueue.h> #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000) @@ -295,7 +295,7 @@ struct drm_sched_job { */ union { struct dma_fence_cb finish_cb; - struct irq_work work; + struct work_struct work; }; uint64_t id; diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 1bfcfb1af352..d4427d0a0e18 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -264,7 +264,8 @@ struct css_set { * List of csets participating in the on-going migration either as * source or destination. Protected by cgroup_mutex. */ - struct list_head mg_preload_node; + struct list_head mg_src_preload_node; + struct list_head mg_dst_preload_node; struct list_head mg_node; /* diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 2c7477354744..314802f98b9d 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -68,6 +68,8 @@ extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, extern ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_retbleed(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 3af34de54330..56d6a0196534 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -149,19 +149,19 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they - * can be used in a manner similar to the following: + * can be used in a manner similar to the following:: * - * -- Find the page of interest. -- - * struct page *page = find_get_page(mapping, offset); + * // Find the page of interest. + * struct page *page = find_get_page(mapping, offset); * - * -- Gain access to the contents of that page. -- - * void *vaddr = kmap_atomic(page); + * // Gain access to the contents of that page. + * void *vaddr = kmap_atomic(page); * - * -- Do something to the contents of that page. -- - * memset(vaddr, 0, PAGE_SIZE); + * // Do something to the contents of that page. + * memset(vaddr, 0, PAGE_SIZE); * - * -- Unmap that page. -- - * kunmap_atomic(vaddr); + * // Unmap that page. + * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h new file mode 100644 index 000000000000..d54b8b7e0746 --- /dev/null +++ b/include/linux/io_uring_types.h @@ -0,0 +1,544 @@ +#ifndef IO_URING_TYPES_H +#define IO_URING_TYPES_H + +#include <linux/blkdev.h> +#include <linux/task_work.h> +#include <linux/bitmap.h> +#include <uapi/linux/io_uring.h> + +struct io_wq_work_node { + struct io_wq_work_node *next; +}; + +struct io_wq_work_list { + struct io_wq_work_node *first; + struct io_wq_work_node *last; +}; + +struct io_wq_work { + struct io_wq_work_node list; + unsigned flags; + /* place it here instead of io_kiocb as it fills padding and saves 4B */ + int cancel_seq; +}; + +struct io_fixed_file { + /* file * with additional FFS_* flags */ + unsigned long file_ptr; +}; + +struct io_file_table { + struct io_fixed_file *files; + unsigned long *bitmap; + unsigned int alloc_hint; +}; + +struct io_hash_bucket { + spinlock_t lock; + struct hlist_head list; +} ____cacheline_aligned_in_smp; + +struct io_hash_table { + struct io_hash_bucket *hbs; + unsigned hash_bits; +}; + +struct io_uring { + u32 head ____cacheline_aligned_in_smp; + u32 tail ____cacheline_aligned_in_smp; +}; + +/* + * This data is shared with the application through the mmap at offsets + * IORING_OFF_SQ_RING and IORING_OFF_CQ_RING. + * + * The offsets to the member fields are published through struct + * io_sqring_offsets when calling io_uring_setup. + */ +struct io_rings { + /* + * Head and tail offsets into the ring; the offsets need to be + * masked to get valid indices. + * + * The kernel controls head of the sq ring and the tail of the cq ring, + * and the application controls tail of the sq ring and the head of the + * cq ring. + */ + struct io_uring sq, cq; + /* + * Bitmasks to apply to head and tail offsets (constant, equals + * ring_entries - 1) + */ + u32 sq_ring_mask, cq_ring_mask; + /* Ring sizes (constant, power of 2) */ + u32 sq_ring_entries, cq_ring_entries; + /* + * Number of invalid entries dropped by the kernel due to + * invalid index stored in array + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * After a new SQ head value was read by the application this + * counter includes all submissions that were dropped reaching + * the new SQ head (and possibly more). + */ + u32 sq_dropped; + /* + * Runtime SQ flags + * + * Written by the kernel, shouldn't be modified by the + * application. + * + * The application needs a full memory barrier before checking + * for IORING_SQ_NEED_WAKEUP after updating the sq tail. + */ + atomic_t sq_flags; + /* + * Runtime CQ flags + * + * Written by the application, shouldn't be modified by the + * kernel. + */ + u32 cq_flags; + /* + * Number of completion events lost because the queue was full; + * this should be avoided by the application by making sure + * there are not more requests pending than there is space in + * the completion queue. + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * As completion events come in out of order this counter is not + * ordered with any other data. + */ + u32 cq_overflow; + /* + * Ring buffer of completion events. + * + * The kernel writes completion events fresh every time they are + * produced, so the application is allowed to modify pending + * entries. + */ + struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp; +}; + +struct io_restriction { + DECLARE_BITMAP(register_op, IORING_REGISTER_LAST); + DECLARE_BITMAP(sqe_op, IORING_OP_LAST); + u8 sqe_flags_allowed; + u8 sqe_flags_required; + bool registered; +}; + +struct io_submit_link { + struct io_kiocb *head; + struct io_kiocb *last; +}; + +struct io_submit_state { + /* inline/task_work completion list, under ->uring_lock */ + struct io_wq_work_node free_list; + /* batch completion logic */ + struct io_wq_work_list compl_reqs; + struct io_submit_link link; + + bool plug_started; + bool need_plug; + unsigned short submit_nr; + struct blk_plug plug; +}; + +struct io_ev_fd { + struct eventfd_ctx *cq_ev_fd; + unsigned int eventfd_async: 1; + struct rcu_head rcu; +}; + +struct io_alloc_cache { + struct hlist_head list; + unsigned int nr_cached; +}; + +struct io_ring_ctx { + /* const or read-mostly hot data */ + struct { + struct percpu_ref refs; + + struct io_rings *rings; + unsigned int flags; + enum task_work_notify_mode notify_method; + unsigned int compat: 1; + unsigned int drain_next: 1; + unsigned int restricted: 1; + unsigned int off_timeout_used: 1; + unsigned int drain_active: 1; + unsigned int drain_disabled: 1; + unsigned int has_evfd: 1; + unsigned int syscall_iopoll: 1; + } ____cacheline_aligned_in_smp; + + /* submission data */ + struct { + struct mutex uring_lock; + + /* + * Ring buffer of indices into array of io_uring_sqe, which is + * mmapped by the application using the IORING_OFF_SQES offset. + * + * This indirection could e.g. be used to assign fixed + * io_uring_sqe entries to operations and only submit them to + * the queue when needed. + * + * The kernel modifies neither the indices array nor the entries + * array. + */ + u32 *sq_array; + struct io_uring_sqe *sq_sqes; + unsigned cached_sq_head; + unsigned sq_entries; + + /* + * Fixed resources fast path, should be accessed only under + * uring_lock, and updated through io_uring_register(2) + */ + struct io_rsrc_node *rsrc_node; + int rsrc_cached_refs; + atomic_t cancel_seq; + struct io_file_table file_table; + unsigned nr_user_files; + unsigned nr_user_bufs; + struct io_mapped_ubuf **user_bufs; + + struct io_submit_state submit_state; + + struct io_buffer_list *io_bl; + struct xarray io_bl_xa; + struct list_head io_buffers_cache; + + struct io_hash_table cancel_table_locked; + struct list_head cq_overflow_list; + struct io_alloc_cache apoll_cache; + struct io_alloc_cache netmsg_cache; + } ____cacheline_aligned_in_smp; + + /* IRQ completion list, under ->completion_lock */ + struct io_wq_work_list locked_free_list; + unsigned int locked_free_nr; + + const struct cred *sq_creds; /* cred used for __io_sq_thread() */ + struct io_sq_data *sq_data; /* if using sq thread polling */ + + struct wait_queue_head sqo_sq_wait; + struct list_head sqd_list; + + unsigned long check_cq; + + unsigned int file_alloc_start; + unsigned int file_alloc_end; + + struct xarray personalities; + u32 pers_next; + + struct { + /* + * We cache a range of free CQEs we can use, once exhausted it + * should go through a slower range setup, see __io_get_cqe() + */ + struct io_uring_cqe *cqe_cached; + struct io_uring_cqe *cqe_sentinel; + + unsigned cached_cq_tail; + unsigned cq_entries; + struct io_ev_fd __rcu *io_ev_fd; + struct wait_queue_head cq_wait; + unsigned cq_extra; + } ____cacheline_aligned_in_smp; + + struct { + spinlock_t completion_lock; + + /* + * ->iopoll_list is protected by the ctx->uring_lock for + * io_uring instances that don't use IORING_SETUP_SQPOLL. + * For SQPOLL, only the single threaded io_sq_thread() will + * manipulate the list, hence no extra locking is needed there. + */ + struct io_wq_work_list iopoll_list; + struct io_hash_table cancel_table; + bool poll_multi_queue; + + struct list_head io_buffers_comp; + } ____cacheline_aligned_in_smp; + + /* timeouts */ + struct { + spinlock_t timeout_lock; + atomic_t cq_timeouts; + struct list_head timeout_list; + struct list_head ltimeout_list; + unsigned cq_last_tm_flush; + } ____cacheline_aligned_in_smp; + + /* Keep this last, we don't need it for the fast path */ + + struct io_restriction restrictions; + struct task_struct *submitter_task; + + /* slow path rsrc auxilary data, used by update/register */ + struct io_rsrc_node *rsrc_backup_node; + struct io_mapped_ubuf *dummy_ubuf; + struct io_rsrc_data *file_data; + struct io_rsrc_data *buf_data; + + struct delayed_work rsrc_put_work; + struct llist_head rsrc_put_llist; + struct list_head rsrc_ref_list; + spinlock_t rsrc_ref_lock; + + struct list_head io_buffers_pages; + + #if defined(CONFIG_UNIX) + struct socket *ring_sock; + #endif + /* hashed buffered write serialization */ + struct io_wq_hash *hash_map; + + /* Only used for accounting purposes */ + struct user_struct *user; + struct mm_struct *mm_account; + + /* ctx exit and cancelation */ + struct llist_head fallback_llist; + struct delayed_work fallback_work; + struct work_struct exit_work; + struct list_head tctx_list; + struct completion ref_comp; + + /* io-wq management, e.g. thread count */ + u32 iowq_limits[2]; + bool iowq_limits_set; + + struct list_head defer_list; + unsigned sq_thread_idle; + /* protected by ->completion_lock */ + unsigned evfd_last_cq_tail; +}; + +enum { + REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, + REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT, + REQ_F_LINK_BIT = IOSQE_IO_LINK_BIT, + REQ_F_HARDLINK_BIT = IOSQE_IO_HARDLINK_BIT, + REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT, + REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT, + REQ_F_CQE_SKIP_BIT = IOSQE_CQE_SKIP_SUCCESS_BIT, + + /* first byte is taken by user flags, shift it to not overlap */ + REQ_F_FAIL_BIT = 8, + REQ_F_INFLIGHT_BIT, + REQ_F_CUR_POS_BIT, + REQ_F_NOWAIT_BIT, + REQ_F_LINK_TIMEOUT_BIT, + REQ_F_NEED_CLEANUP_BIT, + REQ_F_POLLED_BIT, + REQ_F_BUFFER_SELECTED_BIT, + REQ_F_BUFFER_RING_BIT, + REQ_F_REISSUE_BIT, + REQ_F_CREDS_BIT, + REQ_F_REFCOUNT_BIT, + REQ_F_ARM_LTIMEOUT_BIT, + REQ_F_ASYNC_DATA_BIT, + REQ_F_SKIP_LINK_CQES_BIT, + REQ_F_SINGLE_POLL_BIT, + REQ_F_DOUBLE_POLL_BIT, + REQ_F_PARTIAL_IO_BIT, + REQ_F_CQE32_INIT_BIT, + REQ_F_APOLL_MULTISHOT_BIT, + REQ_F_CLEAR_POLLIN_BIT, + REQ_F_HASH_LOCKED_BIT, + /* keep async read/write and isreg together and in order */ + REQ_F_SUPPORT_NOWAIT_BIT, + REQ_F_ISREG_BIT, + + /* not a real bit, just to check we're not overflowing the space */ + __REQ_F_LAST_BIT, +}; + +enum { + /* ctx owns file */ + REQ_F_FIXED_FILE = BIT(REQ_F_FIXED_FILE_BIT), + /* drain existing IO first */ + REQ_F_IO_DRAIN = BIT(REQ_F_IO_DRAIN_BIT), + /* linked sqes */ + REQ_F_LINK = BIT(REQ_F_LINK_BIT), + /* doesn't sever on completion < 0 */ + REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT), + /* IOSQE_ASYNC */ + REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT), + /* IOSQE_BUFFER_SELECT */ + REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT), + /* IOSQE_CQE_SKIP_SUCCESS */ + REQ_F_CQE_SKIP = BIT(REQ_F_CQE_SKIP_BIT), + + /* fail rest of links */ + REQ_F_FAIL = BIT(REQ_F_FAIL_BIT), + /* on inflight list, should be cancelled and waited on exit reliably */ + REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT), + /* read/write uses file position */ + REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT), + /* must not punt to workers */ + REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT), + /* has or had linked timeout */ + REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT), + /* needs cleanup */ + REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), + /* already went through poll handler */ + REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), + /* buffer already selected */ + REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT), + /* buffer selected from ring, needs commit */ + REQ_F_BUFFER_RING = BIT(REQ_F_BUFFER_RING_BIT), + /* caller should reissue async */ + REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), + /* supports async reads/writes */ + REQ_F_SUPPORT_NOWAIT = BIT(REQ_F_SUPPORT_NOWAIT_BIT), + /* regular file */ + REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), + /* has creds assigned */ + REQ_F_CREDS = BIT(REQ_F_CREDS_BIT), + /* skip refcounting if not set */ + REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT), + /* there is a linked timeout that has to be armed */ + REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), + /* ->async_data allocated */ + REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT), + /* don't post CQEs while failing linked requests */ + REQ_F_SKIP_LINK_CQES = BIT(REQ_F_SKIP_LINK_CQES_BIT), + /* single poll may be active */ + REQ_F_SINGLE_POLL = BIT(REQ_F_SINGLE_POLL_BIT), + /* double poll may active */ + REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT), + /* request has already done partial IO */ + REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT), + /* fast poll multishot mode */ + REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT), + /* ->extra1 and ->extra2 are initialised */ + REQ_F_CQE32_INIT = BIT(REQ_F_CQE32_INIT_BIT), + /* recvmsg special flag, clear EPOLLIN */ + REQ_F_CLEAR_POLLIN = BIT(REQ_F_CLEAR_POLLIN_BIT), + /* hashed into ->cancel_hash_locked, protected by ->uring_lock */ + REQ_F_HASH_LOCKED = BIT(REQ_F_HASH_LOCKED_BIT), +}; + +typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked); + +struct io_task_work { + struct llist_node node; + io_req_tw_func_t func; +}; + +struct io_cqe { + __u64 user_data; + __s32 res; + /* fd initially, then cflags for completion */ + union { + __u32 flags; + int fd; + }; +}; + +/* + * Each request type overlays its private data structure on top of this one. + * They must not exceed this one in size. + */ +struct io_cmd_data { + struct file *file; + /* each command gets 56 bytes of data */ + __u8 data[56]; +}; + +#define io_kiocb_to_cmd(req) ((void *) &(req)->cmd) +#define cmd_to_io_kiocb(ptr) ((struct io_kiocb *) ptr) + +struct io_kiocb { + union { + /* + * NOTE! Each of the io_kiocb union members has the file pointer + * as the first entry in their struct definition. So you can + * access the file pointer through any of the sub-structs, + * or directly as just 'file' in this struct. + */ + struct file *file; + struct io_cmd_data cmd; + }; + + u8 opcode; + /* polled IO has completed */ + u8 iopoll_completed; + /* + * Can be either a fixed buffer index, or used with provided buffers. + * For the latter, before issue it points to the buffer group ID, + * and after selection it points to the buffer ID itself. + */ + u16 buf_index; + unsigned int flags; + + struct io_cqe cqe; + + struct io_ring_ctx *ctx; + struct task_struct *task; + + struct io_rsrc_node *rsrc_node; + + union { + /* store used ubuf, so we can prevent reloading */ + struct io_mapped_ubuf *imu; + + /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ + struct io_buffer *kbuf; + + /* + * stores buffer ID for ring provided buffers, valid IFF + * REQ_F_BUFFER_RING is set. + */ + struct io_buffer_list *buf_list; + }; + + union { + /* used by request caches, completion batching and iopoll */ + struct io_wq_work_node comp_list; + /* cache ->apoll->events */ + __poll_t apoll_events; + }; + atomic_t refs; + atomic_t poll_refs; + struct io_task_work io_task_work; + /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ + union { + struct hlist_node hash_node; + struct { + u64 extra1; + u64 extra2; + }; + }; + /* internal polling, see IORING_FEAT_FAST_POLL */ + struct async_poll *apoll; + /* opcode allocated if it needs to store data for async defer */ + void *async_data; + /* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */ + struct io_kiocb *link; + /* custom credentials, valid IFF REQ_F_CREDS is set */ + const struct cred *creds; + struct io_wq_work work; +}; + +struct io_overflow_cqe { + struct list_head list; + struct io_uring_cqe cqe; +}; + +#endif diff --git a/include/linux/kexec.h b/include/linux/kexec.h index ce6536f1d269..475683cd67f1 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -452,6 +452,12 @@ static inline int kexec_crash_loaded(void) { return 0; } #define kexec_in_progress false #endif /* CONFIG_KEXEC_CORE */ +#ifdef CONFIG_KEXEC_SIG +void set_kexec_sig_enforced(void); +#else +static inline void set_kexec_sig_enforced(void) {} +#endif + #endif /* !defined(__ASSEBMLY__) */ #endif /* LINUX_KEXEC_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c20f2d55840c..90a45ef7203b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1513,7 +1513,7 @@ static inline void kvm_arch_end_assignment(struct kvm *kvm) { } -static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) { return false; } @@ -1822,6 +1822,15 @@ struct _kvm_stats_desc { STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) +/* Instantaneous boolean value, read only */ +#define STATS_DESC_IBOOLEAN(SCOPE, name) \ + STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ + KVM_STATS_BASE_POW10, 0) +/* Peak (sticky) boolean value, read/write */ +#define STATS_DESC_PBOOLEAN(SCOPE, name) \ + STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ + KVM_STATS_BASE_POW10, 0) + /* Cumulative time in nanosecond */ #define STATS_DESC_TIME_NSEC(SCOPE, name) \ STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ @@ -1853,7 +1862,7 @@ struct _kvm_stats_desc { HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ HALT_POLL_HIST_COUNT), \ - STATS_DESC_ICOUNTER(VCPU_GENERIC, blocking) + STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) extern struct dentry *kvm_debugfs_dir; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 1773e5df8e65..1b18dfa52e48 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -214,7 +214,7 @@ struct netfs_request_ops { void (*issue_read)(struct netfs_io_subrequest *subreq); bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, - struct folio *folio, void **_fsdata); + struct folio **foliop, void **_fsdata); void (*done)(struct netfs_io_request *rreq); }; diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 15b940ec1eac..10bc88cc3bf6 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -32,11 +32,16 @@ struct unwind_hint { * * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 #ifdef CONFIG_OBJTOOL @@ -124,7 +129,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -177,7 +182,7 @@ struct unwind_hint { #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/include/linux/reset.h b/include/linux/reset.h index 8a21b5756c3e..514ddf003efc 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -731,7 +731,7 @@ static inline int __must_check devm_reset_control_bulk_get_optional_exclusive(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, true, false, true); + return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, false, true, true); } /** diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 505aaf9fe477..81cab4b01edc 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -85,7 +85,7 @@ static inline void exit_thread(struct task_struct *tsk) extern __noreturn void do_group_exit(int); extern void exit_files(struct task_struct *); -extern void exit_itimers(struct signal_struct *); +extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 657a0fc68a3f..fde258b3decd 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -390,6 +390,11 @@ static const bool earlycon_acpi_spcr_enable EARLYCON_USED_OR_UNUSED; static inline int setup_earlycon(char *buf) { return 0; } #endif +static inline bool uart_console_enabled(struct uart_port *port) +{ + return uart_console(port) && (port->cons->flags & CON_ENABLED); +} + struct uart_port *uart_get_console(struct uart_port *ports, int nr, struct console *c); int uart_parse_earlycon(char *p, unsigned char *iotype, resource_size_t *addr, diff --git a/include/linux/socket.h b/include/linux/socket.h index 3c11ef18a9cf..d4523974efbd 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -421,10 +421,9 @@ extern int recvmsg_copy_msghdr(struct msghdr *msg, struct user_msghdr __user *umsg, unsigned flags, struct sockaddr __user **uaddr, struct iovec **iov); -extern int __copy_msghdr_from_user(struct msghdr *kmsg, - struct user_msghdr __user *umsg, - struct sockaddr __user **save_addr, - struct iovec __user **uiov, size_t *nsegs); +extern int __copy_msghdr(struct msghdr *kmsg, + struct user_msghdr *umsg, + struct sockaddr __user **save_addr); /* helpers which do the actual work for syscalls */ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 29917850f079..8df475db88c0 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -260,6 +260,7 @@ struct plat_stmmacenet_data { bool has_crossts; int int_snapshot_num; int ext_snapshot_num; + bool int_snapshot_en; bool ext_snapshot_en; bool multi_msi_en; int msi_mac_vec; diff --git a/include/net/amt.h b/include/net/amt.h index 0e40c3d64fcf..08fc30cf2f34 100644 --- a/include/net/amt.h +++ b/include/net/amt.h @@ -78,6 +78,15 @@ enum amt_status { #define AMT_STATUS_MAX (__AMT_STATUS_MAX - 1) +/* Gateway events only */ +enum amt_event { + AMT_EVENT_NONE, + AMT_EVENT_RECEIVE, + AMT_EVENT_SEND_DISCOVERY, + AMT_EVENT_SEND_REQUEST, + __AMT_EVENT_MAX, +}; + struct amt_header { #if defined(__LITTLE_ENDIAN_BITFIELD) u8 type:4, @@ -292,6 +301,12 @@ struct amt_group_node { struct hlist_head sources[]; }; +#define AMT_MAX_EVENTS 16 +struct amt_events { + enum amt_event event; + struct sk_buff *skb; +}; + struct amt_dev { struct net_device *dev; struct net_device *stream_dev; @@ -308,6 +323,7 @@ struct amt_dev { struct delayed_work req_wq; /* Protected by RTNL */ struct delayed_work secret_wq; + struct work_struct event_wq; /* AMT status */ enum amt_status status; /* Generated key */ @@ -345,6 +361,10 @@ struct amt_dev { /* Used only in gateway mode */ u64 mac:48, reserved:16; + /* AMT gateway side message handler queue */ + struct amt_events events[AMT_MAX_EVENTS]; + u8 event_idx; + u8 nr_events; }; #define AMT_TOS 0xc0 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6d02e12e4702..80f41446b1f0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -8462,11 +8462,12 @@ int cfg80211_bss_color_notify(struct net_device *dev, gfp_t gfp, * cfg80211_obss_color_collision_notify - notify about bss color collision * @dev: network device * @color_bitmap: representations of the colors that the local BSS is aware of + * @gfp: allocation flags */ static inline int cfg80211_obss_color_collision_notify(struct net_device *dev, - u64 color_bitmap) + u64 color_bitmap, gfp_t gfp) { - return cfg80211_bss_color_notify(dev, GFP_KERNEL, + return cfg80211_bss_color_notify(dev, gfp, NL80211_CMD_OBSS_COLOR_COLLISION, 0, color_bitmap); } diff --git a/include/net/compat.h b/include/net/compat.h index 595fee069b82..84c163f40f38 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -46,9 +46,8 @@ struct compat_rtentry { unsigned short rt_irtt; /* Initial RTT */ }; -int __get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg, - struct sockaddr __user **save_addr, compat_uptr_t *ptr, - compat_size_t *len); +int __get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr *msg, + struct sockaddr __user **save_addr); int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *, struct sockaddr __user **, struct iovec **); int put_cmsg_compat(struct msghdr*, int, int, int, void *); diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ebfa3df6f8dc..fd6b510d114b 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -179,7 +179,7 @@ static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) - return inet_bound_dev_eq(!!net->ipv4.sysctl_tcp_l3mdev_accept, + return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept), bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index daead5fb389a..6395f6b9a5d2 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -107,7 +107,8 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { - if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept) + if (!sk->sk_mark && + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)) return skb->mark; return sk->sk_mark; @@ -120,7 +121,7 @@ static inline int inet_request_bound_dev_if(const struct sock *sk, #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); - if (!bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) + if (!bound_dev_if && READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept)) return l3mdev_master_ifindex_by_index(net, skb->skb_iif); #endif @@ -132,7 +133,7 @@ static inline int inet_sk_bound_l3mdev(const struct sock *sk) #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); - if (!net->ipv4.sysctl_tcp_l3mdev_accept) + if (!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept)) return l3mdev_master_ifindex_by_index(net, sk->sk_bound_dev_if); #endif @@ -374,7 +375,7 @@ static inline bool inet_get_convert_csum(struct sock *sk) static inline bool inet_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { - return net->ipv4.sysctl_ip_nonlocal_bind || + return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) || inet->freebind || inet->transparent; } diff --git a/include/net/ip.h b/include/net/ip.h index 26fffda78cca..1c979fd1904c 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -357,7 +357,7 @@ static inline bool sysctl_dev_name_is_allowed(const char *name) static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port) { - return port < net->ipv4.sysctl_ip_prot_sock; + return port < READ_ONCE(net->ipv4.sysctl_ip_prot_sock); } #else @@ -384,7 +384,7 @@ void ipfrag_init(void); void ip_static_sysctl_init(void); #define IP4_REPLY_MARK(net, mark) \ - ((net)->ipv4.sysctl_fwmark_reflect ? (mark) : 0) + (READ_ONCE((net)->ipv4.sysctl_fwmark_reflect) ? (mark) : 0) static inline bool ip_is_fragment(const struct iphdr *iph) { @@ -446,7 +446,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, struct net *net = dev_net(dst->dev); unsigned int mtu; - if (net->ipv4.sysctl_ip_fwd_use_pmtu || + if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) || ip_mtu_locked(dst) || !forwarding) { mtu = rt->rt_pmtu; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ebadb2103968..47642b020706 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6960,10 +6960,11 @@ ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @color_bitmap: a 64 bit bitmap representing the colors that the local BSS is * aware of. + * @gfp: allocation flags */ void ieeee80211_obss_color_collision_notify(struct ieee80211_vif *vif, - u64 color_bitmap); + u64 color_bitmap, gfp_t gfp); /** * ieee80211_is_tx_data - check if frame is a data frame diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 5c4e5a96a984..64cf655c818c 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -657,18 +657,22 @@ static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) tmpl->len = sizeof(struct nft_set_ext); } -static inline void nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id, - unsigned int len) +static inline int nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id, + unsigned int len) { tmpl->len = ALIGN(tmpl->len, nft_set_ext_types[id].align); - BUG_ON(tmpl->len > U8_MAX); + if (tmpl->len > U8_MAX) + return -EINVAL; + tmpl->offset[id] = tmpl->len; tmpl->len += nft_set_ext_types[id].len + len; + + return 0; } -static inline void nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id) +static inline int nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id) { - nft_set_ext_add_length(tmpl, id, 0); + return nft_set_ext_add_length(tmpl, id, 0); } static inline void nft_set_ext_init(struct nft_set_ext *ext, diff --git a/include/net/protocol.h b/include/net/protocol.h index f51c06ae365f..6aef8cb11cc8 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -35,8 +35,6 @@ /* This is used to register protocols. */ struct net_protocol { - int (*early_demux)(struct sk_buff *skb); - int (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); /* This returns an error if we weren't able to handle the error. */ @@ -52,8 +50,6 @@ struct net_protocol { #if IS_ENABLED(CONFIG_IPV6) struct inet6_protocol { - void (*early_demux)(struct sk_buff *skb); - void (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); /* This returns an error if we weren't able to handle the error. */ diff --git a/include/net/raw.h b/include/net/raw.h index 8ad8df594853..c51a635671a7 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -75,7 +75,7 @@ static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) - return inet_bound_dev_eq(!!net->ipv4.sysctl_raw_l3mdev_accept, + return inet_bound_dev_eq(READ_ONCE(net->ipv4.sysctl_raw_l3mdev_accept), bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); diff --git a/include/net/route.h b/include/net/route.h index 991a3985712d..bbcf2aba149f 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -373,7 +373,7 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst) struct net *net = dev_net(dst->dev); if (hoplimit == 0) - hoplimit = net->ipv4.sysctl_ip_default_ttl; + hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl); return hoplimit; } diff --git a/include/net/sock.h b/include/net/sock.h index 72ca97ccb460..9fa54762e077 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1529,7 +1529,7 @@ void __sk_mem_reclaim(struct sock *sk, int amount); /* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { - long val = sk->sk_prot->sysctl_mem[index]; + long val = READ_ONCE(sk->sk_prot->sysctl_mem[index]); #if PAGE_SIZE > SK_MEM_QUANTUM val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT; diff --git a/include/net/tcp.h b/include/net/tcp.h index 1e99f5c61f84..071735e10872 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -932,7 +932,7 @@ extern const struct inet_connection_sock_af_ops ipv6_specific; INDIRECT_CALLABLE_DECLARE(void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb)); -INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb)); +void tcp_v6_early_demux(struct sk_buff *skb); #endif @@ -1403,8 +1403,8 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); s32 delta; - if (!sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle || tp->packets_out || - ca_ops->cong_control) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) || + tp->packets_out || ca_ops->cong_control) return; delta = tcp_jiffies32 - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) @@ -1493,21 +1493,24 @@ static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->keepalive_intvl ? : net->ipv4.sysctl_tcp_keepalive_intvl; + return tp->keepalive_intvl ? : + READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); } static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->keepalive_time ? : net->ipv4.sysctl_tcp_keepalive_time; + return tp->keepalive_time ? : + READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->keepalive_probes ? : net->ipv4.sysctl_tcp_keepalive_probes; + return tp->keepalive_probes ? : + READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) @@ -1520,7 +1523,8 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) static inline int tcp_fin_time(const struct sock *sk) { - int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout; + int fin_timeout = tcp_sk(sk)->linger2 ? : + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout); const int rto = inet_csk(sk)->icsk_rto; if (fin_timeout < (rto << 2) - (rto >> 1)) @@ -2023,7 +2027,7 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat; + return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } bool tcp_stream_memory_free(const struct sock *sk, int wake); diff --git a/include/net/tls.h b/include/net/tls.h index 8017f1703447..8bd938f98bdd 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -704,7 +704,7 @@ int tls_sw_fallback_init(struct sock *sk, struct tls_crypto_info *crypto_info); #ifdef CONFIG_TLS_DEVICE -void tls_device_init(void); +int tls_device_init(void); void tls_device_cleanup(void); void tls_device_sk_destruct(struct sock *sk); int tls_set_device_offload(struct sock *sk, struct tls_context *ctx); @@ -724,7 +724,7 @@ static inline bool tls_is_sk_rx_device_offloaded(struct sock *sk) return tls_get_ctx(sk)->rx_conf == TLS_HW; } #else -static inline void tls_device_init(void) {} +static inline int tls_device_init(void) { return 0; } static inline void tls_device_cleanup(void) {} static inline int diff --git a/include/net/udp.h b/include/net/udp.h index b83a00330566..8dd4aa1485a6 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -167,7 +167,7 @@ static inline void udp_csum_pull_header(struct sk_buff *skb) typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport, __be16 dport); -INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *)); +void udp_v6_early_demux(struct sk_buff *skb); INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, @@ -238,7 +238,7 @@ static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) - return inet_bound_dev_eq(!!net->ipv4.sysctl_udp_l3mdev_accept, + return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_udp_l3mdev_accept), bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index aa2f951b07cd..95a8cfaad15a 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -7,6 +7,7 @@ #include <linux/tracepoint.h> #include <uapi/linux/io_uring.h> +#include <linux/io_uring_types.h> #include <linux/io_uring.h> struct io_wq_work; @@ -97,9 +98,7 @@ TRACE_EVENT(io_uring_register, /** * io_uring_file_get - called before getting references to an SQE file * - * @ctx: pointer to a ring context structure * @req: pointer to a submitted request - * @user_data: user data associated with the request * @fd: SQE file descriptor * * Allows to trace out how often an SQE file reference is obtained, which can @@ -108,9 +107,9 @@ TRACE_EVENT(io_uring_register, */ TRACE_EVENT(io_uring_file_get, - TP_PROTO(void *ctx, void *req, unsigned long long user_data, int fd), + TP_PROTO(struct io_kiocb *req, int fd), - TP_ARGS(ctx, req, user_data, fd), + TP_ARGS(req, fd), TP_STRUCT__entry ( __field( void *, ctx ) @@ -120,9 +119,9 @@ TRACE_EVENT(io_uring_file_get, ), TP_fast_assign( - __entry->ctx = ctx; + __entry->ctx = req->ctx; __entry->req = req; - __entry->user_data = user_data; + __entry->user_data = req->cqe.user_data; __entry->fd = fd; ), @@ -133,22 +132,16 @@ TRACE_EVENT(io_uring_file_get, /** * io_uring_queue_async_work - called before submitting a new async work * - * @ctx: pointer to a ring context structure * @req: pointer to a submitted request - * @user_data: user data associated with the request - * @opcode: opcode of request - * @flags request flags - * @work: pointer to a submitted io_wq_work * @rw: type of workqueue, hashed or normal * * Allows to trace asynchronous work submission. */ TRACE_EVENT(io_uring_queue_async_work, - TP_PROTO(void *ctx, void * req, unsigned long long user_data, u8 opcode, - unsigned int flags, struct io_wq_work *work, int rw), + TP_PROTO(struct io_kiocb *req, int rw), - TP_ARGS(ctx, req, user_data, opcode, flags, work, rw), + TP_ARGS(req, rw), TP_STRUCT__entry ( __field( void *, ctx ) @@ -159,19 +152,19 @@ TRACE_EVENT(io_uring_queue_async_work, __field( struct io_wq_work *, work ) __field( int, rw ) - __string( op_str, io_uring_get_opcode(opcode) ) + __string( op_str, io_uring_get_opcode(req->opcode) ) ), TP_fast_assign( - __entry->ctx = ctx; + __entry->ctx = req->ctx; __entry->req = req; - __entry->user_data = user_data; - __entry->flags = flags; - __entry->opcode = opcode; - __entry->work = work; + __entry->user_data = req->cqe.user_data; + __entry->flags = req->flags; + __entry->opcode = req->opcode; + __entry->work = &req->work; __entry->rw = rw; - __assign_str(op_str, io_uring_get_opcode(opcode)); + __assign_str(op_str, io_uring_get_opcode(req->opcode)); ), TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p", @@ -183,19 +176,16 @@ TRACE_EVENT(io_uring_queue_async_work, /** * io_uring_defer - called when an io_uring request is deferred * - * @ctx: pointer to a ring context structure * @req: pointer to a deferred request - * @user_data: user data associated with the request - * @opcode: opcode of request * * Allows to track deferred requests, to get an insight about what requests are * not started immediately. */ TRACE_EVENT(io_uring_defer, - TP_PROTO(void *ctx, void *req, unsigned long long user_data, u8 opcode), + TP_PROTO(struct io_kiocb *req), - TP_ARGS(ctx, req, user_data, opcode), + TP_ARGS(req), TP_STRUCT__entry ( __field( void *, ctx ) @@ -203,16 +193,16 @@ TRACE_EVENT(io_uring_defer, __field( unsigned long long, data ) __field( u8, opcode ) - __string( op_str, io_uring_get_opcode(opcode) ) + __string( op_str, io_uring_get_opcode(req->opcode) ) ), TP_fast_assign( - __entry->ctx = ctx; + __entry->ctx = req->ctx; __entry->req = req; - __entry->data = user_data; - __entry->opcode = opcode; + __entry->data = req->cqe.user_data; + __entry->opcode = req->opcode; - __assign_str(op_str, io_uring_get_opcode(opcode)); + __assign_str(op_str, io_uring_get_opcode(req->opcode)); ), TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s", @@ -224,7 +214,6 @@ TRACE_EVENT(io_uring_defer, * io_uring_link - called before the io_uring request added into link_list of * another request * - * @ctx: pointer to a ring context structure * @req: pointer to a linked request * @target_req: pointer to a previous request, that would contain @req * @@ -233,9 +222,9 @@ TRACE_EVENT(io_uring_defer, */ TRACE_EVENT(io_uring_link, - TP_PROTO(void *ctx, void *req, void *target_req), + TP_PROTO(struct io_kiocb *req, struct io_kiocb *target_req), - TP_ARGS(ctx, req, target_req), + TP_ARGS(req, target_req), TP_STRUCT__entry ( __field( void *, ctx ) @@ -244,7 +233,7 @@ TRACE_EVENT(io_uring_link, ), TP_fast_assign( - __entry->ctx = ctx; + __entry->ctx = req->ctx; __entry->req = req; __entry->target_req = target_req; ), @@ -285,10 +274,7 @@ TRACE_EVENT(io_uring_cqring_wait, /** * io_uring_fail_link - called before failing a linked request * - * @ctx: pointer to a ring context structure * @req: request, which links were cancelled - * @user_data: user data associated with the request - * @opcode: opcode of request * @link: cancelled link * * Allows to track linked requests cancellation, to see not only that some work @@ -296,9 +282,9 @@ TRACE_EVENT(io_uring_cqring_wait, */ TRACE_EVENT(io_uring_fail_link, - TP_PROTO(void *ctx, void *req, unsigned long long user_data, u8 opcode, void *link), + TP_PROTO(struct io_kiocb *req, struct io_kiocb *link), - TP_ARGS(ctx, req, user_data, opcode, link), + TP_ARGS(req, link), TP_STRUCT__entry ( __field( void *, ctx ) @@ -307,17 +293,17 @@ TRACE_EVENT(io_uring_fail_link, __field( u8, opcode ) __field( void *, link ) - __string( op_str, io_uring_get_opcode(opcode) ) + __string( op_str, io_uring_get_opcode(req->opcode) ) ), TP_fast_assign( - __entry->ctx = ctx; + __entry->ctx = req->ctx; __entry->req = req; - __entry->user_data = user_data; - __entry->opcode = opcode; + __entry->user_data = req->cqe.user_data; + __entry->opcode = req->opcode; __entry->link = link; - __assign_str(op_str, io_uring_get_opcode(opcode)); + __assign_str(op_str, io_uring_get_opcode(req->opcode)); ), TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, link %p", @@ -376,23 +362,17 @@ TRACE_EVENT(io_uring_complete, /** * io_uring_submit_sqe - called before submitting one SQE * - * @ctx: pointer to a ring context structure * @req: pointer to a submitted request - * @user_data: user data associated with the request - * @opcode: opcode of request - * @flags request flags * @force_nonblock: whether a context blocking or not - * @sq_thread: true if sq_thread has submitted this SQE * * Allows to track SQE submitting, to understand what was the source of it, SQ * thread or io_uring_enter call. */ TRACE_EVENT(io_uring_submit_sqe, - TP_PROTO(void *ctx, void *req, unsigned long long user_data, u8 opcode, u32 flags, - bool force_nonblock, bool sq_thread), + TP_PROTO(struct io_kiocb *req, bool force_nonblock), - TP_ARGS(ctx, req, user_data, opcode, flags, force_nonblock, sq_thread), + TP_ARGS(req, force_nonblock), TP_STRUCT__entry ( __field( void *, ctx ) @@ -403,19 +383,19 @@ TRACE_EVENT(io_uring_submit_sqe, __field( bool, force_nonblock ) __field( bool, sq_thread ) - __string( op_str, io_uring_get_opcode(opcode) ) + __string( op_str, io_uring_get_opcode(req->opcode) ) ), TP_fast_assign( - __entry->ctx = ctx; + __entry->ctx = req->ctx; __entry->req = req; - __entry->user_data = user_data; - __entry->opcode = opcode; - __entry->flags = flags; + __entry->user_data = req->cqe.user_data; + __entry->opcode = req->opcode; + __entry->flags = req->flags; __entry->force_nonblock = force_nonblock; - __entry->sq_thread = sq_thread; + __entry->sq_thread = req->ctx->flags & IORING_SETUP_SQPOLL; - __assign_str(op_str, io_uring_get_opcode(opcode)); + __assign_str(op_str, io_uring_get_opcode(req->opcode)); ), TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, " @@ -427,10 +407,7 @@ TRACE_EVENT(io_uring_submit_sqe, /* * io_uring_poll_arm - called after arming a poll wait if successful * - * @ctx: pointer to a ring context structure * @req: pointer to the armed request - * @user_data: user data associated with the request - * @opcode: opcode of request * @mask: request poll events mask * @events: registered events of interest * @@ -439,10 +416,9 @@ TRACE_EVENT(io_uring_submit_sqe, */ TRACE_EVENT(io_uring_poll_arm, - TP_PROTO(void *ctx, void *req, u64 user_data, u8 opcode, - int mask, int events), + TP_PROTO(struct io_kiocb *req, int mask, int events), - TP_ARGS(ctx, req, user_data, opcode, mask, events), + TP_ARGS(req, mask, events), TP_STRUCT__entry ( __field( void *, ctx ) @@ -452,18 +428,18 @@ TRACE_EVENT(io_uring_poll_arm, __field( int, mask ) __field( int, events ) - __string( op_str, io_uring_get_opcode(opcode) ) + __string( op_str, io_uring_get_opcode(req->opcode) ) ), TP_fast_assign( - __entry->ctx = ctx; + __entry->ctx = req->ctx; __entry->req = req; - __entry->user_data = user_data; - __entry->opcode = opcode; + __entry->user_data = req->cqe.user_data; + __entry->opcode = req->opcode; __entry->mask = mask; __entry->events = events; - __assign_str(op_str, io_uring_get_opcode(opcode)); + __assign_str(op_str, io_uring_get_opcode(req->opcode)); ), TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask 0x%x, events 0x%x", @@ -475,18 +451,15 @@ TRACE_EVENT(io_uring_poll_arm, /* * io_uring_task_add - called after adding a task * - * @ctx: pointer to a ring context structure * @req: pointer to request - * @user_data: user data associated with the request - * @opcode: opcode of request * @mask: request poll events mask * */ TRACE_EVENT(io_uring_task_add, - TP_PROTO(void *ctx, void *req, unsigned long long user_data, u8 opcode, int mask), + TP_PROTO(struct io_kiocb *req, int mask), - TP_ARGS(ctx, req, user_data, opcode, mask), + TP_ARGS(req, mask), TP_STRUCT__entry ( __field( void *, ctx ) @@ -495,17 +468,17 @@ TRACE_EVENT(io_uring_task_add, __field( u8, opcode ) __field( int, mask ) - __string( op_str, io_uring_get_opcode(opcode) ) + __string( op_str, io_uring_get_opcode(req->opcode) ) ), TP_fast_assign( - __entry->ctx = ctx; + __entry->ctx = req->ctx; __entry->req = req; - __entry->user_data = user_data; - __entry->opcode = opcode; + __entry->user_data = req->cqe.user_data; + __entry->opcode = req->opcode; __entry->mask = mask; - __assign_str(op_str, io_uring_get_opcode(opcode)); + __assign_str(op_str, io_uring_get_opcode(req->opcode)); ), TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask %x", @@ -518,7 +491,6 @@ TRACE_EVENT(io_uring_task_add, * io_uring_req_failed - called when an sqe is errored dring submission * * @sqe: pointer to the io_uring_sqe that failed - * @ctx: pointer to a ring context structure * @req: pointer to request * @error: error it failed with * @@ -526,9 +498,9 @@ TRACE_EVENT(io_uring_task_add, */ TRACE_EVENT(io_uring_req_failed, - TP_PROTO(const struct io_uring_sqe *sqe, void *ctx, void *req, int error), + TP_PROTO(const struct io_uring_sqe *sqe, struct io_kiocb *req, int error), - TP_ARGS(sqe, ctx, req, error), + TP_ARGS(sqe, req, error), TP_STRUCT__entry ( __field( void *, ctx ) @@ -552,7 +524,7 @@ TRACE_EVENT(io_uring_req_failed, ), TP_fast_assign( - __entry->ctx = ctx; + __entry->ctx = req->ctx; __entry->req = req; __entry->user_data = sqe->user_data; __entry->opcode = sqe->opcode; @@ -622,12 +594,42 @@ TRACE_EVENT(io_uring_cqe_overflow, __entry->ocqe = ocqe; ), - TP_printk("ring %p, user_data 0x%llx, res %d, flags %x, " + TP_printk("ring %p, user_data 0x%llx, res %d, cflags 0x%x, " "overflow_cqe %p", __entry->ctx, __entry->user_data, __entry->res, __entry->cflags, __entry->ocqe) ); +/* + * io_uring_task_work_run - ran task work + * + * @tctx: pointer to a io_uring_task + * @count: how many functions it ran + * @loops: how many loops it ran + * + */ +TRACE_EVENT(io_uring_task_work_run, + + TP_PROTO(void *tctx, unsigned int count, unsigned int loops), + + TP_ARGS(tctx, count, loops), + + TP_STRUCT__entry ( + __field( void *, tctx ) + __field( unsigned int, count ) + __field( unsigned int, loops ) + ), + + TP_fast_assign( + __entry->tctx = tctx; + __entry->count = count; + __entry->loops = loops; + ), + + TP_printk("tctx %p, count %u, loops %u", + __entry->tctx, __entry->count, __entry->loops) +); + #endif /* _TRACE_IO_URING_H */ /* This part must be outside protection */ diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index e282ce02fa2d..6d1626e7a4ce 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -160,7 +160,7 @@ TRACE_EVENT(iocost_ioc_vrate_adj, TP_fast_assign( __assign_str(devname, ioc_name(ioc)); - __entry->old_vrate = atomic64_read(&ioc->vtime_rate);; + __entry->old_vrate = atomic64_read(&ioc->vtime_rate); __entry->new_vrate = new_vrate; __entry->busy_level = ioc->busy_level; __entry->read_missed_ppm = missed_ppm[READ]; diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h index 12c315782766..777ee6cbe933 100644 --- a/include/trace/events/sock.h +++ b/include/trace/events/sock.h @@ -98,7 +98,7 @@ TRACE_EVENT(sock_exceed_buf_limit, TP_STRUCT__entry( __array(char, name, 32) - __field(long *, sysctl_mem) + __array(long, sysctl_mem, 3) __field(long, allocated) __field(int, sysctl_rmem) __field(int, rmem_alloc) @@ -110,7 +110,9 @@ TRACE_EVENT(sock_exceed_buf_limit, TP_fast_assign( strncpy(__entry->name, prot->name, 32); - __entry->sysctl_mem = prot->sysctl_mem; + __entry->sysctl_mem[0] = READ_ONCE(prot->sysctl_mem[0]); + __entry->sysctl_mem[1] = READ_ONCE(prot->sysctl_mem[1]); + __entry->sysctl_mem[2] = READ_ONCE(prot->sysctl_mem[2]); __entry->allocated = allocated; __entry->sysctl_rmem = sk_get_rmem0(sk, prot); __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f4009dbdf62d..ef78e0e1a754 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5222,22 +5222,25 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset) + * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length - * of *src*'s data, -EINVAL if *src* is an invalid dynptr. + * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if + * *flags* is not 0. * - * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len) + * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* - * is a read-only dynptr. + * is a read-only dynptr or if *flags* is not 0. * * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) * Description diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index ef4257ab3026..2557eb7b0561 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -78,10 +78,13 @@ struct input_id { * Note that input core does not clamp reported values to the * [minimum, maximum] limits, such task is left to userspace. * - * The default resolution for main axes (ABS_X, ABS_Y, ABS_Z) - * is reported in units per millimeter (units/mm), resolution - * for rotational axes (ABS_RX, ABS_RY, ABS_RZ) is reported - * in units per radian. + * The default resolution for main axes (ABS_X, ABS_Y, ABS_Z, + * ABS_MT_POSITION_X, ABS_MT_POSITION_Y) is reported in units + * per millimeter (units/mm), resolution for rotational axes + * (ABS_RX, ABS_RY, ABS_RZ) is reported in units per radian. + * The resolution for the size axes (ABS_MT_TOUCH_MAJOR, + * ABS_MT_TOUCH_MINOR, ABS_MT_WIDTH_MAJOR, ABS_MT_WIDTH_MINOR) + * is reported in units per millimeter (units/mm). * When INPUT_PROP_ACCELEROMETER is set the resolution changes. * The main axes (ABS_X, ABS_Y, ABS_Z) are then reported in * units per g (units/g) and in units per degree per second diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0ad3da28d2fc..4c9b11e2e991 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -10,6 +10,7 @@ #include <linux/fs.h> #include <linux/types.h> +#include <linux/time_types.h> /* * IO submission data structure (Submission Queue Entry) @@ -50,6 +51,7 @@ struct io_uring_sqe { __u32 unlink_flags; __u32 hardlink_flags; __u32 xattr_flags; + __u32 msg_ring_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -140,9 +142,12 @@ enum { * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. */ #define IORING_SETUP_TASKRUN_FLAG (1U << 9) - #define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ #define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */ +/* + * Only one task is allowed to submit requests + */ +#define IORING_SETUP_SINGLE_ISSUER (1U << 12) enum io_uring_op { IORING_OP_NOP, @@ -229,10 +234,13 @@ enum io_uring_op { * * IORING_POLL_UPDATE Update existing poll request, matching * sqe->addr as the old user_data field. + * + * IORING_POLL_LEVEL Level triggered poll. */ #define IORING_POLL_ADD_MULTI (1U << 0) #define IORING_POLL_UPDATE_EVENTS (1U << 1) #define IORING_POLL_UPDATE_USER_DATA (1U << 2) +#define IORING_POLL_ADD_LEVEL (1U << 3) /* * ASYNC_CANCEL flags. @@ -241,10 +249,12 @@ enum io_uring_op { * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the * request 'user_data' * IORING_ASYNC_CANCEL_ANY Match any request + * IORING_ASYNC_CANCEL_FD_FIXED 'fd' passed in is a fixed descriptor */ #define IORING_ASYNC_CANCEL_ALL (1U << 0) #define IORING_ASYNC_CANCEL_FD (1U << 1) #define IORING_ASYNC_CANCEL_ANY (1U << 2) +#define IORING_ASYNC_CANCEL_FD_FIXED (1U << 3) /* * send/sendmsg and recv/recvmsg flags (sqe->ioprio) @@ -253,8 +263,13 @@ enum io_uring_op { * or receive and arm poll if that yields an * -EAGAIN result, arm poll upfront and skip * the initial transfer attempt. + * + * IORING_RECV_MULTISHOT Multishot recv. Sets IORING_CQE_F_MORE if + * the handler will continue to report + * CQEs on behalf of the same SQE. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) +#define IORING_RECV_MULTISHOT (1U << 1) /* * accept flags stored in sqe->ioprio @@ -262,6 +277,22 @@ enum io_uring_op { #define IORING_ACCEPT_MULTISHOT (1U << 0) /* + * IORING_OP_MSG_RING command types, stored in sqe->addr + */ +enum { + IORING_MSG_DATA, /* pass sqe->len as 'res' and off as user_data */ + IORING_MSG_SEND_FD, /* send a registered fd to another ring */ +}; + +/* + * IORING_OP_MSG_RING flags (sqe->msg_ring_flags) + * + * IORING_MSG_RING_CQE_SKIP Don't post a CQE to the target ring. Not + * applicable for IORING_MSG_DATA, obviously. + */ +#define IORING_MSG_RING_CQE_SKIP (1U << 0) + +/* * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { @@ -420,6 +451,12 @@ enum { IORING_REGISTER_PBUF_RING = 22, IORING_UNREGISTER_PBUF_RING = 23, + /* sync cancelation API */ + IORING_REGISTER_SYNC_CANCEL = 24, + + /* register a range of fixed file slots for automatic slot allocation */ + IORING_REGISTER_FILE_ALLOC_RANGE = 25, + /* this goes last */ IORING_REGISTER_LAST }; @@ -483,7 +520,7 @@ struct io_uring_probe { __u8 ops_len; /* length of ops[] array below */ __u16 resv; __u32 resv2[3]; - struct io_uring_probe_op ops[0]; + struct io_uring_probe_op ops[]; }; struct io_uring_restriction { @@ -555,4 +592,32 @@ struct io_uring_getevents_arg { __u64 ts; }; +/* + * Argument for IORING_REGISTER_SYNC_CANCEL + */ +struct io_uring_sync_cancel_reg { + __u64 addr; + __s32 fd; + __u32 flags; + struct __kernel_timespec timeout; + __u64 pad[4]; +}; + +/* + * Argument for IORING_REGISTER_FILE_ALLOC_RANGE + * The range is specified as [off, off + len) + */ +struct io_uring_file_index_range { + __u32 off; + __u32 len; + __u64 resv; +}; + +struct io_uring_recvmsg_out { + __u32 namelen; + __u32 controllen; + __u32 payloadlen; + __u32 flags; +}; + #endif diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5088bd9f1922..860f867c50c0 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -2083,7 +2083,8 @@ struct kvm_stats_header { #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) -#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES +#define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN #define KVM_STATS_BASE_SHIFT 8 #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) diff --git a/include/uapi/linux/tty.h b/include/uapi/linux/tty.h index 9d0f06bfbac3..68aeae2addec 100644 --- a/include/uapi/linux/tty.h +++ b/include/uapi/linux/tty.h @@ -38,8 +38,9 @@ #define N_NULL 27 /* Null ldisc used for error handling */ #define N_MCTP 28 /* MCTP-over-serial */ #define N_DEVELOPMENT 29 /* Manual out-of-tree testing */ +#define N_CAN327 30 /* ELM327 based OBD-II interfaces */ /* Always the newest line discipline + 1 */ -#define NR_LDISCS 30 +#define NR_LDISCS 31 #endif /* _UAPI_LINUX_TTY_H */ diff --git a/io_uring/Makefile b/io_uring/Makefile new file mode 100644 index 000000000000..466639c289be --- /dev/null +++ b/io_uring/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for io_uring + +obj-$(CONFIG_IO_URING) += io_uring.o xattr.o nop.o fs.o splice.o \ + sync.o advise.o filetable.o \ + openclose.o uring_cmd.o epoll.o \ + statx.o net.o msg_ring.o timeout.o \ + sqpoll.o fdinfo.o tctx.o poll.o \ + cancel.o kbuf.o rsrc.o rw.o opdef.o +obj-$(CONFIG_IO_WQ) += io-wq.o diff --git a/io_uring/advise.c b/io_uring/advise.c new file mode 100644 index 000000000000..581956934c0b --- /dev/null +++ b/io_uring/advise.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/io_uring.h> + +#include <uapi/linux/fadvise.h> +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "advise.h" + +struct io_fadvise { + struct file *file; + u64 offset; + u32 len; + u32 advice; +}; + +struct io_madvise { + struct file *file; + u64 addr; + u32 len; + u32 advice; +}; + +int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ +#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) + struct io_madvise *ma = io_kiocb_to_cmd(req); + + if (sqe->buf_index || sqe->off || sqe->splice_fd_in) + return -EINVAL; + + ma->addr = READ_ONCE(sqe->addr); + ma->len = READ_ONCE(sqe->len); + ma->advice = READ_ONCE(sqe->fadvise_advice); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +int io_madvise(struct io_kiocb *req, unsigned int issue_flags) +{ +#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) + struct io_madvise *ma = io_kiocb_to_cmd(req); + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice); + io_req_set_res(req, ret, 0); + return IOU_OK; +#else + return -EOPNOTSUPP; +#endif +} + +int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_fadvise *fa = io_kiocb_to_cmd(req); + + if (sqe->buf_index || sqe->addr || sqe->splice_fd_in) + return -EINVAL; + + fa->offset = READ_ONCE(sqe->off); + fa->len = READ_ONCE(sqe->len); + fa->advice = READ_ONCE(sqe->fadvise_advice); + return 0; +} + +int io_fadvise(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_fadvise *fa = io_kiocb_to_cmd(req); + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) { + switch (fa->advice) { + case POSIX_FADV_NORMAL: + case POSIX_FADV_RANDOM: + case POSIX_FADV_SEQUENTIAL: + break; + default: + return -EAGAIN; + } + } + + ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} diff --git a/io_uring/advise.h b/io_uring/advise.h new file mode 100644 index 000000000000..5ece2a045185 --- /dev/null +++ b/io_uring/advise.h @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 + +int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_madvise(struct io_kiocb *req, unsigned int issue_flags); + +int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_fadvise(struct io_kiocb *req, unsigned int issue_flags); diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h new file mode 100644 index 000000000000..729793ae9712 --- /dev/null +++ b/io_uring/alloc_cache.h @@ -0,0 +1,53 @@ +#ifndef IOU_ALLOC_CACHE_H +#define IOU_ALLOC_CACHE_H + +/* + * Don't allow the cache to grow beyond this size. + */ +#define IO_ALLOC_CACHE_MAX 512 + +struct io_cache_entry { + struct hlist_node node; +}; + +static inline bool io_alloc_cache_put(struct io_alloc_cache *cache, + struct io_cache_entry *entry) +{ + if (cache->nr_cached < IO_ALLOC_CACHE_MAX) { + cache->nr_cached++; + hlist_add_head(&entry->node, &cache->list); + return true; + } + return false; +} + +static inline struct io_cache_entry *io_alloc_cache_get(struct io_alloc_cache *cache) +{ + if (!hlist_empty(&cache->list)) { + struct hlist_node *node = cache->list.first; + + hlist_del(node); + return container_of(node, struct io_cache_entry, node); + } + + return NULL; +} + +static inline void io_alloc_cache_init(struct io_alloc_cache *cache) +{ + INIT_HLIST_HEAD(&cache->list); + cache->nr_cached = 0; +} + +static inline void io_alloc_cache_free(struct io_alloc_cache *cache, + void (*free)(struct io_cache_entry *)) +{ + while (!hlist_empty(&cache->list)) { + struct hlist_node *node = cache->list.first; + + hlist_del(node); + free(container_of(node, struct io_cache_entry, node)); + } + cache->nr_cached = 0; +} +#endif diff --git a/io_uring/cancel.c b/io_uring/cancel.c new file mode 100644 index 000000000000..8435a1eba59a --- /dev/null +++ b/io_uring/cancel.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/nospec.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "tctx.h" +#include "poll.h" +#include "timeout.h" +#include "cancel.h" + +struct io_cancel { + struct file *file; + u64 addr; + u32 flags; + s32 fd; +}; + +#define CANCEL_FLAGS (IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \ + IORING_ASYNC_CANCEL_ANY | IORING_ASYNC_CANCEL_FD_FIXED) + +static bool io_cancel_cb(struct io_wq_work *work, void *data) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + struct io_cancel_data *cd = data; + + if (req->ctx != cd->ctx) + return false; + if (cd->flags & IORING_ASYNC_CANCEL_ANY) { + ; + } else if (cd->flags & IORING_ASYNC_CANCEL_FD) { + if (req->file != cd->file) + return false; + } else { + if (req->cqe.user_data != cd->data) + return false; + } + if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) { + if (cd->seq == req->work.cancel_seq) + return false; + req->work.cancel_seq = cd->seq; + } + return true; +} + +static int io_async_cancel_one(struct io_uring_task *tctx, + struct io_cancel_data *cd) +{ + enum io_wq_cancel cancel_ret; + int ret = 0; + bool all; + + if (!tctx || !tctx->io_wq) + return -ENOENT; + + all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); + cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, cd, all); + switch (cancel_ret) { + case IO_WQ_CANCEL_OK: + ret = 0; + break; + case IO_WQ_CANCEL_RUNNING: + ret = -EALREADY; + break; + case IO_WQ_CANCEL_NOTFOUND: + ret = -ENOENT; + break; + } + + return ret; +} + +int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, + unsigned issue_flags) +{ + struct io_ring_ctx *ctx = cd->ctx; + int ret; + + WARN_ON_ONCE(!io_wq_current_is_worker() && tctx != current->io_uring); + + ret = io_async_cancel_one(tctx, cd); + /* + * Fall-through even for -EALREADY, as we may have poll armed + * that need unarming. + */ + if (!ret) + return 0; + + ret = io_poll_cancel(ctx, cd, issue_flags); + if (ret != -ENOENT) + return ret; + + spin_lock(&ctx->completion_lock); + if (!(cd->flags & IORING_ASYNC_CANCEL_FD)) + ret = io_timeout_cancel(ctx, cd); + spin_unlock(&ctx->completion_lock); + return ret; +} + +int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_cancel *cancel = io_kiocb_to_cmd(req); + + if (unlikely(req->flags & REQ_F_BUFFER_SELECT)) + return -EINVAL; + if (sqe->off || sqe->len || sqe->splice_fd_in) + return -EINVAL; + + cancel->addr = READ_ONCE(sqe->addr); + cancel->flags = READ_ONCE(sqe->cancel_flags); + if (cancel->flags & ~CANCEL_FLAGS) + return -EINVAL; + if (cancel->flags & IORING_ASYNC_CANCEL_FD) { + if (cancel->flags & IORING_ASYNC_CANCEL_ANY) + return -EINVAL; + cancel->fd = READ_ONCE(sqe->fd); + } + + return 0; +} + +static int __io_async_cancel(struct io_cancel_data *cd, + struct io_uring_task *tctx, + unsigned int issue_flags) +{ + bool all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); + struct io_ring_ctx *ctx = cd->ctx; + struct io_tctx_node *node; + int ret, nr = 0; + + do { + ret = io_try_cancel(tctx, cd, issue_flags); + if (ret == -ENOENT) + break; + if (!all) + return ret; + nr++; + } while (1); + + /* slow path, try all io-wq's */ + io_ring_submit_lock(ctx, issue_flags); + ret = -ENOENT; + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; + + ret = io_async_cancel_one(tctx, cd); + if (ret != -ENOENT) { + if (!all) + break; + nr++; + } + } + io_ring_submit_unlock(ctx, issue_flags); + return all ? nr : ret; +} + +int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_cancel *cancel = io_kiocb_to_cmd(req); + struct io_cancel_data cd = { + .ctx = req->ctx, + .data = cancel->addr, + .flags = cancel->flags, + .seq = atomic_inc_return(&req->ctx->cancel_seq), + }; + struct io_uring_task *tctx = req->task->io_uring; + int ret; + + if (cd.flags & IORING_ASYNC_CANCEL_FD) { + if (req->flags & REQ_F_FIXED_FILE || + cd.flags & IORING_ASYNC_CANCEL_FD_FIXED) { + req->flags |= REQ_F_FIXED_FILE; + req->file = io_file_get_fixed(req, cancel->fd, + issue_flags); + } else { + req->file = io_file_get_normal(req, cancel->fd); + } + if (!req->file) { + ret = -EBADF; + goto done; + } + cd.file = req->file; + } + + ret = __io_async_cancel(&cd, tctx, issue_flags); +done: + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +void init_hash_table(struct io_hash_table *table, unsigned size) +{ + unsigned int i; + + for (i = 0; i < size; i++) { + spin_lock_init(&table->hbs[i].lock); + INIT_HLIST_HEAD(&table->hbs[i].list); + } +} + +static int __io_sync_cancel(struct io_uring_task *tctx, + struct io_cancel_data *cd, int fd) +{ + struct io_ring_ctx *ctx = cd->ctx; + + /* fixed must be grabbed every time since we drop the uring_lock */ + if ((cd->flags & IORING_ASYNC_CANCEL_FD) && + (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) { + unsigned long file_ptr; + + if (unlikely(fd > ctx->nr_user_files)) + return -EBADF; + fd = array_index_nospec(fd, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; + cd->file = (struct file *) (file_ptr & FFS_MASK); + if (!cd->file) + return -EBADF; + } + + return __io_async_cancel(cd, tctx, 0); +} + +int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg) + __must_hold(&ctx->uring_lock) +{ + struct io_cancel_data cd = { + .ctx = ctx, + .seq = atomic_inc_return(&ctx->cancel_seq), + }; + ktime_t timeout = KTIME_MAX; + struct io_uring_sync_cancel_reg sc; + struct fd f = { }; + DEFINE_WAIT(wait); + int ret; + + if (copy_from_user(&sc, arg, sizeof(sc))) + return -EFAULT; + if (sc.flags & ~CANCEL_FLAGS) + return -EINVAL; + if (sc.pad[0] || sc.pad[1] || sc.pad[2] || sc.pad[3]) + return -EINVAL; + + cd.data = sc.addr; + cd.flags = sc.flags; + + /* we can grab a normal file descriptor upfront */ + if ((cd.flags & IORING_ASYNC_CANCEL_FD) && + !(cd.flags & IORING_ASYNC_CANCEL_FD_FIXED)) { + f = fdget(sc.fd); + if (!f.file) + return -EBADF; + cd.file = f.file; + } + + ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); + + /* found something, done! */ + if (ret != -EALREADY) + goto out; + + if (sc.timeout.tv_sec != -1UL || sc.timeout.tv_nsec != -1UL) { + struct timespec64 ts = { + .tv_sec = sc.timeout.tv_sec, + .tv_nsec = sc.timeout.tv_nsec + }; + + timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); + } + + /* + * Keep looking until we get -ENOENT. we'll get woken everytime + * every time a request completes and will retry the cancelation. + */ + do { + cd.seq = atomic_inc_return(&ctx->cancel_seq); + + prepare_to_wait(&ctx->cq_wait, &wait, TASK_INTERRUPTIBLE); + + ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); + + if (ret != -EALREADY) + break; + + mutex_unlock(&ctx->uring_lock); + ret = io_run_task_work_sig(); + if (ret < 0) { + mutex_lock(&ctx->uring_lock); + break; + } + ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS); + mutex_lock(&ctx->uring_lock); + if (!ret) { + ret = -ETIME; + break; + } + } while (1); + + finish_wait(&ctx->cq_wait, &wait); + + if (ret == -ENOENT || ret > 0) + ret = 0; +out: + fdput(f); + return ret; +} diff --git a/io_uring/cancel.h b/io_uring/cancel.h new file mode 100644 index 000000000000..6a59ee484d0c --- /dev/null +++ b/io_uring/cancel.h @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/io_uring_types.h> + +struct io_cancel_data { + struct io_ring_ctx *ctx; + union { + u64 data; + struct file *file; + }; + u32 flags; + int seq; +}; + + +int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags); + +int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, + unsigned int issue_flags); +void init_hash_table(struct io_hash_table *table, unsigned size); + +int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg); diff --git a/io_uring/epoll.c b/io_uring/epoll.c new file mode 100644 index 000000000000..a8b794471d6b --- /dev/null +++ b/io_uring/epoll.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/uaccess.h> +#include <linux/io_uring.h> +#include <linux/eventpoll.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "epoll.h" + +#if defined(CONFIG_EPOLL) +struct io_epoll { + struct file *file; + int epfd; + int op; + int fd; + struct epoll_event event; +}; + +int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_epoll *epoll = io_kiocb_to_cmd(req); + + pr_warn_once("%s: epoll_ctl support in io_uring is deprecated and will " + "be removed in a future Linux kernel version.\n", + current->comm); + + if (sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + + epoll->epfd = READ_ONCE(sqe->fd); + epoll->op = READ_ONCE(sqe->len); + epoll->fd = READ_ONCE(sqe->off); + + if (ep_op_has_event(epoll->op)) { + struct epoll_event __user *ev; + + ev = u64_to_user_ptr(READ_ONCE(sqe->addr)); + if (copy_from_user(&epoll->event, ev, sizeof(*ev))) + return -EFAULT; + } + + return 0; +} + +int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_epoll *ie = io_kiocb_to_cmd(req); + int ret; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + + ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock); + if (force_nonblock && ret == -EAGAIN) + return -EAGAIN; + + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} +#endif diff --git a/io_uring/epoll.h b/io_uring/epoll.h new file mode 100644 index 000000000000..870cce11ba98 --- /dev/null +++ b/io_uring/epoll.h @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 + +#if defined(CONFIG_EPOLL) +int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags); +#endif diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c new file mode 100644 index 000000000000..b29e2d02216f --- /dev/null +++ b/io_uring/fdinfo.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "sqpoll.h" +#include "fdinfo.h" +#include "cancel.h" +#include "rsrc.h" + +#ifdef CONFIG_PROC_FS +static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id, + const struct cred *cred) +{ + struct user_namespace *uns = seq_user_ns(m); + struct group_info *gi; + kernel_cap_t cap; + unsigned __capi; + int g; + + seq_printf(m, "%5d\n", id); + seq_put_decimal_ull(m, "\tUid:\t", from_kuid_munged(uns, cred->uid)); + seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->euid)); + seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->suid)); + seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->fsuid)); + seq_put_decimal_ull(m, "\n\tGid:\t", from_kgid_munged(uns, cred->gid)); + seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->egid)); + seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->sgid)); + seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->fsgid)); + seq_puts(m, "\n\tGroups:\t"); + gi = cred->group_info; + for (g = 0; g < gi->ngroups; g++) { + seq_put_decimal_ull(m, g ? " " : "", + from_kgid_munged(uns, gi->gid[g])); + } + seq_puts(m, "\n\tCapEff:\t"); + cap = cred->cap_effective; + CAP_FOR_EACH_U32(__capi) + seq_put_hex_ll(m, NULL, cap.cap[CAP_LAST_U32 - __capi], 8); + seq_putc(m, '\n'); + return 0; +} + +static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, + struct seq_file *m) +{ + struct io_sq_data *sq = NULL; + struct io_overflow_cqe *ocqe; + struct io_rings *r = ctx->rings; + unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1; + unsigned int sq_head = READ_ONCE(r->sq.head); + unsigned int sq_tail = READ_ONCE(r->sq.tail); + unsigned int cq_head = READ_ONCE(r->cq.head); + unsigned int cq_tail = READ_ONCE(r->cq.tail); + unsigned int cq_shift = 0; + unsigned int sq_entries, cq_entries; + bool has_lock; + bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32); + unsigned int i; + + if (is_cqe32) + cq_shift = 1; + + /* + * we may get imprecise sqe and cqe info if uring is actively running + * since we get cached_sq_head and cached_cq_tail without uring_lock + * and sq_tail and cq_head are changed by userspace. But it's ok since + * we usually use these info when it is stuck. + */ + seq_printf(m, "SqMask:\t0x%x\n", sq_mask); + seq_printf(m, "SqHead:\t%u\n", sq_head); + seq_printf(m, "SqTail:\t%u\n", sq_tail); + seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head); + seq_printf(m, "CqMask:\t0x%x\n", cq_mask); + seq_printf(m, "CqHead:\t%u\n", cq_head); + seq_printf(m, "CqTail:\t%u\n", cq_tail); + seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail); + seq_printf(m, "SQEs:\t%u\n", sq_tail - ctx->cached_sq_head); + sq_entries = min(sq_tail - sq_head, ctx->sq_entries); + for (i = 0; i < sq_entries; i++) { + unsigned int entry = i + sq_head; + unsigned int sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]); + struct io_uring_sqe *sqe; + + if (sq_idx > sq_mask) + continue; + sqe = &ctx->sq_sqes[sq_idx]; + seq_printf(m, "%5u: opcode:%d, fd:%d, flags:%x, user_data:%llu\n", + sq_idx, sqe->opcode, sqe->fd, sqe->flags, + sqe->user_data); + } + seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head); + cq_entries = min(cq_tail - cq_head, ctx->cq_entries); + for (i = 0; i < cq_entries; i++) { + unsigned int entry = i + cq_head; + struct io_uring_cqe *cqe = &r->cqes[(entry & cq_mask) << cq_shift]; + + if (!is_cqe32) { + seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n", + entry & cq_mask, cqe->user_data, cqe->res, + cqe->flags); + } else { + seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x, " + "extra1:%llu, extra2:%llu\n", + entry & cq_mask, cqe->user_data, cqe->res, + cqe->flags, cqe->big_cqe[0], cqe->big_cqe[1]); + } + } + + /* + * Avoid ABBA deadlock between the seq lock and the io_uring mutex, + * since fdinfo case grabs it in the opposite direction of normal use + * cases. If we fail to get the lock, we just don't iterate any + * structures that could be going away outside the io_uring mutex. + */ + has_lock = mutex_trylock(&ctx->uring_lock); + + if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) { + sq = ctx->sq_data; + if (!sq->thread) + sq = NULL; + } + + seq_printf(m, "SqThread:\t%d\n", sq ? task_pid_nr(sq->thread) : -1); + seq_printf(m, "SqThreadCpu:\t%d\n", sq ? task_cpu(sq->thread) : -1); + seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); + for (i = 0; has_lock && i < ctx->nr_user_files; i++) { + struct file *f = io_file_from_index(&ctx->file_table, i); + + if (f) + seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname); + else + seq_printf(m, "%5u: <none>\n", i); + } + seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); + for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) { + struct io_mapped_ubuf *buf = ctx->user_bufs[i]; + unsigned int len = buf->ubuf_end - buf->ubuf; + + seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len); + } + if (has_lock && !xa_empty(&ctx->personalities)) { + unsigned long index; + const struct cred *cred; + + seq_printf(m, "Personalities:\n"); + xa_for_each(&ctx->personalities, index, cred) + io_uring_show_cred(m, index, cred); + } + if (has_lock) + mutex_unlock(&ctx->uring_lock); + + seq_puts(m, "PollList:\n"); + for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) { + struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i]; + struct io_kiocb *req; + + spin_lock(&hb->lock); + hlist_for_each_entry(req, &hb->list, hash_node) + seq_printf(m, " op=%d, task_works=%d\n", req->opcode, + task_work_pending(req->task)); + spin_unlock(&hb->lock); + } + + seq_puts(m, "CqOverflowList:\n"); + spin_lock(&ctx->completion_lock); + list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) { + struct io_uring_cqe *cqe = &ocqe->cqe; + + seq_printf(m, " user_data=%llu, res=%d, flags=%x\n", + cqe->user_data, cqe->res, cqe->flags); + + } + + spin_unlock(&ctx->completion_lock); +} + +__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct io_ring_ctx *ctx = f->private_data; + + if (percpu_ref_tryget(&ctx->refs)) { + __io_uring_show_fdinfo(ctx, m); + percpu_ref_put(&ctx->refs); + } +} +#endif diff --git a/io_uring/fdinfo.h b/io_uring/fdinfo.h new file mode 100644 index 000000000000..6fde48c450e3 --- /dev/null +++ b/io_uring/fdinfo.h @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 + +void io_uring_show_fdinfo(struct seq_file *m, struct file *f); diff --git a/io_uring/filetable.c b/io_uring/filetable.c new file mode 100644 index 000000000000..7b473259f3f4 --- /dev/null +++ b/io_uring/filetable.c @@ -0,0 +1,193 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/nospec.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "rsrc.h" +#include "filetable.h" + +static int io_file_bitmap_get(struct io_ring_ctx *ctx) +{ + struct io_file_table *table = &ctx->file_table; + unsigned long nr = ctx->file_alloc_end; + int ret; + + do { + ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint); + if (ret != nr) + return ret; + + if (table->alloc_hint == ctx->file_alloc_start) + break; + nr = table->alloc_hint; + table->alloc_hint = ctx->file_alloc_start; + } while (1); + + return -ENFILE; +} + +bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) +{ + table->files = kvcalloc(nr_files, sizeof(table->files[0]), + GFP_KERNEL_ACCOUNT); + if (unlikely(!table->files)) + return false; + + table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT); + if (unlikely(!table->bitmap)) { + kvfree(table->files); + return false; + } + + return true; +} + +void io_free_file_tables(struct io_file_table *table) +{ + kvfree(table->files); + bitmap_free(table->bitmap); + table->files = NULL; + table->bitmap = NULL; +} + +static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, + u32 slot_index) + __must_hold(&req->ctx->uring_lock) +{ + bool needs_switch = false; + struct io_fixed_file *file_slot; + int ret; + + if (io_is_uring_fops(file)) + return -EBADF; + if (!ctx->file_data) + return -ENXIO; + if (slot_index >= ctx->nr_user_files) + return -EINVAL; + + slot_index = array_index_nospec(slot_index, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, slot_index); + + if (file_slot->file_ptr) { + struct file *old_file; + + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto err; + + old_file = (struct file *)(file_slot->file_ptr & FFS_MASK); + ret = io_queue_rsrc_removal(ctx->file_data, slot_index, + ctx->rsrc_node, old_file); + if (ret) + goto err; + file_slot->file_ptr = 0; + io_file_bitmap_clear(&ctx->file_table, slot_index); + needs_switch = true; + } + + ret = io_scm_file_account(ctx, file); + if (!ret) { + *io_get_tag_slot(ctx->file_data, slot_index) = 0; + io_fixed_file_set(file_slot, file); + io_file_bitmap_set(&ctx->file_table, slot_index); + } +err: + if (needs_switch) + io_rsrc_node_switch(ctx, ctx->file_data); + if (ret) + fput(file); + return ret; +} + +int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file, + unsigned int file_slot) +{ + bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC; + int ret; + + if (alloc_slot) { + ret = io_file_bitmap_get(ctx); + if (unlikely(ret < 0)) + return ret; + file_slot = ret; + } else { + file_slot--; + } + + ret = io_install_fixed_file(ctx, file, file_slot); + if (!ret && alloc_slot) + ret = file_slot; + return ret; +} +/* + * Note when io_fixed_fd_install() returns error value, it will ensure + * fput() is called correspondingly. + */ +int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags, + struct file *file, unsigned int file_slot) +{ + struct io_ring_ctx *ctx = req->ctx; + int ret; + + io_ring_submit_lock(ctx, issue_flags); + ret = __io_fixed_fd_install(ctx, file, file_slot); + io_ring_submit_unlock(ctx, issue_flags); + + if (unlikely(ret < 0)) + fput(file); + return ret; +} + +int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset) +{ + struct io_fixed_file *file_slot; + struct file *file; + int ret; + + if (unlikely(!ctx->file_data)) + return -ENXIO; + if (offset >= ctx->nr_user_files) + return -EINVAL; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + return ret; + + offset = array_index_nospec(offset, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, offset); + if (!file_slot->file_ptr) + return -EBADF; + + file = (struct file *)(file_slot->file_ptr & FFS_MASK); + ret = io_queue_rsrc_removal(ctx->file_data, offset, ctx->rsrc_node, file); + if (ret) + return ret; + + file_slot->file_ptr = 0; + io_file_bitmap_clear(&ctx->file_table, offset); + io_rsrc_node_switch(ctx, ctx->file_data); + return 0; +} + +int io_register_file_alloc_range(struct io_ring_ctx *ctx, + struct io_uring_file_index_range __user *arg) +{ + struct io_uring_file_index_range range; + u32 end; + + if (copy_from_user(&range, arg, sizeof(range))) + return -EFAULT; + if (check_add_overflow(range.off, range.len, &end)) + return -EOVERFLOW; + if (range.resv || end > ctx->nr_user_files) + return -EINVAL; + + io_file_table_set_alloc_range(ctx, range.off, range.len); + return 0; +} diff --git a/io_uring/filetable.h b/io_uring/filetable.h new file mode 100644 index 000000000000..ff3a712e11bf --- /dev/null +++ b/io_uring/filetable.h @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef IOU_FILE_TABLE_H +#define IOU_FILE_TABLE_H + +#include <linux/file.h> +#include <linux/io_uring_types.h> + +/* + * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0 + * and define IO_URING_SCM_ALL. For this case, we use SCM for all files as we + * can't safely always dereference the file when the task has exited and ring + * cleanup is done. If a file is tracked and part of SCM, then unix gc on + * process exit may reap it before __io_sqe_files_unregister() is run. + */ +#define FFS_NOWAIT 0x1UL +#define FFS_ISREG 0x2UL +#if defined(CONFIG_64BIT) +#define FFS_SCM 0x4UL +#else +#define IO_URING_SCM_ALL +#define FFS_SCM 0x0UL +#endif +#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG|FFS_SCM) + +bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files); +void io_free_file_tables(struct io_file_table *table); + +int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags, + struct file *file, unsigned int file_slot); +int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file, + unsigned int file_slot); +int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset); + +int io_register_file_alloc_range(struct io_ring_ctx *ctx, + struct io_uring_file_index_range __user *arg); + +unsigned int io_file_get_flags(struct file *file); + +static inline void io_file_bitmap_clear(struct io_file_table *table, int bit) +{ + __clear_bit(bit, table->bitmap); + table->alloc_hint = bit; +} + +static inline void io_file_bitmap_set(struct io_file_table *table, int bit) +{ + WARN_ON_ONCE(test_bit(bit, table->bitmap)); + __set_bit(bit, table->bitmap); + table->alloc_hint = bit + 1; +} + +static inline struct io_fixed_file * +io_fixed_file_slot(struct io_file_table *table, unsigned i) +{ + return &table->files[i]; +} + +static inline struct file *io_file_from_index(struct io_file_table *table, + int index) +{ + struct io_fixed_file *slot = io_fixed_file_slot(table, index); + + return (struct file *) (slot->file_ptr & FFS_MASK); +} + +static inline void io_fixed_file_set(struct io_fixed_file *file_slot, + struct file *file) +{ + unsigned long file_ptr = (unsigned long) file; + + file_ptr |= io_file_get_flags(file); + file_slot->file_ptr = file_ptr; +} + +static inline void io_reset_alloc_hint(struct io_ring_ctx *ctx) +{ + ctx->file_table.alloc_hint = ctx->file_alloc_start; +} + +static inline void io_file_table_set_alloc_range(struct io_ring_ctx *ctx, + unsigned off, unsigned len) +{ + ctx->file_alloc_start = off; + ctx->file_alloc_end = off + len; + io_reset_alloc_hint(ctx); +} + +#endif diff --git a/io_uring/fs.c b/io_uring/fs.c new file mode 100644 index 000000000000..0de4f549bb7d --- /dev/null +++ b/io_uring/fs.c @@ -0,0 +1,293 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "../fs/internal.h" + +#include "io_uring.h" +#include "fs.h" + +struct io_rename { + struct file *file; + int old_dfd; + int new_dfd; + struct filename *oldpath; + struct filename *newpath; + int flags; +}; + +struct io_unlink { + struct file *file; + int dfd; + int flags; + struct filename *filename; +}; + +struct io_mkdir { + struct file *file; + int dfd; + umode_t mode; + struct filename *filename; +}; + +struct io_link { + struct file *file; + int old_dfd; + int new_dfd; + struct filename *oldpath; + struct filename *newpath; + int flags; +}; + +int io_renameat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_rename *ren = io_kiocb_to_cmd(req); + const char __user *oldf, *newf; + + if (sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ren->old_dfd = READ_ONCE(sqe->fd); + oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); + newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ren->new_dfd = READ_ONCE(sqe->len); + ren->flags = READ_ONCE(sqe->rename_flags); + + ren->oldpath = getname(oldf); + if (IS_ERR(ren->oldpath)) + return PTR_ERR(ren->oldpath); + + ren->newpath = getname(newf); + if (IS_ERR(ren->newpath)) { + putname(ren->oldpath); + return PTR_ERR(ren->newpath); + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +int io_renameat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_rename *ren = io_kiocb_to_cmd(req); + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd, + ren->newpath, ren->flags); + + req->flags &= ~REQ_F_NEED_CLEANUP; + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +void io_renameat_cleanup(struct io_kiocb *req) +{ + struct io_rename *ren = io_kiocb_to_cmd(req); + + putname(ren->oldpath); + putname(ren->newpath); +} + +int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_unlink *un = io_kiocb_to_cmd(req); + const char __user *fname; + + if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + un->dfd = READ_ONCE(sqe->fd); + + un->flags = READ_ONCE(sqe->unlink_flags); + if (un->flags & ~AT_REMOVEDIR) + return -EINVAL; + + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); + un->filename = getname(fname); + if (IS_ERR(un->filename)) + return PTR_ERR(un->filename); + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_unlink *un = io_kiocb_to_cmd(req); + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + if (un->flags & AT_REMOVEDIR) + ret = do_rmdir(un->dfd, un->filename); + else + ret = do_unlinkat(un->dfd, un->filename); + + req->flags &= ~REQ_F_NEED_CLEANUP; + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +void io_unlinkat_cleanup(struct io_kiocb *req) +{ + struct io_unlink *ul = io_kiocb_to_cmd(req); + + putname(ul->filename); +} + +int io_mkdirat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_mkdir *mkd = io_kiocb_to_cmd(req); + const char __user *fname; + + if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + mkd->dfd = READ_ONCE(sqe->fd); + mkd->mode = READ_ONCE(sqe->len); + + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); + mkd->filename = getname(fname); + if (IS_ERR(mkd->filename)) + return PTR_ERR(mkd->filename); + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_mkdir *mkd = io_kiocb_to_cmd(req); + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode); + + req->flags &= ~REQ_F_NEED_CLEANUP; + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +void io_mkdirat_cleanup(struct io_kiocb *req) +{ + struct io_mkdir *md = io_kiocb_to_cmd(req); + + putname(md->filename); +} + +int io_symlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_link *sl = io_kiocb_to_cmd(req); + const char __user *oldpath, *newpath; + + if (sqe->len || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + sl->new_dfd = READ_ONCE(sqe->fd); + oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr)); + newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + + sl->oldpath = getname(oldpath); + if (IS_ERR(sl->oldpath)) + return PTR_ERR(sl->oldpath); + + sl->newpath = getname(newpath); + if (IS_ERR(sl->newpath)) { + putname(sl->oldpath); + return PTR_ERR(sl->newpath); + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_link *sl = io_kiocb_to_cmd(req); + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath); + + req->flags &= ~REQ_F_NEED_CLEANUP; + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_link *lnk = io_kiocb_to_cmd(req); + const char __user *oldf, *newf; + + if (sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + lnk->old_dfd = READ_ONCE(sqe->fd); + lnk->new_dfd = READ_ONCE(sqe->len); + oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); + newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + lnk->flags = READ_ONCE(sqe->hardlink_flags); + + lnk->oldpath = getname(oldf); + if (IS_ERR(lnk->oldpath)) + return PTR_ERR(lnk->oldpath); + + lnk->newpath = getname(newf); + if (IS_ERR(lnk->newpath)) { + putname(lnk->oldpath); + return PTR_ERR(lnk->newpath); + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +int io_linkat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_link *lnk = io_kiocb_to_cmd(req); + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_linkat(lnk->old_dfd, lnk->oldpath, lnk->new_dfd, + lnk->newpath, lnk->flags); + + req->flags &= ~REQ_F_NEED_CLEANUP; + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +void io_link_cleanup(struct io_kiocb *req) +{ + struct io_link *sl = io_kiocb_to_cmd(req); + + putname(sl->oldpath); + putname(sl->newpath); +} diff --git a/io_uring/fs.h b/io_uring/fs.h new file mode 100644 index 000000000000..0bb5efe3d6bb --- /dev/null +++ b/io_uring/fs.h @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 + +int io_renameat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_renameat(struct io_kiocb *req, unsigned int issue_flags); +void io_renameat_cleanup(struct io_kiocb *req); + +int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags); +void io_unlinkat_cleanup(struct io_kiocb *req); + +int io_mkdirat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags); +void io_mkdirat_cleanup(struct io_kiocb *req); + +int io_symlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags); + +int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_linkat(struct io_kiocb *req, unsigned int issue_flags); +void io_link_cleanup(struct io_kiocb *req); diff --git a/fs/io-wq.c b/io_uring/io-wq.c index 824623bcf1a5..77df5b43bf52 100644 --- a/fs/io-wq.c +++ b/io_uring/io-wq.c @@ -18,6 +18,8 @@ #include <uapi/linux/io_uring.h> #include "io-wq.h" +#include "slist.h" +#include "io_uring.h" #define WORKER_IDLE_TIMEOUT (5 * HZ) @@ -518,23 +520,11 @@ static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct, return NULL; } -static bool io_flush_signals(void) -{ - if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) { - __set_current_state(TASK_RUNNING); - clear_notify_signal(); - if (task_work_pending(current)) - task_work_run(); - return true; - } - return false; -} - static void io_assign_current_work(struct io_worker *worker, struct io_wq_work *work) { if (work) { - io_flush_signals(); + io_run_task_work(); cond_resched(); } @@ -654,7 +644,7 @@ static int io_wqe_worker(void *data) last_timeout = false; __io_worker_idle(wqe, worker); raw_spin_unlock(&wqe->lock); - if (io_flush_signals()) + if (io_run_task_work()) continue; ret = schedule_timeout(WORKER_IDLE_TIMEOUT); if (signal_pending(current)) { diff --git a/io_uring/io-wq.h b/io_uring/io-wq.h new file mode 100644 index 000000000000..31228426d192 --- /dev/null +++ b/io_uring/io-wq.h @@ -0,0 +1,83 @@ +#ifndef INTERNAL_IO_WQ_H +#define INTERNAL_IO_WQ_H + +#include <linux/refcount.h> +#include <linux/io_uring_types.h> + +struct io_wq; + +enum { + IO_WQ_WORK_CANCEL = 1, + IO_WQ_WORK_HASHED = 2, + IO_WQ_WORK_UNBOUND = 4, + IO_WQ_WORK_CONCURRENT = 16, + + IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */ +}; + +enum io_wq_cancel { + IO_WQ_CANCEL_OK, /* cancelled before started */ + IO_WQ_CANCEL_RUNNING, /* found, running, and attempted cancelled */ + IO_WQ_CANCEL_NOTFOUND, /* work not found */ +}; + +typedef struct io_wq_work *(free_work_fn)(struct io_wq_work *); +typedef void (io_wq_work_fn)(struct io_wq_work *); + +struct io_wq_hash { + refcount_t refs; + unsigned long map; + struct wait_queue_head wait; +}; + +static inline void io_wq_put_hash(struct io_wq_hash *hash) +{ + if (refcount_dec_and_test(&hash->refs)) + kfree(hash); +} + +struct io_wq_data { + struct io_wq_hash *hash; + struct task_struct *task; + io_wq_work_fn *do_work; + free_work_fn *free_work; +}; + +struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data); +void io_wq_exit_start(struct io_wq *wq); +void io_wq_put_and_exit(struct io_wq *wq); + +void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); +void io_wq_hash_work(struct io_wq_work *work, void *val); + +int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask); +int io_wq_max_workers(struct io_wq *wq, int *new_count); + +static inline bool io_wq_is_hashed(struct io_wq_work *work) +{ + return work->flags & IO_WQ_WORK_HASHED; +} + +typedef bool (work_cancel_fn)(struct io_wq_work *, void *); + +enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, + void *data, bool cancel_all); + +#if defined(CONFIG_IO_WQ) +extern void io_wq_worker_sleeping(struct task_struct *); +extern void io_wq_worker_running(struct task_struct *); +#else +static inline void io_wq_worker_sleeping(struct task_struct *tsk) +{ +} +static inline void io_wq_worker_running(struct task_struct *tsk) +{ +} +#endif + +static inline bool io_wq_current_is_worker(void) +{ + return in_task() && (current->flags & PF_IO_WORKER) && + current->worker_private; +} +#endif diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c new file mode 100644 index 000000000000..4b3fd645d023 --- /dev/null +++ b/io_uring/io_uring.c @@ -0,0 +1,3980 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Shared application/kernel submission and completion ring pairs, for + * supporting fast/efficient IO. + * + * A note on the read/write ordering memory barriers that are matched between + * the application and kernel side. + * + * After the application reads the CQ ring tail, it must use an + * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses + * before writing the tail (using smp_load_acquire to read the tail will + * do). It also needs a smp_mb() before updating CQ head (ordering the + * entry load(s) with the head store), pairing with an implicit barrier + * through a control-dependency in io_get_cqe (smp_store_release to + * store head will do). Failure to do so could lead to reading invalid + * CQ entries. + * + * Likewise, the application must use an appropriate smp_wmb() before + * writing the SQ tail (ordering SQ entry stores with the tail store), + * which pairs with smp_load_acquire in io_get_sqring (smp_store_release + * to store the tail will do). And it needs a barrier ordering the SQ + * head load before writing new SQ entries (smp_load_acquire to read + * head will do). + * + * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application + * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after* + * updating the SQ tail; a full memory barrier smp_mb() is needed + * between. + * + * Also see the examples in the liburing library: + * + * git://git.kernel.dk/liburing + * + * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens + * from data shared between the kernel and application. This is done both + * for ordering purposes, but also to ensure that once a value is loaded from + * data that the application could potentially modify, it remains stable. + * + * Copyright (C) 2018-2019 Jens Axboe + * Copyright (c) 2018-2019 Christoph Hellwig + */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/syscalls.h> +#include <net/compat.h> +#include <linux/refcount.h> +#include <linux/uio.h> +#include <linux/bits.h> + +#include <linux/sched/signal.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/fdtable.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/percpu.h> +#include <linux/slab.h> +#include <linux/bvec.h> +#include <linux/net.h> +#include <net/sock.h> +#include <net/af_unix.h> +#include <net/scm.h> +#include <linux/anon_inodes.h> +#include <linux/sched/mm.h> +#include <linux/uaccess.h> +#include <linux/nospec.h> +#include <linux/highmem.h> +#include <linux/fsnotify.h> +#include <linux/fadvise.h> +#include <linux/task_work.h> +#include <linux/io_uring.h> +#include <linux/audit.h> +#include <linux/security.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io-wq.h" + +#include "io_uring.h" +#include "opdef.h" +#include "refs.h" +#include "tctx.h" +#include "sqpoll.h" +#include "fdinfo.h" +#include "kbuf.h" +#include "rsrc.h" +#include "cancel.h" +#include "net.h" + +#include "timeout.h" +#include "poll.h" +#include "alloc_cache.h" + +#define IORING_MAX_ENTRIES 32768 +#define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES) + +#define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ + IORING_REGISTER_LAST + IORING_OP_LAST) + +#define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \ + IOSQE_IO_HARDLINK | IOSQE_ASYNC) + +#define SQE_VALID_FLAGS (SQE_COMMON_FLAGS | IOSQE_BUFFER_SELECT | \ + IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS) + +#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ + REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \ + REQ_F_ASYNC_DATA) + +#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\ + IO_REQ_CLEAN_FLAGS) + +#define IO_TCTX_REFS_CACHE_NR (1U << 10) + +#define IO_COMPL_BATCH 32 +#define IO_REQ_ALLOC_BATCH 8 + +enum { + IO_CHECK_CQ_OVERFLOW_BIT, + IO_CHECK_CQ_DROPPED_BIT, +}; + +struct io_defer_entry { + struct list_head list; + struct io_kiocb *req; + u32 seq; +}; + +/* requests with any of those set should undergo io_disarm_next() */ +#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL) +#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK) + +static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + bool cancel_all); + +static void io_dismantle_req(struct io_kiocb *req); +static void io_clean_op(struct io_kiocb *req); +static void io_queue_sqe(struct io_kiocb *req); + +static void __io_submit_flush_completions(struct io_ring_ctx *ctx); + +static struct kmem_cache *req_cachep; + +struct sock *io_uring_get_socket(struct file *file) +{ +#if defined(CONFIG_UNIX) + if (io_is_uring_fops(file)) { + struct io_ring_ctx *ctx = file->private_data; + + return ctx->ring_sock->sk; + } +#endif + return NULL; +} +EXPORT_SYMBOL(io_uring_get_socket); + +static inline void io_submit_flush_completions(struct io_ring_ctx *ctx) +{ + if (!wq_list_empty(&ctx->submit_state.compl_reqs)) + __io_submit_flush_completions(ctx); +} + +static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) +{ + return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); +} + +static bool io_match_linked(struct io_kiocb *head) +{ + struct io_kiocb *req; + + io_for_each_link(req, head) { + if (req->flags & REQ_F_INFLIGHT) + return true; + } + return false; +} + +/* + * As io_match_task() but protected against racing with linked timeouts. + * User must not hold timeout_lock. + */ +bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, + bool cancel_all) +{ + bool matched; + + if (task && head->task != task) + return false; + if (cancel_all) + return true; + + if (head->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = head->ctx; + + /* protect against races with linked timeouts */ + spin_lock_irq(&ctx->timeout_lock); + matched = io_match_linked(head); + spin_unlock_irq(&ctx->timeout_lock); + } else { + matched = io_match_linked(head); + } + return matched; +} + +static inline void req_fail_link_node(struct io_kiocb *req, int res) +{ + req_set_fail(req); + io_req_set_res(req, res, 0); +} + +static inline void io_req_add_to_cache(struct io_kiocb *req, struct io_ring_ctx *ctx) +{ + wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list); +} + +static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref) +{ + struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); + + complete(&ctx->ref_comp); +} + +static __cold void io_fallback_req_func(struct work_struct *work) +{ + struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, + fallback_work.work); + struct llist_node *node = llist_del_all(&ctx->fallback_llist); + struct io_kiocb *req, *tmp; + bool locked = false; + + percpu_ref_get(&ctx->refs); + llist_for_each_entry_safe(req, tmp, node, io_task_work.node) + req->io_task_work.func(req, &locked); + + if (locked) { + io_submit_flush_completions(ctx); + mutex_unlock(&ctx->uring_lock); + } + percpu_ref_put(&ctx->refs); +} + +static int io_alloc_hash_table(struct io_hash_table *table, unsigned bits) +{ + unsigned hash_buckets = 1U << bits; + size_t hash_size = hash_buckets * sizeof(table->hbs[0]); + + table->hbs = kmalloc(hash_size, GFP_KERNEL); + if (!table->hbs) + return -ENOMEM; + + table->hash_bits = bits; + init_hash_table(table, hash_buckets); + return 0; +} + +static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) +{ + struct io_ring_ctx *ctx; + int hash_bits; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; + + xa_init(&ctx->io_bl_xa); + + /* + * Use 5 bits less than the max cq entries, that should give us around + * 32 entries per hash list if totally full and uniformly spread, but + * don't keep too many buckets to not overconsume memory. + */ + hash_bits = ilog2(p->cq_entries) - 5; + hash_bits = clamp(hash_bits, 1, 8); + if (io_alloc_hash_table(&ctx->cancel_table, hash_bits)) + goto err; + if (io_alloc_hash_table(&ctx->cancel_table_locked, hash_bits)) + goto err; + + ctx->dummy_ubuf = kzalloc(sizeof(*ctx->dummy_ubuf), GFP_KERNEL); + if (!ctx->dummy_ubuf) + goto err; + /* set invalid range, so io_import_fixed() fails meeting it */ + ctx->dummy_ubuf->ubuf = -1UL; + + if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, + 0, GFP_KERNEL)) + goto err; + + ctx->flags = p->flags; + init_waitqueue_head(&ctx->sqo_sq_wait); + INIT_LIST_HEAD(&ctx->sqd_list); + INIT_LIST_HEAD(&ctx->cq_overflow_list); + INIT_LIST_HEAD(&ctx->io_buffers_cache); + io_alloc_cache_init(&ctx->apoll_cache); + io_alloc_cache_init(&ctx->netmsg_cache); + init_completion(&ctx->ref_comp); + xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); + mutex_init(&ctx->uring_lock); + init_waitqueue_head(&ctx->cq_wait); + spin_lock_init(&ctx->completion_lock); + spin_lock_init(&ctx->timeout_lock); + INIT_WQ_LIST(&ctx->iopoll_list); + INIT_LIST_HEAD(&ctx->io_buffers_pages); + INIT_LIST_HEAD(&ctx->io_buffers_comp); + INIT_LIST_HEAD(&ctx->defer_list); + INIT_LIST_HEAD(&ctx->timeout_list); + INIT_LIST_HEAD(&ctx->ltimeout_list); + spin_lock_init(&ctx->rsrc_ref_lock); + INIT_LIST_HEAD(&ctx->rsrc_ref_list); + INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work); + init_llist_head(&ctx->rsrc_put_llist); + INIT_LIST_HEAD(&ctx->tctx_list); + ctx->submit_state.free_list.next = NULL; + INIT_WQ_LIST(&ctx->locked_free_list); + INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); + INIT_WQ_LIST(&ctx->submit_state.compl_reqs); + return ctx; +err: + kfree(ctx->dummy_ubuf); + kfree(ctx->cancel_table.hbs); + kfree(ctx->cancel_table_locked.hbs); + kfree(ctx->io_bl); + xa_destroy(&ctx->io_bl_xa); + kfree(ctx); + return NULL; +} + +static void io_account_cq_overflow(struct io_ring_ctx *ctx) +{ + struct io_rings *r = ctx->rings; + + WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1); + ctx->cq_extra--; +} + +static bool req_need_defer(struct io_kiocb *req, u32 seq) +{ + if (unlikely(req->flags & REQ_F_IO_DRAIN)) { + struct io_ring_ctx *ctx = req->ctx; + + return seq + READ_ONCE(ctx->cq_extra) != ctx->cached_cq_tail; + } + + return false; +} + +static inline void io_req_track_inflight(struct io_kiocb *req) +{ + if (!(req->flags & REQ_F_INFLIGHT)) { + req->flags |= REQ_F_INFLIGHT; + atomic_inc(&req->task->io_uring->inflight_tracked); + } +} + +static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) +{ + if (WARN_ON_ONCE(!req->link)) + return NULL; + + req->flags &= ~REQ_F_ARM_LTIMEOUT; + req->flags |= REQ_F_LINK_TIMEOUT; + + /* linked timeouts should have two refs once prep'ed */ + io_req_set_refcount(req); + __io_req_set_refcount(req->link, 2); + return req->link; +} + +static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) +{ + if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT))) + return NULL; + return __io_prep_linked_timeout(req); +} + +static noinline void __io_arm_ltimeout(struct io_kiocb *req) +{ + io_queue_linked_timeout(__io_prep_linked_timeout(req)); +} + +static inline void io_arm_ltimeout(struct io_kiocb *req) +{ + if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT)) + __io_arm_ltimeout(req); +} + +static void io_prep_async_work(struct io_kiocb *req) +{ + const struct io_op_def *def = &io_op_defs[req->opcode]; + struct io_ring_ctx *ctx = req->ctx; + + if (!(req->flags & REQ_F_CREDS)) { + req->flags |= REQ_F_CREDS; + req->creds = get_current_cred(); + } + + req->work.list.next = NULL; + req->work.flags = 0; + req->work.cancel_seq = atomic_read(&ctx->cancel_seq); + if (req->flags & REQ_F_FORCE_ASYNC) + req->work.flags |= IO_WQ_WORK_CONCURRENT; + + if (req->file && !io_req_ffs_set(req)) + req->flags |= io_file_get_flags(req->file) << REQ_F_SUPPORT_NOWAIT_BIT; + + if (req->flags & REQ_F_ISREG) { + if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL)) + io_wq_hash_work(&req->work, file_inode(req->file)); + } else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) { + if (def->unbound_nonreg_file) + req->work.flags |= IO_WQ_WORK_UNBOUND; + } +} + +static void io_prep_async_link(struct io_kiocb *req) +{ + struct io_kiocb *cur; + + if (req->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->timeout_lock); + io_for_each_link(cur, req) + io_prep_async_work(cur); + spin_unlock_irq(&ctx->timeout_lock); + } else { + io_for_each_link(cur, req) + io_prep_async_work(cur); + } +} + +void io_queue_iowq(struct io_kiocb *req, bool *dont_use) +{ + struct io_kiocb *link = io_prep_linked_timeout(req); + struct io_uring_task *tctx = req->task->io_uring; + + BUG_ON(!tctx); + BUG_ON(!tctx->io_wq); + + /* init ->work of the whole link before punting */ + io_prep_async_link(req); + + /* + * Not expected to happen, but if we do have a bug where this _can_ + * happen, catch it here and ensure the request is marked as + * canceled. That will make io-wq go through the usual work cancel + * procedure rather than attempt to run this request (or create a new + * worker for it). + */ + if (WARN_ON_ONCE(!same_thread_group(req->task, current))) + req->work.flags |= IO_WQ_WORK_CANCEL; + + trace_io_uring_queue_async_work(req, io_wq_is_hashed(&req->work)); + io_wq_enqueue(tctx->io_wq, &req->work); + if (link) + io_queue_linked_timeout(link); +} + +static __cold void io_queue_deferred(struct io_ring_ctx *ctx) +{ + while (!list_empty(&ctx->defer_list)) { + struct io_defer_entry *de = list_first_entry(&ctx->defer_list, + struct io_defer_entry, list); + + if (req_need_defer(de->req, de->seq)) + break; + list_del_init(&de->list); + io_req_task_queue(de->req); + kfree(de); + } +} + +static void io_eventfd_signal(struct io_ring_ctx *ctx) +{ + struct io_ev_fd *ev_fd; + bool skip; + + spin_lock(&ctx->completion_lock); + /* + * Eventfd should only get triggered when at least one event has been + * posted. Some applications rely on the eventfd notification count only + * changing IFF a new CQE has been added to the CQ ring. There's no + * depedency on 1:1 relationship between how many times this function is + * called (and hence the eventfd count) and number of CQEs posted to the + * CQ ring. + */ + skip = ctx->cached_cq_tail == ctx->evfd_last_cq_tail; + ctx->evfd_last_cq_tail = ctx->cached_cq_tail; + spin_unlock(&ctx->completion_lock); + if (skip) + return; + + rcu_read_lock(); + /* + * rcu_dereference ctx->io_ev_fd once and use it for both for checking + * and eventfd_signal + */ + ev_fd = rcu_dereference(ctx->io_ev_fd); + + /* + * Check again if ev_fd exists incase an io_eventfd_unregister call + * completed between the NULL check of ctx->io_ev_fd at the start of + * the function and rcu_read_lock. + */ + if (unlikely(!ev_fd)) + goto out; + if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) + goto out; + + if (!ev_fd->eventfd_async || io_wq_current_is_worker()) + eventfd_signal(ev_fd->cq_ev_fd, 1); +out: + rcu_read_unlock(); +} + +void __io_commit_cqring_flush(struct io_ring_ctx *ctx) +{ + if (ctx->off_timeout_used || ctx->drain_active) { + spin_lock(&ctx->completion_lock); + if (ctx->off_timeout_used) + io_flush_timeouts(ctx); + if (ctx->drain_active) + io_queue_deferred(ctx); + spin_unlock(&ctx->completion_lock); + } + if (ctx->has_evfd) + io_eventfd_signal(ctx); +} + +static inline void io_cqring_ev_posted(struct io_ring_ctx *ctx) +{ + io_commit_cqring_flush(ctx); + io_cqring_wake(ctx); +} + +static inline void __io_cq_unlock_post(struct io_ring_ctx *ctx) + __releases(ctx->completion_lock) +{ + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + io_cqring_ev_posted(ctx); +} + +void io_cq_unlock_post(struct io_ring_ctx *ctx) +{ + __io_cq_unlock_post(ctx); +} + +/* Returns true if there are no backlogged entries after the flush */ +static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) +{ + bool all_flushed; + size_t cqe_size = sizeof(struct io_uring_cqe); + + if (!force && __io_cqring_events(ctx) == ctx->cq_entries) + return false; + + if (ctx->flags & IORING_SETUP_CQE32) + cqe_size <<= 1; + + io_cq_lock(ctx); + while (!list_empty(&ctx->cq_overflow_list)) { + struct io_uring_cqe *cqe = io_get_cqe(ctx); + struct io_overflow_cqe *ocqe; + + if (!cqe && !force) + break; + ocqe = list_first_entry(&ctx->cq_overflow_list, + struct io_overflow_cqe, list); + if (cqe) + memcpy(cqe, &ocqe->cqe, cqe_size); + else + io_account_cq_overflow(ctx); + + list_del(&ocqe->list); + kfree(ocqe); + } + + all_flushed = list_empty(&ctx->cq_overflow_list); + if (all_flushed) { + clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq); + atomic_andnot(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags); + } + + io_cq_unlock_post(ctx); + return all_flushed; +} + +static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx) +{ + bool ret = true; + + if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) { + /* iopoll syncs against uring_lock, not completion_lock */ + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_lock(&ctx->uring_lock); + ret = __io_cqring_overflow_flush(ctx, false); + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_unlock(&ctx->uring_lock); + } + + return ret; +} + +static void __io_put_task(struct task_struct *task, int nr) +{ + struct io_uring_task *tctx = task->io_uring; + + percpu_counter_sub(&tctx->inflight, nr); + if (unlikely(atomic_read(&tctx->in_idle))) + wake_up(&tctx->wait); + put_task_struct_many(task, nr); +} + +/* must to be called somewhat shortly after putting a request */ +static inline void io_put_task(struct task_struct *task, int nr) +{ + if (likely(task == current)) + task->io_uring->cached_refs += nr; + else + __io_put_task(task, nr); +} + +static void io_task_refs_refill(struct io_uring_task *tctx) +{ + unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR; + + percpu_counter_add(&tctx->inflight, refill); + refcount_add(refill, ¤t->usage); + tctx->cached_refs += refill; +} + +static inline void io_get_task_refs(int nr) +{ + struct io_uring_task *tctx = current->io_uring; + + tctx->cached_refs -= nr; + if (unlikely(tctx->cached_refs < 0)) + io_task_refs_refill(tctx); +} + +static __cold void io_uring_drop_tctx_refs(struct task_struct *task) +{ + struct io_uring_task *tctx = task->io_uring; + unsigned int refs = tctx->cached_refs; + + if (refs) { + tctx->cached_refs = 0; + percpu_counter_sub(&tctx->inflight, refs); + put_task_struct_many(task, refs); + } +} + +static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, + s32 res, u32 cflags, u64 extra1, u64 extra2) +{ + struct io_overflow_cqe *ocqe; + size_t ocq_size = sizeof(struct io_overflow_cqe); + bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32); + + if (is_cqe32) + ocq_size += sizeof(struct io_uring_cqe); + + ocqe = kmalloc(ocq_size, GFP_ATOMIC | __GFP_ACCOUNT); + trace_io_uring_cqe_overflow(ctx, user_data, res, cflags, ocqe); + if (!ocqe) { + /* + * If we're in ring overflow flush mode, or in task cancel mode, + * or cannot allocate an overflow entry, then we need to drop it + * on the floor. + */ + io_account_cq_overflow(ctx); + set_bit(IO_CHECK_CQ_DROPPED_BIT, &ctx->check_cq); + return false; + } + if (list_empty(&ctx->cq_overflow_list)) { + set_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq); + atomic_or(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags); + + } + ocqe->cqe.user_data = user_data; + ocqe->cqe.res = res; + ocqe->cqe.flags = cflags; + if (is_cqe32) { + ocqe->cqe.big_cqe[0] = extra1; + ocqe->cqe.big_cqe[1] = extra2; + } + list_add_tail(&ocqe->list, &ctx->cq_overflow_list); + return true; +} + +bool io_req_cqe_overflow(struct io_kiocb *req) +{ + if (!(req->flags & REQ_F_CQE32_INIT)) { + req->extra1 = 0; + req->extra2 = 0; + } + return io_cqring_event_overflow(req->ctx, req->cqe.user_data, + req->cqe.res, req->cqe.flags, + req->extra1, req->extra2); +} + +/* + * writes to the cq entry need to come after reading head; the + * control dependency is enough as we're using WRITE_ONCE to + * fill the cq entry + */ +struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = ctx->rings; + unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1); + unsigned int free, queued, len; + + + /* userspace may cheat modifying the tail, be safe and do min */ + queued = min(__io_cqring_events(ctx), ctx->cq_entries); + free = ctx->cq_entries - queued; + /* we need a contiguous range, limit based on the current array offset */ + len = min(free, ctx->cq_entries - off); + if (!len) + return NULL; + + if (ctx->flags & IORING_SETUP_CQE32) { + off <<= 1; + len <<= 1; + } + + ctx->cqe_cached = &rings->cqes[off]; + ctx->cqe_sentinel = ctx->cqe_cached + len; + + ctx->cached_cq_tail++; + ctx->cqe_cached++; + if (ctx->flags & IORING_SETUP_CQE32) + ctx->cqe_cached++; + return &rings->cqes[off]; +} + +static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, + u64 user_data, s32 res, u32 cflags, + bool allow_overflow) +{ + struct io_uring_cqe *cqe; + + ctx->cq_extra++; + + /* + * If we can't get a cq entry, userspace overflowed the + * submission (by quite a lot). Increment the overflow count in + * the ring. + */ + cqe = io_get_cqe(ctx); + if (likely(cqe)) { + trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0); + + WRITE_ONCE(cqe->user_data, user_data); + WRITE_ONCE(cqe->res, res); + WRITE_ONCE(cqe->flags, cflags); + + if (ctx->flags & IORING_SETUP_CQE32) { + WRITE_ONCE(cqe->big_cqe[0], 0); + WRITE_ONCE(cqe->big_cqe[1], 0); + } + return true; + } + + if (allow_overflow) + return io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0); + + return false; +} + +bool io_post_aux_cqe(struct io_ring_ctx *ctx, + u64 user_data, s32 res, u32 cflags, + bool allow_overflow) +{ + bool filled; + + io_cq_lock(ctx); + filled = io_fill_cqe_aux(ctx, user_data, res, cflags, allow_overflow); + io_cq_unlock_post(ctx); + return filled; +} + +static void __io_req_complete_put(struct io_kiocb *req) +{ + /* + * If we're the last reference to this request, add to our locked + * free_list cache. + */ + if (req_ref_put_and_test(req)) { + struct io_ring_ctx *ctx = req->ctx; + + if (req->flags & IO_REQ_LINK_FLAGS) { + if (req->flags & IO_DISARM_MASK) + io_disarm_next(req); + if (req->link) { + io_req_task_queue(req->link); + req->link = NULL; + } + } + io_req_put_rsrc(req); + /* + * Selected buffer deallocation in io_clean_op() assumes that + * we don't hold ->completion_lock. Clean them here to avoid + * deadlocks. + */ + io_put_kbuf_comp(req); + io_dismantle_req(req); + io_put_task(req->task, 1); + wq_list_add_head(&req->comp_list, &ctx->locked_free_list); + ctx->locked_free_nr++; + } +} + +void __io_req_complete_post(struct io_kiocb *req) +{ + if (!(req->flags & REQ_F_CQE_SKIP)) + __io_fill_cqe_req(req->ctx, req); + __io_req_complete_put(req); +} + +void io_req_complete_post(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + + io_cq_lock(ctx); + __io_req_complete_post(req); + io_cq_unlock_post(ctx); +} + +inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags) +{ + io_req_complete_post(req); +} + +void io_req_complete_failed(struct io_kiocb *req, s32 res) +{ + req_set_fail(req); + io_req_set_res(req, res, io_put_kbuf(req, IO_URING_F_UNLOCKED)); + io_req_complete_post(req); +} + +/* + * Don't initialise the fields below on every allocation, but do that in + * advance and keep them valid across allocations. + */ +static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx) +{ + req->ctx = ctx; + req->link = NULL; + req->async_data = NULL; + /* not necessary, but safer to zero */ + req->cqe.res = 0; +} + +static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, + struct io_submit_state *state) +{ + spin_lock(&ctx->completion_lock); + wq_list_splice(&ctx->locked_free_list, &state->free_list); + ctx->locked_free_nr = 0; + spin_unlock(&ctx->completion_lock); +} + +static inline bool io_req_cache_empty(struct io_ring_ctx *ctx) +{ + return !ctx->submit_state.free_list.next; +} + +/* + * A request might get retired back into the request caches even before opcode + * handlers and io_issue_sqe() are done with it, e.g. inline completion path. + * Because of that, io_alloc_req() should be called only under ->uring_lock + * and with extra caution to not get a request that is still worked on. + */ +static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; + void *reqs[IO_REQ_ALLOC_BATCH]; + int ret, i; + + /* + * If we have more than a batch's worth of requests in our IRQ side + * locked cache, grab the lock and move them over to our submission + * side cache. + */ + if (data_race(ctx->locked_free_nr) > IO_COMPL_BATCH) { + io_flush_cached_locked_reqs(ctx, &ctx->submit_state); + if (!io_req_cache_empty(ctx)) + return true; + } + + ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), reqs); + + /* + * Bulk alloc is all-or-nothing. If we fail to get a batch, + * retry single alloc to be on the safe side. + */ + if (unlikely(ret <= 0)) { + reqs[0] = kmem_cache_alloc(req_cachep, gfp); + if (!reqs[0]) + return false; + ret = 1; + } + + percpu_ref_get_many(&ctx->refs, ret); + for (i = 0; i < ret; i++) { + struct io_kiocb *req = reqs[i]; + + io_preinit_req(req, ctx); + io_req_add_to_cache(req, ctx); + } + return true; +} + +static inline bool io_alloc_req_refill(struct io_ring_ctx *ctx) +{ + if (unlikely(io_req_cache_empty(ctx))) + return __io_alloc_req_refill(ctx); + return true; +} + +static inline struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) +{ + struct io_wq_work_node *node; + + node = wq_stack_extract(&ctx->submit_state.free_list); + return container_of(node, struct io_kiocb, comp_list); +} + +static inline void io_dismantle_req(struct io_kiocb *req) +{ + unsigned int flags = req->flags; + + if (unlikely(flags & IO_REQ_CLEAN_FLAGS)) + io_clean_op(req); + if (!(flags & REQ_F_FIXED_FILE)) + io_put_file(req->file); +} + +__cold void io_free_req(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + + io_req_put_rsrc(req); + io_dismantle_req(req); + io_put_task(req->task, 1); + + spin_lock(&ctx->completion_lock); + wq_list_add_head(&req->comp_list, &ctx->locked_free_list); + ctx->locked_free_nr++; + spin_unlock(&ctx->completion_lock); +} + +static void __io_req_find_next_prep(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + + io_cq_lock(ctx); + io_disarm_next(req); + io_cq_unlock_post(ctx); +} + +static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) +{ + struct io_kiocb *nxt; + + /* + * If LINK is set, we have dependent requests in this chain. If we + * didn't fail this request, queue the first one up, moving any other + * dependencies to the next request. In case of failure, fail the rest + * of the chain. + */ + if (unlikely(req->flags & IO_DISARM_MASK)) + __io_req_find_next_prep(req); + nxt = req->link; + req->link = NULL; + return nxt; +} + +static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked) +{ + if (!ctx) + return; + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) + atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); + if (*locked) { + io_submit_flush_completions(ctx); + mutex_unlock(&ctx->uring_lock); + *locked = false; + } + percpu_ref_put(&ctx->refs); +} + +static unsigned int handle_tw_list(struct llist_node *node, + struct io_ring_ctx **ctx, bool *locked, + struct llist_node *last) +{ + unsigned int count = 0; + + while (node != last) { + struct llist_node *next = node->next; + struct io_kiocb *req = container_of(node, struct io_kiocb, + io_task_work.node); + + prefetch(container_of(next, struct io_kiocb, io_task_work.node)); + + if (req->ctx != *ctx) { + ctx_flush_and_put(*ctx, locked); + *ctx = req->ctx; + /* if not contended, grab and improve batching */ + *locked = mutex_trylock(&(*ctx)->uring_lock); + percpu_ref_get(&(*ctx)->refs); + } + req->io_task_work.func(req, locked); + node = next; + count++; + } + + return count; +} + +/** + * io_llist_xchg - swap all entries in a lock-less list + * @head: the head of lock-less list to delete all entries + * @new: new entry as the head of the list + * + * If list is empty, return NULL, otherwise, return the pointer to the first entry. + * The order of entries returned is from the newest to the oldest added one. + */ +static inline struct llist_node *io_llist_xchg(struct llist_head *head, + struct llist_node *new) +{ + return xchg(&head->first, new); +} + +/** + * io_llist_cmpxchg - possibly swap all entries in a lock-less list + * @head: the head of lock-less list to delete all entries + * @old: expected old value of the first entry of the list + * @new: new entry as the head of the list + * + * perform a cmpxchg on the first entry of the list. + */ + +static inline struct llist_node *io_llist_cmpxchg(struct llist_head *head, + struct llist_node *old, + struct llist_node *new) +{ + return cmpxchg(&head->first, old, new); +} + +void tctx_task_work(struct callback_head *cb) +{ + bool uring_locked = false; + struct io_ring_ctx *ctx = NULL; + struct io_uring_task *tctx = container_of(cb, struct io_uring_task, + task_work); + struct llist_node fake = {}; + struct llist_node *node = io_llist_xchg(&tctx->task_list, &fake); + unsigned int loops = 1; + unsigned int count = handle_tw_list(node, &ctx, &uring_locked, NULL); + + node = io_llist_cmpxchg(&tctx->task_list, &fake, NULL); + while (node != &fake) { + loops++; + node = io_llist_xchg(&tctx->task_list, &fake); + count += handle_tw_list(node, &ctx, &uring_locked, &fake); + node = io_llist_cmpxchg(&tctx->task_list, &fake, NULL); + } + + ctx_flush_and_put(ctx, &uring_locked); + + /* relaxed read is enough as only the task itself sets ->in_idle */ + if (unlikely(atomic_read(&tctx->in_idle))) + io_uring_drop_tctx_refs(current); + + trace_io_uring_task_work_run(tctx, count, loops); +} + +void io_req_task_work_add(struct io_kiocb *req) +{ + struct io_uring_task *tctx = req->task->io_uring; + struct io_ring_ctx *ctx = req->ctx; + struct llist_node *node; + bool running; + + running = !llist_add(&req->io_task_work.node, &tctx->task_list); + + /* task_work already pending, we're done */ + if (running) + return; + + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) + atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); + + if (likely(!task_work_add(req->task, &tctx->task_work, ctx->notify_method))) + return; + + node = llist_del_all(&tctx->task_list); + + while (node) { + req = container_of(node, struct io_kiocb, io_task_work.node); + node = node->next; + if (llist_add(&req->io_task_work.node, + &req->ctx->fallback_llist)) + schedule_delayed_work(&req->ctx->fallback_work, 1); + } +} + +static void io_req_tw_post(struct io_kiocb *req, bool *locked) +{ + io_req_complete_post(req); +} + +void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags) +{ + io_req_set_res(req, res, cflags); + req->io_task_work.func = io_req_tw_post; + io_req_task_work_add(req); +} + +static void io_req_task_cancel(struct io_kiocb *req, bool *locked) +{ + /* not needed for normal modes, but SQPOLL depends on it */ + io_tw_lock(req->ctx, locked); + io_req_complete_failed(req, req->cqe.res); +} + +void io_req_task_submit(struct io_kiocb *req, bool *locked) +{ + io_tw_lock(req->ctx, locked); + /* req->task == current here, checking PF_EXITING is safe */ + if (likely(!(req->task->flags & PF_EXITING))) + io_queue_sqe(req); + else + io_req_complete_failed(req, -EFAULT); +} + +void io_req_task_queue_fail(struct io_kiocb *req, int ret) +{ + io_req_set_res(req, ret, 0); + req->io_task_work.func = io_req_task_cancel; + io_req_task_work_add(req); +} + +void io_req_task_queue(struct io_kiocb *req) +{ + req->io_task_work.func = io_req_task_submit; + io_req_task_work_add(req); +} + +void io_queue_next(struct io_kiocb *req) +{ + struct io_kiocb *nxt = io_req_find_next(req); + + if (nxt) + io_req_task_queue(nxt); +} + +void io_free_batch_list(struct io_ring_ctx *ctx, struct io_wq_work_node *node) + __must_hold(&ctx->uring_lock) +{ + struct task_struct *task = NULL; + int task_refs = 0; + + do { + struct io_kiocb *req = container_of(node, struct io_kiocb, + comp_list); + + if (unlikely(req->flags & IO_REQ_CLEAN_SLOW_FLAGS)) { + if (req->flags & REQ_F_REFCOUNT) { + node = req->comp_list.next; + if (!req_ref_put_and_test(req)) + continue; + } + if ((req->flags & REQ_F_POLLED) && req->apoll) { + struct async_poll *apoll = req->apoll; + + if (apoll->double_poll) + kfree(apoll->double_poll); + if (!io_alloc_cache_put(&ctx->apoll_cache, &apoll->cache)) + kfree(apoll); + req->flags &= ~REQ_F_POLLED; + } + if (req->flags & IO_REQ_LINK_FLAGS) + io_queue_next(req); + if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS)) + io_clean_op(req); + } + if (!(req->flags & REQ_F_FIXED_FILE)) + io_put_file(req->file); + + io_req_put_rsrc_locked(req, ctx); + + if (req->task != task) { + if (task) + io_put_task(task, task_refs); + task = req->task; + task_refs = 0; + } + task_refs++; + node = req->comp_list.next; + io_req_add_to_cache(req, ctx); + } while (node); + + if (task) + io_put_task(task, task_refs); +} + +static void __io_submit_flush_completions(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + struct io_wq_work_node *node, *prev; + struct io_submit_state *state = &ctx->submit_state; + + spin_lock(&ctx->completion_lock); + wq_list_for_each(node, prev, &state->compl_reqs) { + struct io_kiocb *req = container_of(node, struct io_kiocb, + comp_list); + + if (!(req->flags & REQ_F_CQE_SKIP)) + __io_fill_cqe_req(ctx, req); + } + __io_cq_unlock_post(ctx); + + io_free_batch_list(ctx, state->compl_reqs.first); + INIT_WQ_LIST(&state->compl_reqs); +} + +/* + * Drop reference to request, return next in chain (if there is one) if this + * was the last reference to this request. + */ +static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req) +{ + struct io_kiocb *nxt = NULL; + + if (req_ref_put_and_test(req)) { + if (unlikely(req->flags & IO_REQ_LINK_FLAGS)) + nxt = io_req_find_next(req); + io_free_req(req); + } + return nxt; +} + +static unsigned io_cqring_events(struct io_ring_ctx *ctx) +{ + /* See comment at the top of this file */ + smp_rmb(); + return __io_cqring_events(ctx); +} + +/* + * We can't just wait for polled events to come to us, we have to actively + * find and complete them. + */ +static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx) +{ + if (!(ctx->flags & IORING_SETUP_IOPOLL)) + return; + + mutex_lock(&ctx->uring_lock); + while (!wq_list_empty(&ctx->iopoll_list)) { + /* let it sleep and repeat later if can't complete a request */ + if (io_do_iopoll(ctx, true) == 0) + break; + /* + * Ensure we allow local-to-the-cpu processing to take place, + * in this case we need to ensure that we reap all events. + * Also let task_work, etc. to progress by releasing the mutex + */ + if (need_resched()) { + mutex_unlock(&ctx->uring_lock); + cond_resched(); + mutex_lock(&ctx->uring_lock); + } + } + mutex_unlock(&ctx->uring_lock); +} + +static int io_iopoll_check(struct io_ring_ctx *ctx, long min) +{ + unsigned int nr_events = 0; + int ret = 0; + unsigned long check_cq; + + check_cq = READ_ONCE(ctx->check_cq); + if (unlikely(check_cq)) { + if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) + __io_cqring_overflow_flush(ctx, false); + /* + * Similarly do not spin if we have not informed the user of any + * dropped CQE. + */ + if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)) + return -EBADR; + } + /* + * Don't enter poll loop if we already have events pending. + * If we do, we can potentially be spinning for commands that + * already triggered a CQE (eg in error). + */ + if (io_cqring_events(ctx)) + return 0; + + do { + /* + * If a submit got punted to a workqueue, we can have the + * application entering polling for a command before it gets + * issued. That app will hold the uring_lock for the duration + * of the poll right here, so we need to take a breather every + * now and then to ensure that the issue has a chance to add + * the poll to the issued list. Otherwise we can spin here + * forever, while the workqueue is stuck trying to acquire the + * very same mutex. + */ + if (wq_list_empty(&ctx->iopoll_list)) { + u32 tail = ctx->cached_cq_tail; + + mutex_unlock(&ctx->uring_lock); + io_run_task_work(); + mutex_lock(&ctx->uring_lock); + + /* some requests don't go through iopoll_list */ + if (tail != ctx->cached_cq_tail || + wq_list_empty(&ctx->iopoll_list)) + break; + } + ret = io_do_iopoll(ctx, !min); + if (ret < 0) + break; + nr_events += ret; + ret = 0; + } while (nr_events < min && !need_resched()); + + return ret; +} + +void io_req_task_complete(struct io_kiocb *req, bool *locked) +{ + if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) { + unsigned issue_flags = *locked ? 0 : IO_URING_F_UNLOCKED; + + req->cqe.flags |= io_put_kbuf(req, issue_flags); + } + + if (*locked) + io_req_complete_defer(req); + else + io_req_complete_post(req); +} + +/* + * After the iocb has been issued, it's safe to be found on the poll list. + * Adding the kiocb to the list AFTER submission ensures that we don't + * find it from a io_do_iopoll() thread before the issuer is done + * accessing the kiocb cookie. + */ +static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + const bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; + + /* workqueue context doesn't hold uring_lock, grab it now */ + if (unlikely(needs_lock)) + mutex_lock(&ctx->uring_lock); + + /* + * Track whether we have multiple files in our lists. This will impact + * how we do polling eventually, not spinning if we're on potentially + * different devices. + */ + if (wq_list_empty(&ctx->iopoll_list)) { + ctx->poll_multi_queue = false; + } else if (!ctx->poll_multi_queue) { + struct io_kiocb *list_req; + + list_req = container_of(ctx->iopoll_list.first, struct io_kiocb, + comp_list); + if (list_req->file != req->file) + ctx->poll_multi_queue = true; + } + + /* + * For fast devices, IO may have already completed. If it has, add + * it to the front so we find it first. + */ + if (READ_ONCE(req->iopoll_completed)) + wq_list_add_head(&req->comp_list, &ctx->iopoll_list); + else + wq_list_add_tail(&req->comp_list, &ctx->iopoll_list); + + if (unlikely(needs_lock)) { + /* + * If IORING_SETUP_SQPOLL is enabled, sqes are either handle + * in sq thread task context or in io worker task context. If + * current task context is sq thread, we don't need to check + * whether should wake up sq thread. + */ + if ((ctx->flags & IORING_SETUP_SQPOLL) && + wq_has_sleeper(&ctx->sq_data->wait)) + wake_up(&ctx->sq_data->wait); + + mutex_unlock(&ctx->uring_lock); + } +} + +static bool io_bdev_nowait(struct block_device *bdev) +{ + return !bdev || blk_queue_nowait(bdev_get_queue(bdev)); +} + +/* + * If we tracked the file through the SCM inflight mechanism, we could support + * any file. For now, just ensure that anything potentially problematic is done + * inline. + */ +static bool __io_file_supports_nowait(struct file *file, umode_t mode) +{ + if (S_ISBLK(mode)) { + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(I_BDEV(file->f_mapping->host))) + return true; + return false; + } + if (S_ISSOCK(mode)) + return true; + if (S_ISREG(mode)) { + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(file->f_inode->i_sb->s_bdev) && + !io_is_uring_fops(file)) + return true; + return false; + } + + /* any ->read/write should understand O_NONBLOCK */ + if (file->f_flags & O_NONBLOCK) + return true; + return file->f_mode & FMODE_NOWAIT; +} + +/* + * If we tracked the file through the SCM inflight mechanism, we could support + * any file. For now, just ensure that anything potentially problematic is done + * inline. + */ +unsigned int io_file_get_flags(struct file *file) +{ + umode_t mode = file_inode(file)->i_mode; + unsigned int res = 0; + + if (S_ISREG(mode)) + res |= FFS_ISREG; + if (__io_file_supports_nowait(file, mode)) + res |= FFS_NOWAIT; + if (io_file_need_scm(file)) + res |= FFS_SCM; + return res; +} + +bool io_alloc_async_data(struct io_kiocb *req) +{ + WARN_ON_ONCE(!io_op_defs[req->opcode].async_size); + req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL); + if (req->async_data) { + req->flags |= REQ_F_ASYNC_DATA; + return false; + } + return true; +} + +int io_req_prep_async(struct io_kiocb *req) +{ + const struct io_op_def *def = &io_op_defs[req->opcode]; + + /* assign early for deferred execution for non-fixed file */ + if (def->needs_file && !(req->flags & REQ_F_FIXED_FILE)) + req->file = io_file_get_normal(req, req->cqe.fd); + if (!def->prep_async) + return 0; + if (WARN_ON_ONCE(req_has_async_data(req))) + return -EFAULT; + if (io_alloc_async_data(req)) + return -EAGAIN; + + return def->prep_async(req); +} + +static u32 io_get_sequence(struct io_kiocb *req) +{ + u32 seq = req->ctx->cached_sq_head; + struct io_kiocb *cur; + + /* need original cached_sq_head, but it was increased for each req */ + io_for_each_link(cur, req) + seq--; + return seq; +} + +static __cold void io_drain_req(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_defer_entry *de; + int ret; + u32 seq = io_get_sequence(req); + + /* Still need defer if there is pending req in defer list. */ + spin_lock(&ctx->completion_lock); + if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) { + spin_unlock(&ctx->completion_lock); +queue: + ctx->drain_active = false; + io_req_task_queue(req); + return; + } + spin_unlock(&ctx->completion_lock); + + ret = io_req_prep_async(req); + if (ret) { +fail: + io_req_complete_failed(req, ret); + return; + } + io_prep_async_link(req); + de = kmalloc(sizeof(*de), GFP_KERNEL); + if (!de) { + ret = -ENOMEM; + goto fail; + } + + spin_lock(&ctx->completion_lock); + if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) { + spin_unlock(&ctx->completion_lock); + kfree(de); + goto queue; + } + + trace_io_uring_defer(req); + de->req = req; + de->seq = seq; + list_add_tail(&de->list, &ctx->defer_list); + spin_unlock(&ctx->completion_lock); +} + +static void io_clean_op(struct io_kiocb *req) +{ + if (req->flags & REQ_F_BUFFER_SELECTED) { + spin_lock(&req->ctx->completion_lock); + io_put_kbuf_comp(req); + spin_unlock(&req->ctx->completion_lock); + } + + if (req->flags & REQ_F_NEED_CLEANUP) { + const struct io_op_def *def = &io_op_defs[req->opcode]; + + if (def->cleanup) + def->cleanup(req); + } + if ((req->flags & REQ_F_POLLED) && req->apoll) { + kfree(req->apoll->double_poll); + kfree(req->apoll); + req->apoll = NULL; + } + if (req->flags & REQ_F_INFLIGHT) { + struct io_uring_task *tctx = req->task->io_uring; + + atomic_dec(&tctx->inflight_tracked); + } + if (req->flags & REQ_F_CREDS) + put_cred(req->creds); + if (req->flags & REQ_F_ASYNC_DATA) { + kfree(req->async_data); + req->async_data = NULL; + } + req->flags &= ~IO_REQ_CLEAN_FLAGS; +} + +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags) +{ + if (req->file || !io_op_defs[req->opcode].needs_file) + return true; + + if (req->flags & REQ_F_FIXED_FILE) + req->file = io_file_get_fixed(req, req->cqe.fd, issue_flags); + else + req->file = io_file_get_normal(req, req->cqe.fd); + + return !!req->file; +} + +static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) +{ + const struct io_op_def *def = &io_op_defs[req->opcode]; + const struct cred *creds = NULL; + int ret; + + if (unlikely(!io_assign_file(req, issue_flags))) + return -EBADF; + + if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred())) + creds = override_creds(req->creds); + + if (!def->audit_skip) + audit_uring_entry(req->opcode); + + ret = def->issue(req, issue_flags); + + if (!def->audit_skip) + audit_uring_exit(!ret, ret); + + if (creds) + revert_creds(creds); + + if (ret == IOU_OK) { + if (issue_flags & IO_URING_F_COMPLETE_DEFER) + io_req_complete_defer(req); + else + io_req_complete_post(req); + } else if (ret != IOU_ISSUE_SKIP_COMPLETE) + return ret; + + /* If the op doesn't have a file, we're not polling for it */ + if ((req->ctx->flags & IORING_SETUP_IOPOLL) && req->file) + io_iopoll_req_issued(req, issue_flags); + + return 0; +} + +int io_poll_issue(struct io_kiocb *req, bool *locked) +{ + io_tw_lock(req->ctx, locked); + if (unlikely(req->task->flags & PF_EXITING)) + return -EFAULT; + return io_issue_sqe(req, IO_URING_F_NONBLOCK); +} + +struct io_wq_work *io_wq_free_work(struct io_wq_work *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + req = io_put_req_find_next(req); + return req ? &req->work : NULL; +} + +void io_wq_submit_work(struct io_wq_work *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + const struct io_op_def *def = &io_op_defs[req->opcode]; + unsigned int issue_flags = IO_URING_F_UNLOCKED; + bool needs_poll = false; + int ret = 0, err = -ECANCELED; + + /* one will be dropped by ->io_free_work() after returning to io-wq */ + if (!(req->flags & REQ_F_REFCOUNT)) + __io_req_set_refcount(req, 2); + else + req_ref_get(req); + + io_arm_ltimeout(req); + + /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ + if (work->flags & IO_WQ_WORK_CANCEL) { +fail: + io_req_task_queue_fail(req, err); + return; + } + if (!io_assign_file(req, issue_flags)) { + err = -EBADF; + work->flags |= IO_WQ_WORK_CANCEL; + goto fail; + } + + if (req->flags & REQ_F_FORCE_ASYNC) { + bool opcode_poll = def->pollin || def->pollout; + + if (opcode_poll && file_can_poll(req->file)) { + needs_poll = true; + issue_flags |= IO_URING_F_NONBLOCK; + } + } + + do { + ret = io_issue_sqe(req, issue_flags); + if (ret != -EAGAIN) + break; + /* + * We can get EAGAIN for iopolled IO even though we're + * forcing a sync submission from here, since we can't + * wait for request slots on the block side. + */ + if (!needs_poll) { + if (!(req->ctx->flags & IORING_SETUP_IOPOLL)) + break; + cond_resched(); + continue; + } + + if (io_arm_poll_handler(req, issue_flags) == IO_APOLL_OK) + return; + /* aborted or ready, in either case retry blocking */ + needs_poll = false; + issue_flags &= ~IO_URING_F_NONBLOCK; + } while (1); + + /* avoid locking problems by failing it from a clean context */ + if (ret < 0) + io_req_task_queue_fail(req, ret); +} + +inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct file *file = NULL; + unsigned long file_ptr; + + io_ring_submit_lock(ctx, issue_flags); + + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) + goto out; + fd = array_index_nospec(fd, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; + file = (struct file *) (file_ptr & FFS_MASK); + file_ptr &= ~FFS_MASK; + /* mask in overlapping REQ_F and FFS bits */ + req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT); + io_req_set_rsrc_node(req, ctx, 0); + WARN_ON_ONCE(file && !test_bit(fd, ctx->file_table.bitmap)); +out: + io_ring_submit_unlock(ctx, issue_flags); + return file; +} + +struct file *io_file_get_normal(struct io_kiocb *req, int fd) +{ + struct file *file = fget(fd); + + trace_io_uring_file_get(req, fd); + + /* we don't allow fixed io_uring files */ + if (file && io_is_uring_fops(file)) + io_req_track_inflight(req); + return file; +} + +static void io_queue_async(struct io_kiocb *req, int ret) + __must_hold(&req->ctx->uring_lock) +{ + struct io_kiocb *linked_timeout; + + if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) { + io_req_complete_failed(req, ret); + return; + } + + linked_timeout = io_prep_linked_timeout(req); + + switch (io_arm_poll_handler(req, 0)) { + case IO_APOLL_READY: + io_req_task_queue(req); + break; + case IO_APOLL_ABORTED: + /* + * Queued up for async execution, worker will release + * submit reference when the iocb is actually submitted. + */ + io_kbuf_recycle(req, 0); + io_queue_iowq(req, NULL); + break; + case IO_APOLL_OK: + break; + } + + if (linked_timeout) + io_queue_linked_timeout(linked_timeout); +} + +static inline void io_queue_sqe(struct io_kiocb *req) + __must_hold(&req->ctx->uring_lock) +{ + int ret; + + ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); + + /* + * We async punt it if the file wasn't marked NOWAIT, or if the file + * doesn't support non-blocking read/write attempts + */ + if (likely(!ret)) + io_arm_ltimeout(req); + else + io_queue_async(req, ret); +} + +static void io_queue_sqe_fallback(struct io_kiocb *req) + __must_hold(&req->ctx->uring_lock) +{ + if (unlikely(req->flags & REQ_F_FAIL)) { + /* + * We don't submit, fail them all, for that replace hardlinks + * with normal links. Extra REQ_F_LINK is tolerated. + */ + req->flags &= ~REQ_F_HARDLINK; + req->flags |= REQ_F_LINK; + io_req_complete_failed(req, req->cqe.res); + } else if (unlikely(req->ctx->drain_active)) { + io_drain_req(req); + } else { + int ret = io_req_prep_async(req); + + if (unlikely(ret)) + io_req_complete_failed(req, ret); + else + io_queue_iowq(req, NULL); + } +} + +/* + * Check SQE restrictions (opcode and flags). + * + * Returns 'true' if SQE is allowed, 'false' otherwise. + */ +static inline bool io_check_restriction(struct io_ring_ctx *ctx, + struct io_kiocb *req, + unsigned int sqe_flags) +{ + if (!test_bit(req->opcode, ctx->restrictions.sqe_op)) + return false; + + if ((sqe_flags & ctx->restrictions.sqe_flags_required) != + ctx->restrictions.sqe_flags_required) + return false; + + if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed | + ctx->restrictions.sqe_flags_required)) + return false; + + return true; +} + +static void io_init_req_drain(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *head = ctx->submit_state.link.head; + + ctx->drain_active = true; + if (head) { + /* + * If we need to drain a request in the middle of a link, drain + * the head request and the next request/link after the current + * link. Considering sequential execution of links, + * REQ_F_IO_DRAIN will be maintained for every request of our + * link. + */ + head->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC; + ctx->drain_next = true; + } +} + +static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe *sqe) + __must_hold(&ctx->uring_lock) +{ + const struct io_op_def *def; + unsigned int sqe_flags; + int personality; + u8 opcode; + + /* req is partially pre-initialised, see io_preinit_req() */ + req->opcode = opcode = READ_ONCE(sqe->opcode); + /* same numerical values with corresponding REQ_F_*, safe to copy */ + req->flags = sqe_flags = READ_ONCE(sqe->flags); + req->cqe.user_data = READ_ONCE(sqe->user_data); + req->file = NULL; + req->rsrc_node = NULL; + req->task = current; + + if (unlikely(opcode >= IORING_OP_LAST)) { + req->opcode = 0; + return -EINVAL; + } + def = &io_op_defs[opcode]; + if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) { + /* enforce forwards compatibility on users */ + if (sqe_flags & ~SQE_VALID_FLAGS) + return -EINVAL; + if (sqe_flags & IOSQE_BUFFER_SELECT) { + if (!def->buffer_select) + return -EOPNOTSUPP; + req->buf_index = READ_ONCE(sqe->buf_group); + } + if (sqe_flags & IOSQE_CQE_SKIP_SUCCESS) + ctx->drain_disabled = true; + if (sqe_flags & IOSQE_IO_DRAIN) { + if (ctx->drain_disabled) + return -EOPNOTSUPP; + io_init_req_drain(req); + } + } + if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) { + if (ctx->restricted && !io_check_restriction(ctx, req, sqe_flags)) + return -EACCES; + /* knock it to the slow queue path, will be drained there */ + if (ctx->drain_active) + req->flags |= REQ_F_FORCE_ASYNC; + /* if there is no link, we're at "next" request and need to drain */ + if (unlikely(ctx->drain_next) && !ctx->submit_state.link.head) { + ctx->drain_next = false; + ctx->drain_active = true; + req->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC; + } + } + + if (!def->ioprio && sqe->ioprio) + return -EINVAL; + if (!def->iopoll && (ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + + if (def->needs_file) { + struct io_submit_state *state = &ctx->submit_state; + + req->cqe.fd = READ_ONCE(sqe->fd); + + /* + * Plug now if we have more than 2 IO left after this, and the + * target is potentially a read/write to block based storage. + */ + if (state->need_plug && def->plug) { + state->plug_started = true; + state->need_plug = false; + blk_start_plug_nr_ios(&state->plug, state->submit_nr); + } + } + + personality = READ_ONCE(sqe->personality); + if (personality) { + int ret; + + req->creds = xa_load(&ctx->personalities, personality); + if (!req->creds) + return -EINVAL; + get_cred(req->creds); + ret = security_uring_override_creds(req->creds); + if (ret) { + put_cred(req->creds); + return ret; + } + req->flags |= REQ_F_CREDS; + } + + return def->prep(req, sqe); +} + +static __cold int io_submit_fail_init(const struct io_uring_sqe *sqe, + struct io_kiocb *req, int ret) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_submit_link *link = &ctx->submit_state.link; + struct io_kiocb *head = link->head; + + trace_io_uring_req_failed(sqe, req, ret); + + /* + * Avoid breaking links in the middle as it renders links with SQPOLL + * unusable. Instead of failing eagerly, continue assembling the link if + * applicable and mark the head with REQ_F_FAIL. The link flushing code + * should find the flag and handle the rest. + */ + req_fail_link_node(req, ret); + if (head && !(head->flags & REQ_F_FAIL)) + req_fail_link_node(head, -ECANCELED); + + if (!(req->flags & IO_REQ_LINK_FLAGS)) { + if (head) { + link->last->link = req; + link->head = NULL; + req = head; + } + io_queue_sqe_fallback(req); + return ret; + } + + if (head) + link->last->link = req; + else + link->head = req; + link->last = req; + return 0; +} + +static inline int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe *sqe) + __must_hold(&ctx->uring_lock) +{ + struct io_submit_link *link = &ctx->submit_state.link; + int ret; + + ret = io_init_req(ctx, req, sqe); + if (unlikely(ret)) + return io_submit_fail_init(sqe, req, ret); + + /* don't need @sqe from now on */ + trace_io_uring_submit_sqe(req, true); + + /* + * If we already have a head request, queue this one for async + * submittal once the head completes. If we don't have a head but + * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be + * submitted sync once the chain is complete. If none of those + * conditions are true (normal request), then just queue it. + */ + if (unlikely(link->head)) { + ret = io_req_prep_async(req); + if (unlikely(ret)) + return io_submit_fail_init(sqe, req, ret); + + trace_io_uring_link(req, link->head); + link->last->link = req; + link->last = req; + + if (req->flags & IO_REQ_LINK_FLAGS) + return 0; + /* last request of the link, flush it */ + req = link->head; + link->head = NULL; + if (req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)) + goto fallback; + + } else if (unlikely(req->flags & (IO_REQ_LINK_FLAGS | + REQ_F_FORCE_ASYNC | REQ_F_FAIL))) { + if (req->flags & IO_REQ_LINK_FLAGS) { + link->head = req; + link->last = req; + } else { +fallback: + io_queue_sqe_fallback(req); + } + return 0; + } + + io_queue_sqe(req); + return 0; +} + +/* + * Batched submission is done, ensure local IO is flushed out. + */ +static void io_submit_state_end(struct io_ring_ctx *ctx) +{ + struct io_submit_state *state = &ctx->submit_state; + + if (unlikely(state->link.head)) + io_queue_sqe_fallback(state->link.head); + /* flush only after queuing links as they can generate completions */ + io_submit_flush_completions(ctx); + if (state->plug_started) + blk_finish_plug(&state->plug); +} + +/* + * Start submission side cache. + */ +static void io_submit_state_start(struct io_submit_state *state, + unsigned int max_ios) +{ + state->plug_started = false; + state->need_plug = max_ios > 2; + state->submit_nr = max_ios; + /* set only head, no need to init link_last in advance */ + state->link.head = NULL; +} + +static void io_commit_sqring(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = ctx->rings; + + /* + * Ensure any loads from the SQEs are done at this point, + * since once we write the new head, the application could + * write new data to them. + */ + smp_store_release(&rings->sq.head, ctx->cached_sq_head); +} + +/* + * Fetch an sqe, if one is available. Note this returns a pointer to memory + * that is mapped by userspace. This means that care needs to be taken to + * ensure that reads are stable, as we cannot rely on userspace always + * being a good citizen. If members of the sqe are validated and then later + * used, it's important that those reads are done through READ_ONCE() to + * prevent a re-load down the line. + */ +static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) +{ + unsigned head, mask = ctx->sq_entries - 1; + unsigned sq_idx = ctx->cached_sq_head++ & mask; + + /* + * The cached sq head (or cq tail) serves two purposes: + * + * 1) allows us to batch the cost of updating the user visible + * head updates. + * 2) allows the kernel side to track the head on its own, even + * though the application is the one updating it. + */ + head = READ_ONCE(ctx->sq_array[sq_idx]); + if (likely(head < ctx->sq_entries)) { + /* double index for 128-byte SQEs, twice as long */ + if (ctx->flags & IORING_SETUP_SQE128) + head <<= 1; + return &ctx->sq_sqes[head]; + } + + /* drop invalid entries */ + ctx->cq_extra--; + WRITE_ONCE(ctx->rings->sq_dropped, + READ_ONCE(ctx->rings->sq_dropped) + 1); + return NULL; +} + +int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) + __must_hold(&ctx->uring_lock) +{ + unsigned int entries = io_sqring_entries(ctx); + unsigned int left; + int ret; + + if (unlikely(!entries)) + return 0; + /* make sure SQ entry isn't read before tail */ + ret = left = min3(nr, ctx->sq_entries, entries); + io_get_task_refs(left); + io_submit_state_start(&ctx->submit_state, left); + + do { + const struct io_uring_sqe *sqe; + struct io_kiocb *req; + + if (unlikely(!io_alloc_req_refill(ctx))) + break; + req = io_alloc_req(ctx); + sqe = io_get_sqe(ctx); + if (unlikely(!sqe)) { + io_req_add_to_cache(req, ctx); + break; + } + + /* + * Continue submitting even for sqe failure if the + * ring was setup with IORING_SETUP_SUBMIT_ALL + */ + if (unlikely(io_submit_sqe(ctx, req, sqe)) && + !(ctx->flags & IORING_SETUP_SUBMIT_ALL)) { + left--; + break; + } + } while (--left); + + if (unlikely(left)) { + ret -= left; + /* try again if it submitted nothing and can't allocate a req */ + if (!ret && io_req_cache_empty(ctx)) + ret = -EAGAIN; + current->io_uring->cached_refs += left; + } + + io_submit_state_end(ctx); + /* Commit SQ ring head once we've consumed and submitted all SQEs */ + io_commit_sqring(ctx); + return ret; +} + +struct io_wait_queue { + struct wait_queue_entry wq; + struct io_ring_ctx *ctx; + unsigned cq_tail; + unsigned nr_timeouts; +}; + +static inline bool io_should_wake(struct io_wait_queue *iowq) +{ + struct io_ring_ctx *ctx = iowq->ctx; + int dist = ctx->cached_cq_tail - (int) iowq->cq_tail; + + /* + * Wake up if we have enough events, or if a timeout occurred since we + * started waiting. For timeouts, we always want to return to userspace, + * regardless of event count. + */ + return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; +} + +static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, + int wake_flags, void *key) +{ + struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue, + wq); + + /* + * Cannot safely flush overflowed CQEs from here, ensure we wake up + * the task, and the next invocation will do it. + */ + if (io_should_wake(iowq) || + test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &iowq->ctx->check_cq)) + return autoremove_wake_function(curr, mode, wake_flags, key); + return -1; +} + +int io_run_task_work_sig(void) +{ + if (io_run_task_work()) + return 1; + if (task_sigpending(current)) + return -EINTR; + return 0; +} + +/* when returns >0, the caller should retry */ +static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, + struct io_wait_queue *iowq, + ktime_t timeout) +{ + int ret; + unsigned long check_cq; + + /* make sure we run task_work before checking for signals */ + ret = io_run_task_work_sig(); + if (ret || io_should_wake(iowq)) + return ret; + + check_cq = READ_ONCE(ctx->check_cq); + if (unlikely(check_cq)) { + /* let the caller flush overflows, retry */ + if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) + return 1; + if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)) + return -EBADR; + } + if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS)) + return -ETIME; + return 1; +} + +/* + * Wait until events become available, if we don't already have some. The + * application must reap them itself, as they reside on the shared cq ring. + */ +static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, + const sigset_t __user *sig, size_t sigsz, + struct __kernel_timespec __user *uts) +{ + struct io_wait_queue iowq; + struct io_rings *rings = ctx->rings; + ktime_t timeout = KTIME_MAX; + int ret; + + do { + io_cqring_overflow_flush(ctx); + if (io_cqring_events(ctx) >= min_events) + return 0; + if (!io_run_task_work()) + break; + } while (1); + + if (sig) { +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig, + sigsz); + else +#endif + ret = set_user_sigmask(sig, sigsz); + + if (ret) + return ret; + } + + if (uts) { + struct timespec64 ts; + + if (get_timespec64(&ts, uts)) + return -EFAULT; + timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); + } + + init_waitqueue_func_entry(&iowq.wq, io_wake_function); + iowq.wq.private = current; + INIT_LIST_HEAD(&iowq.wq.entry); + iowq.ctx = ctx; + iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); + iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; + + trace_io_uring_cqring_wait(ctx, min_events); + do { + /* if we can't even flush overflow, don't wait for more */ + if (!io_cqring_overflow_flush(ctx)) { + ret = -EBUSY; + break; + } + prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, + TASK_INTERRUPTIBLE); + ret = io_cqring_wait_schedule(ctx, &iowq, timeout); + cond_resched(); + } while (ret > 0); + + finish_wait(&ctx->cq_wait, &iowq.wq); + restore_saved_sigmask_unless(ret == -EINTR); + + return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; +} + +static void io_mem_free(void *ptr) +{ + struct page *page; + + if (!ptr) + return; + + page = virt_to_head_page(ptr); + if (put_page_testzero(page)) + free_compound_page(page); +} + +static void *io_mem_alloc(size_t size) +{ + gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP; + + return (void *) __get_free_pages(gfp, get_order(size)); +} + +static unsigned long rings_size(struct io_ring_ctx *ctx, unsigned int sq_entries, + unsigned int cq_entries, size_t *sq_offset) +{ + struct io_rings *rings; + size_t off, sq_array_size; + + off = struct_size(rings, cqes, cq_entries); + if (off == SIZE_MAX) + return SIZE_MAX; + if (ctx->flags & IORING_SETUP_CQE32) { + if (check_shl_overflow(off, 1, &off)) + return SIZE_MAX; + } + +#ifdef CONFIG_SMP + off = ALIGN(off, SMP_CACHE_BYTES); + if (off == 0) + return SIZE_MAX; +#endif + + if (sq_offset) + *sq_offset = off; + + sq_array_size = array_size(sizeof(u32), sq_entries); + if (sq_array_size == SIZE_MAX) + return SIZE_MAX; + + if (check_add_overflow(off, sq_array_size, &off)) + return SIZE_MAX; + + return off; +} + +static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned int eventfd_async) +{ + struct io_ev_fd *ev_fd; + __s32 __user *fds = arg; + int fd; + + ev_fd = rcu_dereference_protected(ctx->io_ev_fd, + lockdep_is_held(&ctx->uring_lock)); + if (ev_fd) + return -EBUSY; + + if (copy_from_user(&fd, fds, sizeof(*fds))) + return -EFAULT; + + ev_fd = kmalloc(sizeof(*ev_fd), GFP_KERNEL); + if (!ev_fd) + return -ENOMEM; + + ev_fd->cq_ev_fd = eventfd_ctx_fdget(fd); + if (IS_ERR(ev_fd->cq_ev_fd)) { + int ret = PTR_ERR(ev_fd->cq_ev_fd); + kfree(ev_fd); + return ret; + } + + spin_lock(&ctx->completion_lock); + ctx->evfd_last_cq_tail = ctx->cached_cq_tail; + spin_unlock(&ctx->completion_lock); + + ev_fd->eventfd_async = eventfd_async; + ctx->has_evfd = true; + rcu_assign_pointer(ctx->io_ev_fd, ev_fd); + return 0; +} + +static void io_eventfd_put(struct rcu_head *rcu) +{ + struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); + + eventfd_ctx_put(ev_fd->cq_ev_fd); + kfree(ev_fd); +} + +static int io_eventfd_unregister(struct io_ring_ctx *ctx) +{ + struct io_ev_fd *ev_fd; + + ev_fd = rcu_dereference_protected(ctx->io_ev_fd, + lockdep_is_held(&ctx->uring_lock)); + if (ev_fd) { + ctx->has_evfd = false; + rcu_assign_pointer(ctx->io_ev_fd, NULL); + call_rcu(&ev_fd->rcu, io_eventfd_put); + return 0; + } + + return -ENXIO; +} + +static void io_req_caches_free(struct io_ring_ctx *ctx) +{ + struct io_submit_state *state = &ctx->submit_state; + int nr = 0; + + mutex_lock(&ctx->uring_lock); + io_flush_cached_locked_reqs(ctx, state); + + while (!io_req_cache_empty(ctx)) { + struct io_wq_work_node *node; + struct io_kiocb *req; + + node = wq_stack_extract(&state->free_list); + req = container_of(node, struct io_kiocb, comp_list); + kmem_cache_free(req_cachep, req); + nr++; + } + if (nr) + percpu_ref_put_many(&ctx->refs, nr); + mutex_unlock(&ctx->uring_lock); +} + +static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) +{ + io_sq_thread_finish(ctx); + + if (ctx->mm_account) { + mmdrop(ctx->mm_account); + ctx->mm_account = NULL; + } + + io_rsrc_refs_drop(ctx); + /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ + io_wait_rsrc_data(ctx->buf_data); + io_wait_rsrc_data(ctx->file_data); + + mutex_lock(&ctx->uring_lock); + if (ctx->buf_data) + __io_sqe_buffers_unregister(ctx); + if (ctx->file_data) + __io_sqe_files_unregister(ctx); + if (ctx->rings) + __io_cqring_overflow_flush(ctx, true); + io_eventfd_unregister(ctx); + io_alloc_cache_free(&ctx->apoll_cache, io_apoll_cache_free); + io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); + mutex_unlock(&ctx->uring_lock); + io_destroy_buffers(ctx); + if (ctx->sq_creds) + put_cred(ctx->sq_creds); + if (ctx->submitter_task) + put_task_struct(ctx->submitter_task); + + /* there are no registered resources left, nobody uses it */ + if (ctx->rsrc_node) + io_rsrc_node_destroy(ctx->rsrc_node); + if (ctx->rsrc_backup_node) + io_rsrc_node_destroy(ctx->rsrc_backup_node); + flush_delayed_work(&ctx->rsrc_put_work); + flush_delayed_work(&ctx->fallback_work); + + WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)); + WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist)); + +#if defined(CONFIG_UNIX) + if (ctx->ring_sock) { + ctx->ring_sock->file = NULL; /* so that iput() is called */ + sock_release(ctx->ring_sock); + } +#endif + WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); + + io_mem_free(ctx->rings); + io_mem_free(ctx->sq_sqes); + + percpu_ref_exit(&ctx->refs); + free_uid(ctx->user); + io_req_caches_free(ctx); + if (ctx->hash_map) + io_wq_put_hash(ctx->hash_map); + kfree(ctx->cancel_table.hbs); + kfree(ctx->cancel_table_locked.hbs); + kfree(ctx->dummy_ubuf); + kfree(ctx->io_bl); + xa_destroy(&ctx->io_bl_xa); + kfree(ctx); +} + +static __poll_t io_uring_poll(struct file *file, poll_table *wait) +{ + struct io_ring_ctx *ctx = file->private_data; + __poll_t mask = 0; + + poll_wait(file, &ctx->cq_wait, wait); + /* + * synchronizes with barrier from wq_has_sleeper call in + * io_commit_cqring + */ + smp_rmb(); + if (!io_sqring_full(ctx)) + mask |= EPOLLOUT | EPOLLWRNORM; + + /* + * Don't flush cqring overflow list here, just do a simple check. + * Otherwise there could possible be ABBA deadlock: + * CPU0 CPU1 + * ---- ---- + * lock(&ctx->uring_lock); + * lock(&ep->mtx); + * lock(&ctx->uring_lock); + * lock(&ep->mtx); + * + * Users may get EPOLLIN meanwhile seeing nothing in cqring, this + * pushs them to do the flush. + */ + if (io_cqring_events(ctx) || + test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) + mask |= EPOLLIN | EPOLLRDNORM; + + return mask; +} + +static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) +{ + const struct cred *creds; + + creds = xa_erase(&ctx->personalities, id); + if (creds) { + put_cred(creds); + return 0; + } + + return -EINVAL; +} + +struct io_tctx_exit { + struct callback_head task_work; + struct completion completion; + struct io_ring_ctx *ctx; +}; + +static __cold void io_tctx_exit_cb(struct callback_head *cb) +{ + struct io_uring_task *tctx = current->io_uring; + struct io_tctx_exit *work; + + work = container_of(cb, struct io_tctx_exit, task_work); + /* + * When @in_idle, we're in cancellation and it's racy to remove the + * node. It'll be removed by the end of cancellation, just ignore it. + */ + if (!atomic_read(&tctx->in_idle)) + io_uring_del_tctx_node((unsigned long)work->ctx); + complete(&work->completion); +} + +static __cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + return req->ctx == data; +} + +static __cold void io_ring_exit_work(struct work_struct *work) +{ + struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work); + unsigned long timeout = jiffies + HZ * 60 * 5; + unsigned long interval = HZ / 20; + struct io_tctx_exit exit; + struct io_tctx_node *node; + int ret; + + /* + * If we're doing polled IO and end up having requests being + * submitted async (out-of-line), then completions can come in while + * we're waiting for refs to drop. We need to reap these manually, + * as nobody else will be looking for them. + */ + do { + while (io_uring_try_cancel_requests(ctx, NULL, true)) + cond_resched(); + + if (ctx->sq_data) { + struct io_sq_data *sqd = ctx->sq_data; + struct task_struct *tsk; + + io_sq_thread_park(sqd); + tsk = sqd->thread; + if (tsk && tsk->io_uring && tsk->io_uring->io_wq) + io_wq_cancel_cb(tsk->io_uring->io_wq, + io_cancel_ctx_cb, ctx, true); + io_sq_thread_unpark(sqd); + } + + io_req_caches_free(ctx); + + if (WARN_ON_ONCE(time_after(jiffies, timeout))) { + /* there is little hope left, don't run it too often */ + interval = HZ * 60; + } + } while (!wait_for_completion_timeout(&ctx->ref_comp, interval)); + + init_completion(&exit.completion); + init_task_work(&exit.task_work, io_tctx_exit_cb); + exit.ctx = ctx; + /* + * Some may use context even when all refs and requests have been put, + * and they are free to do so while still holding uring_lock or + * completion_lock, see io_req_task_submit(). Apart from other work, + * this lock/unlock section also waits them to finish. + */ + mutex_lock(&ctx->uring_lock); + while (!list_empty(&ctx->tctx_list)) { + WARN_ON_ONCE(time_after(jiffies, timeout)); + + node = list_first_entry(&ctx->tctx_list, struct io_tctx_node, + ctx_node); + /* don't spin on a single task if cancellation failed */ + list_rotate_left(&ctx->tctx_list); + ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL); + if (WARN_ON_ONCE(ret)) + continue; + + mutex_unlock(&ctx->uring_lock); + wait_for_completion(&exit.completion); + mutex_lock(&ctx->uring_lock); + } + mutex_unlock(&ctx->uring_lock); + spin_lock(&ctx->completion_lock); + spin_unlock(&ctx->completion_lock); + + io_ring_ctx_free(ctx); +} + +static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) +{ + unsigned long index; + struct creds *creds; + + mutex_lock(&ctx->uring_lock); + percpu_ref_kill(&ctx->refs); + if (ctx->rings) + __io_cqring_overflow_flush(ctx, true); + xa_for_each(&ctx->personalities, index, creds) + io_unregister_personality(ctx, index); + if (ctx->rings) + io_poll_remove_all(ctx, NULL, true); + mutex_unlock(&ctx->uring_lock); + + /* failed during ring init, it couldn't have issued any requests */ + if (ctx->rings) { + io_kill_timeouts(ctx, NULL, true); + /* if we failed setting up the ctx, we might not have any rings */ + io_iopoll_try_reap_events(ctx); + } + + INIT_WORK(&ctx->exit_work, io_ring_exit_work); + /* + * Use system_unbound_wq to avoid spawning tons of event kworkers + * if we're exiting a ton of rings at the same time. It just adds + * noise and overhead, there's no discernable change in runtime + * over using system_wq. + */ + queue_work(system_unbound_wq, &ctx->exit_work); +} + +static int io_uring_release(struct inode *inode, struct file *file) +{ + struct io_ring_ctx *ctx = file->private_data; + + file->private_data = NULL; + io_ring_ctx_wait_and_kill(ctx); + return 0; +} + +struct io_task_cancel { + struct task_struct *task; + bool all; +}; + +static bool io_cancel_task_cb(struct io_wq_work *work, void *data) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + struct io_task_cancel *cancel = data; + + return io_match_task_safe(req, cancel->task, cancel->all); +} + +static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx, + struct task_struct *task, + bool cancel_all) +{ + struct io_defer_entry *de; + LIST_HEAD(list); + + spin_lock(&ctx->completion_lock); + list_for_each_entry_reverse(de, &ctx->defer_list, list) { + if (io_match_task_safe(de->req, task, cancel_all)) { + list_cut_position(&list, &ctx->defer_list, &de->list); + break; + } + } + spin_unlock(&ctx->completion_lock); + if (list_empty(&list)) + return false; + + while (!list_empty(&list)) { + de = list_first_entry(&list, struct io_defer_entry, list); + list_del_init(&de->list); + io_req_complete_failed(de->req, -ECANCELED); + kfree(de); + } + return true; +} + +static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) +{ + struct io_tctx_node *node; + enum io_wq_cancel cret; + bool ret = false; + + mutex_lock(&ctx->uring_lock); + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; + + /* + * io_wq will stay alive while we hold uring_lock, because it's + * killed after ctx nodes, which requires to take the lock. + */ + if (!tctx || !tctx->io_wq) + continue; + cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true); + ret |= (cret != IO_WQ_CANCEL_NOTFOUND); + } + mutex_unlock(&ctx->uring_lock); + + return ret; +} + +static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + bool cancel_all) +{ + struct io_task_cancel cancel = { .task = task, .all = cancel_all, }; + struct io_uring_task *tctx = task ? task->io_uring : NULL; + enum io_wq_cancel cret; + bool ret = false; + + /* failed during ring init, it couldn't have issued any requests */ + if (!ctx->rings) + return false; + + if (!task) { + ret |= io_uring_try_cancel_iowq(ctx); + } else if (tctx && tctx->io_wq) { + /* + * Cancels requests of all rings, not only @ctx, but + * it's fine as the task is in exit/exec. + */ + cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb, + &cancel, true); + ret |= (cret != IO_WQ_CANCEL_NOTFOUND); + } + + /* SQPOLL thread does its own polling */ + if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) || + (ctx->sq_data && ctx->sq_data->thread == current)) { + while (!wq_list_empty(&ctx->iopoll_list)) { + io_iopoll_try_reap_events(ctx); + ret = true; + } + } + + ret |= io_cancel_defer_files(ctx, task, cancel_all); + mutex_lock(&ctx->uring_lock); + ret |= io_poll_remove_all(ctx, task, cancel_all); + mutex_unlock(&ctx->uring_lock); + ret |= io_kill_timeouts(ctx, task, cancel_all); + if (task) + ret |= io_run_task_work(); + return ret; +} + +static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) +{ + if (tracked) + return atomic_read(&tctx->inflight_tracked); + return percpu_counter_sum(&tctx->inflight); +} + +/* + * Find any io_uring ctx that this task has registered or done IO on, and cancel + * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation. + */ +__cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) +{ + struct io_uring_task *tctx = current->io_uring; + struct io_ring_ctx *ctx; + s64 inflight; + DEFINE_WAIT(wait); + + WARN_ON_ONCE(sqd && sqd->thread != current); + + if (!current->io_uring) + return; + if (tctx->io_wq) + io_wq_exit_start(tctx->io_wq); + + atomic_inc(&tctx->in_idle); + do { + bool loop = false; + + io_uring_drop_tctx_refs(current); + /* read completions before cancelations */ + inflight = tctx_inflight(tctx, !cancel_all); + if (!inflight) + break; + + if (!sqd) { + struct io_tctx_node *node; + unsigned long index; + + xa_for_each(&tctx->xa, index, node) { + /* sqpoll task will cancel all its requests */ + if (node->ctx->sq_data) + continue; + loop |= io_uring_try_cancel_requests(node->ctx, + current, cancel_all); + } + } else { + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + loop |= io_uring_try_cancel_requests(ctx, + current, + cancel_all); + } + + if (loop) { + cond_resched(); + continue; + } + + prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE); + io_run_task_work(); + io_uring_drop_tctx_refs(current); + + /* + * If we've seen completions, retry without waiting. This + * avoids a race where a completion comes in before we did + * prepare_to_wait(). + */ + if (inflight == tctx_inflight(tctx, !cancel_all)) + schedule(); + finish_wait(&tctx->wait, &wait); + } while (1); + + io_uring_clean_tctx(tctx); + if (cancel_all) { + /* + * We shouldn't run task_works after cancel, so just leave + * ->in_idle set for normal exit. + */ + atomic_dec(&tctx->in_idle); + /* for exec all current's requests should be gone, kill tctx */ + __io_uring_free(current); + } +} + +void __io_uring_cancel(bool cancel_all) +{ + io_uring_cancel_generic(cancel_all, NULL); +} + +static void *io_uring_validate_mmap_request(struct file *file, + loff_t pgoff, size_t sz) +{ + struct io_ring_ctx *ctx = file->private_data; + loff_t offset = pgoff << PAGE_SHIFT; + struct page *page; + void *ptr; + + switch (offset) { + case IORING_OFF_SQ_RING: + case IORING_OFF_CQ_RING: + ptr = ctx->rings; + break; + case IORING_OFF_SQES: + ptr = ctx->sq_sqes; + break; + default: + return ERR_PTR(-EINVAL); + } + + page = virt_to_head_page(ptr); + if (sz > page_size(page)) + return ERR_PTR(-EINVAL); + + return ptr; +} + +#ifdef CONFIG_MMU + +static __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma) +{ + size_t sz = vma->vm_end - vma->vm_start; + unsigned long pfn; + void *ptr; + + ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff, sz); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + pfn = virt_to_phys(ptr) >> PAGE_SHIFT; + return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot); +} + +#else /* !CONFIG_MMU */ + +static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -EINVAL; +} + +static unsigned int io_uring_nommu_mmap_capabilities(struct file *file) +{ + return NOMMU_MAP_DIRECT | NOMMU_MAP_READ | NOMMU_MAP_WRITE; +} + +static unsigned long io_uring_nommu_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + void *ptr; + + ptr = io_uring_validate_mmap_request(file, pgoff, len); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + return (unsigned long) ptr; +} + +#endif /* !CONFIG_MMU */ + +static int io_validate_ext_arg(unsigned flags, const void __user *argp, size_t argsz) +{ + if (flags & IORING_ENTER_EXT_ARG) { + struct io_uring_getevents_arg arg; + + if (argsz != sizeof(arg)) + return -EINVAL; + if (copy_from_user(&arg, argp, sizeof(arg))) + return -EFAULT; + } + return 0; +} + +static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz, + struct __kernel_timespec __user **ts, + const sigset_t __user **sig) +{ + struct io_uring_getevents_arg arg; + + /* + * If EXT_ARG isn't set, then we have no timespec and the argp pointer + * is just a pointer to the sigset_t. + */ + if (!(flags & IORING_ENTER_EXT_ARG)) { + *sig = (const sigset_t __user *) argp; + *ts = NULL; + return 0; + } + + /* + * EXT_ARG is set - ensure we agree on the size of it and copy in our + * timespec and sigset_t pointers if good. + */ + if (*argsz != sizeof(arg)) + return -EINVAL; + if (copy_from_user(&arg, argp, sizeof(arg))) + return -EFAULT; + if (arg.pad) + return -EINVAL; + *sig = u64_to_user_ptr(arg.sigmask); + *argsz = arg.sigmask_sz; + *ts = u64_to_user_ptr(arg.ts); + return 0; +} + +SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, + u32, min_complete, u32, flags, const void __user *, argp, + size_t, argsz) +{ + struct io_ring_ctx *ctx; + struct fd f; + long ret; + + io_run_task_work(); + + if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP | + IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG | + IORING_ENTER_REGISTERED_RING))) + return -EINVAL; + + /* + * Ring fd has been registered via IORING_REGISTER_RING_FDS, we + * need only dereference our task private array to find it. + */ + if (flags & IORING_ENTER_REGISTERED_RING) { + struct io_uring_task *tctx = current->io_uring; + + if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX)) + return -EINVAL; + fd = array_index_nospec(fd, IO_RINGFD_REG_MAX); + f.file = tctx->registered_rings[fd]; + f.flags = 0; + if (unlikely(!f.file)) + return -EBADF; + } else { + f = fdget(fd); + if (unlikely(!f.file)) + return -EBADF; + ret = -EOPNOTSUPP; + if (unlikely(!io_is_uring_fops(f.file))) + goto out; + } + + ctx = f.file->private_data; + ret = -EBADFD; + if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED)) + goto out; + + /* + * For SQ polling, the thread will do all submissions and completions. + * Just return the requested submit count, and wake the thread if + * we were asked to. + */ + ret = 0; + if (ctx->flags & IORING_SETUP_SQPOLL) { + io_cqring_overflow_flush(ctx); + + if (unlikely(ctx->sq_data->thread == NULL)) { + ret = -EOWNERDEAD; + goto out; + } + if (flags & IORING_ENTER_SQ_WAKEUP) + wake_up(&ctx->sq_data->wait); + if (flags & IORING_ENTER_SQ_WAIT) { + ret = io_sqpoll_wait_sq(ctx); + if (ret) + goto out; + } + ret = to_submit; + } else if (to_submit) { + ret = io_uring_add_tctx_node(ctx); + if (unlikely(ret)) + goto out; + + mutex_lock(&ctx->uring_lock); + ret = io_submit_sqes(ctx, to_submit); + if (ret != to_submit) { + mutex_unlock(&ctx->uring_lock); + goto out; + } + if ((flags & IORING_ENTER_GETEVENTS) && ctx->syscall_iopoll) + goto iopoll_locked; + mutex_unlock(&ctx->uring_lock); + } + if (flags & IORING_ENTER_GETEVENTS) { + int ret2; + if (ctx->syscall_iopoll) { + /* + * We disallow the app entering submit/complete with + * polling, but we still need to lock the ring to + * prevent racing with polled issue that got punted to + * a workqueue. + */ + mutex_lock(&ctx->uring_lock); +iopoll_locked: + ret2 = io_validate_ext_arg(flags, argp, argsz); + if (likely(!ret2)) { + min_complete = min(min_complete, + ctx->cq_entries); + ret2 = io_iopoll_check(ctx, min_complete); + } + mutex_unlock(&ctx->uring_lock); + } else { + const sigset_t __user *sig; + struct __kernel_timespec __user *ts; + + ret2 = io_get_ext_arg(flags, argp, &argsz, &ts, &sig); + if (likely(!ret2)) { + min_complete = min(min_complete, + ctx->cq_entries); + ret2 = io_cqring_wait(ctx, min_complete, sig, + argsz, ts); + } + } + + if (!ret) { + ret = ret2; + + /* + * EBADR indicates that one or more CQE were dropped. + * Once the user has been informed we can clear the bit + * as they are obviously ok with those drops. + */ + if (unlikely(ret2 == -EBADR)) + clear_bit(IO_CHECK_CQ_DROPPED_BIT, + &ctx->check_cq); + } + } +out: + fdput(f); + return ret; +} + +static const struct file_operations io_uring_fops = { + .release = io_uring_release, + .mmap = io_uring_mmap, +#ifndef CONFIG_MMU + .get_unmapped_area = io_uring_nommu_get_unmapped_area, + .mmap_capabilities = io_uring_nommu_mmap_capabilities, +#endif + .poll = io_uring_poll, +#ifdef CONFIG_PROC_FS + .show_fdinfo = io_uring_show_fdinfo, +#endif +}; + +bool io_is_uring_fops(struct file *file) +{ + return file->f_op == &io_uring_fops; +} + +static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, + struct io_uring_params *p) +{ + struct io_rings *rings; + size_t size, sq_array_offset; + + /* make sure these are sane, as we already accounted them */ + ctx->sq_entries = p->sq_entries; + ctx->cq_entries = p->cq_entries; + + size = rings_size(ctx, p->sq_entries, p->cq_entries, &sq_array_offset); + if (size == SIZE_MAX) + return -EOVERFLOW; + + rings = io_mem_alloc(size); + if (!rings) + return -ENOMEM; + + ctx->rings = rings; + ctx->sq_array = (u32 *)((char *)rings + sq_array_offset); + rings->sq_ring_mask = p->sq_entries - 1; + rings->cq_ring_mask = p->cq_entries - 1; + rings->sq_ring_entries = p->sq_entries; + rings->cq_ring_entries = p->cq_entries; + + if (p->flags & IORING_SETUP_SQE128) + size = array_size(2 * sizeof(struct io_uring_sqe), p->sq_entries); + else + size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); + if (size == SIZE_MAX) { + io_mem_free(ctx->rings); + ctx->rings = NULL; + return -EOVERFLOW; + } + + ctx->sq_sqes = io_mem_alloc(size); + if (!ctx->sq_sqes) { + io_mem_free(ctx->rings); + ctx->rings = NULL; + return -ENOMEM; + } + + return 0; +} + +static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) +{ + int ret, fd; + + fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); + if (fd < 0) + return fd; + + ret = __io_uring_add_tctx_node(ctx, false); + if (ret) { + put_unused_fd(fd); + return ret; + } + fd_install(fd, file); + return fd; +} + +/* + * Allocate an anonymous fd, this is what constitutes the application + * visible backing of an io_uring instance. The application mmaps this + * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled, + * we have to tie this fd to a socket for file garbage collection purposes. + */ +static struct file *io_uring_get_file(struct io_ring_ctx *ctx) +{ + struct file *file; +#if defined(CONFIG_UNIX) + int ret; + + ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP, + &ctx->ring_sock); + if (ret) + return ERR_PTR(ret); +#endif + + file = anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx, + O_RDWR | O_CLOEXEC, NULL); +#if defined(CONFIG_UNIX) + if (IS_ERR(file)) { + sock_release(ctx->ring_sock); + ctx->ring_sock = NULL; + } else { + ctx->ring_sock->file = file; + } +#endif + return file; +} + +static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, + struct io_uring_params __user *params) +{ + struct io_ring_ctx *ctx; + struct file *file; + int ret; + + if (!entries) + return -EINVAL; + if (entries > IORING_MAX_ENTRIES) { + if (!(p->flags & IORING_SETUP_CLAMP)) + return -EINVAL; + entries = IORING_MAX_ENTRIES; + } + + /* + * Use twice as many entries for the CQ ring. It's possible for the + * application to drive a higher depth than the size of the SQ ring, + * since the sqes are only used at submission time. This allows for + * some flexibility in overcommitting a bit. If the application has + * set IORING_SETUP_CQSIZE, it will have passed in the desired number + * of CQ ring entries manually. + */ + p->sq_entries = roundup_pow_of_two(entries); + if (p->flags & IORING_SETUP_CQSIZE) { + /* + * If IORING_SETUP_CQSIZE is set, we do the same roundup + * to a power-of-two, if it isn't already. We do NOT impose + * any cq vs sq ring sizing. + */ + if (!p->cq_entries) + return -EINVAL; + if (p->cq_entries > IORING_MAX_CQ_ENTRIES) { + if (!(p->flags & IORING_SETUP_CLAMP)) + return -EINVAL; + p->cq_entries = IORING_MAX_CQ_ENTRIES; + } + p->cq_entries = roundup_pow_of_two(p->cq_entries); + if (p->cq_entries < p->sq_entries) + return -EINVAL; + } else { + p->cq_entries = 2 * p->sq_entries; + } + + ctx = io_ring_ctx_alloc(p); + if (!ctx) + return -ENOMEM; + + /* + * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user + * space applications don't need to do io completion events + * polling again, they can rely on io_sq_thread to do polling + * work, which can reduce cpu usage and uring_lock contention. + */ + if (ctx->flags & IORING_SETUP_IOPOLL && + !(ctx->flags & IORING_SETUP_SQPOLL)) + ctx->syscall_iopoll = 1; + + ctx->compat = in_compat_syscall(); + if (!capable(CAP_IPC_LOCK)) + ctx->user = get_uid(current_user()); + + /* + * For SQPOLL, we just need a wakeup, always. For !SQPOLL, if + * COOP_TASKRUN is set, then IPIs are never needed by the app. + */ + ret = -EINVAL; + if (ctx->flags & IORING_SETUP_SQPOLL) { + /* IPI related flags don't make sense with SQPOLL */ + if (ctx->flags & (IORING_SETUP_COOP_TASKRUN | + IORING_SETUP_TASKRUN_FLAG)) + goto err; + ctx->notify_method = TWA_SIGNAL_NO_IPI; + } else if (ctx->flags & IORING_SETUP_COOP_TASKRUN) { + ctx->notify_method = TWA_SIGNAL_NO_IPI; + } else { + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) + goto err; + ctx->notify_method = TWA_SIGNAL; + } + + /* + * This is just grabbed for accounting purposes. When a process exits, + * the mm is exited and dropped before the files, hence we need to hang + * on to this mm purely for the purposes of being able to unaccount + * memory (locked/pinned vm). It's not used for anything else. + */ + mmgrab(current->mm); + ctx->mm_account = current->mm; + + ret = io_allocate_scq_urings(ctx, p); + if (ret) + goto err; + + ret = io_sq_offload_create(ctx, p); + if (ret) + goto err; + /* always set a rsrc node */ + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto err; + io_rsrc_node_switch(ctx, NULL); + + memset(&p->sq_off, 0, sizeof(p->sq_off)); + p->sq_off.head = offsetof(struct io_rings, sq.head); + p->sq_off.tail = offsetof(struct io_rings, sq.tail); + p->sq_off.ring_mask = offsetof(struct io_rings, sq_ring_mask); + p->sq_off.ring_entries = offsetof(struct io_rings, sq_ring_entries); + p->sq_off.flags = offsetof(struct io_rings, sq_flags); + p->sq_off.dropped = offsetof(struct io_rings, sq_dropped); + p->sq_off.array = (char *)ctx->sq_array - (char *)ctx->rings; + + memset(&p->cq_off, 0, sizeof(p->cq_off)); + p->cq_off.head = offsetof(struct io_rings, cq.head); + p->cq_off.tail = offsetof(struct io_rings, cq.tail); + p->cq_off.ring_mask = offsetof(struct io_rings, cq_ring_mask); + p->cq_off.ring_entries = offsetof(struct io_rings, cq_ring_entries); + p->cq_off.overflow = offsetof(struct io_rings, cq_overflow); + p->cq_off.cqes = offsetof(struct io_rings, cqes); + p->cq_off.flags = offsetof(struct io_rings, cq_flags); + + p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | + IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | + IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | + IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | + IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | + IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP | + IORING_FEAT_LINKED_FILE; + + if (copy_to_user(params, p, sizeof(*p))) { + ret = -EFAULT; + goto err; + } + + file = io_uring_get_file(ctx); + if (IS_ERR(file)) { + ret = PTR_ERR(file); + goto err; + } + + /* + * Install ring fd as the very last thing, so we don't risk someone + * having closed it before we finish setup + */ + ret = io_uring_install_fd(ctx, file); + if (ret < 0) { + /* fput will clean it up */ + fput(file); + return ret; + } + + trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); + return ret; +err: + io_ring_ctx_wait_and_kill(ctx); + return ret; +} + +/* + * Sets up an aio uring context, and returns the fd. Applications asks for a + * ring size, we return the actual sq/cq ring sizes (among other things) in the + * params structure passed in. + */ +static long io_uring_setup(u32 entries, struct io_uring_params __user *params) +{ + struct io_uring_params p; + int i; + + if (copy_from_user(&p, params, sizeof(p))) + return -EFAULT; + for (i = 0; i < ARRAY_SIZE(p.resv); i++) { + if (p.resv[i]) + return -EINVAL; + } + + if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL | + IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE | + IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ | + IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL | + IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG | + IORING_SETUP_SQE128 | IORING_SETUP_CQE32 | + IORING_SETUP_SINGLE_ISSUER)) + return -EINVAL; + + return io_uring_create(entries, &p, params); +} + +SYSCALL_DEFINE2(io_uring_setup, u32, entries, + struct io_uring_params __user *, params) +{ + return io_uring_setup(entries, params); +} + +static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) +{ + struct io_uring_probe *p; + size_t size; + int i, ret; + + size = struct_size(p, ops, nr_args); + if (size == SIZE_MAX) + return -EOVERFLOW; + p = kzalloc(size, GFP_KERNEL); + if (!p) + return -ENOMEM; + + ret = -EFAULT; + if (copy_from_user(p, arg, size)) + goto out; + ret = -EINVAL; + if (memchr_inv(p, 0, size)) + goto out; + + p->last_op = IORING_OP_LAST - 1; + if (nr_args > IORING_OP_LAST) + nr_args = IORING_OP_LAST; + + for (i = 0; i < nr_args; i++) { + p->ops[i].op = i; + if (!io_op_defs[i].not_supported) + p->ops[i].flags = IO_URING_OP_SUPPORTED; + } + p->ops_len = i; + + ret = 0; + if (copy_to_user(arg, p, size)) + ret = -EFAULT; +out: + kfree(p); + return ret; +} + +static int io_register_personality(struct io_ring_ctx *ctx) +{ + const struct cred *creds; + u32 id; + int ret; + + creds = get_current_cred(); + + ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds, + XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL); + if (ret < 0) { + put_cred(creds); + return ret; + } + return id; +} + +static __cold int io_register_restrictions(struct io_ring_ctx *ctx, + void __user *arg, unsigned int nr_args) +{ + struct io_uring_restriction *res; + size_t size; + int i, ret; + + /* Restrictions allowed only if rings started disabled */ + if (!(ctx->flags & IORING_SETUP_R_DISABLED)) + return -EBADFD; + + /* We allow only a single restrictions registration */ + if (ctx->restrictions.registered) + return -EBUSY; + + if (!arg || nr_args > IORING_MAX_RESTRICTIONS) + return -EINVAL; + + size = array_size(nr_args, sizeof(*res)); + if (size == SIZE_MAX) + return -EOVERFLOW; + + res = memdup_user(arg, size); + if (IS_ERR(res)) + return PTR_ERR(res); + + ret = 0; + + for (i = 0; i < nr_args; i++) { + switch (res[i].opcode) { + case IORING_RESTRICTION_REGISTER_OP: + if (res[i].register_op >= IORING_REGISTER_LAST) { + ret = -EINVAL; + goto out; + } + + __set_bit(res[i].register_op, + ctx->restrictions.register_op); + break; + case IORING_RESTRICTION_SQE_OP: + if (res[i].sqe_op >= IORING_OP_LAST) { + ret = -EINVAL; + goto out; + } + + __set_bit(res[i].sqe_op, ctx->restrictions.sqe_op); + break; + case IORING_RESTRICTION_SQE_FLAGS_ALLOWED: + ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags; + break; + case IORING_RESTRICTION_SQE_FLAGS_REQUIRED: + ctx->restrictions.sqe_flags_required = res[i].sqe_flags; + break; + default: + ret = -EINVAL; + goto out; + } + } + +out: + /* Reset all restrictions if an error happened */ + if (ret != 0) + memset(&ctx->restrictions, 0, sizeof(ctx->restrictions)); + else + ctx->restrictions.registered = true; + + kfree(res); + return ret; +} + +static int io_register_enable_rings(struct io_ring_ctx *ctx) +{ + if (!(ctx->flags & IORING_SETUP_R_DISABLED)) + return -EBADFD; + + if (ctx->restrictions.registered) + ctx->restricted = 1; + + ctx->flags &= ~IORING_SETUP_R_DISABLED; + if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait)) + wake_up(&ctx->sq_data->wait); + return 0; +} + +static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, + void __user *arg, unsigned len) +{ + struct io_uring_task *tctx = current->io_uring; + cpumask_var_t new_mask; + int ret; + + if (!tctx || !tctx->io_wq) + return -EINVAL; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_clear(new_mask); + if (len > cpumask_size()) + len = cpumask_size(); + + if (in_compat_syscall()) { + ret = compat_get_bitmap(cpumask_bits(new_mask), + (const compat_ulong_t __user *)arg, + len * 8 /* CHAR_BIT */); + } else { + ret = copy_from_user(new_mask, arg, len); + } + + if (ret) { + free_cpumask_var(new_mask); + return -EFAULT; + } + + ret = io_wq_cpu_affinity(tctx->io_wq, new_mask); + free_cpumask_var(new_mask); + return ret; +} + +static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx) +{ + struct io_uring_task *tctx = current->io_uring; + + if (!tctx || !tctx->io_wq) + return -EINVAL; + + return io_wq_cpu_affinity(tctx->io_wq, NULL); +} + +static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx, + void __user *arg) + __must_hold(&ctx->uring_lock) +{ + struct io_tctx_node *node; + struct io_uring_task *tctx = NULL; + struct io_sq_data *sqd = NULL; + __u32 new_count[2]; + int i, ret; + + if (copy_from_user(new_count, arg, sizeof(new_count))) + return -EFAULT; + for (i = 0; i < ARRAY_SIZE(new_count); i++) + if (new_count[i] > INT_MAX) + return -EINVAL; + + if (ctx->flags & IORING_SETUP_SQPOLL) { + sqd = ctx->sq_data; + if (sqd) { + /* + * Observe the correct sqd->lock -> ctx->uring_lock + * ordering. Fine to drop uring_lock here, we hold + * a ref to the ctx. + */ + refcount_inc(&sqd->refs); + mutex_unlock(&ctx->uring_lock); + mutex_lock(&sqd->lock); + mutex_lock(&ctx->uring_lock); + if (sqd->thread) + tctx = sqd->thread->io_uring; + } + } else { + tctx = current->io_uring; + } + + BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits)); + + for (i = 0; i < ARRAY_SIZE(new_count); i++) + if (new_count[i]) + ctx->iowq_limits[i] = new_count[i]; + ctx->iowq_limits_set = true; + + if (tctx && tctx->io_wq) { + ret = io_wq_max_workers(tctx->io_wq, new_count); + if (ret) + goto err; + } else { + memset(new_count, 0, sizeof(new_count)); + } + + if (sqd) { + mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } + + if (copy_to_user(arg, new_count, sizeof(new_count))) + return -EFAULT; + + /* that's it for SQPOLL, only the SQPOLL task creates requests */ + if (sqd) + return 0; + + /* now propagate the restriction to all registered users */ + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; + + if (WARN_ON_ONCE(!tctx->io_wq)) + continue; + + for (i = 0; i < ARRAY_SIZE(new_count); i++) + new_count[i] = ctx->iowq_limits[i]; + /* ignore errors, it always returns zero anyway */ + (void)io_wq_max_workers(tctx->io_wq, new_count); + } + return 0; +err: + if (sqd) { + mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } + return ret; +} + +static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, + void __user *arg, unsigned nr_args) + __releases(ctx->uring_lock) + __acquires(ctx->uring_lock) +{ + int ret; + + /* + * We don't quiesce the refs for register anymore and so it can't be + * dying as we're holding a file ref here. + */ + if (WARN_ON_ONCE(percpu_ref_is_dying(&ctx->refs))) + return -ENXIO; + + if (ctx->restricted) { + if (opcode >= IORING_REGISTER_LAST) + return -EINVAL; + opcode = array_index_nospec(opcode, IORING_REGISTER_LAST); + if (!test_bit(opcode, ctx->restrictions.register_op)) + return -EACCES; + } + + switch (opcode) { + case IORING_REGISTER_BUFFERS: + ret = -EFAULT; + if (!arg) + break; + ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL); + break; + case IORING_UNREGISTER_BUFFERS: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_sqe_buffers_unregister(ctx); + break; + case IORING_REGISTER_FILES: + ret = -EFAULT; + if (!arg) + break; + ret = io_sqe_files_register(ctx, arg, nr_args, NULL); + break; + case IORING_UNREGISTER_FILES: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_sqe_files_unregister(ctx); + break; + case IORING_REGISTER_FILES_UPDATE: + ret = io_register_files_update(ctx, arg, nr_args); + break; + case IORING_REGISTER_EVENTFD: + ret = -EINVAL; + if (nr_args != 1) + break; + ret = io_eventfd_register(ctx, arg, 0); + break; + case IORING_REGISTER_EVENTFD_ASYNC: + ret = -EINVAL; + if (nr_args != 1) + break; + ret = io_eventfd_register(ctx, arg, 1); + break; + case IORING_UNREGISTER_EVENTFD: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_eventfd_unregister(ctx); + break; + case IORING_REGISTER_PROBE: + ret = -EINVAL; + if (!arg || nr_args > 256) + break; + ret = io_probe(ctx, arg, nr_args); + break; + case IORING_REGISTER_PERSONALITY: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_register_personality(ctx); + break; + case IORING_UNREGISTER_PERSONALITY: + ret = -EINVAL; + if (arg) + break; + ret = io_unregister_personality(ctx, nr_args); + break; + case IORING_REGISTER_ENABLE_RINGS: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_register_enable_rings(ctx); + break; + case IORING_REGISTER_RESTRICTIONS: + ret = io_register_restrictions(ctx, arg, nr_args); + break; + case IORING_REGISTER_FILES2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE); + break; + case IORING_REGISTER_FILES_UPDATE2: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_FILE); + break; + case IORING_REGISTER_BUFFERS2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER); + break; + case IORING_REGISTER_BUFFERS_UPDATE: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_BUFFER); + break; + case IORING_REGISTER_IOWQ_AFF: + ret = -EINVAL; + if (!arg || !nr_args) + break; + ret = io_register_iowq_aff(ctx, arg, nr_args); + break; + case IORING_UNREGISTER_IOWQ_AFF: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_unregister_iowq_aff(ctx); + break; + case IORING_REGISTER_IOWQ_MAX_WORKERS: + ret = -EINVAL; + if (!arg || nr_args != 2) + break; + ret = io_register_iowq_max_workers(ctx, arg); + break; + case IORING_REGISTER_RING_FDS: + ret = io_ringfd_register(ctx, arg, nr_args); + break; + case IORING_UNREGISTER_RING_FDS: + ret = io_ringfd_unregister(ctx, arg, nr_args); + break; + case IORING_REGISTER_PBUF_RING: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_register_pbuf_ring(ctx, arg); + break; + case IORING_UNREGISTER_PBUF_RING: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_unregister_pbuf_ring(ctx, arg); + break; + case IORING_REGISTER_SYNC_CANCEL: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_sync_cancel(ctx, arg); + break; + case IORING_REGISTER_FILE_ALLOC_RANGE: + ret = -EINVAL; + if (!arg || nr_args) + break; + ret = io_register_file_alloc_range(ctx, arg); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, + void __user *, arg, unsigned int, nr_args) +{ + struct io_ring_ctx *ctx; + long ret = -EBADF; + struct fd f; + + f = fdget(fd); + if (!f.file) + return -EBADF; + + ret = -EOPNOTSUPP; + if (!io_is_uring_fops(f.file)) + goto out_fput; + + ctx = f.file->private_data; + + io_run_task_work(); + + mutex_lock(&ctx->uring_lock); + ret = __io_uring_register(ctx, opcode, arg, nr_args); + mutex_unlock(&ctx->uring_lock); + trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, ret); +out_fput: + fdput(f); + return ret; +} + +static int __init io_uring_init(void) +{ +#define __BUILD_BUG_VERIFY_ELEMENT(stype, eoffset, etype, ename) do { \ + BUILD_BUG_ON(offsetof(stype, ename) != eoffset); \ + BUILD_BUG_ON(sizeof(etype) != sizeof_field(stype, ename)); \ +} while (0) + +#define BUILD_BUG_SQE_ELEM(eoffset, etype, ename) \ + __BUILD_BUG_VERIFY_ELEMENT(struct io_uring_sqe, eoffset, etype, ename) + BUILD_BUG_ON(sizeof(struct io_uring_sqe) != 64); + BUILD_BUG_SQE_ELEM(0, __u8, opcode); + BUILD_BUG_SQE_ELEM(1, __u8, flags); + BUILD_BUG_SQE_ELEM(2, __u16, ioprio); + BUILD_BUG_SQE_ELEM(4, __s32, fd); + BUILD_BUG_SQE_ELEM(8, __u64, off); + BUILD_BUG_SQE_ELEM(8, __u64, addr2); + BUILD_BUG_SQE_ELEM(16, __u64, addr); + BUILD_BUG_SQE_ELEM(16, __u64, splice_off_in); + BUILD_BUG_SQE_ELEM(24, __u32, len); + BUILD_BUG_SQE_ELEM(28, __kernel_rwf_t, rw_flags); + BUILD_BUG_SQE_ELEM(28, /* compat */ int, rw_flags); + BUILD_BUG_SQE_ELEM(28, /* compat */ __u32, rw_flags); + BUILD_BUG_SQE_ELEM(28, __u32, fsync_flags); + BUILD_BUG_SQE_ELEM(28, /* compat */ __u16, poll_events); + BUILD_BUG_SQE_ELEM(28, __u32, poll32_events); + BUILD_BUG_SQE_ELEM(28, __u32, sync_range_flags); + BUILD_BUG_SQE_ELEM(28, __u32, msg_flags); + BUILD_BUG_SQE_ELEM(28, __u32, timeout_flags); + BUILD_BUG_SQE_ELEM(28, __u32, accept_flags); + BUILD_BUG_SQE_ELEM(28, __u32, cancel_flags); + BUILD_BUG_SQE_ELEM(28, __u32, open_flags); + BUILD_BUG_SQE_ELEM(28, __u32, statx_flags); + BUILD_BUG_SQE_ELEM(28, __u32, fadvise_advice); + BUILD_BUG_SQE_ELEM(28, __u32, splice_flags); + BUILD_BUG_SQE_ELEM(32, __u64, user_data); + BUILD_BUG_SQE_ELEM(40, __u16, buf_index); + BUILD_BUG_SQE_ELEM(40, __u16, buf_group); + BUILD_BUG_SQE_ELEM(42, __u16, personality); + BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); + BUILD_BUG_SQE_ELEM(44, __u32, file_index); + BUILD_BUG_SQE_ELEM(48, __u64, addr3); + + BUILD_BUG_ON(sizeof(struct io_uring_files_update) != + sizeof(struct io_uring_rsrc_update)); + BUILD_BUG_ON(sizeof(struct io_uring_rsrc_update) > + sizeof(struct io_uring_rsrc_update2)); + + /* ->buf_index is u16 */ + BUILD_BUG_ON(offsetof(struct io_uring_buf_ring, bufs) != 0); + BUILD_BUG_ON(offsetof(struct io_uring_buf, resv) != + offsetof(struct io_uring_buf_ring, tail)); + + /* should fit into one byte */ + BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8)); + BUILD_BUG_ON(SQE_COMMON_FLAGS >= (1 << 8)); + BUILD_BUG_ON((SQE_VALID_FLAGS | SQE_COMMON_FLAGS) != SQE_VALID_FLAGS); + + BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int)); + + BUILD_BUG_ON(sizeof(atomic_t) != sizeof(u32)); + + io_uring_optable_init(); + + req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC | + SLAB_ACCOUNT); + return 0; +}; +__initcall(io_uring_init); diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h new file mode 100644 index 000000000000..5db0a60dc04e --- /dev/null +++ b/io_uring/io_uring.h @@ -0,0 +1,261 @@ +#ifndef IOU_CORE_H +#define IOU_CORE_H + +#include <linux/errno.h> +#include <linux/lockdep.h> +#include <linux/io_uring_types.h> +#include "io-wq.h" +#include "slist.h" +#include "filetable.h" + +#ifndef CREATE_TRACE_POINTS +#include <trace/events/io_uring.h> +#endif + +enum { + IOU_OK = 0, + IOU_ISSUE_SKIP_COMPLETE = -EIOCBQUEUED, + + /* + * Intended only when both REQ_F_POLLED and REQ_F_APOLL_MULTISHOT + * are set to indicate to the poll runner that multishot should be + * removed and the result is set on req->cqe.res. + */ + IOU_STOP_MULTISHOT = -ECANCELED, +}; + +struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx); +bool io_req_cqe_overflow(struct io_kiocb *req); +int io_run_task_work_sig(void); +void io_req_complete_failed(struct io_kiocb *req, s32 res); +void __io_req_complete(struct io_kiocb *req, unsigned issue_flags); +void io_req_complete_post(struct io_kiocb *req); +void __io_req_complete_post(struct io_kiocb *req); +bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags, + bool allow_overflow); +void __io_commit_cqring_flush(struct io_ring_ctx *ctx); + +struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages); + +struct file *io_file_get_normal(struct io_kiocb *req, int fd); +struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned issue_flags); + +static inline bool io_req_ffs_set(struct io_kiocb *req) +{ + return req->flags & REQ_F_FIXED_FILE; +} + +bool io_is_uring_fops(struct file *file); +bool io_alloc_async_data(struct io_kiocb *req); +void io_req_task_work_add(struct io_kiocb *req); +void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags); +void io_req_task_queue(struct io_kiocb *req); +void io_queue_iowq(struct io_kiocb *req, bool *dont_use); +void io_req_task_complete(struct io_kiocb *req, bool *locked); +void io_req_task_queue_fail(struct io_kiocb *req, int ret); +void io_req_task_submit(struct io_kiocb *req, bool *locked); +void tctx_task_work(struct callback_head *cb); +__cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); +int io_uring_alloc_task_context(struct task_struct *task, + struct io_ring_ctx *ctx); + +int io_poll_issue(struct io_kiocb *req, bool *locked); +int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr); +int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin); +void io_free_batch_list(struct io_ring_ctx *ctx, struct io_wq_work_node *node); +int io_req_prep_async(struct io_kiocb *req); + +struct io_wq_work *io_wq_free_work(struct io_wq_work *work); +void io_wq_submit_work(struct io_wq_work *work); + +void io_free_req(struct io_kiocb *req); +void io_queue_next(struct io_kiocb *req); + +bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, + bool cancel_all); + +#define io_for_each_link(pos, head) \ + for (pos = (head); pos; pos = pos->link) + +static inline void io_cq_lock(struct io_ring_ctx *ctx) + __acquires(ctx->completion_lock) +{ + spin_lock(&ctx->completion_lock); +} + +void io_cq_unlock_post(struct io_ring_ctx *ctx); + +static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) +{ + if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) { + struct io_uring_cqe *cqe = ctx->cqe_cached; + + ctx->cached_cq_tail++; + ctx->cqe_cached++; + if (ctx->flags & IORING_SETUP_CQE32) + ctx->cqe_cached++; + return cqe; + } + + return __io_get_cqe(ctx); +} + +static inline bool __io_fill_cqe_req(struct io_ring_ctx *ctx, + struct io_kiocb *req) +{ + struct io_uring_cqe *cqe; + + /* + * If we can't get a cq entry, userspace overflowed the + * submission (by quite a lot). Increment the overflow count in + * the ring. + */ + cqe = io_get_cqe(ctx); + if (unlikely(!cqe)) + return io_req_cqe_overflow(req); + + trace_io_uring_complete(req->ctx, req, req->cqe.user_data, + req->cqe.res, req->cqe.flags, + (req->flags & REQ_F_CQE32_INIT) ? req->extra1 : 0, + (req->flags & REQ_F_CQE32_INIT) ? req->extra2 : 0); + + memcpy(cqe, &req->cqe, sizeof(*cqe)); + + if (ctx->flags & IORING_SETUP_CQE32) { + u64 extra1 = 0, extra2 = 0; + + if (req->flags & REQ_F_CQE32_INIT) { + extra1 = req->extra1; + extra2 = req->extra2; + } + + WRITE_ONCE(cqe->big_cqe[0], extra1); + WRITE_ONCE(cqe->big_cqe[1], extra2); + } + return true; +} + +static inline void req_set_fail(struct io_kiocb *req) +{ + req->flags |= REQ_F_FAIL; + if (req->flags & REQ_F_CQE_SKIP) { + req->flags &= ~REQ_F_CQE_SKIP; + req->flags |= REQ_F_SKIP_LINK_CQES; + } +} + +static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags) +{ + req->cqe.res = res; + req->cqe.flags = cflags; +} + +static inline bool req_has_async_data(struct io_kiocb *req) +{ + return req->flags & REQ_F_ASYNC_DATA; +} + +static inline void io_put_file(struct file *file) +{ + if (file) + fput(file); +} + +static inline void io_ring_submit_unlock(struct io_ring_ctx *ctx, + unsigned issue_flags) +{ + lockdep_assert_held(&ctx->uring_lock); + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); +} + +static inline void io_ring_submit_lock(struct io_ring_ctx *ctx, + unsigned issue_flags) +{ + /* + * "Normal" inline submissions always hold the uring_lock, since we + * grab it from the system call. Same is true for the SQPOLL offload. + * The only exception is when we've detached the request and issue it + * from an async worker thread, grab the lock for that case. + */ + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_lock(&ctx->uring_lock); + lockdep_assert_held(&ctx->uring_lock); +} + +static inline void io_commit_cqring(struct io_ring_ctx *ctx) +{ + /* order cqe stores with ring update */ + smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail); +} + +static inline void io_cqring_wake(struct io_ring_ctx *ctx) +{ + /* + * wake_up_all() may seem excessive, but io_wake_function() and + * io_should_wake() handle the termination of the loop and only + * wake as many waiters as we need to. + */ + if (wq_has_sleeper(&ctx->cq_wait)) + wake_up_all(&ctx->cq_wait); +} + +static inline bool io_sqring_full(struct io_ring_ctx *ctx) +{ + struct io_rings *r = ctx->rings; + + return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == ctx->sq_entries; +} + +static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = ctx->rings; + + /* make sure SQ entry isn't read before tail */ + return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head; +} + +static inline bool io_run_task_work(void) +{ + if (test_thread_flag(TIF_NOTIFY_SIGNAL)) { + __set_current_state(TASK_RUNNING); + clear_notify_signal(); + if (task_work_pending(current)) + task_work_run(); + return true; + } + + return false; +} + +static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked) +{ + if (!*locked) { + mutex_lock(&ctx->uring_lock); + *locked = true; + } +} + +/* + * Don't complete immediately but use deferred completion infrastructure. + * Protected by ->uring_lock and can only be used either with + * IO_URING_F_COMPLETE_DEFER or inside a tw handler holding the mutex. + */ +static inline void io_req_complete_defer(struct io_kiocb *req) + __must_hold(&req->ctx->uring_lock) +{ + struct io_submit_state *state = &req->ctx->submit_state; + + lockdep_assert_held(&req->ctx->uring_lock); + + wq_list_add_tail(&req->comp_list, &state->compl_reqs); +} + +static inline void io_commit_cqring_flush(struct io_ring_ctx *ctx) +{ + if (unlikely(ctx->off_timeout_used || ctx->drain_active || ctx->has_evfd)) + __io_commit_cqring_flush(ctx); +} + +#endif diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c new file mode 100644 index 000000000000..e538fa7cb727 --- /dev/null +++ b/io_uring/kbuf.c @@ -0,0 +1,549 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/poll.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "opdef.h" +#include "kbuf.h" + +#define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf)) + +#define BGID_ARRAY 64 + +struct io_provide_buf { + struct file *file; + __u64 addr; + __u32 len; + __u32 bgid; + __u16 nbufs; + __u16 bid; +}; + +static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, + unsigned int bgid) +{ + if (ctx->io_bl && bgid < BGID_ARRAY) + return &ctx->io_bl[bgid]; + + return xa_load(&ctx->io_bl_xa, bgid); +} + +static int io_buffer_add_list(struct io_ring_ctx *ctx, + struct io_buffer_list *bl, unsigned int bgid) +{ + bl->bgid = bgid; + if (bgid < BGID_ARRAY) + return 0; + + return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); +} + +void io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_buffer_list *bl; + struct io_buffer *buf; + + /* + * For legacy provided buffer mode, don't recycle if we already did + * IO to this buffer. For ring-mapped provided buffer mode, we should + * increment ring->head to explicitly monopolize the buffer to avoid + * multiple use. + */ + if (req->flags & REQ_F_PARTIAL_IO) + return; + + io_ring_submit_lock(ctx, issue_flags); + + buf = req->kbuf; + bl = io_buffer_get_list(ctx, buf->bgid); + list_add(&buf->list, &bl->buf_list); + req->flags &= ~REQ_F_BUFFER_SELECTED; + req->buf_index = buf->bgid; + + io_ring_submit_unlock(ctx, issue_flags); + return; +} + +unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags) +{ + unsigned int cflags; + + /* + * We can add this buffer back to two lists: + * + * 1) The io_buffers_cache list. This one is protected by the + * ctx->uring_lock. If we already hold this lock, add back to this + * list as we can grab it from issue as well. + * 2) The io_buffers_comp list. This one is protected by the + * ctx->completion_lock. + * + * We migrate buffers from the comp_list to the issue cache list + * when we need one. + */ + if (req->flags & REQ_F_BUFFER_RING) { + /* no buffers to recycle for this case */ + cflags = __io_put_kbuf_list(req, NULL); + } else if (issue_flags & IO_URING_F_UNLOCKED) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock(&ctx->completion_lock); + cflags = __io_put_kbuf_list(req, &ctx->io_buffers_comp); + spin_unlock(&ctx->completion_lock); + } else { + lockdep_assert_held(&req->ctx->uring_lock); + + cflags = __io_put_kbuf_list(req, &req->ctx->io_buffers_cache); + } + return cflags; +} + +static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len, + struct io_buffer_list *bl) +{ + if (!list_empty(&bl->buf_list)) { + struct io_buffer *kbuf; + + kbuf = list_first_entry(&bl->buf_list, struct io_buffer, list); + list_del(&kbuf->list); + if (*len == 0 || *len > kbuf->len) + *len = kbuf->len; + req->flags |= REQ_F_BUFFER_SELECTED; + req->kbuf = kbuf; + req->buf_index = kbuf->bid; + return u64_to_user_ptr(kbuf->addr); + } + return NULL; +} + +static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, + struct io_buffer_list *bl, + unsigned int issue_flags) +{ + struct io_uring_buf_ring *br = bl->buf_ring; + struct io_uring_buf *buf; + __u16 head = bl->head; + + if (unlikely(smp_load_acquire(&br->tail) == head)) + return NULL; + + head &= bl->mask; + if (head < IO_BUFFER_LIST_BUF_PER_PAGE) { + buf = &br->bufs[head]; + } else { + int off = head & (IO_BUFFER_LIST_BUF_PER_PAGE - 1); + int index = head / IO_BUFFER_LIST_BUF_PER_PAGE; + buf = page_address(bl->buf_pages[index]); + buf += off; + } + if (*len == 0 || *len > buf->len) + *len = buf->len; + req->flags |= REQ_F_BUFFER_RING; + req->buf_list = bl; + req->buf_index = buf->bid; + + if (issue_flags & IO_URING_F_UNLOCKED || !file_can_poll(req->file)) { + /* + * If we came in unlocked, we have no choice but to consume the + * buffer here, otherwise nothing ensures that the buffer won't + * get used by others. This does mean it'll be pinned until the + * IO completes, coming in unlocked means we're being called from + * io-wq context and there may be further retries in async hybrid + * mode. For the locked case, the caller must call commit when + * the transfer completes (or if we get -EAGAIN and must poll of + * retry). + */ + req->buf_list = NULL; + bl->head++; + } + return u64_to_user_ptr(buf->addr); +} + +void __user *io_buffer_select(struct io_kiocb *req, size_t *len, + unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_buffer_list *bl; + void __user *ret = NULL; + + io_ring_submit_lock(req->ctx, issue_flags); + + bl = io_buffer_get_list(ctx, req->buf_index); + if (likely(bl)) { + if (bl->buf_nr_pages) + ret = io_ring_buffer_select(req, len, bl, issue_flags); + else + ret = io_provided_buffer_select(req, len, bl); + } + io_ring_submit_unlock(req->ctx, issue_flags); + return ret; +} + +static __cold int io_init_bl_list(struct io_ring_ctx *ctx) +{ + int i; + + ctx->io_bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), + GFP_KERNEL); + if (!ctx->io_bl) + return -ENOMEM; + + for (i = 0; i < BGID_ARRAY; i++) { + INIT_LIST_HEAD(&ctx->io_bl[i].buf_list); + ctx->io_bl[i].bgid = i; + } + + return 0; +} + +static int __io_remove_buffers(struct io_ring_ctx *ctx, + struct io_buffer_list *bl, unsigned nbufs) +{ + unsigned i = 0; + + /* shouldn't happen */ + if (!nbufs) + return 0; + + if (bl->buf_nr_pages) { + int j; + + i = bl->buf_ring->tail - bl->head; + for (j = 0; j < bl->buf_nr_pages; j++) + unpin_user_page(bl->buf_pages[j]); + kvfree(bl->buf_pages); + bl->buf_pages = NULL; + bl->buf_nr_pages = 0; + /* make sure it's seen as empty */ + INIT_LIST_HEAD(&bl->buf_list); + return i; + } + + /* the head kbuf is the list itself */ + while (!list_empty(&bl->buf_list)) { + struct io_buffer *nxt; + + nxt = list_first_entry(&bl->buf_list, struct io_buffer, list); + list_del(&nxt->list); + if (++i == nbufs) + return i; + cond_resched(); + } + i++; + + return i; +} + +void io_destroy_buffers(struct io_ring_ctx *ctx) +{ + struct io_buffer_list *bl; + unsigned long index; + int i; + + for (i = 0; i < BGID_ARRAY; i++) { + if (!ctx->io_bl) + break; + __io_remove_buffers(ctx, &ctx->io_bl[i], -1U); + } + + xa_for_each(&ctx->io_bl_xa, index, bl) { + xa_erase(&ctx->io_bl_xa, bl->bgid); + __io_remove_buffers(ctx, bl, -1U); + kfree(bl); + } + + while (!list_empty(&ctx->io_buffers_pages)) { + struct page *page; + + page = list_first_entry(&ctx->io_buffers_pages, struct page, lru); + list_del_init(&page->lru); + __free_page(page); + } +} + +int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_provide_buf *p = io_kiocb_to_cmd(req); + u64 tmp; + + if (sqe->rw_flags || sqe->addr || sqe->len || sqe->off || + sqe->splice_fd_in) + return -EINVAL; + + tmp = READ_ONCE(sqe->fd); + if (!tmp || tmp > USHRT_MAX) + return -EINVAL; + + memset(p, 0, sizeof(*p)); + p->nbufs = tmp; + p->bgid = READ_ONCE(sqe->buf_group); + return 0; +} + +int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_provide_buf *p = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + struct io_buffer_list *bl; + int ret = 0; + + io_ring_submit_lock(ctx, issue_flags); + + ret = -ENOENT; + bl = io_buffer_get_list(ctx, p->bgid); + if (bl) { + ret = -EINVAL; + /* can't use provide/remove buffers command on mapped buffers */ + if (!bl->buf_nr_pages) + ret = __io_remove_buffers(ctx, bl, p->nbufs); + } + if (ret < 0) + req_set_fail(req); + + /* complete before unlock, IOPOLL may need the lock */ + io_req_set_res(req, ret, 0); + __io_req_complete(req, issue_flags); + io_ring_submit_unlock(ctx, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; +} + +int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + unsigned long size, tmp_check; + struct io_provide_buf *p = io_kiocb_to_cmd(req); + u64 tmp; + + if (sqe->rw_flags || sqe->splice_fd_in) + return -EINVAL; + + tmp = READ_ONCE(sqe->fd); + if (!tmp || tmp > USHRT_MAX) + return -E2BIG; + p->nbufs = tmp; + p->addr = READ_ONCE(sqe->addr); + p->len = READ_ONCE(sqe->len); + + if (check_mul_overflow((unsigned long)p->len, (unsigned long)p->nbufs, + &size)) + return -EOVERFLOW; + if (check_add_overflow((unsigned long)p->addr, size, &tmp_check)) + return -EOVERFLOW; + + size = (unsigned long)p->len * p->nbufs; + if (!access_ok(u64_to_user_ptr(p->addr), size)) + return -EFAULT; + + p->bgid = READ_ONCE(sqe->buf_group); + tmp = READ_ONCE(sqe->off); + if (tmp > USHRT_MAX) + return -E2BIG; + p->bid = tmp; + return 0; +} + +static int io_refill_buffer_cache(struct io_ring_ctx *ctx) +{ + struct io_buffer *buf; + struct page *page; + int bufs_in_page; + + /* + * Completions that don't happen inline (eg not under uring_lock) will + * add to ->io_buffers_comp. If we don't have any free buffers, check + * the completion list and splice those entries first. + */ + if (!list_empty_careful(&ctx->io_buffers_comp)) { + spin_lock(&ctx->completion_lock); + if (!list_empty(&ctx->io_buffers_comp)) { + list_splice_init(&ctx->io_buffers_comp, + &ctx->io_buffers_cache); + spin_unlock(&ctx->completion_lock); + return 0; + } + spin_unlock(&ctx->completion_lock); + } + + /* + * No free buffers and no completion entries either. Allocate a new + * page worth of buffer entries and add those to our freelist. + */ + page = alloc_page(GFP_KERNEL_ACCOUNT); + if (!page) + return -ENOMEM; + + list_add(&page->lru, &ctx->io_buffers_pages); + + buf = page_address(page); + bufs_in_page = PAGE_SIZE / sizeof(*buf); + while (bufs_in_page) { + list_add_tail(&buf->list, &ctx->io_buffers_cache); + buf++; + bufs_in_page--; + } + + return 0; +} + +static int io_add_buffers(struct io_ring_ctx *ctx, struct io_provide_buf *pbuf, + struct io_buffer_list *bl) +{ + struct io_buffer *buf; + u64 addr = pbuf->addr; + int i, bid = pbuf->bid; + + for (i = 0; i < pbuf->nbufs; i++) { + if (list_empty(&ctx->io_buffers_cache) && + io_refill_buffer_cache(ctx)) + break; + buf = list_first_entry(&ctx->io_buffers_cache, struct io_buffer, + list); + list_move_tail(&buf->list, &bl->buf_list); + buf->addr = addr; + buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT); + buf->bid = bid; + buf->bgid = pbuf->bgid; + addr += pbuf->len; + bid++; + cond_resched(); + } + + return i ? 0 : -ENOMEM; +} + +int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_provide_buf *p = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + struct io_buffer_list *bl; + int ret = 0; + + io_ring_submit_lock(ctx, issue_flags); + + if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) { + ret = io_init_bl_list(ctx); + if (ret) + goto err; + } + + bl = io_buffer_get_list(ctx, p->bgid); + if (unlikely(!bl)) { + bl = kzalloc(sizeof(*bl), GFP_KERNEL); + if (!bl) { + ret = -ENOMEM; + goto err; + } + INIT_LIST_HEAD(&bl->buf_list); + ret = io_buffer_add_list(ctx, bl, p->bgid); + if (ret) { + kfree(bl); + goto err; + } + } + /* can't add buffers via this command for a mapped buffer ring */ + if (bl->buf_nr_pages) { + ret = -EINVAL; + goto err; + } + + ret = io_add_buffers(ctx, p, bl); +err: + if (ret < 0) + req_set_fail(req); + /* complete before unlock, IOPOLL may need the lock */ + io_req_set_res(req, ret, 0); + __io_req_complete(req, issue_flags); + io_ring_submit_unlock(ctx, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; +} + +int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) +{ + struct io_uring_buf_ring *br; + struct io_uring_buf_reg reg; + struct io_buffer_list *bl, *free_bl = NULL; + struct page **pages; + int nr_pages; + + if (copy_from_user(®, arg, sizeof(reg))) + return -EFAULT; + + if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2]) + return -EINVAL; + if (!reg.ring_addr) + return -EFAULT; + if (reg.ring_addr & ~PAGE_MASK) + return -EINVAL; + if (!is_power_of_2(reg.ring_entries)) + return -EINVAL; + + /* cannot disambiguate full vs empty due to head/tail size */ + if (reg.ring_entries >= 65536) + return -EINVAL; + + if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) { + int ret = io_init_bl_list(ctx); + if (ret) + return ret; + } + + bl = io_buffer_get_list(ctx, reg.bgid); + if (bl) { + /* if mapped buffer ring OR classic exists, don't allow */ + if (bl->buf_nr_pages || !list_empty(&bl->buf_list)) + return -EEXIST; + } else { + free_bl = bl = kzalloc(sizeof(*bl), GFP_KERNEL); + if (!bl) + return -ENOMEM; + } + + pages = io_pin_pages(reg.ring_addr, + struct_size(br, bufs, reg.ring_entries), + &nr_pages); + if (IS_ERR(pages)) { + kfree(free_bl); + return PTR_ERR(pages); + } + + br = page_address(pages[0]); + bl->buf_pages = pages; + bl->buf_nr_pages = nr_pages; + bl->nr_entries = reg.ring_entries; + bl->buf_ring = br; + bl->mask = reg.ring_entries - 1; + io_buffer_add_list(ctx, bl, reg.bgid); + return 0; +} + +int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) +{ + struct io_uring_buf_reg reg; + struct io_buffer_list *bl; + + if (copy_from_user(®, arg, sizeof(reg))) + return -EFAULT; + if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2]) + return -EINVAL; + + bl = io_buffer_get_list(ctx, reg.bgid); + if (!bl) + return -ENOENT; + if (!bl->buf_nr_pages) + return -EINVAL; + + __io_remove_buffers(ctx, bl, -1U); + if (bl->bgid >= BGID_ARRAY) { + xa_erase(&ctx->io_bl_xa, bl->bgid); + kfree(bl); + } + return 0; +} diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h new file mode 100644 index 000000000000..d6af208d109f --- /dev/null +++ b/io_uring/kbuf.h @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef IOU_KBUF_H +#define IOU_KBUF_H + +#include <uapi/linux/io_uring.h> + +struct io_buffer_list { + /* + * If ->buf_nr_pages is set, then buf_pages/buf_ring are used. If not, + * then these are classic provided buffers and ->buf_list is used. + */ + union { + struct list_head buf_list; + struct { + struct page **buf_pages; + struct io_uring_buf_ring *buf_ring; + }; + }; + __u16 bgid; + + /* below is for ring provided buffers */ + __u16 buf_nr_pages; + __u16 nr_entries; + __u16 head; + __u16 mask; +}; + +struct io_buffer { + struct list_head list; + __u64 addr; + __u32 len; + __u16 bid; + __u16 bgid; +}; + +void __user *io_buffer_select(struct io_kiocb *req, size_t *len, + unsigned int issue_flags); +void io_destroy_buffers(struct io_ring_ctx *ctx); + +int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags); + +int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags); + +int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); +int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); + +unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags); + +void io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags); + +static inline void io_kbuf_recycle_ring(struct io_kiocb *req) +{ + /* + * We don't need to recycle for REQ_F_BUFFER_RING, we can just clear + * the flag and hence ensure that bl->head doesn't get incremented. + * If the tail has already been incremented, hang on to it. + * The exception is partial io, that case we should increment bl->head + * to monopolize the buffer. + */ + if (req->buf_list) { + if (req->flags & REQ_F_PARTIAL_IO) { + /* + * If we end up here, then the io_uring_lock has + * been kept held since we retrieved the buffer. + * For the io-wq case, we already cleared + * req->buf_list when the buffer was retrieved, + * hence it cannot be set here for that case. + */ + req->buf_list->head++; + req->buf_list = NULL; + } else { + req->buf_index = req->buf_list->bgid; + req->flags &= ~REQ_F_BUFFER_RING; + } + } +} + +static inline bool io_do_buffer_select(struct io_kiocb *req) +{ + if (!(req->flags & REQ_F_BUFFER_SELECT)) + return false; + return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)); +} + +static inline void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags) +{ + /* + * READV uses fields in `struct io_rw` (len/addr) to stash the selected + * buffer data. However if that buffer is recycled the original request + * data stored in addr is lost. Therefore forbid recycling for now. + */ + if (req->opcode == IORING_OP_READV) + return; + + if (req->flags & REQ_F_BUFFER_SELECTED) + io_kbuf_recycle_legacy(req, issue_flags); + if (req->flags & REQ_F_BUFFER_RING) + io_kbuf_recycle_ring(req); +} + +static inline unsigned int __io_put_kbuf_list(struct io_kiocb *req, + struct list_head *list) +{ + unsigned int ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT); + + if (req->flags & REQ_F_BUFFER_RING) { + if (req->buf_list) { + req->buf_index = req->buf_list->bgid; + req->buf_list->head++; + } + req->flags &= ~REQ_F_BUFFER_RING; + } else { + req->buf_index = req->kbuf->bgid; + list_add(&req->kbuf->list, list); + req->flags &= ~REQ_F_BUFFER_SELECTED; + } + + return ret; +} + +static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req) +{ + lockdep_assert_held(&req->ctx->completion_lock); + + if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING))) + return 0; + return __io_put_kbuf_list(req, &req->ctx->io_buffers_comp); +} + +static inline unsigned int io_put_kbuf(struct io_kiocb *req, + unsigned issue_flags) +{ + + if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING))) + return 0; + return __io_put_kbuf(req, issue_flags); +} +#endif diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c new file mode 100644 index 000000000000..753d16734319 --- /dev/null +++ b/io_uring/msg_ring.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/slab.h> +#include <linux/nospec.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "rsrc.h" +#include "filetable.h" +#include "msg_ring.h" + +struct io_msg { + struct file *file; + u64 user_data; + u32 len; + u32 cmd; + u32 src_fd; + u32 dst_fd; + u32 flags; +}; + +static int io_msg_ring_data(struct io_kiocb *req) +{ + struct io_ring_ctx *target_ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req); + + if (msg->src_fd || msg->dst_fd || msg->flags) + return -EINVAL; + + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0, true)) + return 0; + + return -EOVERFLOW; +} + +static void io_double_unlock_ctx(struct io_ring_ctx *ctx, + struct io_ring_ctx *octx, + unsigned int issue_flags) +{ + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); + mutex_unlock(&octx->uring_lock); +} + +static int io_double_lock_ctx(struct io_ring_ctx *ctx, + struct io_ring_ctx *octx, + unsigned int issue_flags) +{ + /* + * To ensure proper ordering between the two ctxs, we can only + * attempt a trylock on the target. If that fails and we already have + * the source ctx lock, punt to io-wq. + */ + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + if (!mutex_trylock(&octx->uring_lock)) + return -EAGAIN; + return 0; + } + + /* Always grab smallest value ctx first. We know ctx != octx. */ + if (ctx < octx) { + mutex_lock(&ctx->uring_lock); + mutex_lock(&octx->uring_lock); + } else { + mutex_lock(&octx->uring_lock); + mutex_lock(&ctx->uring_lock); + } + + return 0; +} + +static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *target_ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + unsigned long file_ptr; + struct file *src_file; + int ret; + + if (target_ctx == ctx) + return -EINVAL; + + ret = io_double_lock_ctx(ctx, target_ctx, issue_flags); + if (unlikely(ret)) + return ret; + + ret = -EBADF; + if (unlikely(msg->src_fd >= ctx->nr_user_files)) + goto out_unlock; + + msg->src_fd = array_index_nospec(msg->src_fd, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, msg->src_fd)->file_ptr; + src_file = (struct file *) (file_ptr & FFS_MASK); + get_file(src_file); + + ret = __io_fixed_fd_install(target_ctx, src_file, msg->dst_fd); + if (ret < 0) { + fput(src_file); + goto out_unlock; + } + + if (msg->flags & IORING_MSG_RING_CQE_SKIP) + goto out_unlock; + + /* + * If this fails, the target still received the file descriptor but + * wasn't notified of the fact. This means that if this request + * completes with -EOVERFLOW, then the sender must ensure that a + * later IORING_OP_MSG_RING delivers the message. + */ + if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0, true)) + ret = -EOVERFLOW; +out_unlock: + io_double_unlock_ctx(ctx, target_ctx, issue_flags); + return ret; +} + +int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_msg *msg = io_kiocb_to_cmd(req); + + if (unlikely(sqe->buf_index || sqe->personality)) + return -EINVAL; + + msg->user_data = READ_ONCE(sqe->off); + msg->len = READ_ONCE(sqe->len); + msg->cmd = READ_ONCE(sqe->addr); + msg->src_fd = READ_ONCE(sqe->addr3); + msg->dst_fd = READ_ONCE(sqe->file_index); + msg->flags = READ_ONCE(sqe->msg_ring_flags); + if (msg->flags & ~IORING_MSG_RING_CQE_SKIP) + return -EINVAL; + + return 0; +} + +int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_msg *msg = io_kiocb_to_cmd(req); + int ret; + + ret = -EBADFD; + if (!io_is_uring_fops(req->file)) + goto done; + + switch (msg->cmd) { + case IORING_MSG_DATA: + ret = io_msg_ring_data(req); + break; + case IORING_MSG_SEND_FD: + ret = io_msg_send_fd(req, issue_flags); + break; + default: + ret = -EINVAL; + break; + } + +done: + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + /* put file to avoid an attempt to IOPOLL the req */ + io_put_file(req->file); + req->file = NULL; + return IOU_OK; +} diff --git a/io_uring/msg_ring.h b/io_uring/msg_ring.h new file mode 100644 index 000000000000..fb9601f202d0 --- /dev/null +++ b/io_uring/msg_ring.h @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 + +int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags); diff --git a/io_uring/net.c b/io_uring/net.c new file mode 100644 index 000000000000..e61efa31c729 --- /dev/null +++ b/io_uring/net.c @@ -0,0 +1,1047 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/slab.h> +#include <linux/net.h> +#include <linux/compat.h> +#include <net/compat.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "kbuf.h" +#include "alloc_cache.h" +#include "net.h" + +#if defined(CONFIG_NET) +struct io_shutdown { + struct file *file; + int how; +}; + +struct io_accept { + struct file *file; + struct sockaddr __user *addr; + int __user *addr_len; + int flags; + u32 file_slot; + unsigned long nofile; +}; + +struct io_socket { + struct file *file; + int domain; + int type; + int protocol; + int flags; + u32 file_slot; + unsigned long nofile; +}; + +struct io_connect { + struct file *file; + struct sockaddr __user *addr; + int addr_len; +}; + +struct io_sr_msg { + struct file *file; + union { + struct compat_msghdr __user *umsg_compat; + struct user_msghdr __user *umsg; + void __user *buf; + }; + int msg_flags; + size_t len; + size_t done_io; + unsigned int flags; +}; + +#define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED) + +int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_shutdown *shutdown = io_kiocb_to_cmd(req); + + if (unlikely(sqe->off || sqe->addr || sqe->rw_flags || + sqe->buf_index || sqe->splice_fd_in)) + return -EINVAL; + + shutdown->how = READ_ONCE(sqe->len); + return 0; +} + +int io_shutdown(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_shutdown *shutdown = io_kiocb_to_cmd(req); + struct socket *sock; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + sock = sock_from_file(req->file); + if (unlikely(!sock)) + return -ENOTSOCK; + + ret = __sys_shutdown_sock(sock, shutdown->how); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +static bool io_net_retry(struct socket *sock, int flags) +{ + if (!(flags & MSG_WAITALL)) + return false; + return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; +} + +static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_async_msghdr *hdr = req->async_data; + + if (!hdr || issue_flags & IO_URING_F_UNLOCKED) + return; + + /* Let normal cleanup path reap it if we fail adding to the cache */ + if (io_alloc_cache_put(&req->ctx->netmsg_cache, &hdr->cache)) { + req->async_data = NULL; + req->flags &= ~REQ_F_ASYNC_DATA; + } +} + +static struct io_async_msghdr *io_recvmsg_alloc_async(struct io_kiocb *req, + unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_cache_entry *entry; + + if (!(issue_flags & IO_URING_F_UNLOCKED) && + (entry = io_alloc_cache_get(&ctx->netmsg_cache)) != NULL) { + struct io_async_msghdr *hdr; + + hdr = container_of(entry, struct io_async_msghdr, cache); + req->flags |= REQ_F_ASYNC_DATA; + req->async_data = hdr; + return hdr; + } + + if (!io_alloc_async_data(req)) + return req->async_data; + + return NULL; +} + +static int io_setup_async_msg(struct io_kiocb *req, + struct io_async_msghdr *kmsg, + unsigned int issue_flags) +{ + struct io_async_msghdr *async_msg = req->async_data; + + if (async_msg) + return -EAGAIN; + async_msg = io_recvmsg_alloc_async(req, issue_flags); + if (!async_msg) { + kfree(kmsg->free_iov); + return -ENOMEM; + } + req->flags |= REQ_F_NEED_CLEANUP; + memcpy(async_msg, kmsg, sizeof(*kmsg)); + async_msg->msg.msg_name = &async_msg->addr; + /* if were using fast_iov, set it to the new one */ + if (!async_msg->free_iov) + async_msg->msg.msg_iter.iov = async_msg->fast_iov; + + return -EAGAIN; +} + +static int io_sendmsg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + + iomsg->msg.msg_name = &iomsg->addr; + iomsg->free_iov = iomsg->fast_iov; + return sendmsg_copy_msghdr(&iomsg->msg, sr->umsg, sr->msg_flags, + &iomsg->free_iov); +} + +int io_sendmsg_prep_async(struct io_kiocb *req) +{ + int ret; + + ret = io_sendmsg_copy_hdr(req, req->async_data); + if (!ret) + req->flags |= REQ_F_NEED_CLEANUP; + return ret; +} + +void io_sendmsg_recvmsg_cleanup(struct io_kiocb *req) +{ + struct io_async_msghdr *io = req->async_data; + + kfree(io->free_iov); +} + +int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + + if (unlikely(sqe->file_index || sqe->addr2)) + return -EINVAL; + + sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + sr->len = READ_ONCE(sqe->len); + sr->flags = READ_ONCE(sqe->ioprio); + if (sr->flags & ~IORING_RECVSEND_POLL_FIRST) + return -EINVAL; + sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; + if (sr->msg_flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + sr->done_io = 0; + return 0; +} + +int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + struct io_async_msghdr iomsg, *kmsg; + struct socket *sock; + unsigned flags; + int min_ret = 0; + int ret; + + sock = sock_from_file(req->file); + if (unlikely(!sock)) + return -ENOTSOCK; + + if (req_has_async_data(req)) { + kmsg = req->async_data; + } else { + ret = io_sendmsg_copy_hdr(req, &iomsg); + if (ret) + return ret; + kmsg = &iomsg; + } + + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return io_setup_async_msg(req, kmsg, issue_flags); + + flags = sr->msg_flags; + if (issue_flags & IO_URING_F_NONBLOCK) + flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL) + min_ret = iov_iter_count(&kmsg->msg.msg_iter); + + ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); + + if (ret < min_ret) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return io_setup_async_msg(req, kmsg, issue_flags); + if (ret == -ERESTARTSYS) + ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return io_setup_async_msg(req, kmsg, issue_flags); + } + req_set_fail(req); + } + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); + req->flags &= ~REQ_F_NEED_CLEANUP; + io_netmsg_recycle(req, issue_flags); + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +int io_send(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + struct msghdr msg; + struct iovec iov; + struct socket *sock; + unsigned flags; + int min_ret = 0; + int ret; + + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return -EAGAIN; + + sock = sock_from_file(req->file); + if (unlikely(!sock)) + return -ENOTSOCK; + + ret = import_single_range(WRITE, sr->buf, sr->len, &iov, &msg.msg_iter); + if (unlikely(ret)) + return ret; + + msg.msg_name = NULL; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_namelen = 0; + + flags = sr->msg_flags; + if (issue_flags & IO_URING_F_NONBLOCK) + flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL) + min_ret = iov_iter_count(&msg.msg_iter); + + msg.msg_flags = flags; + ret = sock_sendmsg(sock, &msg); + if (ret < min_ret) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->len -= ret; + sr->buf += ret; + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return -EAGAIN; + } + req_set_fail(req); + } + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +static bool io_recvmsg_multishot_overflow(struct io_async_msghdr *iomsg) +{ + int hdr; + + if (iomsg->namelen < 0) + return true; + if (check_add_overflow((int)sizeof(struct io_uring_recvmsg_out), + iomsg->namelen, &hdr)) + return true; + if (check_add_overflow(hdr, (int)iomsg->controllen, &hdr)) + return true; + + return false; +} + +static int __io_recvmsg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + struct user_msghdr msg; + int ret; + + if (copy_from_user(&msg, sr->umsg, sizeof(*sr->umsg))) + return -EFAULT; + + ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr); + if (ret) + return ret; + + if (req->flags & REQ_F_BUFFER_SELECT) { + if (msg.msg_iovlen == 0) { + sr->len = iomsg->fast_iov[0].iov_len = 0; + iomsg->fast_iov[0].iov_base = NULL; + iomsg->free_iov = NULL; + } else if (msg.msg_iovlen > 1) { + return -EINVAL; + } else { + if (copy_from_user(iomsg->fast_iov, msg.msg_iov, sizeof(*msg.msg_iov))) + return -EFAULT; + sr->len = iomsg->fast_iov[0].iov_len; + iomsg->free_iov = NULL; + } + + if (req->flags & REQ_F_APOLL_MULTISHOT) { + iomsg->namelen = msg.msg_namelen; + iomsg->controllen = msg.msg_controllen; + if (io_recvmsg_multishot_overflow(iomsg)) + return -EOVERFLOW; + } + } else { + iomsg->free_iov = iomsg->fast_iov; + ret = __import_iovec(READ, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, + &iomsg->free_iov, &iomsg->msg.msg_iter, + false); + if (ret > 0) + ret = 0; + } + + return ret; +} + +#ifdef CONFIG_COMPAT +static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + struct compat_msghdr msg; + struct compat_iovec __user *uiov; + int ret; + + if (copy_from_user(&msg, sr->umsg_compat, sizeof(msg))) + return -EFAULT; + + ret = __get_compat_msghdr(&iomsg->msg, &msg, &iomsg->uaddr); + if (ret) + return ret; + + uiov = compat_ptr(msg.msg_iov); + if (req->flags & REQ_F_BUFFER_SELECT) { + compat_ssize_t clen; + + if (msg.msg_iovlen == 0) { + sr->len = 0; + iomsg->free_iov = NULL; + } else if (msg.msg_iovlen > 1) { + return -EINVAL; + } else { + if (!access_ok(uiov, sizeof(*uiov))) + return -EFAULT; + if (__get_user(clen, &uiov->iov_len)) + return -EFAULT; + if (clen < 0) + return -EINVAL; + sr->len = clen; + iomsg->free_iov = NULL; + } + + if (req->flags & REQ_F_APOLL_MULTISHOT) { + iomsg->namelen = msg.msg_namelen; + iomsg->controllen = msg.msg_controllen; + if (io_recvmsg_multishot_overflow(iomsg)) + return -EOVERFLOW; + } + } else { + iomsg->free_iov = iomsg->fast_iov; + ret = __import_iovec(READ, (struct iovec __user *)uiov, msg.msg_iovlen, + UIO_FASTIOV, &iomsg->free_iov, + &iomsg->msg.msg_iter, true); + if (ret < 0) + return ret; + } + + return 0; +} +#endif + +static int io_recvmsg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg) +{ + iomsg->msg.msg_name = &iomsg->addr; + +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + return __io_compat_recvmsg_copy_hdr(req, iomsg); +#endif + + return __io_recvmsg_copy_hdr(req, iomsg); +} + +int io_recvmsg_prep_async(struct io_kiocb *req) +{ + int ret; + + ret = io_recvmsg_copy_hdr(req, req->async_data); + if (!ret) + req->flags |= REQ_F_NEED_CLEANUP; + return ret; +} + +#define RECVMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT) + +int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + + if (unlikely(sqe->file_index || sqe->addr2)) + return -EINVAL; + + sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + sr->len = READ_ONCE(sqe->len); + sr->flags = READ_ONCE(sqe->ioprio); + if (sr->flags & ~(RECVMSG_FLAGS)) + return -EINVAL; + sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; + if (sr->msg_flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + if (sr->msg_flags & MSG_ERRQUEUE) + req->flags |= REQ_F_CLEAR_POLLIN; + if (sr->flags & IORING_RECV_MULTISHOT) { + if (!(req->flags & REQ_F_BUFFER_SELECT)) + return -EINVAL; + if (sr->msg_flags & MSG_WAITALL) + return -EINVAL; + if (req->opcode == IORING_OP_RECV && sr->len) + return -EINVAL; + req->flags |= REQ_F_APOLL_MULTISHOT; + } + +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + sr->done_io = 0; + return 0; +} + +static inline void io_recv_prep_retry(struct io_kiocb *req) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + + sr->done_io = 0; + sr->len = 0; /* get from the provided buffer */ +} + +/* + * Finishes io_recv and io_recvmsg. + * + * Returns true if it is actually finished, or false if it should run + * again (for multishot). + */ +static inline bool io_recv_finish(struct io_kiocb *req, int *ret, + unsigned int cflags, bool mshot_finished) +{ + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + io_req_set_res(req, *ret, cflags); + *ret = IOU_OK; + return true; + } + + if (!mshot_finished) { + if (io_post_aux_cqe(req->ctx, req->cqe.user_data, *ret, + cflags | IORING_CQE_F_MORE, false)) { + io_recv_prep_retry(req); + return false; + } + /* + * Otherwise stop multishot but use the current result. + * Probably will end up going into overflow, but this means + * we cannot trust the ordering anymore + */ + } + + io_req_set_res(req, *ret, cflags); + + if (req->flags & REQ_F_POLLED) + *ret = IOU_STOP_MULTISHOT; + else + *ret = IOU_OK; + return true; +} + +static int io_recvmsg_prep_multishot(struct io_async_msghdr *kmsg, + struct io_sr_msg *sr, void __user **buf, + size_t *len) +{ + unsigned long ubuf = (unsigned long) *buf; + unsigned long hdr; + + hdr = sizeof(struct io_uring_recvmsg_out) + kmsg->namelen + + kmsg->controllen; + if (*len < hdr) + return -EFAULT; + + if (kmsg->controllen) { + unsigned long control = ubuf + hdr - kmsg->controllen; + + kmsg->msg.msg_control_user = (void *) control; + kmsg->msg.msg_controllen = kmsg->controllen; + } + + sr->buf = *buf; /* stash for later copy */ + *buf = (void *) (ubuf + hdr); + kmsg->payloadlen = *len = *len - hdr; + return 0; +} + +struct io_recvmsg_multishot_hdr { + struct io_uring_recvmsg_out msg; + struct sockaddr_storage addr; +}; + +static int io_recvmsg_multishot(struct socket *sock, struct io_sr_msg *io, + struct io_async_msghdr *kmsg, + unsigned int flags, bool *finished) +{ + int err; + int copy_len; + struct io_recvmsg_multishot_hdr hdr; + + if (kmsg->namelen) + kmsg->msg.msg_name = &hdr.addr; + kmsg->msg.msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); + kmsg->msg.msg_namelen = 0; + + if (sock->file->f_flags & O_NONBLOCK) + flags |= MSG_DONTWAIT; + + err = sock_recvmsg(sock, &kmsg->msg, flags); + *finished = err <= 0; + if (err < 0) + return err; + + hdr.msg = (struct io_uring_recvmsg_out) { + .controllen = kmsg->controllen - kmsg->msg.msg_controllen, + .flags = kmsg->msg.msg_flags & ~MSG_CMSG_COMPAT + }; + + hdr.msg.payloadlen = err; + if (err > kmsg->payloadlen) + err = kmsg->payloadlen; + + copy_len = sizeof(struct io_uring_recvmsg_out); + if (kmsg->msg.msg_namelen > kmsg->namelen) + copy_len += kmsg->namelen; + else + copy_len += kmsg->msg.msg_namelen; + + /* + * "fromlen shall refer to the value before truncation.." + * 1003.1g + */ + hdr.msg.namelen = kmsg->msg.msg_namelen; + + /* ensure that there is no gap between hdr and sockaddr_storage */ + BUILD_BUG_ON(offsetof(struct io_recvmsg_multishot_hdr, addr) != + sizeof(struct io_uring_recvmsg_out)); + if (copy_to_user(io->buf, &hdr, copy_len)) { + *finished = true; + return -EFAULT; + } + + return sizeof(struct io_uring_recvmsg_out) + kmsg->namelen + + kmsg->controllen + err; +} + +int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + struct io_async_msghdr iomsg, *kmsg; + struct socket *sock; + unsigned int cflags; + unsigned flags; + int ret, min_ret = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + bool mshot_finished = true; + + sock = sock_from_file(req->file); + if (unlikely(!sock)) + return -ENOTSOCK; + + if (req_has_async_data(req)) { + kmsg = req->async_data; + } else { + ret = io_recvmsg_copy_hdr(req, &iomsg); + if (ret) + return ret; + kmsg = &iomsg; + } + + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return io_setup_async_msg(req, kmsg, issue_flags); + +retry_multishot: + if (io_do_buffer_select(req)) { + void __user *buf; + size_t len = sr->len; + + buf = io_buffer_select(req, &len, issue_flags); + if (!buf) + return -ENOBUFS; + + if (req->flags & REQ_F_APOLL_MULTISHOT) { + ret = io_recvmsg_prep_multishot(kmsg, sr, &buf, &len); + if (ret) { + io_kbuf_recycle(req, issue_flags); + return ret; + } + } + + kmsg->fast_iov[0].iov_base = buf; + kmsg->fast_iov[0].iov_len = len; + iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, + len); + } + + flags = sr->msg_flags; + if (force_nonblock) + flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL) + min_ret = iov_iter_count(&kmsg->msg.msg_iter); + + kmsg->msg.msg_get_inq = 1; + if (req->flags & REQ_F_APOLL_MULTISHOT) + ret = io_recvmsg_multishot(sock, sr, kmsg, flags, + &mshot_finished); + else + ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, + kmsg->uaddr, flags); + + if (ret < min_ret) { + if (ret == -EAGAIN && force_nonblock) { + ret = io_setup_async_msg(req, kmsg, issue_flags); + if (ret == -EAGAIN && (req->flags & IO_APOLL_MULTI_POLLED) == + IO_APOLL_MULTI_POLLED) { + io_kbuf_recycle(req, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + return ret; + } + if (ret == -ERESTARTSYS) + ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return io_setup_async_msg(req, kmsg, issue_flags); + } + req_set_fail(req); + } else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { + req_set_fail(req); + } + + if (ret > 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; + else + io_kbuf_recycle(req, issue_flags); + + cflags = io_put_kbuf(req, issue_flags); + if (kmsg->msg.msg_inq) + cflags |= IORING_CQE_F_SOCK_NONEMPTY; + + if (!io_recv_finish(req, &ret, cflags, mshot_finished)) + goto retry_multishot; + + if (mshot_finished) { + io_netmsg_recycle(req, issue_flags); + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); + req->flags &= ~REQ_F_NEED_CLEANUP; + } + + return ret; +} + +int io_recv(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + struct msghdr msg; + struct socket *sock; + struct iovec iov; + unsigned int cflags; + unsigned flags; + int ret, min_ret = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + size_t len = sr->len; + + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return -EAGAIN; + + sock = sock_from_file(req->file); + if (unlikely(!sock)) + return -ENOTSOCK; + +retry_multishot: + if (io_do_buffer_select(req)) { + void __user *buf; + + buf = io_buffer_select(req, &len, issue_flags); + if (!buf) + return -ENOBUFS; + sr->buf = buf; + } + + ret = import_single_range(READ, sr->buf, len, &iov, &msg.msg_iter); + if (unlikely(ret)) + goto out_free; + + msg.msg_name = NULL; + msg.msg_namelen = 0; + msg.msg_control = NULL; + msg.msg_get_inq = 1; + msg.msg_flags = 0; + msg.msg_controllen = 0; + msg.msg_iocb = NULL; + + flags = sr->msg_flags; + if (force_nonblock) + flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL) + min_ret = iov_iter_count(&msg.msg_iter); + + ret = sock_recvmsg(sock, &msg, flags); + if (ret < min_ret) { + if (ret == -EAGAIN && force_nonblock) { + if ((req->flags & IO_APOLL_MULTI_POLLED) == IO_APOLL_MULTI_POLLED) { + io_kbuf_recycle(req, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + + return -EAGAIN; + } + if (ret == -ERESTARTSYS) + ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->len -= ret; + sr->buf += ret; + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return -EAGAIN; + } + req_set_fail(req); + } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { +out_free: + req_set_fail(req); + } + + if (ret > 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; + else + io_kbuf_recycle(req, issue_flags); + + cflags = io_put_kbuf(req, issue_flags); + if (msg.msg_inq) + cflags |= IORING_CQE_F_SOCK_NONEMPTY; + + if (!io_recv_finish(req, &ret, cflags, ret <= 0)) + goto retry_multishot; + + return ret; +} + +int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_accept *accept = io_kiocb_to_cmd(req); + unsigned flags; + + if (sqe->len || sqe->buf_index) + return -EINVAL; + + accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + accept->flags = READ_ONCE(sqe->accept_flags); + accept->nofile = rlimit(RLIMIT_NOFILE); + flags = READ_ONCE(sqe->ioprio); + if (flags & ~IORING_ACCEPT_MULTISHOT) + return -EINVAL; + + accept->file_slot = READ_ONCE(sqe->file_index); + if (accept->file_slot) { + if (accept->flags & SOCK_CLOEXEC) + return -EINVAL; + if (flags & IORING_ACCEPT_MULTISHOT && + accept->file_slot != IORING_FILE_INDEX_ALLOC) + return -EINVAL; + } + if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK)) + accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + if (flags & IORING_ACCEPT_MULTISHOT) + req->flags |= REQ_F_APOLL_MULTISHOT; + return 0; +} + +int io_accept(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_accept *accept = io_kiocb_to_cmd(req); + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0; + bool fixed = !!accept->file_slot; + struct file *file; + int ret, fd; + +retry: + if (!fixed) { + fd = __get_unused_fd_flags(accept->flags, accept->nofile); + if (unlikely(fd < 0)) + return fd; + } + file = do_accept(req->file, file_flags, accept->addr, accept->addr_len, + accept->flags); + if (IS_ERR(file)) { + if (!fixed) + put_unused_fd(fd); + ret = PTR_ERR(file); + if (ret == -EAGAIN && force_nonblock) { + /* + * if it's multishot and polled, we don't need to + * return EAGAIN to arm the poll infra since it + * has already been done + */ + if ((req->flags & IO_APOLL_MULTI_POLLED) == + IO_APOLL_MULTI_POLLED) + ret = IOU_ISSUE_SKIP_COMPLETE; + return ret; + } + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } else if (!fixed) { + fd_install(fd, file); + ret = fd; + } else { + ret = io_fixed_fd_install(req, issue_flags, file, + accept->file_slot); + } + + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + io_req_set_res(req, ret, 0); + return IOU_OK; + } + + if (ret >= 0 && + io_post_aux_cqe(ctx, req->cqe.user_data, ret, IORING_CQE_F_MORE, false)) + goto retry; + + io_req_set_res(req, ret, 0); + if (req->flags & REQ_F_POLLED) + return IOU_STOP_MULTISHOT; + return IOU_OK; +} + +int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_socket *sock = io_kiocb_to_cmd(req); + + if (sqe->addr || sqe->rw_flags || sqe->buf_index) + return -EINVAL; + + sock->domain = READ_ONCE(sqe->fd); + sock->type = READ_ONCE(sqe->off); + sock->protocol = READ_ONCE(sqe->len); + sock->file_slot = READ_ONCE(sqe->file_index); + sock->nofile = rlimit(RLIMIT_NOFILE); + + sock->flags = sock->type & ~SOCK_TYPE_MASK; + if (sock->file_slot && (sock->flags & SOCK_CLOEXEC)) + return -EINVAL; + if (sock->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + return 0; +} + +int io_socket(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_socket *sock = io_kiocb_to_cmd(req); + bool fixed = !!sock->file_slot; + struct file *file; + int ret, fd; + + if (!fixed) { + fd = __get_unused_fd_flags(sock->flags, sock->nofile); + if (unlikely(fd < 0)) + return fd; + } + file = __sys_socket_file(sock->domain, sock->type, sock->protocol); + if (IS_ERR(file)) { + if (!fixed) + put_unused_fd(fd); + ret = PTR_ERR(file); + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } else if (!fixed) { + fd_install(fd, file); + ret = fd; + } else { + ret = io_fixed_fd_install(req, issue_flags, file, + sock->file_slot); + } + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +int io_connect_prep_async(struct io_kiocb *req) +{ + struct io_async_connect *io = req->async_data; + struct io_connect *conn = io_kiocb_to_cmd(req); + + return move_addr_to_kernel(conn->addr, conn->addr_len, &io->address); +} + +int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_connect *conn = io_kiocb_to_cmd(req); + + if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) + return -EINVAL; + + conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + conn->addr_len = READ_ONCE(sqe->addr2); + return 0; +} + +int io_connect(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_connect *connect = io_kiocb_to_cmd(req); + struct io_async_connect __io, *io; + unsigned file_flags; + int ret; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + + if (req_has_async_data(req)) { + io = req->async_data; + } else { + ret = move_addr_to_kernel(connect->addr, + connect->addr_len, + &__io.address); + if (ret) + goto out; + io = &__io; + } + + file_flags = force_nonblock ? O_NONBLOCK : 0; + + ret = __sys_connect_file(req->file, &io->address, + connect->addr_len, file_flags); + if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) { + if (req_has_async_data(req)) + return -EAGAIN; + if (io_alloc_async_data(req)) { + ret = -ENOMEM; + goto out; + } + memcpy(req->async_data, &__io, sizeof(__io)); + return -EAGAIN; + } + if (ret == -ERESTARTSYS) + ret = -EINTR; +out: + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +void io_netmsg_cache_free(struct io_cache_entry *entry) +{ + kfree(container_of(entry, struct io_async_msghdr, cache)); +} +#endif diff --git a/io_uring/net.h b/io_uring/net.h new file mode 100644 index 000000000000..db20ce9d6546 --- /dev/null +++ b/io_uring/net.h @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/net.h> +#include <linux/uio.h> + +#include "alloc_cache.h" + +#if defined(CONFIG_NET) +struct io_async_msghdr { + union { + struct iovec fast_iov[UIO_FASTIOV]; + struct { + struct iovec fast_iov_one; + __kernel_size_t controllen; + int namelen; + __kernel_size_t payloadlen; + }; + struct io_cache_entry cache; + }; + /* points to an allocated iov, if NULL we use fast_iov instead */ + struct iovec *free_iov; + struct sockaddr __user *uaddr; + struct msghdr msg; + struct sockaddr_storage addr; +}; + +struct io_async_connect { + struct sockaddr_storage address; +}; + +int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_shutdown(struct io_kiocb *req, unsigned int issue_flags); + +int io_sendmsg_prep_async(struct io_kiocb *req); +void io_sendmsg_recvmsg_cleanup(struct io_kiocb *req); +int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags); +int io_send(struct io_kiocb *req, unsigned int issue_flags); + +int io_recvmsg_prep_async(struct io_kiocb *req); +int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags); +int io_recv(struct io_kiocb *req, unsigned int issue_flags); + +int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_accept(struct io_kiocb *req, unsigned int issue_flags); + +int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_socket(struct io_kiocb *req, unsigned int issue_flags); + +int io_connect_prep_async(struct io_kiocb *req); +int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_connect(struct io_kiocb *req, unsigned int issue_flags); + +void io_netmsg_cache_free(struct io_cache_entry *entry); +#else +static inline void io_netmsg_cache_free(struct io_cache_entry *entry) +{ +} +#endif diff --git a/io_uring/nop.c b/io_uring/nop.c new file mode 100644 index 000000000000..d956599a3c1b --- /dev/null +++ b/io_uring/nop.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "nop.h" + +int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + return 0; +} + +/* + * IORING_OP_NOP just posts a completion event, nothing else. + */ +int io_nop(struct io_kiocb *req, unsigned int issue_flags) +{ + io_req_set_res(req, 0, 0); + return IOU_OK; +} diff --git a/io_uring/nop.h b/io_uring/nop.h new file mode 100644 index 000000000000..97f1535c9dec --- /dev/null +++ b/io_uring/nop.h @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 + +int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_nop(struct io_kiocb *req, unsigned int issue_flags); diff --git a/io_uring/opdef.c b/io_uring/opdef.c new file mode 100644 index 000000000000..a7b84b43e6c2 --- /dev/null +++ b/io_uring/opdef.c @@ -0,0 +1,494 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * io_uring opcode handling table + */ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/io_uring.h> + +#include "io_uring.h" +#include "opdef.h" +#include "refs.h" +#include "tctx.h" +#include "sqpoll.h" +#include "fdinfo.h" +#include "kbuf.h" +#include "rsrc.h" + +#include "xattr.h" +#include "nop.h" +#include "fs.h" +#include "splice.h" +#include "sync.h" +#include "advise.h" +#include "openclose.h" +#include "uring_cmd.h" +#include "epoll.h" +#include "statx.h" +#include "net.h" +#include "msg_ring.h" +#include "timeout.h" +#include "poll.h" +#include "cancel.h" +#include "rw.h" + +static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags) +{ + WARN_ON_ONCE(1); + return -ECANCELED; +} + +static __maybe_unused int io_eopnotsupp_prep(struct io_kiocb *kiocb, + const struct io_uring_sqe *sqe) +{ + return -EOPNOTSUPP; +} + +const struct io_op_def io_op_defs[] = { + [IORING_OP_NOP] = { + .audit_skip = 1, + .iopoll = 1, + .name = "NOP", + .prep = io_nop_prep, + .issue = io_nop, + }, + [IORING_OP_READV] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .buffer_select = 1, + .plug = 1, + .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, + .async_size = sizeof(struct io_async_rw), + .name = "READV", + .prep = io_prep_rw, + .issue = io_read, + .prep_async = io_readv_prep_async, + .cleanup = io_readv_writev_cleanup, + }, + [IORING_OP_WRITEV] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .plug = 1, + .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, + .async_size = sizeof(struct io_async_rw), + .name = "WRITEV", + .prep = io_prep_rw, + .issue = io_write, + .prep_async = io_writev_prep_async, + .cleanup = io_readv_writev_cleanup, + }, + [IORING_OP_FSYNC] = { + .needs_file = 1, + .audit_skip = 1, + .name = "FSYNC", + .prep = io_fsync_prep, + .issue = io_fsync, + }, + [IORING_OP_READ_FIXED] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .plug = 1, + .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, + .async_size = sizeof(struct io_async_rw), + .name = "READ_FIXED", + .prep = io_prep_rw, + .issue = io_read, + }, + [IORING_OP_WRITE_FIXED] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .plug = 1, + .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, + .async_size = sizeof(struct io_async_rw), + .name = "WRITE_FIXED", + .prep = io_prep_rw, + .issue = io_write, + }, + [IORING_OP_POLL_ADD] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .audit_skip = 1, + .name = "POLL_ADD", + .prep = io_poll_add_prep, + .issue = io_poll_add, + }, + [IORING_OP_POLL_REMOVE] = { + .audit_skip = 1, + .name = "POLL_REMOVE", + .prep = io_poll_remove_prep, + .issue = io_poll_remove, + }, + [IORING_OP_SYNC_FILE_RANGE] = { + .needs_file = 1, + .audit_skip = 1, + .name = "SYNC_FILE_RANGE", + .prep = io_sfr_prep, + .issue = io_sync_file_range, + }, + [IORING_OP_SENDMSG] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .ioprio = 1, + .name = "SENDMSG", +#if defined(CONFIG_NET) + .async_size = sizeof(struct io_async_msghdr), + .prep = io_sendmsg_prep, + .issue = io_sendmsg, + .prep_async = io_sendmsg_prep_async, + .cleanup = io_sendmsg_recvmsg_cleanup, +#else + .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_RECVMSG] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .buffer_select = 1, + .ioprio = 1, + .name = "RECVMSG", +#if defined(CONFIG_NET) + .async_size = sizeof(struct io_async_msghdr), + .prep = io_recvmsg_prep, + .issue = io_recvmsg, + .prep_async = io_recvmsg_prep_async, + .cleanup = io_sendmsg_recvmsg_cleanup, +#else + .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_TIMEOUT] = { + .audit_skip = 1, + .async_size = sizeof(struct io_timeout_data), + .name = "TIMEOUT", + .prep = io_timeout_prep, + .issue = io_timeout, + }, + [IORING_OP_TIMEOUT_REMOVE] = { + /* used by timeout updates' prep() */ + .audit_skip = 1, + .name = "TIMEOUT_REMOVE", + .prep = io_timeout_remove_prep, + .issue = io_timeout_remove, + }, + [IORING_OP_ACCEPT] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .poll_exclusive = 1, + .ioprio = 1, /* used for flags */ + .name = "ACCEPT", +#if defined(CONFIG_NET) + .prep = io_accept_prep, + .issue = io_accept, +#else + .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_ASYNC_CANCEL] = { + .audit_skip = 1, + .name = "ASYNC_CANCEL", + .prep = io_async_cancel_prep, + .issue = io_async_cancel, + }, + [IORING_OP_LINK_TIMEOUT] = { + .audit_skip = 1, + .async_size = sizeof(struct io_timeout_data), + .name = "LINK_TIMEOUT", + .prep = io_link_timeout_prep, + .issue = io_no_issue, + }, + [IORING_OP_CONNECT] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .name = "CONNECT", +#if defined(CONFIG_NET) + .async_size = sizeof(struct io_async_connect), + .prep = io_connect_prep, + .issue = io_connect, + .prep_async = io_connect_prep_async, +#else + .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_FALLOCATE] = { + .needs_file = 1, + .name = "FALLOCATE", + .prep = io_fallocate_prep, + .issue = io_fallocate, + }, + [IORING_OP_OPENAT] = { + .name = "OPENAT", + .prep = io_openat_prep, + .issue = io_openat, + .cleanup = io_open_cleanup, + }, + [IORING_OP_CLOSE] = { + .name = "CLOSE", + .prep = io_close_prep, + .issue = io_close, + }, + [IORING_OP_FILES_UPDATE] = { + .audit_skip = 1, + .iopoll = 1, + .name = "FILES_UPDATE", + .prep = io_files_update_prep, + .issue = io_files_update, + }, + [IORING_OP_STATX] = { + .audit_skip = 1, + .name = "STATX", + .prep = io_statx_prep, + .issue = io_statx, + .cleanup = io_statx_cleanup, + }, + [IORING_OP_READ] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .buffer_select = 1, + .plug = 1, + .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, + .async_size = sizeof(struct io_async_rw), + .name = "READ", + .prep = io_prep_rw, + .issue = io_read, + }, + [IORING_OP_WRITE] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .plug = 1, + .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, + .async_size = sizeof(struct io_async_rw), + .name = "WRITE", + .prep = io_prep_rw, + .issue = io_write, + }, + [IORING_OP_FADVISE] = { + .needs_file = 1, + .audit_skip = 1, + .name = "FADVISE", + .prep = io_fadvise_prep, + .issue = io_fadvise, + }, + [IORING_OP_MADVISE] = { + .name = "MADVISE", + .prep = io_madvise_prep, + .issue = io_madvise, + }, + [IORING_OP_SEND] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .audit_skip = 1, + .ioprio = 1, + .name = "SEND", +#if defined(CONFIG_NET) + .prep = io_sendmsg_prep, + .issue = io_send, +#else + .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_RECV] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .buffer_select = 1, + .audit_skip = 1, + .ioprio = 1, + .name = "RECV", +#if defined(CONFIG_NET) + .prep = io_recvmsg_prep, + .issue = io_recv, +#else + .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_OPENAT2] = { + .name = "OPENAT2", + .prep = io_openat2_prep, + .issue = io_openat2, + .cleanup = io_open_cleanup, + }, + [IORING_OP_EPOLL_CTL] = { + .unbound_nonreg_file = 1, + .audit_skip = 1, + .name = "EPOLL", +#if defined(CONFIG_EPOLL) + .prep = io_epoll_ctl_prep, + .issue = io_epoll_ctl, +#else + .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_SPLICE] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + .audit_skip = 1, + .name = "SPLICE", + .prep = io_splice_prep, + .issue = io_splice, + }, + [IORING_OP_PROVIDE_BUFFERS] = { + .audit_skip = 1, + .iopoll = 1, + .name = "PROVIDE_BUFFERS", + .prep = io_provide_buffers_prep, + .issue = io_provide_buffers, + }, + [IORING_OP_REMOVE_BUFFERS] = { + .audit_skip = 1, + .iopoll = 1, + .name = "REMOVE_BUFFERS", + .prep = io_remove_buffers_prep, + .issue = io_remove_buffers, + }, + [IORING_OP_TEE] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + .audit_skip = 1, + .name = "TEE", + .prep = io_tee_prep, + .issue = io_tee, + }, + [IORING_OP_SHUTDOWN] = { + .needs_file = 1, + .name = "SHUTDOWN", +#if defined(CONFIG_NET) + .prep = io_shutdown_prep, + .issue = io_shutdown, +#else + .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_RENAMEAT] = { + .name = "RENAMEAT", + .prep = io_renameat_prep, + .issue = io_renameat, + .cleanup = io_renameat_cleanup, + }, + [IORING_OP_UNLINKAT] = { + .name = "UNLINKAT", + .prep = io_unlinkat_prep, + .issue = io_unlinkat, + .cleanup = io_unlinkat_cleanup, + }, + [IORING_OP_MKDIRAT] = { + .name = "MKDIRAT", + .prep = io_mkdirat_prep, + .issue = io_mkdirat, + .cleanup = io_mkdirat_cleanup, + }, + [IORING_OP_SYMLINKAT] = { + .name = "SYMLINKAT", + .prep = io_symlinkat_prep, + .issue = io_symlinkat, + .cleanup = io_link_cleanup, + }, + [IORING_OP_LINKAT] = { + .name = "LINKAT", + .prep = io_linkat_prep, + .issue = io_linkat, + .cleanup = io_link_cleanup, + }, + [IORING_OP_MSG_RING] = { + .needs_file = 1, + .iopoll = 1, + .name = "MSG_RING", + .prep = io_msg_ring_prep, + .issue = io_msg_ring, + }, + [IORING_OP_FSETXATTR] = { + .needs_file = 1, + .name = "FSETXATTR", + .prep = io_fsetxattr_prep, + .issue = io_fsetxattr, + .cleanup = io_xattr_cleanup, + }, + [IORING_OP_SETXATTR] = { + .name = "SETXATTR", + .prep = io_setxattr_prep, + .issue = io_setxattr, + .cleanup = io_xattr_cleanup, + }, + [IORING_OP_FGETXATTR] = { + .needs_file = 1, + .name = "FGETXATTR", + .prep = io_fgetxattr_prep, + .issue = io_fgetxattr, + .cleanup = io_xattr_cleanup, + }, + [IORING_OP_GETXATTR] = { + .name = "GETXATTR", + .prep = io_getxattr_prep, + .issue = io_getxattr, + .cleanup = io_xattr_cleanup, + }, + [IORING_OP_SOCKET] = { + .audit_skip = 1, + .name = "SOCKET", +#if defined(CONFIG_NET) + .prep = io_socket_prep, + .issue = io_socket, +#else + .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_URING_CMD] = { + .needs_file = 1, + .plug = 1, + .name = "URING_CMD", + .async_size = uring_cmd_pdu_size(1), + .prep = io_uring_cmd_prep, + .issue = io_uring_cmd, + .prep_async = io_uring_cmd_prep_async, + }, +}; + +const char *io_uring_get_opcode(u8 opcode) +{ + if (opcode < IORING_OP_LAST) + return io_op_defs[opcode].name; + return "INVALID"; +} + +void __init io_uring_optable_init(void) +{ + int i; + + BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); + + for (i = 0; i < ARRAY_SIZE(io_op_defs); i++) { + BUG_ON(!io_op_defs[i].prep); + if (io_op_defs[i].prep != io_eopnotsupp_prep) + BUG_ON(!io_op_defs[i].issue); + WARN_ON_ONCE(!io_op_defs[i].name); + } +} diff --git a/io_uring/opdef.h b/io_uring/opdef.h new file mode 100644 index 000000000000..ece8ed4f96c4 --- /dev/null +++ b/io_uring/opdef.h @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef IOU_OP_DEF_H +#define IOU_OP_DEF_H + +struct io_op_def { + /* needs req->file assigned */ + unsigned needs_file : 1; + /* should block plug */ + unsigned plug : 1; + /* hash wq insertion if file is a regular file */ + unsigned hash_reg_file : 1; + /* unbound wq insertion if file is a non-regular file */ + unsigned unbound_nonreg_file : 1; + /* set if opcode supports polled "wait" */ + unsigned pollin : 1; + unsigned pollout : 1; + unsigned poll_exclusive : 1; + /* op supports buffer selection */ + unsigned buffer_select : 1; + /* opcode is not supported by this kernel */ + unsigned not_supported : 1; + /* skip auditing */ + unsigned audit_skip : 1; + /* supports ioprio */ + unsigned ioprio : 1; + /* supports iopoll */ + unsigned iopoll : 1; + /* size of async data needed, if any */ + unsigned short async_size; + + const char *name; + + int (*prep)(struct io_kiocb *, const struct io_uring_sqe *); + int (*issue)(struct io_kiocb *, unsigned int); + int (*prep_async)(struct io_kiocb *); + void (*cleanup)(struct io_kiocb *); +}; + +extern const struct io_op_def io_op_defs[]; + +void io_uring_optable_init(void); +#endif diff --git a/io_uring/openclose.c b/io_uring/openclose.c new file mode 100644 index 000000000000..d1818ec9169b --- /dev/null +++ b/io_uring/openclose.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/fdtable.h> +#include <linux/fsnotify.h> +#include <linux/namei.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "../fs/internal.h" + +#include "io_uring.h" +#include "rsrc.h" +#include "openclose.h" + +struct io_open { + struct file *file; + int dfd; + u32 file_slot; + struct filename *filename; + struct open_how how; + unsigned long nofile; +}; + +struct io_close { + struct file *file; + int fd; + u32 file_slot; +}; + +static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_open *open = io_kiocb_to_cmd(req); + const char __user *fname; + int ret; + + if (unlikely(sqe->buf_index)) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + /* open.how should be already initialised */ + if (!(open->how.flags & O_PATH) && force_o_largefile()) + open->how.flags |= O_LARGEFILE; + + open->dfd = READ_ONCE(sqe->fd); + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); + open->filename = getname(fname); + if (IS_ERR(open->filename)) { + ret = PTR_ERR(open->filename); + open->filename = NULL; + return ret; + } + + open->file_slot = READ_ONCE(sqe->file_index); + if (open->file_slot && (open->how.flags & O_CLOEXEC)) + return -EINVAL; + + open->nofile = rlimit(RLIMIT_NOFILE); + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_open *open = io_kiocb_to_cmd(req); + u64 mode = READ_ONCE(sqe->len); + u64 flags = READ_ONCE(sqe->open_flags); + + open->how = build_open_how(flags, mode); + return __io_openat_prep(req, sqe); +} + +int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_open *open = io_kiocb_to_cmd(req); + struct open_how __user *how; + size_t len; + int ret; + + how = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + len = READ_ONCE(sqe->len); + if (len < OPEN_HOW_SIZE_VER0) + return -EINVAL; + + ret = copy_struct_from_user(&open->how, sizeof(open->how), how, len); + if (ret) + return ret; + + return __io_openat_prep(req, sqe); +} + +int io_openat2(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_open *open = io_kiocb_to_cmd(req); + struct open_flags op; + struct file *file; + bool resolve_nonblock, nonblock_set; + bool fixed = !!open->file_slot; + int ret; + + ret = build_open_flags(&open->how, &op); + if (ret) + goto err; + nonblock_set = op.open_flag & O_NONBLOCK; + resolve_nonblock = open->how.resolve & RESOLVE_CACHED; + if (issue_flags & IO_URING_F_NONBLOCK) { + /* + * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open, + * it'll always -EAGAIN + */ + if (open->how.flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + return -EAGAIN; + op.lookup_flags |= LOOKUP_CACHED; + op.open_flag |= O_NONBLOCK; + } + + if (!fixed) { + ret = __get_unused_fd_flags(open->how.flags, open->nofile); + if (ret < 0) + goto err; + } + + file = do_filp_open(open->dfd, open->filename, &op); + if (IS_ERR(file)) { + /* + * We could hang on to this 'fd' on retrying, but seems like + * marginal gain for something that is now known to be a slower + * path. So just put it, and we'll get a new one when we retry. + */ + if (!fixed) + put_unused_fd(ret); + + ret = PTR_ERR(file); + /* only retry if RESOLVE_CACHED wasn't already set by application */ + if (ret == -EAGAIN && + (!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK))) + return -EAGAIN; + goto err; + } + + if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set) + file->f_flags &= ~O_NONBLOCK; + fsnotify_open(file); + + if (!fixed) + fd_install(ret, file); + else + ret = io_fixed_fd_install(req, issue_flags, file, + open->file_slot); +err: + putname(open->filename); + req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +int io_openat(struct io_kiocb *req, unsigned int issue_flags) +{ + return io_openat2(req, issue_flags); +} + +void io_open_cleanup(struct io_kiocb *req) +{ + struct io_open *open = io_kiocb_to_cmd(req); + + if (open->filename) + putname(open->filename); +} + +int __io_close_fixed(struct io_ring_ctx *ctx, unsigned int issue_flags, + unsigned int offset) +{ + int ret; + + io_ring_submit_lock(ctx, issue_flags); + ret = io_fixed_fd_remove(ctx, offset); + io_ring_submit_unlock(ctx, issue_flags); + + return ret; +} + +static inline int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_close *close = io_kiocb_to_cmd(req); + + return __io_close_fixed(req->ctx, issue_flags, close->file_slot - 1); +} + +int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_close *close = io_kiocb_to_cmd(req); + + if (sqe->off || sqe->addr || sqe->len || sqe->rw_flags || sqe->buf_index) + return -EINVAL; + if (req->flags & REQ_F_FIXED_FILE) + return -EBADF; + + close->fd = READ_ONCE(sqe->fd); + close->file_slot = READ_ONCE(sqe->file_index); + if (close->file_slot && close->fd) + return -EINVAL; + + return 0; +} + +int io_close(struct io_kiocb *req, unsigned int issue_flags) +{ + struct files_struct *files = current->files; + struct io_close *close = io_kiocb_to_cmd(req); + struct fdtable *fdt; + struct file *file; + int ret = -EBADF; + + if (close->file_slot) { + ret = io_close_fixed(req, issue_flags); + goto err; + } + + spin_lock(&files->file_lock); + fdt = files_fdtable(files); + if (close->fd >= fdt->max_fds) { + spin_unlock(&files->file_lock); + goto err; + } + file = rcu_dereference_protected(fdt->fd[close->fd], + lockdep_is_held(&files->file_lock)); + if (!file || io_is_uring_fops(file)) { + spin_unlock(&files->file_lock); + goto err; + } + + /* if the file has a flush method, be safe and punt to async */ + if (file->f_op->flush && (issue_flags & IO_URING_F_NONBLOCK)) { + spin_unlock(&files->file_lock); + return -EAGAIN; + } + + file = __close_fd_get_file(close->fd); + spin_unlock(&files->file_lock); + if (!file) + goto err; + + /* No ->flush() or already async, safely close from here */ + ret = filp_close(file, current->files); +err: + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} diff --git a/io_uring/openclose.h b/io_uring/openclose.h new file mode 100644 index 000000000000..4b1c28d3a66c --- /dev/null +++ b/io_uring/openclose.h @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 + +int __io_close_fixed(struct io_ring_ctx *ctx, unsigned int issue_flags, + unsigned int offset); + +int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_openat(struct io_kiocb *req, unsigned int issue_flags); +void io_open_cleanup(struct io_kiocb *req); + +int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_openat2(struct io_kiocb *req, unsigned int issue_flags); + +int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_close(struct io_kiocb *req, unsigned int issue_flags); diff --git a/io_uring/poll.c b/io_uring/poll.c new file mode 100644 index 000000000000..dadd293749b0 --- /dev/null +++ b/io_uring/poll.c @@ -0,0 +1,965 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/poll.h> +#include <linux/hashtable.h> +#include <linux/io_uring.h> + +#include <trace/events/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "refs.h" +#include "opdef.h" +#include "kbuf.h" +#include "poll.h" +#include "cancel.h" + +struct io_poll_update { + struct file *file; + u64 old_user_data; + u64 new_user_data; + __poll_t events; + bool update_events; + bool update_user_data; +}; + +struct io_poll_table { + struct poll_table_struct pt; + struct io_kiocb *req; + int nr_entries; + int error; + bool owning; + /* output value, set only if arm poll returns >0 */ + __poll_t result_mask; +}; + +#define IO_POLL_CANCEL_FLAG BIT(31) +#define IO_POLL_REF_MASK GENMASK(30, 0) + +#define IO_WQE_F_DOUBLE 1 + +static inline struct io_kiocb *wqe_to_req(struct wait_queue_entry *wqe) +{ + unsigned long priv = (unsigned long)wqe->private; + + return (struct io_kiocb *)(priv & ~IO_WQE_F_DOUBLE); +} + +static inline bool wqe_is_double(struct wait_queue_entry *wqe) +{ + unsigned long priv = (unsigned long)wqe->private; + + return priv & IO_WQE_F_DOUBLE; +} + +/* + * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can + * bump it and acquire ownership. It's disallowed to modify requests while not + * owning it, that prevents from races for enqueueing task_work's and b/w + * arming poll and wakeups. + */ +static inline bool io_poll_get_ownership(struct io_kiocb *req) +{ + return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); +} + +static void io_poll_mark_cancelled(struct io_kiocb *req) +{ + atomic_or(IO_POLL_CANCEL_FLAG, &req->poll_refs); +} + +static struct io_poll *io_poll_get_double(struct io_kiocb *req) +{ + /* pure poll stashes this in ->async_data, poll driven retry elsewhere */ + if (req->opcode == IORING_OP_POLL_ADD) + return req->async_data; + return req->apoll->double_poll; +} + +static struct io_poll *io_poll_get_single(struct io_kiocb *req) +{ + if (req->opcode == IORING_OP_POLL_ADD) + return io_kiocb_to_cmd(req); + return &req->apoll->poll; +} + +static void io_poll_req_insert(struct io_kiocb *req) +{ + struct io_hash_table *table = &req->ctx->cancel_table; + u32 index = hash_long(req->cqe.user_data, table->hash_bits); + struct io_hash_bucket *hb = &table->hbs[index]; + + spin_lock(&hb->lock); + hlist_add_head(&req->hash_node, &hb->list); + spin_unlock(&hb->lock); +} + +static void io_poll_req_delete(struct io_kiocb *req, struct io_ring_ctx *ctx) +{ + struct io_hash_table *table = &req->ctx->cancel_table; + u32 index = hash_long(req->cqe.user_data, table->hash_bits); + spinlock_t *lock = &table->hbs[index].lock; + + spin_lock(lock); + hash_del(&req->hash_node); + spin_unlock(lock); +} + +static void io_poll_req_insert_locked(struct io_kiocb *req) +{ + struct io_hash_table *table = &req->ctx->cancel_table_locked; + u32 index = hash_long(req->cqe.user_data, table->hash_bits); + + hlist_add_head(&req->hash_node, &table->hbs[index].list); +} + +static void io_poll_tw_hash_eject(struct io_kiocb *req, bool *locked) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (req->flags & REQ_F_HASH_LOCKED) { + /* + * ->cancel_table_locked is protected by ->uring_lock in + * contrast to per bucket spinlocks. Likely, tctx_task_work() + * already grabbed the mutex for us, but there is a chance it + * failed. + */ + io_tw_lock(ctx, locked); + hash_del(&req->hash_node); + req->flags &= ~REQ_F_HASH_LOCKED; + } else { + io_poll_req_delete(req, ctx); + } +} + +static void io_init_poll_iocb(struct io_poll *poll, __poll_t events, + wait_queue_func_t wake_func) +{ + poll->head = NULL; +#define IO_POLL_UNMASK (EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP) + /* mask in events that we always want/need */ + poll->events = events | IO_POLL_UNMASK; + INIT_LIST_HEAD(&poll->wait.entry); + init_waitqueue_func_entry(&poll->wait, wake_func); +} + +static inline void io_poll_remove_entry(struct io_poll *poll) +{ + struct wait_queue_head *head = smp_load_acquire(&poll->head); + + if (head) { + spin_lock_irq(&head->lock); + list_del_init(&poll->wait.entry); + poll->head = NULL; + spin_unlock_irq(&head->lock); + } +} + +static void io_poll_remove_entries(struct io_kiocb *req) +{ + /* + * Nothing to do if neither of those flags are set. Avoid dipping + * into the poll/apoll/double cachelines if we can. + */ + if (!(req->flags & (REQ_F_SINGLE_POLL | REQ_F_DOUBLE_POLL))) + return; + + /* + * While we hold the waitqueue lock and the waitqueue is nonempty, + * wake_up_pollfree() will wait for us. However, taking the waitqueue + * lock in the first place can race with the waitqueue being freed. + * + * We solve this as eventpoll does: by taking advantage of the fact that + * all users of wake_up_pollfree() will RCU-delay the actual free. If + * we enter rcu_read_lock() and see that the pointer to the queue is + * non-NULL, we can then lock it without the memory being freed out from + * under us. + * + * Keep holding rcu_read_lock() as long as we hold the queue lock, in + * case the caller deletes the entry from the queue, leaving it empty. + * In that case, only RCU prevents the queue memory from being freed. + */ + rcu_read_lock(); + if (req->flags & REQ_F_SINGLE_POLL) + io_poll_remove_entry(io_poll_get_single(req)); + if (req->flags & REQ_F_DOUBLE_POLL) + io_poll_remove_entry(io_poll_get_double(req)); + rcu_read_unlock(); +} + +enum { + IOU_POLL_DONE = 0, + IOU_POLL_NO_ACTION = 1, + IOU_POLL_REMOVE_POLL_USE_RES = 2, +}; + +/* + * All poll tw should go through this. Checks for poll events, manages + * references, does rewait, etc. + * + * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action require, + * which is either spurious wakeup or multishot CQE is served. + * IOU_POLL_DONE when it's done with the request, then the mask is stored in req->cqe.res. + * IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot poll and that the result + * is stored in req->cqe. + */ +static int io_poll_check_events(struct io_kiocb *req, bool *locked) +{ + struct io_ring_ctx *ctx = req->ctx; + int v, ret; + + /* req->task == current here, checking PF_EXITING is safe */ + if (unlikely(req->task->flags & PF_EXITING)) + return -ECANCELED; + + do { + v = atomic_read(&req->poll_refs); + + /* tw handler should be the owner, and so have some references */ + if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK))) + return IOU_POLL_DONE; + if (v & IO_POLL_CANCEL_FLAG) + return -ECANCELED; + + /* the mask was stashed in __io_poll_execute */ + if (!req->cqe.res) { + struct poll_table_struct pt = { ._key = req->apoll_events }; + req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events; + } + + if ((unlikely(!req->cqe.res))) + continue; + if (req->apoll_events & EPOLLONESHOT) + return IOU_POLL_DONE; + + /* multishot, just fill a CQE and proceed */ + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + __poll_t mask = mangle_poll(req->cqe.res & + req->apoll_events); + + if (!io_post_aux_cqe(ctx, req->cqe.user_data, + mask, IORING_CQE_F_MORE, false)) { + io_req_set_res(req, mask, 0); + return IOU_POLL_REMOVE_POLL_USE_RES; + } + } else { + ret = io_poll_issue(req, locked); + if (ret == IOU_STOP_MULTISHOT) + return IOU_POLL_REMOVE_POLL_USE_RES; + if (ret < 0) + return ret; + } + + /* + * Release all references, retry if someone tried to restart + * task_work while we were executing it. + */ + } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs)); + + return IOU_POLL_NO_ACTION; +} + +static void io_poll_task_func(struct io_kiocb *req, bool *locked) +{ + int ret; + + ret = io_poll_check_events(req, locked); + if (ret == IOU_POLL_NO_ACTION) + return; + + if (ret == IOU_POLL_DONE) { + struct io_poll *poll = io_kiocb_to_cmd(req); + req->cqe.res = mangle_poll(req->cqe.res & poll->events); + } else if (ret != IOU_POLL_REMOVE_POLL_USE_RES) { + req->cqe.res = ret; + req_set_fail(req); + } + + io_poll_remove_entries(req); + io_poll_tw_hash_eject(req, locked); + + io_req_set_res(req, req->cqe.res, 0); + io_req_task_complete(req, locked); +} + +static void io_apoll_task_func(struct io_kiocb *req, bool *locked) +{ + int ret; + + ret = io_poll_check_events(req, locked); + if (ret == IOU_POLL_NO_ACTION) + return; + + io_poll_remove_entries(req); + io_poll_tw_hash_eject(req, locked); + + if (ret == IOU_POLL_REMOVE_POLL_USE_RES) + io_req_complete_post(req); + else if (ret == IOU_POLL_DONE) + io_req_task_submit(req, locked); + else + io_req_complete_failed(req, ret); +} + +static void __io_poll_execute(struct io_kiocb *req, int mask) +{ + io_req_set_res(req, mask, 0); + /* + * This is useful for poll that is armed on behalf of another + * request, and where the wakeup path could be on a different + * CPU. We want to avoid pulling in req->apoll->events for that + * case. + */ + if (req->opcode == IORING_OP_POLL_ADD) + req->io_task_work.func = io_poll_task_func; + else + req->io_task_work.func = io_apoll_task_func; + + trace_io_uring_task_add(req, mask); + io_req_task_work_add(req); +} + +static inline void io_poll_execute(struct io_kiocb *req, int res) +{ + if (io_poll_get_ownership(req)) + __io_poll_execute(req, res); +} + +static void io_poll_cancel_req(struct io_kiocb *req) +{ + io_poll_mark_cancelled(req); + /* kick tw, which should complete the request */ + io_poll_execute(req, 0); +} + +#define IO_ASYNC_POLL_COMMON (EPOLLONESHOT | EPOLLPRI) + +static __cold int io_pollfree_wake(struct io_kiocb *req, struct io_poll *poll) +{ + io_poll_mark_cancelled(req); + /* we have to kick tw in case it's not already */ + io_poll_execute(req, 0); + + /* + * If the waitqueue is being freed early but someone is already + * holds ownership over it, we have to tear down the request as + * best we can. That means immediately removing the request from + * its waitqueue and preventing all further accesses to the + * waitqueue via the request. + */ + list_del_init(&poll->wait.entry); + + /* + * Careful: this *must* be the last step, since as soon + * as req->head is NULL'ed out, the request can be + * completed and freed, since aio_poll_complete_work() + * will no longer need to take the waitqueue lock. + */ + smp_store_release(&poll->head, NULL); + return 1; +} + +static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, + void *key) +{ + struct io_kiocb *req = wqe_to_req(wait); + struct io_poll *poll = container_of(wait, struct io_poll, wait); + __poll_t mask = key_to_poll(key); + + if (unlikely(mask & POLLFREE)) + return io_pollfree_wake(req, poll); + + /* for instances that support it check for an event match first */ + if (mask && !(mask & (poll->events & ~IO_ASYNC_POLL_COMMON))) + return 0; + + if (io_poll_get_ownership(req)) { + /* optional, saves extra locking for removal in tw handler */ + if (mask && poll->events & EPOLLONESHOT) { + list_del_init(&poll->wait.entry); + poll->head = NULL; + if (wqe_is_double(wait)) + req->flags &= ~REQ_F_DOUBLE_POLL; + else + req->flags &= ~REQ_F_SINGLE_POLL; + } + __io_poll_execute(req, mask); + } + return 1; +} + +static void io_poll_double_prepare(struct io_kiocb *req) +{ + struct wait_queue_head *head; + struct io_poll *poll = io_poll_get_single(req); + + /* head is RCU protected, see io_poll_remove_entries() comments */ + rcu_read_lock(); + head = smp_load_acquire(&poll->head); + /* + * poll arm may not hold ownership and so race with + * io_poll_wake() by modifying req->flags. There is only one + * poll entry queued, serialise with it by taking its head lock. + */ + if (head) + spin_lock_irq(&head->lock); + + req->flags |= REQ_F_DOUBLE_POLL; + if (req->opcode == IORING_OP_POLL_ADD) + req->flags |= REQ_F_ASYNC_DATA; + + if (head) + spin_unlock_irq(&head->lock); + rcu_read_unlock(); +} + +static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt, + struct wait_queue_head *head, + struct io_poll **poll_ptr) +{ + struct io_kiocb *req = pt->req; + unsigned long wqe_private = (unsigned long) req; + + /* + * The file being polled uses multiple waitqueues for poll handling + * (e.g. one for read, one for write). Setup a separate io_poll + * if this happens. + */ + if (unlikely(pt->nr_entries)) { + struct io_poll *first = poll; + + /* double add on the same waitqueue head, ignore */ + if (first->head == head) + return; + /* already have a 2nd entry, fail a third attempt */ + if (*poll_ptr) { + if ((*poll_ptr)->head == head) + return; + pt->error = -EINVAL; + return; + } + + poll = kmalloc(sizeof(*poll), GFP_ATOMIC); + if (!poll) { + pt->error = -ENOMEM; + return; + } + + /* mark as double wq entry */ + wqe_private |= IO_WQE_F_DOUBLE; + io_init_poll_iocb(poll, first->events, first->wait.func); + io_poll_double_prepare(req); + *poll_ptr = poll; + } else { + /* fine to modify, there is no poll queued to race with us */ + req->flags |= REQ_F_SINGLE_POLL; + } + + pt->nr_entries++; + poll->head = head; + poll->wait.private = (void *) wqe_private; + + if (poll->events & EPOLLEXCLUSIVE) + add_wait_queue_exclusive(head, &poll->wait); + else + add_wait_queue(head, &poll->wait); +} + +static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, + struct poll_table_struct *p) +{ + struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); + struct io_poll *poll = io_kiocb_to_cmd(pt->req); + + __io_queue_proc(poll, pt, head, + (struct io_poll **) &pt->req->async_data); +} + +static bool io_poll_can_finish_inline(struct io_kiocb *req, + struct io_poll_table *pt) +{ + return pt->owning || io_poll_get_ownership(req); +} + +/* + * Returns 0 when it's handed over for polling. The caller owns the requests if + * it returns non-zero, but otherwise should not touch it. Negative values + * contain an error code. When the result is >0, the polling has completed + * inline and ipt.result_mask is set to the mask. + */ +static int __io_arm_poll_handler(struct io_kiocb *req, + struct io_poll *poll, + struct io_poll_table *ipt, __poll_t mask, + unsigned issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + int v; + + INIT_HLIST_NODE(&req->hash_node); + req->work.cancel_seq = atomic_read(&ctx->cancel_seq); + io_init_poll_iocb(poll, mask, io_poll_wake); + poll->file = req->file; + req->apoll_events = poll->events; + + ipt->pt._key = mask; + ipt->req = req; + ipt->error = 0; + ipt->nr_entries = 0; + /* + * Polling is either completed here or via task_work, so if we're in the + * task context we're naturally serialised with tw by merit of running + * the same task. When it's io-wq, take the ownership to prevent tw + * from running. However, when we're in the task context, skip taking + * it as an optimisation. + * + * Note: even though the request won't be completed/freed, without + * ownership we still can race with io_poll_wake(). + * io_poll_can_finish_inline() tries to deal with that. + */ + ipt->owning = issue_flags & IO_URING_F_UNLOCKED; + atomic_set(&req->poll_refs, (int)ipt->owning); + + /* io-wq doesn't hold uring_lock */ + if (issue_flags & IO_URING_F_UNLOCKED) + req->flags &= ~REQ_F_HASH_LOCKED; + + mask = vfs_poll(req->file, &ipt->pt) & poll->events; + + if (unlikely(ipt->error || !ipt->nr_entries)) { + io_poll_remove_entries(req); + + if (!io_poll_can_finish_inline(req, ipt)) { + io_poll_mark_cancelled(req); + return 0; + } else if (mask && (poll->events & EPOLLET)) { + ipt->result_mask = mask; + return 1; + } + return ipt->error ?: -EINVAL; + } + + if (mask && + ((poll->events & (EPOLLET|EPOLLONESHOT)) == (EPOLLET|EPOLLONESHOT))) { + if (!io_poll_can_finish_inline(req, ipt)) + return 0; + io_poll_remove_entries(req); + ipt->result_mask = mask; + /* no one else has access to the req, forget about the ref */ + return 1; + } + + if (req->flags & REQ_F_HASH_LOCKED) + io_poll_req_insert_locked(req); + else + io_poll_req_insert(req); + + if (mask && (poll->events & EPOLLET) && + io_poll_can_finish_inline(req, ipt)) { + __io_poll_execute(req, mask); + return 0; + } + + if (ipt->owning) { + /* + * Release ownership. If someone tried to queue a tw while it was + * locked, kick it off for them. + */ + v = atomic_dec_return(&req->poll_refs); + if (unlikely(v & IO_POLL_REF_MASK)) + __io_poll_execute(req, 0); + } + return 0; +} + +static void io_async_queue_proc(struct file *file, struct wait_queue_head *head, + struct poll_table_struct *p) +{ + struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); + struct async_poll *apoll = pt->req->apoll; + + __io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll); +} + +static struct async_poll *io_req_alloc_apoll(struct io_kiocb *req, + unsigned issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_cache_entry *entry; + struct async_poll *apoll; + + if (req->flags & REQ_F_POLLED) { + apoll = req->apoll; + kfree(apoll->double_poll); + } else if (!(issue_flags & IO_URING_F_UNLOCKED) && + (entry = io_alloc_cache_get(&ctx->apoll_cache)) != NULL) { + apoll = container_of(entry, struct async_poll, cache); + } else { + apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); + if (unlikely(!apoll)) + return NULL; + } + apoll->double_poll = NULL; + req->apoll = apoll; + return apoll; +} + +int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) +{ + const struct io_op_def *def = &io_op_defs[req->opcode]; + struct async_poll *apoll; + struct io_poll_table ipt; + __poll_t mask = POLLPRI | POLLERR | EPOLLET; + int ret; + + /* + * apoll requests already grab the mutex to complete in the tw handler, + * so removal from the mutex-backed hash is free, use it by default. + */ + req->flags |= REQ_F_HASH_LOCKED; + + if (!def->pollin && !def->pollout) + return IO_APOLL_ABORTED; + if (!file_can_poll(req->file)) + return IO_APOLL_ABORTED; + if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED) + return IO_APOLL_ABORTED; + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) + mask |= EPOLLONESHOT; + + if (def->pollin) { + mask |= EPOLLIN | EPOLLRDNORM; + + /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ + if (req->flags & REQ_F_CLEAR_POLLIN) + mask &= ~EPOLLIN; + } else { + mask |= EPOLLOUT | EPOLLWRNORM; + } + if (def->poll_exclusive) + mask |= EPOLLEXCLUSIVE; + + apoll = io_req_alloc_apoll(req, issue_flags); + if (!apoll) + return IO_APOLL_ABORTED; + req->flags |= REQ_F_POLLED; + ipt.pt._qproc = io_async_queue_proc; + + io_kbuf_recycle(req, issue_flags); + + ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask, issue_flags); + if (ret) + return ret > 0 ? IO_APOLL_READY : IO_APOLL_ABORTED; + trace_io_uring_poll_arm(req, mask, apoll->poll.events); + return IO_APOLL_OK; +} + +static __cold bool io_poll_remove_all_table(struct task_struct *tsk, + struct io_hash_table *table, + bool cancel_all) +{ + unsigned nr_buckets = 1U << table->hash_bits; + struct hlist_node *tmp; + struct io_kiocb *req; + bool found = false; + int i; + + for (i = 0; i < nr_buckets; i++) { + struct io_hash_bucket *hb = &table->hbs[i]; + + spin_lock(&hb->lock); + hlist_for_each_entry_safe(req, tmp, &hb->list, hash_node) { + if (io_match_task_safe(req, tsk, cancel_all)) { + hlist_del_init(&req->hash_node); + io_poll_cancel_req(req); + found = true; + } + } + spin_unlock(&hb->lock); + } + return found; +} + +/* + * Returns true if we found and killed one or more poll requests + */ +__cold bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, + bool cancel_all) + __must_hold(&ctx->uring_lock) +{ + bool ret; + + ret = io_poll_remove_all_table(tsk, &ctx->cancel_table, cancel_all); + ret |= io_poll_remove_all_table(tsk, &ctx->cancel_table_locked, cancel_all); + return ret; +} + +static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only, + struct io_cancel_data *cd, + struct io_hash_table *table, + struct io_hash_bucket **out_bucket) +{ + struct io_kiocb *req; + u32 index = hash_long(cd->data, table->hash_bits); + struct io_hash_bucket *hb = &table->hbs[index]; + + *out_bucket = NULL; + + spin_lock(&hb->lock); + hlist_for_each_entry(req, &hb->list, hash_node) { + if (cd->data != req->cqe.user_data) + continue; + if (poll_only && req->opcode != IORING_OP_POLL_ADD) + continue; + if (cd->flags & IORING_ASYNC_CANCEL_ALL) { + if (cd->seq == req->work.cancel_seq) + continue; + req->work.cancel_seq = cd->seq; + } + *out_bucket = hb; + return req; + } + spin_unlock(&hb->lock); + return NULL; +} + +static struct io_kiocb *io_poll_file_find(struct io_ring_ctx *ctx, + struct io_cancel_data *cd, + struct io_hash_table *table, + struct io_hash_bucket **out_bucket) +{ + unsigned nr_buckets = 1U << table->hash_bits; + struct io_kiocb *req; + int i; + + *out_bucket = NULL; + + for (i = 0; i < nr_buckets; i++) { + struct io_hash_bucket *hb = &table->hbs[i]; + + spin_lock(&hb->lock); + hlist_for_each_entry(req, &hb->list, hash_node) { + if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) && + req->file != cd->file) + continue; + if (cd->seq == req->work.cancel_seq) + continue; + req->work.cancel_seq = cd->seq; + *out_bucket = hb; + return req; + } + spin_unlock(&hb->lock); + } + return NULL; +} + +static int io_poll_disarm(struct io_kiocb *req) +{ + if (!req) + return -ENOENT; + if (!io_poll_get_ownership(req)) + return -EALREADY; + io_poll_remove_entries(req); + hash_del(&req->hash_node); + return 0; +} + +static int __io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, + struct io_hash_table *table) +{ + struct io_hash_bucket *bucket; + struct io_kiocb *req; + + if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_ANY)) + req = io_poll_file_find(ctx, cd, table, &bucket); + else + req = io_poll_find(ctx, false, cd, table, &bucket); + + if (req) + io_poll_cancel_req(req); + if (bucket) + spin_unlock(&bucket->lock); + return req ? 0 : -ENOENT; +} + +int io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, + unsigned issue_flags) +{ + int ret; + + ret = __io_poll_cancel(ctx, cd, &ctx->cancel_table); + if (ret != -ENOENT) + return ret; + + io_ring_submit_lock(ctx, issue_flags); + ret = __io_poll_cancel(ctx, cd, &ctx->cancel_table_locked); + io_ring_submit_unlock(ctx, issue_flags); + return ret; +} + +static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe, + unsigned int flags) +{ + u32 events; + + events = READ_ONCE(sqe->poll32_events); +#ifdef __BIG_ENDIAN + events = swahw32(events); +#endif + if (!(flags & IORING_POLL_ADD_MULTI)) + events |= EPOLLONESHOT; + if (!(flags & IORING_POLL_ADD_LEVEL)) + events |= EPOLLET; + return demangle_poll(events) | + (events & (EPOLLEXCLUSIVE|EPOLLONESHOT|EPOLLET)); +} + +int io_poll_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_poll_update *upd = io_kiocb_to_cmd(req); + u32 flags; + + if (sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + flags = READ_ONCE(sqe->len); + if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA | + IORING_POLL_ADD_MULTI)) + return -EINVAL; + /* meaningless without update */ + if (flags == IORING_POLL_ADD_MULTI) + return -EINVAL; + + upd->old_user_data = READ_ONCE(sqe->addr); + upd->update_events = flags & IORING_POLL_UPDATE_EVENTS; + upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA; + + upd->new_user_data = READ_ONCE(sqe->off); + if (!upd->update_user_data && upd->new_user_data) + return -EINVAL; + if (upd->update_events) + upd->events = io_poll_parse_events(sqe, flags); + else if (sqe->poll32_events) + return -EINVAL; + + return 0; +} + +int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_poll *poll = io_kiocb_to_cmd(req); + u32 flags; + + if (sqe->buf_index || sqe->off || sqe->addr) + return -EINVAL; + flags = READ_ONCE(sqe->len); + if (flags & ~(IORING_POLL_ADD_MULTI|IORING_POLL_ADD_LEVEL)) + return -EINVAL; + if ((flags & IORING_POLL_ADD_MULTI) && (req->flags & REQ_F_CQE_SKIP)) + return -EINVAL; + + poll->events = io_poll_parse_events(sqe, flags); + return 0; +} + +int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_poll *poll = io_kiocb_to_cmd(req); + struct io_poll_table ipt; + int ret; + + ipt.pt._qproc = io_poll_queue_proc; + + /* + * If sqpoll or single issuer, there is no contention for ->uring_lock + * and we'll end up holding it in tw handlers anyway. + */ + if (req->ctx->flags & (IORING_SETUP_SQPOLL|IORING_SETUP_SINGLE_ISSUER)) + req->flags |= REQ_F_HASH_LOCKED; + + ret = __io_arm_poll_handler(req, poll, &ipt, poll->events, issue_flags); + if (ret > 0) { + io_req_set_res(req, ipt.result_mask, 0); + return IOU_OK; + } + return ret ?: IOU_ISSUE_SKIP_COMPLETE; +} + +int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_poll_update *poll_update = io_kiocb_to_cmd(req); + struct io_cancel_data cd = { .data = poll_update->old_user_data, }; + struct io_ring_ctx *ctx = req->ctx; + struct io_hash_bucket *bucket; + struct io_kiocb *preq; + int ret2, ret = 0; + bool locked; + + preq = io_poll_find(ctx, true, &cd, &ctx->cancel_table, &bucket); + ret2 = io_poll_disarm(preq); + if (bucket) + spin_unlock(&bucket->lock); + if (!ret2) + goto found; + if (ret2 != -ENOENT) { + ret = ret2; + goto out; + } + + io_ring_submit_lock(ctx, issue_flags); + preq = io_poll_find(ctx, true, &cd, &ctx->cancel_table_locked, &bucket); + ret2 = io_poll_disarm(preq); + if (bucket) + spin_unlock(&bucket->lock); + io_ring_submit_unlock(ctx, issue_flags); + if (ret2) { + ret = ret2; + goto out; + } + +found: + if (WARN_ON_ONCE(preq->opcode != IORING_OP_POLL_ADD)) { + ret = -EFAULT; + goto out; + } + + if (poll_update->update_events || poll_update->update_user_data) { + /* only mask one event flags, keep behavior flags */ + if (poll_update->update_events) { + struct io_poll *poll = io_kiocb_to_cmd(preq); + + poll->events &= ~0xffff; + poll->events |= poll_update->events & 0xffff; + poll->events |= IO_POLL_UNMASK; + } + if (poll_update->update_user_data) + preq->cqe.user_data = poll_update->new_user_data; + + ret2 = io_poll_add(preq, issue_flags); + /* successfully updated, don't complete poll request */ + if (!ret2 || ret2 == -EIOCBQUEUED) + goto out; + } + + req_set_fail(preq); + io_req_set_res(preq, -ECANCELED, 0); + locked = !(issue_flags & IO_URING_F_UNLOCKED); + io_req_task_complete(preq, &locked); +out: + if (ret < 0) { + req_set_fail(req); + return ret; + } + /* complete update request, we're done with it */ + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +void io_apoll_cache_free(struct io_cache_entry *entry) +{ + kfree(container_of(entry, struct async_poll, cache)); +} diff --git a/io_uring/poll.h b/io_uring/poll.h new file mode 100644 index 000000000000..5f3bae50fc81 --- /dev/null +++ b/io_uring/poll.h @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "alloc_cache.h" + +enum { + IO_APOLL_OK, + IO_APOLL_ABORTED, + IO_APOLL_READY +}; + +struct io_poll { + struct file *file; + struct wait_queue_head *head; + __poll_t events; + struct wait_queue_entry wait; +}; + +struct async_poll { + union { + struct io_poll poll; + struct io_cache_entry cache; + }; + struct io_poll *double_poll; +}; + +int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_poll_add(struct io_kiocb *req, unsigned int issue_flags); + +int io_poll_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags); + +struct io_cancel_data; +int io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, + unsigned issue_flags); +int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags); +bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, + bool cancel_all); + +void io_apoll_cache_free(struct io_cache_entry *entry); diff --git a/io_uring/refs.h b/io_uring/refs.h new file mode 100644 index 000000000000..1336de3f2a30 --- /dev/null +++ b/io_uring/refs.h @@ -0,0 +1,48 @@ +#ifndef IOU_REQ_REF_H +#define IOU_REQ_REF_H + +#include <linux/atomic.h> +#include <linux/io_uring_types.h> + +/* + * Shamelessly stolen from the mm implementation of page reference checking, + * see commit f958d7b528b1 for details. + */ +#define req_ref_zero_or_close_to_overflow(req) \ + ((unsigned int) atomic_read(&(req->refs)) + 127u <= 127u) + +static inline bool req_ref_inc_not_zero(struct io_kiocb *req) +{ + WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); + return atomic_inc_not_zero(&req->refs); +} + +static inline bool req_ref_put_and_test(struct io_kiocb *req) +{ + if (likely(!(req->flags & REQ_F_REFCOUNT))) + return true; + + WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); + return atomic_dec_and_test(&req->refs); +} + +static inline void req_ref_get(struct io_kiocb *req) +{ + WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); + WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); + atomic_inc(&req->refs); +} + +static inline void __io_req_set_refcount(struct io_kiocb *req, int nr) +{ + if (!(req->flags & REQ_F_REFCOUNT)) { + req->flags |= REQ_F_REFCOUNT; + atomic_set(&req->refs, nr); + } +} + +static inline void io_req_set_refcount(struct io_kiocb *req) +{ + __io_req_set_refcount(req, 1); +} +#endif diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c new file mode 100644 index 000000000000..7f66b0e25674 --- /dev/null +++ b/io_uring/rsrc.c @@ -0,0 +1,1373 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/nospec.h> +#include <linux/hugetlb.h> +#include <linux/compat.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "openclose.h" +#include "rsrc.h" + +struct io_rsrc_update { + struct file *file; + u64 arg; + u32 nr_args; + u32 offset; +}; + +static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, + struct io_mapped_ubuf **pimu, + struct page **last_hpage); + +#define IO_RSRC_REF_BATCH 100 + +/* only define max */ +#define IORING_MAX_FIXED_FILES (1U << 20) +#define IORING_MAX_REG_BUFFERS (1U << 14) + +void io_rsrc_refs_drop(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + if (ctx->rsrc_cached_refs) { + io_rsrc_put_node(ctx->rsrc_node, ctx->rsrc_cached_refs); + ctx->rsrc_cached_refs = 0; + } +} + +static inline void __io_unaccount_mem(struct user_struct *user, + unsigned long nr_pages) +{ + atomic_long_sub(nr_pages, &user->locked_vm); +} + +static inline int __io_account_mem(struct user_struct *user, + unsigned long nr_pages) +{ + unsigned long page_limit, cur_pages, new_pages; + + /* Don't allow more pages than we can safely lock */ + page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + cur_pages = atomic_long_read(&user->locked_vm); + do { + new_pages = cur_pages + nr_pages; + if (new_pages > page_limit) + return -ENOMEM; + } while (!atomic_long_try_cmpxchg(&user->locked_vm, + &cur_pages, new_pages)); + return 0; +} + +static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) +{ + if (ctx->user) + __io_unaccount_mem(ctx->user, nr_pages); + + if (ctx->mm_account) + atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm); +} + +static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) +{ + int ret; + + if (ctx->user) { + ret = __io_account_mem(ctx->user, nr_pages); + if (ret) + return ret; + } + + if (ctx->mm_account) + atomic64_add(nr_pages, &ctx->mm_account->pinned_vm); + + return 0; +} + +static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst, + void __user *arg, unsigned index) +{ + struct iovec __user *src; + +#ifdef CONFIG_COMPAT + if (ctx->compat) { + struct compat_iovec __user *ciovs; + struct compat_iovec ciov; + + ciovs = (struct compat_iovec __user *) arg; + if (copy_from_user(&ciov, &ciovs[index], sizeof(ciov))) + return -EFAULT; + + dst->iov_base = u64_to_user_ptr((u64)ciov.iov_base); + dst->iov_len = ciov.iov_len; + return 0; + } +#endif + src = (struct iovec __user *) arg; + if (copy_from_user(dst, &src[index], sizeof(*dst))) + return -EFAULT; + return 0; +} + +static int io_buffer_validate(struct iovec *iov) +{ + unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1); + + /* + * Don't impose further limits on the size and buffer + * constraints here, we'll -EINVAL later when IO is + * submitted if they are wrong. + */ + if (!iov->iov_base) + return iov->iov_len ? -EFAULT : 0; + if (!iov->iov_len) + return -EFAULT; + + /* arbitrary limit, but we need something */ + if (iov->iov_len > SZ_1G) + return -EFAULT; + + if (check_add_overflow((unsigned long)iov->iov_base, acct_len, &tmp)) + return -EOVERFLOW; + + return 0; +} + +static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slot) +{ + struct io_mapped_ubuf *imu = *slot; + unsigned int i; + + if (imu != ctx->dummy_ubuf) { + for (i = 0; i < imu->nr_bvecs; i++) + unpin_user_page(imu->bvec[i].bv_page); + if (imu->acct_pages) + io_unaccount_mem(ctx, imu->acct_pages); + kvfree(imu); + } + *slot = NULL; +} + +void io_rsrc_refs_refill(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + ctx->rsrc_cached_refs += IO_RSRC_REF_BATCH; + percpu_ref_get_many(&ctx->rsrc_node->refs, IO_RSRC_REF_BATCH); +} + +static void __io_rsrc_put_work(struct io_rsrc_node *ref_node) +{ + struct io_rsrc_data *rsrc_data = ref_node->rsrc_data; + struct io_ring_ctx *ctx = rsrc_data->ctx; + struct io_rsrc_put *prsrc, *tmp; + + list_for_each_entry_safe(prsrc, tmp, &ref_node->rsrc_list, list) { + list_del(&prsrc->list); + + if (prsrc->tag) { + if (ctx->flags & IORING_SETUP_IOPOLL) { + mutex_lock(&ctx->uring_lock); + io_post_aux_cqe(ctx, prsrc->tag, 0, 0, true); + mutex_unlock(&ctx->uring_lock); + } else { + io_post_aux_cqe(ctx, prsrc->tag, 0, 0, true); + } + } + + rsrc_data->do_put(ctx, prsrc); + kfree(prsrc); + } + + io_rsrc_node_destroy(ref_node); + if (atomic_dec_and_test(&rsrc_data->refs)) + complete(&rsrc_data->done); +} + +void io_rsrc_put_work(struct work_struct *work) +{ + struct io_ring_ctx *ctx; + struct llist_node *node; + + ctx = container_of(work, struct io_ring_ctx, rsrc_put_work.work); + node = llist_del_all(&ctx->rsrc_put_llist); + + while (node) { + struct io_rsrc_node *ref_node; + struct llist_node *next = node->next; + + ref_node = llist_entry(node, struct io_rsrc_node, llist); + __io_rsrc_put_work(ref_node); + node = next; + } +} + +void io_wait_rsrc_data(struct io_rsrc_data *data) +{ + if (data && !atomic_dec_and_test(&data->refs)) + wait_for_completion(&data->done); +} + +void io_rsrc_node_destroy(struct io_rsrc_node *ref_node) +{ + percpu_ref_exit(&ref_node->refs); + kfree(ref_node); +} + +static __cold void io_rsrc_node_ref_zero(struct percpu_ref *ref) +{ + struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs); + struct io_ring_ctx *ctx = node->rsrc_data->ctx; + unsigned long flags; + bool first_add = false; + unsigned long delay = HZ; + + spin_lock_irqsave(&ctx->rsrc_ref_lock, flags); + node->done = true; + + /* if we are mid-quiesce then do not delay */ + if (node->rsrc_data->quiesce) + delay = 0; + + while (!list_empty(&ctx->rsrc_ref_list)) { + node = list_first_entry(&ctx->rsrc_ref_list, + struct io_rsrc_node, node); + /* recycle ref nodes in order */ + if (!node->done) + break; + list_del(&node->node); + first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist); + } + spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags); + + if (first_add) + mod_delayed_work(system_wq, &ctx->rsrc_put_work, delay); +} + +static struct io_rsrc_node *io_rsrc_node_alloc(void) +{ + struct io_rsrc_node *ref_node; + + ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); + if (!ref_node) + return NULL; + + if (percpu_ref_init(&ref_node->refs, io_rsrc_node_ref_zero, + 0, GFP_KERNEL)) { + kfree(ref_node); + return NULL; + } + INIT_LIST_HEAD(&ref_node->node); + INIT_LIST_HEAD(&ref_node->rsrc_list); + ref_node->done = false; + return ref_node; +} + +void io_rsrc_node_switch(struct io_ring_ctx *ctx, + struct io_rsrc_data *data_to_kill) + __must_hold(&ctx->uring_lock) +{ + WARN_ON_ONCE(!ctx->rsrc_backup_node); + WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node); + + io_rsrc_refs_drop(ctx); + + if (data_to_kill) { + struct io_rsrc_node *rsrc_node = ctx->rsrc_node; + + rsrc_node->rsrc_data = data_to_kill; + spin_lock_irq(&ctx->rsrc_ref_lock); + list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list); + spin_unlock_irq(&ctx->rsrc_ref_lock); + + atomic_inc(&data_to_kill->refs); + percpu_ref_kill(&rsrc_node->refs); + ctx->rsrc_node = NULL; + } + + if (!ctx->rsrc_node) { + ctx->rsrc_node = ctx->rsrc_backup_node; + ctx->rsrc_backup_node = NULL; + } +} + +int io_rsrc_node_switch_start(struct io_ring_ctx *ctx) +{ + if (ctx->rsrc_backup_node) + return 0; + ctx->rsrc_backup_node = io_rsrc_node_alloc(); + return ctx->rsrc_backup_node ? 0 : -ENOMEM; +} + +__cold static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, + struct io_ring_ctx *ctx) +{ + int ret; + + /* As we may drop ->uring_lock, other task may have started quiesce */ + if (data->quiesce) + return -ENXIO; + + data->quiesce = true; + do { + ret = io_rsrc_node_switch_start(ctx); + if (ret) + break; + io_rsrc_node_switch(ctx, data); + + /* kill initial ref, already quiesced if zero */ + if (atomic_dec_and_test(&data->refs)) + break; + mutex_unlock(&ctx->uring_lock); + flush_delayed_work(&ctx->rsrc_put_work); + ret = wait_for_completion_interruptible(&data->done); + if (!ret) { + mutex_lock(&ctx->uring_lock); + if (atomic_read(&data->refs) > 0) { + /* + * it has been revived by another thread while + * we were unlocked + */ + mutex_unlock(&ctx->uring_lock); + } else { + break; + } + } + + atomic_inc(&data->refs); + /* wait for all works potentially completing data->done */ + flush_delayed_work(&ctx->rsrc_put_work); + reinit_completion(&data->done); + + ret = io_run_task_work_sig(); + mutex_lock(&ctx->uring_lock); + } while (ret >= 0); + data->quiesce = false; + + return ret; +} + +static void io_free_page_table(void **table, size_t size) +{ + unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); + + for (i = 0; i < nr_tables; i++) + kfree(table[i]); + kfree(table); +} + +static void io_rsrc_data_free(struct io_rsrc_data *data) +{ + size_t size = data->nr * sizeof(data->tags[0][0]); + + if (data->tags) + io_free_page_table((void **)data->tags, size); + kfree(data); +} + +static __cold void **io_alloc_page_table(size_t size) +{ + unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); + size_t init_size = size; + void **table; + + table = kcalloc(nr_tables, sizeof(*table), GFP_KERNEL_ACCOUNT); + if (!table) + return NULL; + + for (i = 0; i < nr_tables; i++) { + unsigned int this_size = min_t(size_t, size, PAGE_SIZE); + + table[i] = kzalloc(this_size, GFP_KERNEL_ACCOUNT); + if (!table[i]) { + io_free_page_table(table, init_size); + return NULL; + } + size -= this_size; + } + return table; +} + +__cold static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, + rsrc_put_fn *do_put, u64 __user *utags, + unsigned nr, struct io_rsrc_data **pdata) +{ + struct io_rsrc_data *data; + int ret = -ENOMEM; + unsigned i; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + data->tags = (u64 **)io_alloc_page_table(nr * sizeof(data->tags[0][0])); + if (!data->tags) { + kfree(data); + return -ENOMEM; + } + + data->nr = nr; + data->ctx = ctx; + data->do_put = do_put; + if (utags) { + ret = -EFAULT; + for (i = 0; i < nr; i++) { + u64 *tag_slot = io_get_tag_slot(data, i); + + if (copy_from_user(tag_slot, &utags[i], + sizeof(*tag_slot))) + goto fail; + } + } + + atomic_set(&data->refs, 1); + init_completion(&data->done); + *pdata = data; + return 0; +fail: + io_rsrc_data_free(data); + return ret; +} + +static int __io_sqe_files_update(struct io_ring_ctx *ctx, + struct io_uring_rsrc_update2 *up, + unsigned nr_args) +{ + u64 __user *tags = u64_to_user_ptr(up->tags); + __s32 __user *fds = u64_to_user_ptr(up->data); + struct io_rsrc_data *data = ctx->file_data; + struct io_fixed_file *file_slot; + struct file *file; + int fd, i, err = 0; + unsigned int done; + bool needs_switch = false; + + if (!ctx->file_data) + return -ENXIO; + if (up->offset + nr_args > ctx->nr_user_files) + return -EINVAL; + + for (done = 0; done < nr_args; done++) { + u64 tag = 0; + + if ((tags && copy_from_user(&tag, &tags[done], sizeof(tag))) || + copy_from_user(&fd, &fds[done], sizeof(fd))) { + err = -EFAULT; + break; + } + if ((fd == IORING_REGISTER_FILES_SKIP || fd == -1) && tag) { + err = -EINVAL; + break; + } + if (fd == IORING_REGISTER_FILES_SKIP) + continue; + + i = array_index_nospec(up->offset + done, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, i); + + if (file_slot->file_ptr) { + file = (struct file *)(file_slot->file_ptr & FFS_MASK); + err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file); + if (err) + break; + file_slot->file_ptr = 0; + io_file_bitmap_clear(&ctx->file_table, i); + needs_switch = true; + } + if (fd != -1) { + file = fget(fd); + if (!file) { + err = -EBADF; + break; + } + /* + * Don't allow io_uring instances to be registered. If + * UNIX isn't enabled, then this causes a reference + * cycle and this instance can never get freed. If UNIX + * is enabled we'll handle it just fine, but there's + * still no point in allowing a ring fd as it doesn't + * support regular read/write anyway. + */ + if (io_is_uring_fops(file)) { + fput(file); + err = -EBADF; + break; + } + err = io_scm_file_account(ctx, file); + if (err) { + fput(file); + break; + } + *io_get_tag_slot(data, i) = tag; + io_fixed_file_set(file_slot, file); + io_file_bitmap_set(&ctx->file_table, i); + } + } + + if (needs_switch) + io_rsrc_node_switch(ctx, data); + return done ? done : err; +} + +static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, + struct io_uring_rsrc_update2 *up, + unsigned int nr_args) +{ + u64 __user *tags = u64_to_user_ptr(up->tags); + struct iovec iov, __user *iovs = u64_to_user_ptr(up->data); + struct page *last_hpage = NULL; + bool needs_switch = false; + __u32 done; + int i, err; + + if (!ctx->buf_data) + return -ENXIO; + if (up->offset + nr_args > ctx->nr_user_bufs) + return -EINVAL; + + for (done = 0; done < nr_args; done++) { + struct io_mapped_ubuf *imu; + int offset = up->offset + done; + u64 tag = 0; + + err = io_copy_iov(ctx, &iov, iovs, done); + if (err) + break; + if (tags && copy_from_user(&tag, &tags[done], sizeof(tag))) { + err = -EFAULT; + break; + } + err = io_buffer_validate(&iov); + if (err) + break; + if (!iov.iov_base && tag) { + err = -EINVAL; + break; + } + err = io_sqe_buffer_register(ctx, &iov, &imu, &last_hpage); + if (err) + break; + + i = array_index_nospec(offset, ctx->nr_user_bufs); + if (ctx->user_bufs[i] != ctx->dummy_ubuf) { + err = io_queue_rsrc_removal(ctx->buf_data, i, + ctx->rsrc_node, ctx->user_bufs[i]); + if (unlikely(err)) { + io_buffer_unmap(ctx, &imu); + break; + } + ctx->user_bufs[i] = ctx->dummy_ubuf; + needs_switch = true; + } + + ctx->user_bufs[i] = imu; + *io_get_tag_slot(ctx->buf_data, offset) = tag; + } + + if (needs_switch) + io_rsrc_node_switch(ctx, ctx->buf_data); + return done ? done : err; +} + +static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, + struct io_uring_rsrc_update2 *up, + unsigned nr_args) +{ + __u32 tmp; + int err; + + if (check_add_overflow(up->offset, nr_args, &tmp)) + return -EOVERFLOW; + err = io_rsrc_node_switch_start(ctx); + if (err) + return err; + + switch (type) { + case IORING_RSRC_FILE: + return __io_sqe_files_update(ctx, up, nr_args); + case IORING_RSRC_BUFFER: + return __io_sqe_buffers_update(ctx, up, nr_args); + } + return -EINVAL; +} + +int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) +{ + struct io_uring_rsrc_update2 up; + + if (!nr_args) + return -EINVAL; + memset(&up, 0, sizeof(up)); + if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update))) + return -EFAULT; + if (up.resv || up.resv2) + return -EINVAL; + return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args); +} + +int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned size, unsigned type) +{ + struct io_uring_rsrc_update2 up; + + if (size != sizeof(up)) + return -EINVAL; + if (copy_from_user(&up, arg, sizeof(up))) + return -EFAULT; + if (!up.nr || up.resv || up.resv2) + return -EINVAL; + return __io_register_rsrc_update(ctx, type, &up, up.nr); +} + +__cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, + unsigned int size, unsigned int type) +{ + struct io_uring_rsrc_register rr; + + /* keep it extendible */ + if (size != sizeof(rr)) + return -EINVAL; + + memset(&rr, 0, sizeof(rr)); + if (copy_from_user(&rr, arg, size)) + return -EFAULT; + if (!rr.nr || rr.resv2) + return -EINVAL; + if (rr.flags & ~IORING_RSRC_REGISTER_SPARSE) + return -EINVAL; + + switch (type) { + case IORING_RSRC_FILE: + if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data) + break; + return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data), + rr.nr, u64_to_user_ptr(rr.tags)); + case IORING_RSRC_BUFFER: + if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data) + break; + return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data), + rr.nr, u64_to_user_ptr(rr.tags)); + } + return -EINVAL; +} + +int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_rsrc_update *up = io_kiocb_to_cmd(req); + + if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) + return -EINVAL; + if (sqe->rw_flags || sqe->splice_fd_in) + return -EINVAL; + + up->offset = READ_ONCE(sqe->off); + up->nr_args = READ_ONCE(sqe->len); + if (!up->nr_args) + return -EINVAL; + up->arg = READ_ONCE(sqe->addr); + return 0; +} + +static int io_files_update_with_index_alloc(struct io_kiocb *req, + unsigned int issue_flags) +{ + struct io_rsrc_update *up = io_kiocb_to_cmd(req); + __s32 __user *fds = u64_to_user_ptr(up->arg); + unsigned int done; + struct file *file; + int ret, fd; + + if (!req->ctx->file_data) + return -ENXIO; + + for (done = 0; done < up->nr_args; done++) { + if (copy_from_user(&fd, &fds[done], sizeof(fd))) { + ret = -EFAULT; + break; + } + + file = fget(fd); + if (!file) { + ret = -EBADF; + break; + } + ret = io_fixed_fd_install(req, issue_flags, file, + IORING_FILE_INDEX_ALLOC); + if (ret < 0) + break; + if (copy_to_user(&fds[done], &ret, sizeof(ret))) { + __io_close_fixed(req->ctx, issue_flags, ret); + ret = -EFAULT; + break; + } + } + + if (done) + return done; + return ret; +} + +int io_files_update(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_rsrc_update *up = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + struct io_uring_rsrc_update2 up2; + int ret; + + up2.offset = up->offset; + up2.data = up->arg; + up2.nr = 0; + up2.tags = 0; + up2.resv = 0; + up2.resv2 = 0; + + if (up->offset == IORING_FILE_INDEX_ALLOC) { + ret = io_files_update_with_index_alloc(req, issue_flags); + } else { + io_ring_submit_lock(ctx, issue_flags); + ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, + &up2, up->nr_args); + io_ring_submit_unlock(ctx, issue_flags); + } + + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, + struct io_rsrc_node *node, void *rsrc) +{ + u64 *tag_slot = io_get_tag_slot(data, idx); + struct io_rsrc_put *prsrc; + + prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); + if (!prsrc) + return -ENOMEM; + + prsrc->tag = *tag_slot; + *tag_slot = 0; + prsrc->rsrc = rsrc; + list_add(&prsrc->list, &node->rsrc_list); + return 0; +} + +void __io_sqe_files_unregister(struct io_ring_ctx *ctx) +{ +#if !defined(IO_URING_SCM_ALL) + int i; + + for (i = 0; i < ctx->nr_user_files; i++) { + struct file *file = io_file_from_index(&ctx->file_table, i); + + if (!file) + continue; + if (io_fixed_file_slot(&ctx->file_table, i)->file_ptr & FFS_SCM) + continue; + io_file_bitmap_clear(&ctx->file_table, i); + fput(file); + } +#endif + +#if defined(CONFIG_UNIX) + if (ctx->ring_sock) { + struct sock *sock = ctx->ring_sock->sk; + struct sk_buff *skb; + + while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL) + kfree_skb(skb); + } +#endif + io_free_file_tables(&ctx->file_table); + io_rsrc_data_free(ctx->file_data); + ctx->file_data = NULL; + ctx->nr_user_files = 0; +} + +int io_sqe_files_unregister(struct io_ring_ctx *ctx) +{ + unsigned nr = ctx->nr_user_files; + int ret; + + if (!ctx->file_data) + return -ENXIO; + + /* + * Quiesce may unlock ->uring_lock, and while it's not held + * prevent new requests using the table. + */ + ctx->nr_user_files = 0; + ret = io_rsrc_ref_quiesce(ctx->file_data, ctx); + ctx->nr_user_files = nr; + if (!ret) + __io_sqe_files_unregister(ctx); + return ret; +} + +/* + * Ensure the UNIX gc is aware of our file set, so we are certain that + * the io_uring can be safely unregistered on process exit, even if we have + * loops in the file referencing. We account only files that can hold other + * files because otherwise they can't form a loop and so are not interesting + * for GC. + */ +int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file) +{ +#if defined(CONFIG_UNIX) + struct sock *sk = ctx->ring_sock->sk; + struct sk_buff_head *head = &sk->sk_receive_queue; + struct scm_fp_list *fpl; + struct sk_buff *skb; + + if (likely(!io_file_need_scm(file))) + return 0; + + /* + * See if we can merge this file into an existing skb SCM_RIGHTS + * file set. If there's no room, fall back to allocating a new skb + * and filling it in. + */ + spin_lock_irq(&head->lock); + skb = skb_peek(head); + if (skb && UNIXCB(skb).fp->count < SCM_MAX_FD) + __skb_unlink(skb, head); + else + skb = NULL; + spin_unlock_irq(&head->lock); + + if (!skb) { + fpl = kzalloc(sizeof(*fpl), GFP_KERNEL); + if (!fpl) + return -ENOMEM; + + skb = alloc_skb(0, GFP_KERNEL); + if (!skb) { + kfree(fpl); + return -ENOMEM; + } + + fpl->user = get_uid(current_user()); + fpl->max = SCM_MAX_FD; + fpl->count = 0; + + UNIXCB(skb).fp = fpl; + skb->sk = sk; + skb->destructor = unix_destruct_scm; + refcount_add(skb->truesize, &sk->sk_wmem_alloc); + } + + fpl = UNIXCB(skb).fp; + fpl->fp[fpl->count++] = get_file(file); + unix_inflight(fpl->user, file); + skb_queue_head(head, skb); + fput(file); +#endif + return 0; +} + +static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) +{ + struct file *file = prsrc->file; +#if defined(CONFIG_UNIX) + struct sock *sock = ctx->ring_sock->sk; + struct sk_buff_head list, *head = &sock->sk_receive_queue; + struct sk_buff *skb; + int i; + + if (!io_file_need_scm(file)) { + fput(file); + return; + } + + __skb_queue_head_init(&list); + + /* + * Find the skb that holds this file in its SCM_RIGHTS. When found, + * remove this entry and rearrange the file array. + */ + skb = skb_dequeue(head); + while (skb) { + struct scm_fp_list *fp; + + fp = UNIXCB(skb).fp; + for (i = 0; i < fp->count; i++) { + int left; + + if (fp->fp[i] != file) + continue; + + unix_notinflight(fp->user, fp->fp[i]); + left = fp->count - 1 - i; + if (left) { + memmove(&fp->fp[i], &fp->fp[i + 1], + left * sizeof(struct file *)); + } + fp->count--; + if (!fp->count) { + kfree_skb(skb); + skb = NULL; + } else { + __skb_queue_tail(&list, skb); + } + fput(file); + file = NULL; + break; + } + + if (!file) + break; + + __skb_queue_tail(&list, skb); + + skb = skb_dequeue(head); + } + + if (skb_peek(&list)) { + spin_lock_irq(&head->lock); + while ((skb = __skb_dequeue(&list)) != NULL) + __skb_queue_tail(head, skb); + spin_unlock_irq(&head->lock); + } +#else + fput(file); +#endif +} + +int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args, u64 __user *tags) +{ + __s32 __user *fds = (__s32 __user *) arg; + struct file *file; + int fd, ret; + unsigned i; + + if (ctx->file_data) + return -EBUSY; + if (!nr_args) + return -EINVAL; + if (nr_args > IORING_MAX_FIXED_FILES) + return -EMFILE; + if (nr_args > rlimit(RLIMIT_NOFILE)) + return -EMFILE; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + return ret; + ret = io_rsrc_data_alloc(ctx, io_rsrc_file_put, tags, nr_args, + &ctx->file_data); + if (ret) + return ret; + + if (!io_alloc_file_tables(&ctx->file_table, nr_args)) { + io_rsrc_data_free(ctx->file_data); + ctx->file_data = NULL; + return -ENOMEM; + } + + for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { + struct io_fixed_file *file_slot; + + if (fds && copy_from_user(&fd, &fds[i], sizeof(fd))) { + ret = -EFAULT; + goto fail; + } + /* allow sparse sets */ + if (!fds || fd == -1) { + ret = -EINVAL; + if (unlikely(*io_get_tag_slot(ctx->file_data, i))) + goto fail; + continue; + } + + file = fget(fd); + ret = -EBADF; + if (unlikely(!file)) + goto fail; + + /* + * Don't allow io_uring instances to be registered. If UNIX + * isn't enabled, then this causes a reference cycle and this + * instance can never get freed. If UNIX is enabled we'll + * handle it just fine, but there's still no point in allowing + * a ring fd as it doesn't support regular read/write anyway. + */ + if (io_is_uring_fops(file)) { + fput(file); + goto fail; + } + ret = io_scm_file_account(ctx, file); + if (ret) { + fput(file); + goto fail; + } + file_slot = io_fixed_file_slot(&ctx->file_table, i); + io_fixed_file_set(file_slot, file); + io_file_bitmap_set(&ctx->file_table, i); + } + + /* default it to the whole table */ + io_file_table_set_alloc_range(ctx, 0, ctx->nr_user_files); + io_rsrc_node_switch(ctx, NULL); + return 0; +fail: + __io_sqe_files_unregister(ctx); + return ret; +} + +static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) +{ + io_buffer_unmap(ctx, &prsrc->buf); + prsrc->buf = NULL; +} + +void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx) +{ + unsigned int i; + + for (i = 0; i < ctx->nr_user_bufs; i++) + io_buffer_unmap(ctx, &ctx->user_bufs[i]); + kfree(ctx->user_bufs); + io_rsrc_data_free(ctx->buf_data); + ctx->user_bufs = NULL; + ctx->buf_data = NULL; + ctx->nr_user_bufs = 0; +} + +int io_sqe_buffers_unregister(struct io_ring_ctx *ctx) +{ + unsigned nr = ctx->nr_user_bufs; + int ret; + + if (!ctx->buf_data) + return -ENXIO; + + /* + * Quiesce may unlock ->uring_lock, and while it's not held + * prevent new requests using the table. + */ + ctx->nr_user_bufs = 0; + ret = io_rsrc_ref_quiesce(ctx->buf_data, ctx); + ctx->nr_user_bufs = nr; + if (!ret) + __io_sqe_buffers_unregister(ctx); + return ret; +} + +/* + * Not super efficient, but this is just a registration time. And we do cache + * the last compound head, so generally we'll only do a full search if we don't + * match that one. + * + * We check if the given compound head page has already been accounted, to + * avoid double accounting it. This allows us to account the full size of the + * page, not just the constituent pages of a huge page. + */ +static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages, + int nr_pages, struct page *hpage) +{ + int i, j; + + /* check current page array */ + for (i = 0; i < nr_pages; i++) { + if (!PageCompound(pages[i])) + continue; + if (compound_head(pages[i]) == hpage) + return true; + } + + /* check previously registered pages */ + for (i = 0; i < ctx->nr_user_bufs; i++) { + struct io_mapped_ubuf *imu = ctx->user_bufs[i]; + + for (j = 0; j < imu->nr_bvecs; j++) { + if (!PageCompound(imu->bvec[j].bv_page)) + continue; + if (compound_head(imu->bvec[j].bv_page) == hpage) + return true; + } + } + + return false; +} + +static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, + int nr_pages, struct io_mapped_ubuf *imu, + struct page **last_hpage) +{ + int i, ret; + + imu->acct_pages = 0; + for (i = 0; i < nr_pages; i++) { + if (!PageCompound(pages[i])) { + imu->acct_pages++; + } else { + struct page *hpage; + + hpage = compound_head(pages[i]); + if (hpage == *last_hpage) + continue; + *last_hpage = hpage; + if (headpage_already_acct(ctx, pages, i, hpage)) + continue; + imu->acct_pages += page_size(hpage) >> PAGE_SHIFT; + } + } + + if (!imu->acct_pages) + return 0; + + ret = io_account_mem(ctx, imu->acct_pages); + if (ret) + imu->acct_pages = 0; + return ret; +} + +struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages) +{ + unsigned long start, end, nr_pages; + struct vm_area_struct **vmas = NULL; + struct page **pages = NULL; + int i, pret, ret = -ENOMEM; + + end = (ubuf + len + PAGE_SIZE - 1) >> PAGE_SHIFT; + start = ubuf >> PAGE_SHIFT; + nr_pages = end - start; + + pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); + if (!pages) + goto done; + + vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!vmas) + goto done; + + ret = 0; + mmap_read_lock(current->mm); + pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, + pages, vmas); + if (pret == nr_pages) { + /* don't support file backed memory */ + for (i = 0; i < nr_pages; i++) { + struct vm_area_struct *vma = vmas[i]; + + if (vma_is_shmem(vma)) + continue; + if (vma->vm_file && + !is_file_hugepages(vma->vm_file)) { + ret = -EOPNOTSUPP; + break; + } + } + *npages = nr_pages; + } else { + ret = pret < 0 ? pret : -EFAULT; + } + mmap_read_unlock(current->mm); + if (ret) { + /* + * if we did partial map, or found file backed vmas, + * release any pages we did get + */ + if (pret > 0) + unpin_user_pages(pages, pret); + goto done; + } + ret = 0; +done: + kvfree(vmas); + if (ret < 0) { + kvfree(pages); + pages = ERR_PTR(ret); + } + return pages; +} + +static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, + struct io_mapped_ubuf **pimu, + struct page **last_hpage) +{ + struct io_mapped_ubuf *imu = NULL; + struct page **pages = NULL; + unsigned long off; + size_t size; + int ret, nr_pages, i; + + *pimu = ctx->dummy_ubuf; + if (!iov->iov_base) + return 0; + + ret = -ENOMEM; + pages = io_pin_pages((unsigned long) iov->iov_base, iov->iov_len, + &nr_pages); + if (IS_ERR(pages)) { + ret = PTR_ERR(pages); + pages = NULL; + goto done; + } + + imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL); + if (!imu) + goto done; + + ret = io_buffer_account_pin(ctx, pages, nr_pages, imu, last_hpage); + if (ret) { + unpin_user_pages(pages, nr_pages); + goto done; + } + + off = (unsigned long) iov->iov_base & ~PAGE_MASK; + size = iov->iov_len; + for (i = 0; i < nr_pages; i++) { + size_t vec_len; + + vec_len = min_t(size_t, size, PAGE_SIZE - off); + imu->bvec[i].bv_page = pages[i]; + imu->bvec[i].bv_len = vec_len; + imu->bvec[i].bv_offset = off; + off = 0; + size -= vec_len; + } + /* store original address for later verification */ + imu->ubuf = (unsigned long) iov->iov_base; + imu->ubuf_end = imu->ubuf + iov->iov_len; + imu->nr_bvecs = nr_pages; + *pimu = imu; + ret = 0; +done: + if (ret) + kvfree(imu); + kvfree(pages); + return ret; +} + +static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args) +{ + ctx->user_bufs = kcalloc(nr_args, sizeof(*ctx->user_bufs), GFP_KERNEL); + return ctx->user_bufs ? 0 : -ENOMEM; +} + +int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned int nr_args, u64 __user *tags) +{ + struct page *last_hpage = NULL; + struct io_rsrc_data *data; + int i, ret; + struct iovec iov; + + BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16)); + + if (ctx->user_bufs) + return -EBUSY; + if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS) + return -EINVAL; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + return ret; + ret = io_rsrc_data_alloc(ctx, io_rsrc_buf_put, tags, nr_args, &data); + if (ret) + return ret; + ret = io_buffers_map_alloc(ctx, nr_args); + if (ret) { + io_rsrc_data_free(data); + return ret; + } + + for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) { + if (arg) { + ret = io_copy_iov(ctx, &iov, arg, i); + if (ret) + break; + ret = io_buffer_validate(&iov); + if (ret) + break; + } else { + memset(&iov, 0, sizeof(iov)); + } + + if (!iov.iov_base && *io_get_tag_slot(data, i)) { + ret = -EINVAL; + break; + } + + ret = io_sqe_buffer_register(ctx, &iov, &ctx->user_bufs[i], + &last_hpage); + if (ret) + break; + } + + WARN_ON_ONCE(ctx->buf_data); + + ctx->buf_data = data; + if (ret) + __io_sqe_buffers_unregister(ctx); + else + io_rsrc_node_switch(ctx, NULL); + return ret; +} + +int io_import_fixed(int ddir, struct iov_iter *iter, + struct io_mapped_ubuf *imu, + u64 buf_addr, size_t len) +{ + u64 buf_end; + size_t offset; + + if (WARN_ON_ONCE(!imu)) + return -EFAULT; + if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end))) + return -EFAULT; + /* not inside the mapped region */ + if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end)) + return -EFAULT; + + /* + * May not be a start of buffer, set size appropriately + * and advance us to the beginning. + */ + offset = buf_addr - imu->ubuf; + iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, offset + len); + + if (offset) { + /* + * Don't use iov_iter_advance() here, as it's really slow for + * using the latter parts of a big fixed buffer - it iterates + * over each segment manually. We can cheat a bit here, because + * we know that: + * + * 1) it's a BVEC iter, we set it up + * 2) all bvecs are PAGE_SIZE in size, except potentially the + * first and last bvec + * + * So just find our index, and adjust the iterator afterwards. + * If the offset is within the first bvec (or the whole first + * bvec, just use iov_iter_advance(). This makes it easier + * since we can just skip the first segment, which may not + * be PAGE_SIZE aligned. + */ + const struct bio_vec *bvec = imu->bvec; + + if (offset <= bvec->bv_len) { + iov_iter_advance(iter, offset); + } else { + unsigned long seg_skip; + + /* skip first vec */ + offset -= bvec->bv_len; + seg_skip = 1 + (offset >> PAGE_SHIFT); + + iter->bvec = bvec + seg_skip; + iter->nr_segs -= seg_skip; + iter->count -= bvec->bv_len + offset; + iter->iov_offset = offset & ~PAGE_MASK; + } + } + + return 0; +} diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h new file mode 100644 index 000000000000..87f58315b247 --- /dev/null +++ b/io_uring/rsrc.h @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef IOU_RSRC_H +#define IOU_RSRC_H + +#include <net/af_unix.h> + +#define IO_RSRC_TAG_TABLE_SHIFT (PAGE_SHIFT - 3) +#define IO_RSRC_TAG_TABLE_MAX (1U << IO_RSRC_TAG_TABLE_SHIFT) +#define IO_RSRC_TAG_TABLE_MASK (IO_RSRC_TAG_TABLE_MAX - 1) + +enum { + IORING_RSRC_FILE = 0, + IORING_RSRC_BUFFER = 1, +}; + +struct io_rsrc_put { + struct list_head list; + u64 tag; + union { + void *rsrc; + struct file *file; + struct io_mapped_ubuf *buf; + }; +}; + +typedef void (rsrc_put_fn)(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc); + +struct io_rsrc_data { + struct io_ring_ctx *ctx; + + u64 **tags; + unsigned int nr; + rsrc_put_fn *do_put; + atomic_t refs; + struct completion done; + bool quiesce; +}; + +struct io_rsrc_node { + struct percpu_ref refs; + struct list_head node; + struct list_head rsrc_list; + struct io_rsrc_data *rsrc_data; + struct llist_node llist; + bool done; +}; + +struct io_mapped_ubuf { + u64 ubuf; + u64 ubuf_end; + unsigned int nr_bvecs; + unsigned long acct_pages; + struct bio_vec bvec[]; +}; + +void io_rsrc_put_work(struct work_struct *work); +void io_rsrc_refs_refill(struct io_ring_ctx *ctx); +void io_wait_rsrc_data(struct io_rsrc_data *data); +void io_rsrc_node_destroy(struct io_rsrc_node *ref_node); +void io_rsrc_refs_drop(struct io_ring_ctx *ctx); +int io_rsrc_node_switch_start(struct io_ring_ctx *ctx); +int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, + struct io_rsrc_node *node, void *rsrc); +void io_rsrc_node_switch(struct io_ring_ctx *ctx, + struct io_rsrc_data *data_to_kill); + +int io_import_fixed(int ddir, struct iov_iter *iter, + struct io_mapped_ubuf *imu, + u64 buf_addr, size_t len); + +void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx); +int io_sqe_buffers_unregister(struct io_ring_ctx *ctx); +int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned int nr_args, u64 __user *tags); +void __io_sqe_files_unregister(struct io_ring_ctx *ctx); +int io_sqe_files_unregister(struct io_ring_ctx *ctx); +int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args, u64 __user *tags); + +int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file); + +#if defined(CONFIG_UNIX) +static inline bool io_file_need_scm(struct file *filp) +{ +#if defined(IO_URING_SCM_ALL) + return true; +#else + return !!unix_get_socket(filp); +#endif +} +#else +static inline bool io_file_need_scm(struct file *filp) +{ + return false; +} +#endif + +static inline int io_scm_file_account(struct io_ring_ctx *ctx, + struct file *file) +{ + if (likely(!io_file_need_scm(file))) + return 0; + return __io_scm_file_account(ctx, file); +} + +int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args); +int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned size, unsigned type); +int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, + unsigned int size, unsigned int type); + +static inline void io_rsrc_put_node(struct io_rsrc_node *node, int nr) +{ + percpu_ref_put_many(&node->refs, nr); +} + +static inline void io_req_put_rsrc(struct io_kiocb *req) +{ + if (req->rsrc_node) + io_rsrc_put_node(req->rsrc_node, 1); +} + +static inline void io_req_put_rsrc_locked(struct io_kiocb *req, + struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + struct io_rsrc_node *node = req->rsrc_node; + + if (node) { + if (node == ctx->rsrc_node) + ctx->rsrc_cached_refs++; + else + io_rsrc_put_node(node, 1); + } +} + +static inline void io_req_set_rsrc_node(struct io_kiocb *req, + struct io_ring_ctx *ctx, + unsigned int issue_flags) +{ + if (!req->rsrc_node) { + req->rsrc_node = ctx->rsrc_node; + + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + lockdep_assert_held(&ctx->uring_lock); + ctx->rsrc_cached_refs--; + if (unlikely(ctx->rsrc_cached_refs < 0)) + io_rsrc_refs_refill(ctx); + } else { + percpu_ref_get(&req->rsrc_node->refs); + } + } +} + +static inline u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx) +{ + unsigned int off = idx & IO_RSRC_TAG_TABLE_MASK; + unsigned int table_idx = idx >> IO_RSRC_TAG_TABLE_SHIFT; + + return &data->tags[table_idx][off]; +} + +int io_files_update(struct io_kiocb *req, unsigned int issue_flags); +int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +#endif diff --git a/io_uring/rw.c b/io_uring/rw.c new file mode 100644 index 000000000000..c50a0d66d67a --- /dev/null +++ b/io_uring/rw.c @@ -0,0 +1,1020 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/blk-mq.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/fsnotify.h> +#include <linux/poll.h> +#include <linux/nospec.h> +#include <linux/compat.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "opdef.h" +#include "kbuf.h" +#include "rsrc.h" +#include "rw.h" + +struct io_rw { + /* NOTE: kiocb has the file as the first member, so don't do it here */ + struct kiocb kiocb; + u64 addr; + u32 len; + rwf_t flags; +}; + +static inline bool io_file_supports_nowait(struct io_kiocb *req) +{ + return req->flags & REQ_F_SUPPORT_NOWAIT; +} + +int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_rw *rw = io_kiocb_to_cmd(req); + unsigned ioprio; + int ret; + + rw->kiocb.ki_pos = READ_ONCE(sqe->off); + /* used for fixed read/write too - just read unconditionally */ + req->buf_index = READ_ONCE(sqe->buf_index); + + if (req->opcode == IORING_OP_READ_FIXED || + req->opcode == IORING_OP_WRITE_FIXED) { + struct io_ring_ctx *ctx = req->ctx; + u16 index; + + if (unlikely(req->buf_index >= ctx->nr_user_bufs)) + return -EFAULT; + index = array_index_nospec(req->buf_index, ctx->nr_user_bufs); + req->imu = ctx->user_bufs[index]; + io_req_set_rsrc_node(req, ctx, 0); + } + + ioprio = READ_ONCE(sqe->ioprio); + if (ioprio) { + ret = ioprio_check_cap(ioprio); + if (ret) + return ret; + + rw->kiocb.ki_ioprio = ioprio; + } else { + rw->kiocb.ki_ioprio = get_current_ioprio(); + } + + rw->addr = READ_ONCE(sqe->addr); + rw->len = READ_ONCE(sqe->len); + rw->flags = READ_ONCE(sqe->rw_flags); + return 0; +} + +void io_readv_writev_cleanup(struct io_kiocb *req) +{ + struct io_async_rw *io = req->async_data; + + kfree(io->free_iovec); +} + +static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) +{ + switch (ret) { + case -EIOCBQUEUED: + break; + case -ERESTARTSYS: + case -ERESTARTNOINTR: + case -ERESTARTNOHAND: + case -ERESTART_RESTARTBLOCK: + /* + * We can't just restart the syscall, since previously + * submitted sqes may already be in progress. Just fail this + * IO with EINTR. + */ + ret = -EINTR; + fallthrough; + default: + kiocb->ki_complete(kiocb, ret); + } +} + +static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) +{ + struct io_rw *rw = io_kiocb_to_cmd(req); + + if (rw->kiocb.ki_pos != -1) + return &rw->kiocb.ki_pos; + + if (!(req->file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + rw->kiocb.ki_pos = req->file->f_pos; + return &rw->kiocb.ki_pos; + } + + rw->kiocb.ki_pos = 0; + return NULL; +} + +static void io_req_task_queue_reissue(struct io_kiocb *req) +{ + req->io_task_work.func = io_queue_iowq; + io_req_task_work_add(req); +} + +#ifdef CONFIG_BLOCK +static bool io_resubmit_prep(struct io_kiocb *req) +{ + struct io_async_rw *io = req->async_data; + + if (!req_has_async_data(req)) + return !io_req_prep_async(req); + iov_iter_restore(&io->s.iter, &io->s.iter_state); + return true; +} + +static bool io_rw_should_reissue(struct io_kiocb *req) +{ + umode_t mode = file_inode(req->file)->i_mode; + struct io_ring_ctx *ctx = req->ctx; + + if (!S_ISBLK(mode) && !S_ISREG(mode)) + return false; + if ((req->flags & REQ_F_NOWAIT) || (io_wq_current_is_worker() && + !(ctx->flags & IORING_SETUP_IOPOLL))) + return false; + /* + * If ref is dying, we might be running poll reap from the exit work. + * Don't attempt to reissue from that path, just let it fail with + * -EAGAIN. + */ + if (percpu_ref_is_dying(&ctx->refs)) + return false; + /* + * Play it safe and assume not safe to re-import and reissue if we're + * not in the original thread group (or in task context). + */ + if (!same_thread_group(req->task, current) || !in_task()) + return false; + return true; +} +#else +static bool io_resubmit_prep(struct io_kiocb *req) +{ + return false; +} +static bool io_rw_should_reissue(struct io_kiocb *req) +{ + return false; +} +#endif + +static void kiocb_end_write(struct io_kiocb *req) +{ + /* + * Tell lockdep we inherited freeze protection from submission + * thread. + */ + if (req->flags & REQ_F_ISREG) { + struct super_block *sb = file_inode(req->file)->i_sb; + + __sb_writers_acquired(sb, SB_FREEZE_WRITE); + sb_end_write(sb); + } +} + +static bool __io_complete_rw_common(struct io_kiocb *req, long res) +{ + struct io_rw *rw = io_kiocb_to_cmd(req); + + if (rw->kiocb.ki_flags & IOCB_WRITE) { + kiocb_end_write(req); + fsnotify_modify(req->file); + } else { + fsnotify_access(req->file); + } + if (unlikely(res != req->cqe.res)) { + if ((res == -EAGAIN || res == -EOPNOTSUPP) && + io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO; + return true; + } + req_set_fail(req); + req->cqe.res = res; + } + return false; +} + +static void io_complete_rw(struct kiocb *kiocb, long res) +{ + struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb); + struct io_kiocb *req = cmd_to_io_kiocb(rw); + + if (__io_complete_rw_common(req, res)) + return; + io_req_set_res(req, res, 0); + req->io_task_work.func = io_req_task_complete; + io_req_task_work_add(req); +} + +static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) +{ + struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb); + struct io_kiocb *req = cmd_to_io_kiocb(rw); + + if (kiocb->ki_flags & IOCB_WRITE) + kiocb_end_write(req); + if (unlikely(res != req->cqe.res)) { + if (res == -EAGAIN && io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO; + return; + } + req->cqe.res = res; + } + + /* order with io_iopoll_complete() checking ->iopoll_completed */ + smp_store_release(&req->iopoll_completed, 1); +} + +static int kiocb_done(struct io_kiocb *req, ssize_t ret, + unsigned int issue_flags) +{ + struct io_async_rw *io = req->async_data; + struct io_rw *rw = io_kiocb_to_cmd(req); + + /* add previously done IO, if any */ + if (req_has_async_data(req) && io->bytes_done > 0) { + if (ret < 0) + ret = io->bytes_done; + else + ret += io->bytes_done; + } + + if (req->flags & REQ_F_CUR_POS) + req->file->f_pos = rw->kiocb.ki_pos; + if (ret >= 0 && (rw->kiocb.ki_complete == io_complete_rw)) { + if (!__io_complete_rw_common(req, ret)) { + io_req_set_res(req, req->cqe.res, + io_put_kbuf(req, issue_flags)); + return IOU_OK; + } + } else { + io_rw_done(&rw->kiocb, ret); + } + + if (req->flags & REQ_F_REISSUE) { + req->flags &= ~REQ_F_REISSUE; + if (io_resubmit_prep(req)) + io_req_task_queue_reissue(req); + else + io_req_task_queue_fail(req, ret); + } + return IOU_ISSUE_SKIP_COMPLETE; +} + +#ifdef CONFIG_COMPAT +static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov, + unsigned int issue_flags) +{ + struct io_rw *rw = io_kiocb_to_cmd(req); + struct compat_iovec __user *uiov; + compat_ssize_t clen; + void __user *buf; + size_t len; + + uiov = u64_to_user_ptr(rw->addr); + if (!access_ok(uiov, sizeof(*uiov))) + return -EFAULT; + if (__get_user(clen, &uiov->iov_len)) + return -EFAULT; + if (clen < 0) + return -EINVAL; + + len = clen; + buf = io_buffer_select(req, &len, issue_flags); + if (!buf) + return -ENOBUFS; + rw->addr = (unsigned long) buf; + iov[0].iov_base = buf; + rw->len = iov[0].iov_len = (compat_size_t) len; + return 0; +} +#endif + +static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, + unsigned int issue_flags) +{ + struct io_rw *rw = io_kiocb_to_cmd(req); + struct iovec __user *uiov = u64_to_user_ptr(rw->addr); + void __user *buf; + ssize_t len; + + if (copy_from_user(iov, uiov, sizeof(*uiov))) + return -EFAULT; + + len = iov[0].iov_len; + if (len < 0) + return -EINVAL; + buf = io_buffer_select(req, &len, issue_flags); + if (!buf) + return -ENOBUFS; + rw->addr = (unsigned long) buf; + iov[0].iov_base = buf; + rw->len = iov[0].iov_len = len; + return 0; +} + +static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, + unsigned int issue_flags) +{ + struct io_rw *rw = io_kiocb_to_cmd(req); + + if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) { + iov[0].iov_base = u64_to_user_ptr(rw->addr); + iov[0].iov_len = rw->len; + return 0; + } + if (rw->len != 1) + return -EINVAL; + +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + return io_compat_import(req, iov, issue_flags); +#endif + + return __io_iov_buffer_select(req, iov, issue_flags); +} + +static struct iovec *__io_import_iovec(int ddir, struct io_kiocb *req, + struct io_rw_state *s, + unsigned int issue_flags) +{ + struct io_rw *rw = io_kiocb_to_cmd(req); + struct iov_iter *iter = &s->iter; + u8 opcode = req->opcode; + struct iovec *iovec; + void __user *buf; + size_t sqe_len; + ssize_t ret; + + if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { + ret = io_import_fixed(ddir, iter, req->imu, rw->addr, rw->len); + if (ret) + return ERR_PTR(ret); + return NULL; + } + + buf = u64_to_user_ptr(rw->addr); + sqe_len = rw->len; + + if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) { + if (io_do_buffer_select(req)) { + buf = io_buffer_select(req, &sqe_len, issue_flags); + if (!buf) + return ERR_PTR(-ENOBUFS); + rw->addr = (unsigned long) buf; + rw->len = sqe_len; + } + + ret = import_single_range(ddir, buf, sqe_len, s->fast_iov, iter); + if (ret) + return ERR_PTR(ret); + return NULL; + } + + iovec = s->fast_iov; + if (req->flags & REQ_F_BUFFER_SELECT) { + ret = io_iov_buffer_select(req, iovec, issue_flags); + if (ret) + return ERR_PTR(ret); + iov_iter_init(iter, ddir, iovec, 1, iovec->iov_len); + return NULL; + } + + ret = __import_iovec(ddir, buf, sqe_len, UIO_FASTIOV, &iovec, iter, + req->ctx->compat); + if (unlikely(ret < 0)) + return ERR_PTR(ret); + return iovec; +} + +static inline int io_import_iovec(int rw, struct io_kiocb *req, + struct iovec **iovec, struct io_rw_state *s, + unsigned int issue_flags) +{ + *iovec = __io_import_iovec(rw, req, s, issue_flags); + if (unlikely(IS_ERR(*iovec))) + return PTR_ERR(*iovec); + + iov_iter_save_state(&s->iter, &s->iter_state); + return 0; +} + +static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb) +{ + return (kiocb->ki_filp->f_mode & FMODE_STREAM) ? NULL : &kiocb->ki_pos; +} + +/* + * For files that don't have ->read_iter() and ->write_iter(), handle them + * by looping over ->read() or ->write() manually. + */ +static ssize_t loop_rw_iter(int ddir, struct io_rw *rw, struct iov_iter *iter) +{ + struct kiocb *kiocb = &rw->kiocb; + struct file *file = kiocb->ki_filp; + ssize_t ret = 0; + loff_t *ppos; + + /* + * Don't support polled IO through this interface, and we can't + * support non-blocking either. For the latter, this just causes + * the kiocb to be handled from an async context. + */ + if (kiocb->ki_flags & IOCB_HIPRI) + return -EOPNOTSUPP; + if ((kiocb->ki_flags & IOCB_NOWAIT) && + !(kiocb->ki_filp->f_flags & O_NONBLOCK)) + return -EAGAIN; + + ppos = io_kiocb_ppos(kiocb); + + while (iov_iter_count(iter)) { + struct iovec iovec; + ssize_t nr; + + if (!iov_iter_is_bvec(iter)) { + iovec = iov_iter_iovec(iter); + } else { + iovec.iov_base = u64_to_user_ptr(rw->addr); + iovec.iov_len = rw->len; + } + + if (ddir == READ) { + nr = file->f_op->read(file, iovec.iov_base, + iovec.iov_len, ppos); + } else { + nr = file->f_op->write(file, iovec.iov_base, + iovec.iov_len, ppos); + } + + if (nr < 0) { + if (!ret) + ret = nr; + break; + } + ret += nr; + if (!iov_iter_is_bvec(iter)) { + iov_iter_advance(iter, nr); + } else { + rw->addr += nr; + rw->len -= nr; + if (!rw->len) + break; + } + if (nr != iovec.iov_len) + break; + } + + return ret; +} + +static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, + const struct iovec *fast_iov, struct iov_iter *iter) +{ + struct io_async_rw *io = req->async_data; + + memcpy(&io->s.iter, iter, sizeof(*iter)); + io->free_iovec = iovec; + io->bytes_done = 0; + /* can only be fixed buffers, no need to do anything */ + if (iov_iter_is_bvec(iter)) + return; + if (!iovec) { + unsigned iov_off = 0; + + io->s.iter.iov = io->s.fast_iov; + if (iter->iov != fast_iov) { + iov_off = iter->iov - fast_iov; + io->s.iter.iov += iov_off; + } + if (io->s.fast_iov != fast_iov) + memcpy(io->s.fast_iov + iov_off, fast_iov + iov_off, + sizeof(struct iovec) * iter->nr_segs); + } else { + req->flags |= REQ_F_NEED_CLEANUP; + } +} + +static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, + struct io_rw_state *s, bool force) +{ + if (!force && !io_op_defs[req->opcode].prep_async) + return 0; + if (!req_has_async_data(req)) { + struct io_async_rw *iorw; + + if (io_alloc_async_data(req)) { + kfree(iovec); + return -ENOMEM; + } + + io_req_map_rw(req, iovec, s->fast_iov, &s->iter); + iorw = req->async_data; + /* we've copied and mapped the iter, ensure state is saved */ + iov_iter_save_state(&iorw->s.iter, &iorw->s.iter_state); + } + return 0; +} + +static inline int io_rw_prep_async(struct io_kiocb *req, int rw) +{ + struct io_async_rw *iorw = req->async_data; + struct iovec *iov; + int ret; + + /* submission path, ->uring_lock should already be taken */ + ret = io_import_iovec(rw, req, &iov, &iorw->s, 0); + if (unlikely(ret < 0)) + return ret; + + iorw->bytes_done = 0; + iorw->free_iovec = iov; + if (iov) + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +int io_readv_prep_async(struct io_kiocb *req) +{ + return io_rw_prep_async(req, READ); +} + +int io_writev_prep_async(struct io_kiocb *req) +{ + return io_rw_prep_async(req, WRITE); +} + +/* + * This is our waitqueue callback handler, registered through __folio_lock_async() + * when we initially tried to do the IO with the iocb armed our waitqueue. + * This gets called when the page is unlocked, and we generally expect that to + * happen when the page IO is completed and the page is now uptodate. This will + * queue a task_work based retry of the operation, attempting to copy the data + * again. If the latter fails because the page was NOT uptodate, then we will + * do a thread based blocking retry of the operation. That's the unexpected + * slow path. + */ +static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, + int sync, void *arg) +{ + struct wait_page_queue *wpq; + struct io_kiocb *req = wait->private; + struct io_rw *rw = io_kiocb_to_cmd(req); + struct wait_page_key *key = arg; + + wpq = container_of(wait, struct wait_page_queue, wait); + + if (!wake_page_match(wpq, key)) + return 0; + + rw->kiocb.ki_flags &= ~IOCB_WAITQ; + list_del_init(&wait->entry); + io_req_task_queue(req); + return 1; +} + +/* + * This controls whether a given IO request should be armed for async page + * based retry. If we return false here, the request is handed to the async + * worker threads for retry. If we're doing buffered reads on a regular file, + * we prepare a private wait_page_queue entry and retry the operation. This + * will either succeed because the page is now uptodate and unlocked, or it + * will register a callback when the page is unlocked at IO completion. Through + * that callback, io_uring uses task_work to setup a retry of the operation. + * That retry will attempt the buffered read again. The retry will generally + * succeed, or in rare cases where it fails, we then fall back to using the + * async worker threads for a blocking retry. + */ +static bool io_rw_should_retry(struct io_kiocb *req) +{ + struct io_async_rw *io = req->async_data; + struct wait_page_queue *wait = &io->wpq; + struct io_rw *rw = io_kiocb_to_cmd(req); + struct kiocb *kiocb = &rw->kiocb; + + /* never retry for NOWAIT, we just complete with -EAGAIN */ + if (req->flags & REQ_F_NOWAIT) + return false; + + /* Only for buffered IO */ + if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI)) + return false; + + /* + * just use poll if we can, and don't attempt if the fs doesn't + * support callback based unlocks + */ + if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC)) + return false; + + wait->wait.func = io_async_buf_func; + wait->wait.private = req; + wait->wait.flags = 0; + INIT_LIST_HEAD(&wait->wait.entry); + kiocb->ki_flags |= IOCB_WAITQ; + kiocb->ki_flags &= ~IOCB_NOWAIT; + kiocb->ki_waitq = wait; + return true; +} + +static inline int io_iter_do_read(struct io_rw *rw, struct iov_iter *iter) +{ + struct file *file = rw->kiocb.ki_filp; + + if (likely(file->f_op->read_iter)) + return call_read_iter(file, &rw->kiocb, iter); + else if (file->f_op->read) + return loop_rw_iter(READ, rw, iter); + else + return -EINVAL; +} + +static bool need_read_all(struct io_kiocb *req) +{ + return req->flags & REQ_F_ISREG || + S_ISBLK(file_inode(req->file)->i_mode); +} + +static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) +{ + struct io_rw *rw = io_kiocb_to_cmd(req); + struct kiocb *kiocb = &rw->kiocb; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = req->file; + int ret; + + if (unlikely(!file || !(file->f_mode & mode))) + return -EBADF; + + if (!io_req_ffs_set(req)) + req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; + + kiocb->ki_flags = iocb_flags(file); + ret = kiocb_set_rw_flags(kiocb, rw->flags); + if (unlikely(ret)) + return ret; + + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) + req->flags |= REQ_F_NOWAIT; + + if (ctx->flags & IORING_SETUP_IOPOLL) { + if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) + return -EOPNOTSUPP; + + kiocb->private = NULL; + kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; + kiocb->ki_complete = io_complete_rw_iopoll; + req->iopoll_completed = 0; + } else { + if (kiocb->ki_flags & IOCB_HIPRI) + return -EINVAL; + kiocb->ki_complete = io_complete_rw; + } + + return 0; +} + +int io_read(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_rw *rw = io_kiocb_to_cmd(req); + struct io_rw_state __s, *s = &__s; + struct iovec *iovec; + struct kiocb *kiocb = &rw->kiocb; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + struct io_async_rw *io; + ssize_t ret, ret2; + loff_t *ppos; + + if (!req_has_async_data(req)) { + ret = io_import_iovec(READ, req, &iovec, s, issue_flags); + if (unlikely(ret < 0)) + return ret; + } else { + io = req->async_data; + s = &io->s; + + /* + * Safe and required to re-import if we're using provided + * buffers, as we dropped the selected one before retry. + */ + if (io_do_buffer_select(req)) { + ret = io_import_iovec(READ, req, &iovec, s, issue_flags); + if (unlikely(ret < 0)) + return ret; + } + + /* + * We come here from an earlier attempt, restore our state to + * match in case it doesn't. It's cheap enough that we don't + * need to make this conditional. + */ + iov_iter_restore(&s->iter, &s->iter_state); + iovec = NULL; + } + ret = io_rw_init_file(req, FMODE_READ); + if (unlikely(ret)) { + kfree(iovec); + return ret; + } + req->cqe.res = iov_iter_count(&s->iter); + + if (force_nonblock) { + /* If the file doesn't support async, just async punt */ + if (unlikely(!io_file_supports_nowait(req))) { + ret = io_setup_async_rw(req, iovec, s, true); + return ret ?: -EAGAIN; + } + kiocb->ki_flags |= IOCB_NOWAIT; + } else { + /* Ensure we clear previously set non-block flag */ + kiocb->ki_flags &= ~IOCB_NOWAIT; + } + + ppos = io_kiocb_update_pos(req); + + ret = rw_verify_area(READ, req->file, ppos, req->cqe.res); + if (unlikely(ret)) { + kfree(iovec); + return ret; + } + + ret = io_iter_do_read(rw, &s->iter); + + if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) { + req->flags &= ~REQ_F_REISSUE; + /* if we can poll, just do that */ + if (req->opcode == IORING_OP_READ && file_can_poll(req->file)) + return -EAGAIN; + /* IOPOLL retry should happen for io-wq threads */ + if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) + goto done; + /* no retry on NONBLOCK nor RWF_NOWAIT */ + if (req->flags & REQ_F_NOWAIT) + goto done; + ret = 0; + } else if (ret == -EIOCBQUEUED) { + if (iovec) + kfree(iovec); + return IOU_ISSUE_SKIP_COMPLETE; + } else if (ret == req->cqe.res || ret <= 0 || !force_nonblock || + (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) { + /* read all, failed, already did sync or don't want to retry */ + goto done; + } + + /* + * Don't depend on the iter state matching what was consumed, or being + * untouched in case of error. Restore it and we'll advance it + * manually if we need to. + */ + iov_iter_restore(&s->iter, &s->iter_state); + + ret2 = io_setup_async_rw(req, iovec, s, true); + if (ret2) + return ret2; + + iovec = NULL; + io = req->async_data; + s = &io->s; + /* + * Now use our persistent iterator and state, if we aren't already. + * We've restored and mapped the iter to match. + */ + + do { + /* + * We end up here because of a partial read, either from + * above or inside this loop. Advance the iter by the bytes + * that were consumed. + */ + iov_iter_advance(&s->iter, ret); + if (!iov_iter_count(&s->iter)) + break; + io->bytes_done += ret; + iov_iter_save_state(&s->iter, &s->iter_state); + + /* if we can retry, do so with the callbacks armed */ + if (!io_rw_should_retry(req)) { + kiocb->ki_flags &= ~IOCB_WAITQ; + return -EAGAIN; + } + + /* + * Now retry read with the IOCB_WAITQ parts set in the iocb. If + * we get -EIOCBQUEUED, then we'll get a notification when the + * desired page gets unlocked. We can also get a partial read + * here, and if we do, then just retry at the new offset. + */ + ret = io_iter_do_read(rw, &s->iter); + if (ret == -EIOCBQUEUED) + return IOU_ISSUE_SKIP_COMPLETE; + /* we got some bytes, but not all. retry. */ + kiocb->ki_flags &= ~IOCB_WAITQ; + iov_iter_restore(&s->iter, &s->iter_state); + } while (ret > 0); +done: + /* it's faster to check here then delegate to kfree */ + if (iovec) + kfree(iovec); + return kiocb_done(req, ret, issue_flags); +} + +int io_write(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_rw *rw = io_kiocb_to_cmd(req); + struct io_rw_state __s, *s = &__s; + struct iovec *iovec; + struct kiocb *kiocb = &rw->kiocb; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + ssize_t ret, ret2; + loff_t *ppos; + + if (!req_has_async_data(req)) { + ret = io_import_iovec(WRITE, req, &iovec, s, issue_flags); + if (unlikely(ret < 0)) + return ret; + } else { + struct io_async_rw *io = req->async_data; + + s = &io->s; + iov_iter_restore(&s->iter, &s->iter_state); + iovec = NULL; + } + ret = io_rw_init_file(req, FMODE_WRITE); + if (unlikely(ret)) { + kfree(iovec); + return ret; + } + req->cqe.res = iov_iter_count(&s->iter); + + if (force_nonblock) { + /* If the file doesn't support async, just async punt */ + if (unlikely(!io_file_supports_nowait(req))) + goto copy_iov; + + /* file path doesn't support NOWAIT for non-direct_IO */ + if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) && + (req->flags & REQ_F_ISREG)) + goto copy_iov; + + kiocb->ki_flags |= IOCB_NOWAIT; + } else { + /* Ensure we clear previously set non-block flag */ + kiocb->ki_flags &= ~IOCB_NOWAIT; + } + + ppos = io_kiocb_update_pos(req); + + ret = rw_verify_area(WRITE, req->file, ppos, req->cqe.res); + if (unlikely(ret)) { + kfree(iovec); + return ret; + } + + /* + * Open-code file_start_write here to grab freeze protection, + * which will be released by another thread in + * io_complete_rw(). Fool lockdep by telling it the lock got + * released so that it doesn't complain about the held lock when + * we return to userspace. + */ + if (req->flags & REQ_F_ISREG) { + sb_start_write(file_inode(req->file)->i_sb); + __sb_writers_release(file_inode(req->file)->i_sb, + SB_FREEZE_WRITE); + } + kiocb->ki_flags |= IOCB_WRITE; + + if (likely(req->file->f_op->write_iter)) + ret2 = call_write_iter(req->file, kiocb, &s->iter); + else if (req->file->f_op->write) + ret2 = loop_rw_iter(WRITE, rw, &s->iter); + else + ret2 = -EINVAL; + + if (req->flags & REQ_F_REISSUE) { + req->flags &= ~REQ_F_REISSUE; + ret2 = -EAGAIN; + } + + /* + * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just + * retry them without IOCB_NOWAIT. + */ + if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT)) + ret2 = -EAGAIN; + /* no retry on NONBLOCK nor RWF_NOWAIT */ + if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT)) + goto done; + if (!force_nonblock || ret2 != -EAGAIN) { + /* IOPOLL retry should happen for io-wq threads */ + if (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL)) + goto copy_iov; +done: + ret = kiocb_done(req, ret2, issue_flags); + } else { +copy_iov: + iov_iter_restore(&s->iter, &s->iter_state); + ret = io_setup_async_rw(req, iovec, s, false); + return ret ?: -EAGAIN; + } + /* it's reportedly faster than delegating the null check to kfree() */ + if (iovec) + kfree(iovec); + return ret; +} + +static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) +{ + io_commit_cqring_flush(ctx); + if (ctx->flags & IORING_SETUP_SQPOLL) + io_cqring_wake(ctx); +} + +int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) +{ + struct io_wq_work_node *pos, *start, *prev; + unsigned int poll_flags = BLK_POLL_NOSLEEP; + DEFINE_IO_COMP_BATCH(iob); + int nr_events = 0; + + /* + * Only spin for completions if we don't have multiple devices hanging + * off our complete list. + */ + if (ctx->poll_multi_queue || force_nonspin) + poll_flags |= BLK_POLL_ONESHOT; + + wq_list_for_each(pos, start, &ctx->iopoll_list) { + struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list); + struct io_rw *rw = io_kiocb_to_cmd(req); + int ret; + + /* + * Move completed and retryable entries to our local lists. + * If we find a request that requires polling, break out + * and complete those lists first, if we have entries there. + */ + if (READ_ONCE(req->iopoll_completed)) + break; + + ret = rw->kiocb.ki_filp->f_op->iopoll(&rw->kiocb, &iob, poll_flags); + if (unlikely(ret < 0)) + return ret; + else if (ret) + poll_flags |= BLK_POLL_ONESHOT; + + /* iopoll may have completed current req */ + if (!rq_list_empty(iob.req_list) || + READ_ONCE(req->iopoll_completed)) + break; + } + + if (!rq_list_empty(iob.req_list)) + iob.complete(&iob); + else if (!pos) + return 0; + + prev = start; + wq_list_for_each_resume(pos, prev) { + struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list); + + /* order with io_complete_rw_iopoll(), e.g. ->result updates */ + if (!smp_load_acquire(&req->iopoll_completed)) + break; + nr_events++; + if (unlikely(req->flags & REQ_F_CQE_SKIP)) + continue; + + req->cqe.flags = io_put_kbuf(req, 0); + __io_fill_cqe_req(req->ctx, req); + } + + if (unlikely(!nr_events)) + return 0; + + io_commit_cqring(ctx); + io_cqring_ev_posted_iopoll(ctx); + pos = start ? start->next : ctx->iopoll_list.first; + wq_list_cut(&ctx->iopoll_list, prev, start); + io_free_batch_list(ctx, pos); + return nr_events; +} diff --git a/io_uring/rw.h b/io_uring/rw.h new file mode 100644 index 000000000000..0204c3fcafa5 --- /dev/null +++ b/io_uring/rw.h @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/pagemap.h> + +struct io_rw_state { + struct iov_iter iter; + struct iov_iter_state iter_state; + struct iovec fast_iov[UIO_FASTIOV]; +}; + +struct io_async_rw { + struct io_rw_state s; + const struct iovec *free_iovec; + size_t bytes_done; + struct wait_page_queue wpq; +}; + +int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_read(struct io_kiocb *req, unsigned int issue_flags); +int io_readv_prep_async(struct io_kiocb *req); +int io_write(struct io_kiocb *req, unsigned int issue_flags); +int io_writev_prep_async(struct io_kiocb *req); +void io_readv_writev_cleanup(struct io_kiocb *req); diff --git a/fs/io-wq.h b/io_uring/slist.h index ba6eee76d028..f27601fa4660 100644 --- a/fs/io-wq.h +++ b/io_uring/slist.h @@ -1,33 +1,7 @@ -#ifndef INTERNAL_IO_WQ_H -#define INTERNAL_IO_WQ_H +#ifndef INTERNAL_IO_SLIST_H +#define INTERNAL_IO_SLIST_H -#include <linux/refcount.h> - -struct io_wq; - -enum { - IO_WQ_WORK_CANCEL = 1, - IO_WQ_WORK_HASHED = 2, - IO_WQ_WORK_UNBOUND = 4, - IO_WQ_WORK_CONCURRENT = 16, - - IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */ -}; - -enum io_wq_cancel { - IO_WQ_CANCEL_OK, /* cancelled before started */ - IO_WQ_CANCEL_RUNNING, /* found, running, and attempted cancelled */ - IO_WQ_CANCEL_NOTFOUND, /* work not found */ -}; - -struct io_wq_work_node { - struct io_wq_work_node *next; -}; - -struct io_wq_work_list { - struct io_wq_work_node *first; - struct io_wq_work_node *last; -}; +#include <linux/io_uring_types.h> #define wq_list_for_each(pos, prv, head) \ for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next) @@ -36,6 +10,7 @@ struct io_wq_work_list { for (; pos; prv = pos, pos = (pos)->next) #define wq_list_empty(list) (READ_ONCE((list)->first) == NULL) + #define INIT_WQ_LIST(list) do { \ (list)->first = NULL; \ } while (0) @@ -152,12 +127,6 @@ struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack) return node; } -struct io_wq_work { - struct io_wq_work_node list; - unsigned flags; - int cancel_seq; -}; - static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) { if (!work->list.next) @@ -166,63 +135,4 @@ static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) return container_of(work->list.next, struct io_wq_work, list); } -typedef struct io_wq_work *(free_work_fn)(struct io_wq_work *); -typedef void (io_wq_work_fn)(struct io_wq_work *); - -struct io_wq_hash { - refcount_t refs; - unsigned long map; - struct wait_queue_head wait; -}; - -static inline void io_wq_put_hash(struct io_wq_hash *hash) -{ - if (refcount_dec_and_test(&hash->refs)) - kfree(hash); -} - -struct io_wq_data { - struct io_wq_hash *hash; - struct task_struct *task; - io_wq_work_fn *do_work; - free_work_fn *free_work; -}; - -struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data); -void io_wq_exit_start(struct io_wq *wq); -void io_wq_put_and_exit(struct io_wq *wq); - -void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); -void io_wq_hash_work(struct io_wq_work *work, void *val); - -int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask); -int io_wq_max_workers(struct io_wq *wq, int *new_count); - -static inline bool io_wq_is_hashed(struct io_wq_work *work) -{ - return work->flags & IO_WQ_WORK_HASHED; -} - -typedef bool (work_cancel_fn)(struct io_wq_work *, void *); - -enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, - void *data, bool cancel_all); - -#if defined(CONFIG_IO_WQ) -extern void io_wq_worker_sleeping(struct task_struct *); -extern void io_wq_worker_running(struct task_struct *); -#else -static inline void io_wq_worker_sleeping(struct task_struct *tsk) -{ -} -static inline void io_wq_worker_running(struct task_struct *tsk) -{ -} -#endif - -static inline bool io_wq_current_is_worker(void) -{ - return in_task() && (current->flags & PF_IO_WORKER) && - current->worker_private; -} -#endif +#endif // INTERNAL_IO_SLIST_H
\ No newline at end of file diff --git a/io_uring/splice.c b/io_uring/splice.c new file mode 100644 index 000000000000..b013ba34bffa --- /dev/null +++ b/io_uring/splice.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/io_uring.h> +#include <linux/splice.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "splice.h" + +struct io_splice { + struct file *file_out; + loff_t off_out; + loff_t off_in; + u64 len; + int splice_fd_in; + unsigned int flags; +}; + +static int __io_splice_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_splice *sp = io_kiocb_to_cmd(req); + unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL; + + sp->len = READ_ONCE(sqe->len); + sp->flags = READ_ONCE(sqe->splice_flags); + if (unlikely(sp->flags & ~valid_flags)) + return -EINVAL; + sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); + return 0; +} + +int io_tee_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + if (READ_ONCE(sqe->splice_off_in) || READ_ONCE(sqe->off)) + return -EINVAL; + return __io_splice_prep(req, sqe); +} + +int io_tee(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_splice *sp = io_kiocb_to_cmd(req); + struct file *out = sp->file_out; + unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + struct file *in; + long ret = 0; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + + if (sp->len) + ret = do_tee(in, out, sp->len, flags); + + if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) + io_put_file(in); +done: + if (ret != sp->len) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_splice *sp = io_kiocb_to_cmd(req); + + sp->off_in = READ_ONCE(sqe->splice_off_in); + sp->off_out = READ_ONCE(sqe->off); + return __io_splice_prep(req, sqe); +} + +int io_splice(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_splice *sp = io_kiocb_to_cmd(req); + struct file *out = sp->file_out; + unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + loff_t *poff_in, *poff_out; + struct file *in; + long ret = 0; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + + poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; + poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; + + if (sp->len) + ret = do_splice(in, poff_in, out, poff_out, sp->len, flags); + + if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) + io_put_file(in); +done: + if (ret != sp->len) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} diff --git a/io_uring/splice.h b/io_uring/splice.h new file mode 100644 index 000000000000..542f94168ad3 --- /dev/null +++ b/io_uring/splice.h @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 + +int io_tee_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_tee(struct io_kiocb *req, unsigned int issue_flags); + +int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_splice(struct io_kiocb *req, unsigned int issue_flags); diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c new file mode 100644 index 000000000000..76d4d70c733a --- /dev/null +++ b/io_uring/sqpoll.c @@ -0,0 +1,425 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Contains the core associated with submission side polling of the SQ + * ring, offloading submissions from the application to a kernel thread. + */ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/audit.h> +#include <linux/security.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "sqpoll.h" + +#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 + +enum { + IO_SQ_THREAD_SHOULD_STOP = 0, + IO_SQ_THREAD_SHOULD_PARK, +}; + +void io_sq_thread_unpark(struct io_sq_data *sqd) + __releases(&sqd->lock) +{ + WARN_ON_ONCE(sqd->thread == current); + + /* + * Do the dance but not conditional clear_bit() because it'd race with + * other threads incrementing park_pending and setting the bit. + */ + clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + if (atomic_dec_return(&sqd->park_pending)) + set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + mutex_unlock(&sqd->lock); +} + +void io_sq_thread_park(struct io_sq_data *sqd) + __acquires(&sqd->lock) +{ + WARN_ON_ONCE(sqd->thread == current); + + atomic_inc(&sqd->park_pending); + set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + mutex_lock(&sqd->lock); + if (sqd->thread) + wake_up_process(sqd->thread); +} + +void io_sq_thread_stop(struct io_sq_data *sqd) +{ + WARN_ON_ONCE(sqd->thread == current); + WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)); + + set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); + mutex_lock(&sqd->lock); + if (sqd->thread) + wake_up_process(sqd->thread); + mutex_unlock(&sqd->lock); + wait_for_completion(&sqd->exited); +} + +void io_put_sq_data(struct io_sq_data *sqd) +{ + if (refcount_dec_and_test(&sqd->refs)) { + WARN_ON_ONCE(atomic_read(&sqd->park_pending)); + + io_sq_thread_stop(sqd); + kfree(sqd); + } +} + +static __cold void io_sqd_update_thread_idle(struct io_sq_data *sqd) +{ + struct io_ring_ctx *ctx; + unsigned sq_thread_idle = 0; + + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle); + sqd->sq_thread_idle = sq_thread_idle; +} + +void io_sq_thread_finish(struct io_ring_ctx *ctx) +{ + struct io_sq_data *sqd = ctx->sq_data; + + if (sqd) { + io_sq_thread_park(sqd); + list_del_init(&ctx->sqd_list); + io_sqd_update_thread_idle(sqd); + io_sq_thread_unpark(sqd); + + io_put_sq_data(sqd); + ctx->sq_data = NULL; + } +} + +static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p) +{ + struct io_ring_ctx *ctx_attach; + struct io_sq_data *sqd; + struct fd f; + + f = fdget(p->wq_fd); + if (!f.file) + return ERR_PTR(-ENXIO); + if (!io_is_uring_fops(f.file)) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + ctx_attach = f.file->private_data; + sqd = ctx_attach->sq_data; + if (!sqd) { + fdput(f); + return ERR_PTR(-EINVAL); + } + if (sqd->task_tgid != current->tgid) { + fdput(f); + return ERR_PTR(-EPERM); + } + + refcount_inc(&sqd->refs); + fdput(f); + return sqd; +} + +static struct io_sq_data *io_get_sq_data(struct io_uring_params *p, + bool *attached) +{ + struct io_sq_data *sqd; + + *attached = false; + if (p->flags & IORING_SETUP_ATTACH_WQ) { + sqd = io_attach_sq_data(p); + if (!IS_ERR(sqd)) { + *attached = true; + return sqd; + } + /* fall through for EPERM case, setup new sqd/task */ + if (PTR_ERR(sqd) != -EPERM) + return sqd; + } + + sqd = kzalloc(sizeof(*sqd), GFP_KERNEL); + if (!sqd) + return ERR_PTR(-ENOMEM); + + atomic_set(&sqd->park_pending, 0); + refcount_set(&sqd->refs, 1); + INIT_LIST_HEAD(&sqd->ctx_list); + mutex_init(&sqd->lock); + init_waitqueue_head(&sqd->wait); + init_completion(&sqd->exited); + return sqd; +} + +static inline bool io_sqd_events_pending(struct io_sq_data *sqd) +{ + return READ_ONCE(sqd->state); +} + +static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) +{ + unsigned int to_submit; + int ret = 0; + + to_submit = io_sqring_entries(ctx); + /* if we're handling multiple rings, cap submit size for fairness */ + if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE) + to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE; + + if (!wq_list_empty(&ctx->iopoll_list) || to_submit) { + const struct cred *creds = NULL; + + if (ctx->sq_creds != current_cred()) + creds = override_creds(ctx->sq_creds); + + mutex_lock(&ctx->uring_lock); + if (!wq_list_empty(&ctx->iopoll_list)) + io_do_iopoll(ctx, true); + + /* + * Don't submit if refs are dying, good for io_uring_register(), + * but also it is relied upon by io_ring_exit_work() + */ + if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) && + !(ctx->flags & IORING_SETUP_R_DISABLED)) + ret = io_submit_sqes(ctx, to_submit); + mutex_unlock(&ctx->uring_lock); + + if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) + wake_up(&ctx->sqo_sq_wait); + if (creds) + revert_creds(creds); + } + + return ret; +} + +static bool io_sqd_handle_event(struct io_sq_data *sqd) +{ + bool did_sig = false; + struct ksignal ksig; + + if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) || + signal_pending(current)) { + mutex_unlock(&sqd->lock); + if (signal_pending(current)) + did_sig = get_signal(&ksig); + cond_resched(); + mutex_lock(&sqd->lock); + } + return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); +} + +static int io_sq_thread(void *data) +{ + struct io_sq_data *sqd = data; + struct io_ring_ctx *ctx; + unsigned long timeout = 0; + char buf[TASK_COMM_LEN]; + DEFINE_WAIT(wait); + + snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); + set_task_comm(current, buf); + + if (sqd->sq_cpu != -1) + set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu)); + else + set_cpus_allowed_ptr(current, cpu_online_mask); + current->flags |= PF_NO_SETAFFINITY; + + audit_alloc_kernel(current); + + mutex_lock(&sqd->lock); + while (1) { + bool cap_entries, sqt_spin = false; + + if (io_sqd_events_pending(sqd) || signal_pending(current)) { + if (io_sqd_handle_event(sqd)) + break; + timeout = jiffies + sqd->sq_thread_idle; + } + + cap_entries = !list_is_singular(&sqd->ctx_list); + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { + int ret = __io_sq_thread(ctx, cap_entries); + + if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list))) + sqt_spin = true; + } + if (io_run_task_work()) + sqt_spin = true; + + if (sqt_spin || !time_after(jiffies, timeout)) { + cond_resched(); + if (sqt_spin) + timeout = jiffies + sqd->sq_thread_idle; + continue; + } + + prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE); + if (!io_sqd_events_pending(sqd) && !task_work_pending(current)) { + bool needs_sched = true; + + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { + atomic_or(IORING_SQ_NEED_WAKEUP, + &ctx->rings->sq_flags); + if ((ctx->flags & IORING_SETUP_IOPOLL) && + !wq_list_empty(&ctx->iopoll_list)) { + needs_sched = false; + break; + } + + /* + * Ensure the store of the wakeup flag is not + * reordered with the load of the SQ tail + */ + smp_mb__after_atomic(); + + if (io_sqring_entries(ctx)) { + needs_sched = false; + break; + } + } + + if (needs_sched) { + mutex_unlock(&sqd->lock); + schedule(); + mutex_lock(&sqd->lock); + } + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + atomic_andnot(IORING_SQ_NEED_WAKEUP, + &ctx->rings->sq_flags); + } + + finish_wait(&sqd->wait, &wait); + timeout = jiffies + sqd->sq_thread_idle; + } + + io_uring_cancel_generic(true, sqd); + sqd->thread = NULL; + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags); + io_run_task_work(); + mutex_unlock(&sqd->lock); + + audit_free(current); + + complete(&sqd->exited); + do_exit(0); +} + +int io_sqpoll_wait_sq(struct io_ring_ctx *ctx) +{ + DEFINE_WAIT(wait); + + do { + if (!io_sqring_full(ctx)) + break; + prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE); + + if (!io_sqring_full(ctx)) + break; + schedule(); + } while (!signal_pending(current)); + + finish_wait(&ctx->sqo_sq_wait, &wait); + return 0; +} + +__cold int io_sq_offload_create(struct io_ring_ctx *ctx, + struct io_uring_params *p) +{ + int ret; + + /* Retain compatibility with failing for an invalid attach attempt */ + if ((ctx->flags & (IORING_SETUP_ATTACH_WQ | IORING_SETUP_SQPOLL)) == + IORING_SETUP_ATTACH_WQ) { + struct fd f; + + f = fdget(p->wq_fd); + if (!f.file) + return -ENXIO; + if (!io_is_uring_fops(f.file)) { + fdput(f); + return -EINVAL; + } + fdput(f); + } + if (ctx->flags & IORING_SETUP_SQPOLL) { + struct task_struct *tsk; + struct io_sq_data *sqd; + bool attached; + + ret = security_uring_sqpoll(); + if (ret) + return ret; + + sqd = io_get_sq_data(p, &attached); + if (IS_ERR(sqd)) { + ret = PTR_ERR(sqd); + goto err; + } + + ctx->sq_creds = get_current_cred(); + ctx->sq_data = sqd; + ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); + if (!ctx->sq_thread_idle) + ctx->sq_thread_idle = HZ; + + io_sq_thread_park(sqd); + list_add(&ctx->sqd_list, &sqd->ctx_list); + io_sqd_update_thread_idle(sqd); + /* don't attach to a dying SQPOLL thread, would be racy */ + ret = (attached && !sqd->thread) ? -ENXIO : 0; + io_sq_thread_unpark(sqd); + + if (ret < 0) + goto err; + if (attached) + return 0; + + if (p->flags & IORING_SETUP_SQ_AFF) { + int cpu = p->sq_thread_cpu; + + ret = -EINVAL; + if (cpu >= nr_cpu_ids || !cpu_online(cpu)) + goto err_sqpoll; + sqd->sq_cpu = cpu; + } else { + sqd->sq_cpu = -1; + } + + sqd->task_pid = current->pid; + sqd->task_tgid = current->tgid; + tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE); + if (IS_ERR(tsk)) { + ret = PTR_ERR(tsk); + goto err_sqpoll; + } + + sqd->thread = tsk; + ret = io_uring_alloc_task_context(tsk, ctx); + wake_up_new_task(tsk); + if (ret) + goto err; + } else if (p->flags & IORING_SETUP_SQ_AFF) { + /* Can't have SQ_AFF without SQPOLL */ + ret = -EINVAL; + goto err; + } + + return 0; +err_sqpoll: + complete(&ctx->sq_data->exited); +err: + io_sq_thread_finish(ctx); + return ret; +} diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h new file mode 100644 index 000000000000..0c3fbcd1f583 --- /dev/null +++ b/io_uring/sqpoll.h @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 + +struct io_sq_data { + refcount_t refs; + atomic_t park_pending; + struct mutex lock; + + /* ctx's that are using this sqd */ + struct list_head ctx_list; + + struct task_struct *thread; + struct wait_queue_head wait; + + unsigned sq_thread_idle; + int sq_cpu; + pid_t task_pid; + pid_t task_tgid; + + unsigned long state; + struct completion exited; +}; + +int io_sq_offload_create(struct io_ring_ctx *ctx, struct io_uring_params *p); +void io_sq_thread_finish(struct io_ring_ctx *ctx); +void io_sq_thread_stop(struct io_sq_data *sqd); +void io_sq_thread_park(struct io_sq_data *sqd); +void io_sq_thread_unpark(struct io_sq_data *sqd); +void io_put_sq_data(struct io_sq_data *sqd); +int io_sqpoll_wait_sq(struct io_ring_ctx *ctx); diff --git a/io_uring/statx.c b/io_uring/statx.c new file mode 100644 index 000000000000..6056cd7f4876 --- /dev/null +++ b/io_uring/statx.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "../fs/internal.h" + +#include "io_uring.h" +#include "statx.h" + +struct io_statx { + struct file *file; + int dfd; + unsigned int mask; + unsigned int flags; + struct filename *filename; + struct statx __user *buffer; +}; + +int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_statx *sx = io_kiocb_to_cmd(req); + const char __user *path; + + if (sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + if (req->flags & REQ_F_FIXED_FILE) + return -EBADF; + + sx->dfd = READ_ONCE(sqe->fd); + sx->mask = READ_ONCE(sqe->len); + path = u64_to_user_ptr(READ_ONCE(sqe->addr)); + sx->buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + sx->flags = READ_ONCE(sqe->statx_flags); + + sx->filename = getname_flags(path, + getname_statx_lookup_flags(sx->flags), + NULL); + + if (IS_ERR(sx->filename)) { + int ret = PTR_ERR(sx->filename); + + sx->filename = NULL; + return ret; + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +int io_statx(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_statx *sx = io_kiocb_to_cmd(req); + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_statx(sx->dfd, sx->filename, sx->flags, sx->mask, sx->buffer); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +void io_statx_cleanup(struct io_kiocb *req) +{ + struct io_statx *sx = io_kiocb_to_cmd(req); + + if (sx->filename) + putname(sx->filename); +} diff --git a/io_uring/statx.h b/io_uring/statx.h new file mode 100644 index 000000000000..9a17f4d45a7d --- /dev/null +++ b/io_uring/statx.h @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 + +int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_statx(struct io_kiocb *req, unsigned int issue_flags); +void io_statx_cleanup(struct io_kiocb *req); diff --git a/io_uring/sync.c b/io_uring/sync.c new file mode 100644 index 000000000000..f2102afa79ca --- /dev/null +++ b/io_uring/sync.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/io_uring.h> +#include <linux/fsnotify.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "sync.h" + +struct io_sync { + struct file *file; + loff_t len; + loff_t off; + int flags; + int mode; +}; + +int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sync *sync = io_kiocb_to_cmd(req); + + if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in)) + return -EINVAL; + + sync->off = READ_ONCE(sqe->off); + sync->len = READ_ONCE(sqe->len); + sync->flags = READ_ONCE(sqe->sync_range_flags); + return 0; +} + +int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_sync *sync = io_kiocb_to_cmd(req); + int ret; + + /* sync_file_range always requires a blocking context */ + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = sync_file_range(req->file, sync->off, sync->len, sync->flags); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sync *sync = io_kiocb_to_cmd(req); + + if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in)) + return -EINVAL; + + sync->flags = READ_ONCE(sqe->fsync_flags); + if (unlikely(sync->flags & ~IORING_FSYNC_DATASYNC)) + return -EINVAL; + + sync->off = READ_ONCE(sqe->off); + sync->len = READ_ONCE(sqe->len); + return 0; +} + +int io_fsync(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_sync *sync = io_kiocb_to_cmd(req); + loff_t end = sync->off + sync->len; + int ret; + + /* fsync always requires a blocking context */ + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = vfs_fsync_range(req->file, sync->off, end > 0 ? end : LLONG_MAX, + sync->flags & IORING_FSYNC_DATASYNC); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +int io_fallocate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sync *sync = io_kiocb_to_cmd(req); + + if (sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) + return -EINVAL; + + sync->off = READ_ONCE(sqe->off); + sync->len = READ_ONCE(sqe->addr); + sync->mode = READ_ONCE(sqe->len); + return 0; +} + +int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_sync *sync = io_kiocb_to_cmd(req); + int ret; + + /* fallocate always requiring blocking context */ + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + ret = vfs_fallocate(req->file, sync->mode, sync->off, sync->len); + if (ret >= 0) + fsnotify_modify(req->file); + io_req_set_res(req, ret, 0); + return IOU_OK; +} diff --git a/io_uring/sync.h b/io_uring/sync.h new file mode 100644 index 000000000000..e873c888da79 --- /dev/null +++ b/io_uring/sync.h @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 + +int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags); + +int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_fsync(struct io_kiocb *req, unsigned int issue_flags); + +int io_fallocate(struct io_kiocb *req, unsigned int issue_flags); +int io_fallocate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); diff --git a/io_uring/tctx.c b/io_uring/tctx.c new file mode 100644 index 000000000000..7f97d97fef0a --- /dev/null +++ b/io_uring/tctx.c @@ -0,0 +1,340 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/nospec.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "tctx.h" + +static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx, + struct task_struct *task) +{ + struct io_wq_hash *hash; + struct io_wq_data data; + unsigned int concurrency; + + mutex_lock(&ctx->uring_lock); + hash = ctx->hash_map; + if (!hash) { + hash = kzalloc(sizeof(*hash), GFP_KERNEL); + if (!hash) { + mutex_unlock(&ctx->uring_lock); + return ERR_PTR(-ENOMEM); + } + refcount_set(&hash->refs, 1); + init_waitqueue_head(&hash->wait); + ctx->hash_map = hash; + } + mutex_unlock(&ctx->uring_lock); + + data.hash = hash; + data.task = task; + data.free_work = io_wq_free_work; + data.do_work = io_wq_submit_work; + + /* Do QD, or 4 * CPUS, whatever is smallest */ + concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); + + return io_wq_create(concurrency, &data); +} + +void __io_uring_free(struct task_struct *tsk) +{ + struct io_uring_task *tctx = tsk->io_uring; + + WARN_ON_ONCE(!xa_empty(&tctx->xa)); + WARN_ON_ONCE(tctx->io_wq); + WARN_ON_ONCE(tctx->cached_refs); + + percpu_counter_destroy(&tctx->inflight); + kfree(tctx); + tsk->io_uring = NULL; +} + +__cold int io_uring_alloc_task_context(struct task_struct *task, + struct io_ring_ctx *ctx) +{ + struct io_uring_task *tctx; + int ret; + + tctx = kzalloc(sizeof(*tctx), GFP_KERNEL); + if (unlikely(!tctx)) + return -ENOMEM; + + ret = percpu_counter_init(&tctx->inflight, 0, GFP_KERNEL); + if (unlikely(ret)) { + kfree(tctx); + return ret; + } + + tctx->io_wq = io_init_wq_offload(ctx, task); + if (IS_ERR(tctx->io_wq)) { + ret = PTR_ERR(tctx->io_wq); + percpu_counter_destroy(&tctx->inflight); + kfree(tctx); + return ret; + } + + xa_init(&tctx->xa); + init_waitqueue_head(&tctx->wait); + atomic_set(&tctx->in_idle, 0); + atomic_set(&tctx->inflight_tracked, 0); + task->io_uring = tctx; + init_llist_head(&tctx->task_list); + init_task_work(&tctx->task_work, tctx_task_work); + return 0; +} + +static int io_register_submitter(struct io_ring_ctx *ctx) +{ + int ret = 0; + + mutex_lock(&ctx->uring_lock); + if (!ctx->submitter_task) + ctx->submitter_task = get_task_struct(current); + else if (ctx->submitter_task != current) + ret = -EEXIST; + mutex_unlock(&ctx->uring_lock); + + return ret; +} + +int __io_uring_add_tctx_node(struct io_ring_ctx *ctx, bool submitter) +{ + struct io_uring_task *tctx = current->io_uring; + struct io_tctx_node *node; + int ret; + + if ((ctx->flags & IORING_SETUP_SINGLE_ISSUER) && submitter) { + ret = io_register_submitter(ctx); + if (ret) + return ret; + } + + if (unlikely(!tctx)) { + ret = io_uring_alloc_task_context(current, ctx); + if (unlikely(ret)) + return ret; + + tctx = current->io_uring; + if (ctx->iowq_limits_set) { + unsigned int limits[2] = { ctx->iowq_limits[0], + ctx->iowq_limits[1], }; + + ret = io_wq_max_workers(tctx->io_wq, limits); + if (ret) + return ret; + } + } + if (!xa_load(&tctx->xa, (unsigned long)ctx)) { + node = kmalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return -ENOMEM; + node->ctx = ctx; + node->task = current; + + ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx, + node, GFP_KERNEL)); + if (ret) { + kfree(node); + return ret; + } + + mutex_lock(&ctx->uring_lock); + list_add(&node->ctx_node, &ctx->tctx_list); + mutex_unlock(&ctx->uring_lock); + } + if (submitter) + tctx->last = ctx; + return 0; +} + +/* + * Remove this io_uring_file -> task mapping. + */ +__cold void io_uring_del_tctx_node(unsigned long index) +{ + struct io_uring_task *tctx = current->io_uring; + struct io_tctx_node *node; + + if (!tctx) + return; + node = xa_erase(&tctx->xa, index); + if (!node) + return; + + WARN_ON_ONCE(current != node->task); + WARN_ON_ONCE(list_empty(&node->ctx_node)); + + mutex_lock(&node->ctx->uring_lock); + list_del(&node->ctx_node); + mutex_unlock(&node->ctx->uring_lock); + + if (tctx->last == node->ctx) + tctx->last = NULL; + kfree(node); +} + +__cold void io_uring_clean_tctx(struct io_uring_task *tctx) +{ + struct io_wq *wq = tctx->io_wq; + struct io_tctx_node *node; + unsigned long index; + + xa_for_each(&tctx->xa, index, node) { + io_uring_del_tctx_node(index); + cond_resched(); + } + if (wq) { + /* + * Must be after io_uring_del_tctx_node() (removes nodes under + * uring_lock) to avoid race with io_uring_try_cancel_iowq(). + */ + io_wq_put_and_exit(wq); + tctx->io_wq = NULL; + } +} + +void io_uring_unreg_ringfd(void) +{ + struct io_uring_task *tctx = current->io_uring; + int i; + + for (i = 0; i < IO_RINGFD_REG_MAX; i++) { + if (tctx->registered_rings[i]) { + fput(tctx->registered_rings[i]); + tctx->registered_rings[i] = NULL; + } + } +} + +static int io_ring_add_registered_fd(struct io_uring_task *tctx, int fd, + int start, int end) +{ + struct file *file; + int offset; + + for (offset = start; offset < end; offset++) { + offset = array_index_nospec(offset, IO_RINGFD_REG_MAX); + if (tctx->registered_rings[offset]) + continue; + + file = fget(fd); + if (!file) { + return -EBADF; + } else if (!io_is_uring_fops(file)) { + fput(file); + return -EOPNOTSUPP; + } + tctx->registered_rings[offset] = file; + return offset; + } + + return -EBUSY; +} + +/* + * Register a ring fd to avoid fdget/fdput for each io_uring_enter() + * invocation. User passes in an array of struct io_uring_rsrc_update + * with ->data set to the ring_fd, and ->offset given for the desired + * index. If no index is desired, application may set ->offset == -1U + * and we'll find an available index. Returns number of entries + * successfully processed, or < 0 on error if none were processed. + */ +int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, + unsigned nr_args) +{ + struct io_uring_rsrc_update __user *arg = __arg; + struct io_uring_rsrc_update reg; + struct io_uring_task *tctx; + int ret, i; + + if (!nr_args || nr_args > IO_RINGFD_REG_MAX) + return -EINVAL; + + mutex_unlock(&ctx->uring_lock); + ret = __io_uring_add_tctx_node(ctx, false); + mutex_lock(&ctx->uring_lock); + if (ret) + return ret; + + tctx = current->io_uring; + for (i = 0; i < nr_args; i++) { + int start, end; + + if (copy_from_user(®, &arg[i], sizeof(reg))) { + ret = -EFAULT; + break; + } + + if (reg.resv) { + ret = -EINVAL; + break; + } + + if (reg.offset == -1U) { + start = 0; + end = IO_RINGFD_REG_MAX; + } else { + if (reg.offset >= IO_RINGFD_REG_MAX) { + ret = -EINVAL; + break; + } + start = reg.offset; + end = start + 1; + } + + ret = io_ring_add_registered_fd(tctx, reg.data, start, end); + if (ret < 0) + break; + + reg.offset = ret; + if (copy_to_user(&arg[i], ®, sizeof(reg))) { + fput(tctx->registered_rings[reg.offset]); + tctx->registered_rings[reg.offset] = NULL; + ret = -EFAULT; + break; + } + } + + return i ? i : ret; +} + +int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg, + unsigned nr_args) +{ + struct io_uring_rsrc_update __user *arg = __arg; + struct io_uring_task *tctx = current->io_uring; + struct io_uring_rsrc_update reg; + int ret = 0, i; + + if (!nr_args || nr_args > IO_RINGFD_REG_MAX) + return -EINVAL; + if (!tctx) + return 0; + + for (i = 0; i < nr_args; i++) { + if (copy_from_user(®, &arg[i], sizeof(reg))) { + ret = -EFAULT; + break; + } + if (reg.resv || reg.data || reg.offset >= IO_RINGFD_REG_MAX) { + ret = -EINVAL; + break; + } + + reg.offset = array_index_nospec(reg.offset, IO_RINGFD_REG_MAX); + if (tctx->registered_rings[reg.offset]) { + fput(tctx->registered_rings[reg.offset]); + tctx->registered_rings[reg.offset] = NULL; + } + } + + return i ? i : ret; +} diff --git a/io_uring/tctx.h b/io_uring/tctx.h new file mode 100644 index 000000000000..8a33ff6e5d91 --- /dev/null +++ b/io_uring/tctx.h @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/llist.h> + +/* + * Arbitrary limit, can be raised if need be + */ +#define IO_RINGFD_REG_MAX 16 + +struct io_uring_task { + /* submission side */ + int cached_refs; + const struct io_ring_ctx *last; + struct io_wq *io_wq; + struct file *registered_rings[IO_RINGFD_REG_MAX]; + + struct xarray xa; + struct wait_queue_head wait; + atomic_t in_idle; + atomic_t inflight_tracked; + struct percpu_counter inflight; + + struct { /* task_work */ + struct llist_head task_list; + struct callback_head task_work; + } ____cacheline_aligned_in_smp; +}; + +struct io_tctx_node { + struct list_head ctx_node; + struct task_struct *task; + struct io_ring_ctx *ctx; +}; + +int io_uring_alloc_task_context(struct task_struct *task, + struct io_ring_ctx *ctx); +void io_uring_del_tctx_node(unsigned long index); +int __io_uring_add_tctx_node(struct io_ring_ctx *ctx, bool submitter); +void io_uring_clean_tctx(struct io_uring_task *tctx); + +void io_uring_unreg_ringfd(void); +int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, + unsigned nr_args); +int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg, + unsigned nr_args); + +/* + * Note that this task has used io_uring. We use it for cancelation purposes. + */ +static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) +{ + struct io_uring_task *tctx = current->io_uring; + + if (likely(tctx && tctx->last == ctx)) + return 0; + return __io_uring_add_tctx_node(ctx, true); +} diff --git a/io_uring/timeout.c b/io_uring/timeout.c new file mode 100644 index 000000000000..2f9e56935479 --- /dev/null +++ b/io_uring/timeout.c @@ -0,0 +1,644 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/io_uring.h> + +#include <trace/events/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "refs.h" +#include "cancel.h" +#include "timeout.h" + +struct io_timeout { + struct file *file; + u32 off; + u32 target_seq; + struct list_head list; + /* head of the link, used by linked timeouts only */ + struct io_kiocb *head; + /* for linked completions */ + struct io_kiocb *prev; +}; + +struct io_timeout_rem { + struct file *file; + u64 addr; + + /* timeout update */ + struct timespec64 ts; + u32 flags; + bool ltimeout; +}; + +static inline bool io_is_timeout_noseq(struct io_kiocb *req) +{ + struct io_timeout *timeout = io_kiocb_to_cmd(req); + + return !timeout->off; +} + +static inline void io_put_req(struct io_kiocb *req) +{ + if (req_ref_put_and_test(req)) { + io_queue_next(req); + io_free_req(req); + } +} + +static bool io_kill_timeout(struct io_kiocb *req, int status) + __must_hold(&req->ctx->completion_lock) + __must_hold(&req->ctx->timeout_lock) +{ + struct io_timeout_data *io = req->async_data; + + if (hrtimer_try_to_cancel(&io->timer) != -1) { + struct io_timeout *timeout = io_kiocb_to_cmd(req); + + if (status) + req_set_fail(req); + atomic_set(&req->ctx->cq_timeouts, + atomic_read(&req->ctx->cq_timeouts) + 1); + list_del_init(&timeout->list); + io_req_tw_post_queue(req, status, 0); + return true; + } + return false; +} + +__cold void io_flush_timeouts(struct io_ring_ctx *ctx) + __must_hold(&ctx->completion_lock) +{ + u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + struct io_timeout *timeout, *tmp; + + spin_lock_irq(&ctx->timeout_lock); + list_for_each_entry_safe(timeout, tmp, &ctx->timeout_list, list) { + struct io_kiocb *req = cmd_to_io_kiocb(timeout); + u32 events_needed, events_got; + + if (io_is_timeout_noseq(req)) + break; + + /* + * Since seq can easily wrap around over time, subtract + * the last seq at which timeouts were flushed before comparing. + * Assuming not more than 2^31-1 events have happened since, + * these subtractions won't have wrapped, so we can check if + * target is in [last_seq, current_seq] by comparing the two. + */ + events_needed = timeout->target_seq - ctx->cq_last_tm_flush; + events_got = seq - ctx->cq_last_tm_flush; + if (events_got < events_needed) + break; + + io_kill_timeout(req, 0); + } + ctx->cq_last_tm_flush = seq; + spin_unlock_irq(&ctx->timeout_lock); +} + +static void io_req_tw_fail_links(struct io_kiocb *link, bool *locked) +{ + io_tw_lock(link->ctx, locked); + while (link) { + struct io_kiocb *nxt = link->link; + long res = -ECANCELED; + + if (link->flags & REQ_F_FAIL) + res = link->cqe.res; + link->link = NULL; + io_req_set_res(link, res, 0); + io_req_task_complete(link, locked); + link = nxt; + } +} + +static void io_fail_links(struct io_kiocb *req) + __must_hold(&req->ctx->completion_lock) +{ + struct io_kiocb *link = req->link; + bool ignore_cqes = req->flags & REQ_F_SKIP_LINK_CQES; + + if (!link) + return; + + while (link) { + if (ignore_cqes) + link->flags |= REQ_F_CQE_SKIP; + else + link->flags &= ~REQ_F_CQE_SKIP; + trace_io_uring_fail_link(req, link); + link = link->link; + } + + link = req->link; + link->io_task_work.func = io_req_tw_fail_links; + io_req_task_work_add(link); + req->link = NULL; +} + +static inline void io_remove_next_linked(struct io_kiocb *req) +{ + struct io_kiocb *nxt = req->link; + + req->link = nxt->link; + nxt->link = NULL; +} + +bool io_disarm_next(struct io_kiocb *req) + __must_hold(&req->ctx->completion_lock) +{ + struct io_kiocb *link = NULL; + bool posted = false; + + if (req->flags & REQ_F_ARM_LTIMEOUT) { + link = req->link; + req->flags &= ~REQ_F_ARM_LTIMEOUT; + if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { + io_remove_next_linked(req); + io_req_tw_post_queue(link, -ECANCELED, 0); + posted = true; + } + } else if (req->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->timeout_lock); + link = io_disarm_linked_timeout(req); + spin_unlock_irq(&ctx->timeout_lock); + if (link) { + posted = true; + io_req_tw_post_queue(link, -ECANCELED, 0); + } + } + if (unlikely((req->flags & REQ_F_FAIL) && + !(req->flags & REQ_F_HARDLINK))) { + posted |= (req->link != NULL); + io_fail_links(req); + } + return posted; +} + +struct io_kiocb *__io_disarm_linked_timeout(struct io_kiocb *req, + struct io_kiocb *link) + __must_hold(&req->ctx->completion_lock) + __must_hold(&req->ctx->timeout_lock) +{ + struct io_timeout_data *io = link->async_data; + struct io_timeout *timeout = io_kiocb_to_cmd(link); + + io_remove_next_linked(req); + timeout->head = NULL; + if (hrtimer_try_to_cancel(&io->timer) != -1) { + list_del(&timeout->list); + return link; + } + + return NULL; +} + +static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) +{ + struct io_timeout_data *data = container_of(timer, + struct io_timeout_data, timer); + struct io_kiocb *req = data->req; + struct io_timeout *timeout = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->timeout_lock, flags); + list_del_init(&timeout->list); + atomic_set(&req->ctx->cq_timeouts, + atomic_read(&req->ctx->cq_timeouts) + 1); + spin_unlock_irqrestore(&ctx->timeout_lock, flags); + + if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS)) + req_set_fail(req); + + io_req_set_res(req, -ETIME, 0); + req->io_task_work.func = io_req_task_complete; + io_req_task_work_add(req); + return HRTIMER_NORESTART; +} + +static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, + struct io_cancel_data *cd) + __must_hold(&ctx->timeout_lock) +{ + struct io_timeout *timeout; + struct io_timeout_data *io; + struct io_kiocb *req = NULL; + + list_for_each_entry(timeout, &ctx->timeout_list, list) { + struct io_kiocb *tmp = cmd_to_io_kiocb(timeout); + + if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) && + cd->data != tmp->cqe.user_data) + continue; + if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) { + if (cd->seq == tmp->work.cancel_seq) + continue; + tmp->work.cancel_seq = cd->seq; + } + req = tmp; + break; + } + if (!req) + return ERR_PTR(-ENOENT); + + io = req->async_data; + if (hrtimer_try_to_cancel(&io->timer) == -1) + return ERR_PTR(-EALREADY); + timeout = io_kiocb_to_cmd(req); + list_del_init(&timeout->list); + return req; +} + +int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) + __must_hold(&ctx->completion_lock) +{ + struct io_kiocb *req; + + spin_lock_irq(&ctx->timeout_lock); + req = io_timeout_extract(ctx, cd); + spin_unlock_irq(&ctx->timeout_lock); + + if (IS_ERR(req)) + return PTR_ERR(req); + io_req_task_queue_fail(req, -ECANCELED); + return 0; +} + +static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) +{ + unsigned issue_flags = *locked ? 0 : IO_URING_F_UNLOCKED; + struct io_timeout *timeout = io_kiocb_to_cmd(req); + struct io_kiocb *prev = timeout->prev; + int ret = -ENOENT; + + if (prev) { + if (!(req->task->flags & PF_EXITING)) { + struct io_cancel_data cd = { + .ctx = req->ctx, + .data = prev->cqe.user_data, + }; + + ret = io_try_cancel(req->task->io_uring, &cd, issue_flags); + } + io_req_set_res(req, ret ?: -ETIME, 0); + io_req_complete_post(req); + io_put_req(prev); + } else { + io_req_set_res(req, -ETIME, 0); + io_req_complete_post(req); + } +} + +static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) +{ + struct io_timeout_data *data = container_of(timer, + struct io_timeout_data, timer); + struct io_kiocb *prev, *req = data->req; + struct io_timeout *timeout = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->timeout_lock, flags); + prev = timeout->head; + timeout->head = NULL; + + /* + * We don't expect the list to be empty, that will only happen if we + * race with the completion of the linked work. + */ + if (prev) { + io_remove_next_linked(prev); + if (!req_ref_inc_not_zero(prev)) + prev = NULL; + } + list_del(&timeout->list); + timeout->prev = prev; + spin_unlock_irqrestore(&ctx->timeout_lock, flags); + + req->io_task_work.func = io_req_task_link_timeout; + io_req_task_work_add(req); + return HRTIMER_NORESTART; +} + +static clockid_t io_timeout_get_clock(struct io_timeout_data *data) +{ + switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) { + case IORING_TIMEOUT_BOOTTIME: + return CLOCK_BOOTTIME; + case IORING_TIMEOUT_REALTIME: + return CLOCK_REALTIME; + default: + /* can't happen, vetted at prep time */ + WARN_ON_ONCE(1); + fallthrough; + case 0: + return CLOCK_MONOTONIC; + } +} + +static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, + struct timespec64 *ts, enum hrtimer_mode mode) + __must_hold(&ctx->timeout_lock) +{ + struct io_timeout_data *io; + struct io_timeout *timeout; + struct io_kiocb *req = NULL; + + list_for_each_entry(timeout, &ctx->ltimeout_list, list) { + struct io_kiocb *tmp = cmd_to_io_kiocb(timeout); + + if (user_data == tmp->cqe.user_data) { + req = tmp; + break; + } + } + if (!req) + return -ENOENT; + + io = req->async_data; + if (hrtimer_try_to_cancel(&io->timer) == -1) + return -EALREADY; + hrtimer_init(&io->timer, io_timeout_get_clock(io), mode); + io->timer.function = io_link_timeout_fn; + hrtimer_start(&io->timer, timespec64_to_ktime(*ts), mode); + return 0; +} + +static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, + struct timespec64 *ts, enum hrtimer_mode mode) + __must_hold(&ctx->timeout_lock) +{ + struct io_cancel_data cd = { .data = user_data, }; + struct io_kiocb *req = io_timeout_extract(ctx, &cd); + struct io_timeout *timeout = io_kiocb_to_cmd(req); + struct io_timeout_data *data; + + if (IS_ERR(req)) + return PTR_ERR(req); + + timeout->off = 0; /* noseq */ + data = req->async_data; + list_add_tail(&timeout->list, &ctx->timeout_list); + hrtimer_init(&data->timer, io_timeout_get_clock(data), mode); + data->timer.function = io_timeout_fn; + hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode); + return 0; +} + +int io_timeout_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_timeout_rem *tr = io_kiocb_to_cmd(req); + + if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) + return -EINVAL; + if (sqe->buf_index || sqe->len || sqe->splice_fd_in) + return -EINVAL; + + tr->ltimeout = false; + tr->addr = READ_ONCE(sqe->addr); + tr->flags = READ_ONCE(sqe->timeout_flags); + if (tr->flags & IORING_TIMEOUT_UPDATE_MASK) { + if (hweight32(tr->flags & IORING_TIMEOUT_CLOCK_MASK) > 1) + return -EINVAL; + if (tr->flags & IORING_LINK_TIMEOUT_UPDATE) + tr->ltimeout = true; + if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS)) + return -EINVAL; + if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2))) + return -EFAULT; + if (tr->ts.tv_sec < 0 || tr->ts.tv_nsec < 0) + return -EINVAL; + } else if (tr->flags) { + /* timeout removal doesn't support flags */ + return -EINVAL; + } + + return 0; +} + +static inline enum hrtimer_mode io_translate_timeout_mode(unsigned int flags) +{ + return (flags & IORING_TIMEOUT_ABS) ? HRTIMER_MODE_ABS + : HRTIMER_MODE_REL; +} + +/* + * Remove or update an existing timeout command + */ +int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_timeout_rem *tr = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + int ret; + + if (!(tr->flags & IORING_TIMEOUT_UPDATE)) { + struct io_cancel_data cd = { .data = tr->addr, }; + + spin_lock(&ctx->completion_lock); + ret = io_timeout_cancel(ctx, &cd); + spin_unlock(&ctx->completion_lock); + } else { + enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags); + + spin_lock_irq(&ctx->timeout_lock); + if (tr->ltimeout) + ret = io_linked_timeout_update(ctx, tr->addr, &tr->ts, mode); + else + ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode); + spin_unlock_irq(&ctx->timeout_lock); + } + + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + +static int __io_timeout_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe, + bool is_timeout_link) +{ + struct io_timeout *timeout = io_kiocb_to_cmd(req); + struct io_timeout_data *data; + unsigned flags; + u32 off = READ_ONCE(sqe->off); + + if (sqe->buf_index || sqe->len != 1 || sqe->splice_fd_in) + return -EINVAL; + if (off && is_timeout_link) + return -EINVAL; + flags = READ_ONCE(sqe->timeout_flags); + if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK | + IORING_TIMEOUT_ETIME_SUCCESS)) + return -EINVAL; + /* more than one clock specified is invalid, obviously */ + if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1) + return -EINVAL; + + INIT_LIST_HEAD(&timeout->list); + timeout->off = off; + if (unlikely(off && !req->ctx->off_timeout_used)) + req->ctx->off_timeout_used = true; + + if (WARN_ON_ONCE(req_has_async_data(req))) + return -EFAULT; + if (io_alloc_async_data(req)) + return -ENOMEM; + + data = req->async_data; + data->req = req; + data->flags = flags; + + if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr))) + return -EFAULT; + + if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0) + return -EINVAL; + + INIT_LIST_HEAD(&timeout->list); + data->mode = io_translate_timeout_mode(flags); + hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); + + if (is_timeout_link) { + struct io_submit_link *link = &req->ctx->submit_state.link; + + if (!link->head) + return -EINVAL; + if (link->last->opcode == IORING_OP_LINK_TIMEOUT) + return -EINVAL; + timeout->head = link->last; + link->last->flags |= REQ_F_ARM_LTIMEOUT; + } + return 0; +} + +int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + return __io_timeout_prep(req, sqe, false); +} + +int io_link_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + return __io_timeout_prep(req, sqe, true); +} + +int io_timeout(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_timeout *timeout = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + struct io_timeout_data *data = req->async_data; + struct list_head *entry; + u32 tail, off = timeout->off; + + spin_lock_irq(&ctx->timeout_lock); + + /* + * sqe->off holds how many events that need to occur for this + * timeout event to be satisfied. If it isn't set, then this is + * a pure timeout request, sequence isn't used. + */ + if (io_is_timeout_noseq(req)) { + entry = ctx->timeout_list.prev; + goto add; + } + + tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + timeout->target_seq = tail + off; + + /* Update the last seq here in case io_flush_timeouts() hasn't. + * This is safe because ->completion_lock is held, and submissions + * and completions are never mixed in the same ->completion_lock section. + */ + ctx->cq_last_tm_flush = tail; + + /* + * Insertion sort, ensuring the first entry in the list is always + * the one we need first. + */ + list_for_each_prev(entry, &ctx->timeout_list) { + struct io_timeout *nextt = list_entry(entry, struct io_timeout, list); + struct io_kiocb *nxt = cmd_to_io_kiocb(nextt); + + if (io_is_timeout_noseq(nxt)) + continue; + /* nxt.seq is behind @tail, otherwise would've been completed */ + if (off >= nextt->target_seq - tail) + break; + } +add: + list_add(&timeout->list, entry); + data->timer.function = io_timeout_fn; + hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); + spin_unlock_irq(&ctx->timeout_lock); + return IOU_ISSUE_SKIP_COMPLETE; +} + +void io_queue_linked_timeout(struct io_kiocb *req) +{ + struct io_timeout *timeout = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->timeout_lock); + /* + * If the back reference is NULL, then our linked request finished + * before we got a chance to setup the timer + */ + if (timeout->head) { + struct io_timeout_data *data = req->async_data; + + data->timer.function = io_link_timeout_fn; + hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), + data->mode); + list_add_tail(&timeout->list, &ctx->ltimeout_list); + } + spin_unlock_irq(&ctx->timeout_lock); + /* drop submission reference */ + io_put_req(req); +} + +static bool io_match_task(struct io_kiocb *head, struct task_struct *task, + bool cancel_all) + __must_hold(&req->ctx->timeout_lock) +{ + struct io_kiocb *req; + + if (task && head->task != task) + return false; + if (cancel_all) + return true; + + io_for_each_link(req, head) { + if (req->flags & REQ_F_INFLIGHT) + return true; + } + return false; +} + +/* Returns true if we found and killed one or more timeouts */ +__cold bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, + bool cancel_all) +{ + struct io_timeout *timeout, *tmp; + int canceled = 0; + + io_cq_lock(ctx); + spin_lock_irq(&ctx->timeout_lock); + list_for_each_entry_safe(timeout, tmp, &ctx->timeout_list, list) { + struct io_kiocb *req = cmd_to_io_kiocb(timeout); + + if (io_match_task(req, tsk, cancel_all) && + io_kill_timeout(req, -ECANCELED)) + canceled++; + } + spin_unlock_irq(&ctx->timeout_lock); + io_cq_unlock_post(ctx); + return canceled != 0; +} diff --git a/io_uring/timeout.h b/io_uring/timeout.h new file mode 100644 index 000000000000..858c62644897 --- /dev/null +++ b/io_uring/timeout.h @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 + +struct io_timeout_data { + struct io_kiocb *req; + struct hrtimer timer; + struct timespec64 ts; + enum hrtimer_mode mode; + u32 flags; +}; + +struct io_kiocb *__io_disarm_linked_timeout(struct io_kiocb *req, + struct io_kiocb *link); + +static inline struct io_kiocb *io_disarm_linked_timeout(struct io_kiocb *req) +{ + struct io_kiocb *link = req->link; + + if (link && link->opcode == IORING_OP_LINK_TIMEOUT) + return __io_disarm_linked_timeout(req, link); + + return NULL; +} + +__cold void io_flush_timeouts(struct io_ring_ctx *ctx); +struct io_cancel_data; +int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd); +__cold bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, + bool cancel_all); +void io_queue_linked_timeout(struct io_kiocb *req); +bool io_disarm_next(struct io_kiocb *req); + +int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_link_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_timeout(struct io_kiocb *req, unsigned int issue_flags); +int io_timeout_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags); diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c new file mode 100644 index 000000000000..0a421ed51e7e --- /dev/null +++ b/io_uring/uring_cmd.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "io_uring.h" +#include "uring_cmd.h" + +static void io_uring_cmd_work(struct io_kiocb *req, bool *locked) +{ + struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req); + + ioucmd->task_work_cb(ioucmd); +} + +void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)) +{ + struct io_kiocb *req = cmd_to_io_kiocb(ioucmd); + + ioucmd->task_work_cb = task_work_cb; + req->io_task_work.func = io_uring_cmd_work; + io_req_task_work_add(req); +} +EXPORT_SYMBOL_GPL(io_uring_cmd_complete_in_task); + +static inline void io_req_set_cqe32_extra(struct io_kiocb *req, + u64 extra1, u64 extra2) +{ + req->extra1 = extra1; + req->extra2 = extra2; + req->flags |= REQ_F_CQE32_INIT; +} + +/* + * Called by consumers of io_uring_cmd, if they originally returned + * -EIOCBQUEUED upon receiving the command. + */ +void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2) +{ + struct io_kiocb *req = cmd_to_io_kiocb(ioucmd); + + if (ret < 0) + req_set_fail(req); + + io_req_set_res(req, 0, ret); + if (req->ctx->flags & IORING_SETUP_CQE32) + io_req_set_cqe32_extra(req, res2, 0); + __io_req_complete(req, 0); +} +EXPORT_SYMBOL_GPL(io_uring_cmd_done); + +int io_uring_cmd_prep_async(struct io_kiocb *req) +{ + struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req); + size_t cmd_size; + + cmd_size = uring_cmd_pdu_size(req->ctx->flags & IORING_SETUP_SQE128); + + memcpy(req->async_data, ioucmd->cmd, cmd_size); + return 0; +} + +int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req); + + if (sqe->rw_flags || sqe->__pad1) + return -EINVAL; + ioucmd->cmd = sqe->cmd; + ioucmd->cmd_op = READ_ONCE(sqe->cmd_op); + return 0; +} + +int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + struct file *file = req->file; + int ret; + + if (!req->file->f_op->uring_cmd) + return -EOPNOTSUPP; + + if (ctx->flags & IORING_SETUP_SQE128) + issue_flags |= IO_URING_F_SQE128; + if (ctx->flags & IORING_SETUP_CQE32) + issue_flags |= IO_URING_F_CQE32; + if (ctx->flags & IORING_SETUP_IOPOLL) + issue_flags |= IO_URING_F_IOPOLL; + + if (req_has_async_data(req)) + ioucmd->cmd = req->async_data; + + ret = file->f_op->uring_cmd(ioucmd, issue_flags); + if (ret == -EAGAIN) { + if (!req_has_async_data(req)) { + if (io_alloc_async_data(req)) + return -ENOMEM; + io_uring_cmd_prep_async(req); + } + return -EAGAIN; + } + + if (ret != -EIOCBQUEUED) { + io_uring_cmd_done(ioucmd, ret, 0); + return IOU_OK; + } + + return IOU_ISSUE_SKIP_COMPLETE; +} diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h new file mode 100644 index 000000000000..7c6697d13cb2 --- /dev/null +++ b/io_uring/uring_cmd.h @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags); +int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_uring_cmd_prep_async(struct io_kiocb *req); + +/* + * The URING_CMD payload starts at 'cmd' in the first sqe, and continues into + * the following sqe if SQE128 is used. + */ +#define uring_cmd_pdu_size(is_sqe128) \ + ((1 + !!(is_sqe128)) * sizeof(struct io_uring_sqe) - \ + offsetof(struct io_uring_sqe, cmd)) diff --git a/io_uring/xattr.c b/io_uring/xattr.c new file mode 100644 index 000000000000..b179f9acd5ac --- /dev/null +++ b/io_uring/xattr.c @@ -0,0 +1,258 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/io_uring.h> +#include <linux/xattr.h> + +#include <uapi/linux/io_uring.h> + +#include "../fs/internal.h" + +#include "io_uring.h" +#include "xattr.h" + +struct io_xattr { + struct file *file; + struct xattr_ctx ctx; + struct filename *filename; +}; + +void io_xattr_cleanup(struct io_kiocb *req) +{ + struct io_xattr *ix = io_kiocb_to_cmd(req); + + if (ix->filename) + putname(ix->filename); + + kfree(ix->ctx.kname); + kvfree(ix->ctx.kvalue); +} + +static void io_xattr_finish(struct io_kiocb *req, int ret) +{ + req->flags &= ~REQ_F_NEED_CLEANUP; + + io_xattr_cleanup(req); + io_req_set_res(req, ret, 0); +} + +static int __io_getxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = io_kiocb_to_cmd(req); + const char __user *name; + int ret; + + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ix->filename = NULL; + ix->ctx.kvalue = NULL; + name = u64_to_user_ptr(READ_ONCE(sqe->addr)); + ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ix->ctx.size = READ_ONCE(sqe->len); + ix->ctx.flags = READ_ONCE(sqe->xattr_flags); + + if (ix->ctx.flags) + return -EINVAL; + + ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL); + if (!ix->ctx.kname) + return -ENOMEM; + + ret = strncpy_from_user(ix->ctx.kname->name, name, + sizeof(ix->ctx.kname->name)); + if (!ret || ret == sizeof(ix->ctx.kname->name)) + ret = -ERANGE; + if (ret < 0) { + kfree(ix->ctx.kname); + return ret; + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +int io_fgetxattr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + return __io_getxattr_prep(req, sqe); +} + +int io_getxattr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = io_kiocb_to_cmd(req); + const char __user *path; + int ret; + + ret = __io_getxattr_prep(req, sqe); + if (ret) + return ret; + + path = u64_to_user_ptr(READ_ONCE(sqe->addr3)); + + ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL); + if (IS_ERR(ix->filename)) { + ret = PTR_ERR(ix->filename); + ix->filename = NULL; + } + + return ret; +} + +int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = io_kiocb_to_cmd(req); + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_getxattr(mnt_user_ns(req->file->f_path.mnt), + req->file->f_path.dentry, + &ix->ctx); + + io_xattr_finish(req, ret); + return IOU_OK; +} + +int io_getxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = io_kiocb_to_cmd(req); + unsigned int lookup_flags = LOOKUP_FOLLOW; + struct path path; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + +retry: + ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL); + if (!ret) { + ret = do_getxattr(mnt_user_ns(path.mnt), + path.dentry, + &ix->ctx); + + path_put(&path); + if (retry_estale(ret, lookup_flags)) { + lookup_flags |= LOOKUP_REVAL; + goto retry; + } + } + + io_xattr_finish(req, ret); + return IOU_OK; +} + +static int __io_setxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = io_kiocb_to_cmd(req); + const char __user *name; + int ret; + + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ix->filename = NULL; + name = u64_to_user_ptr(READ_ONCE(sqe->addr)); + ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ix->ctx.kvalue = NULL; + ix->ctx.size = READ_ONCE(sqe->len); + ix->ctx.flags = READ_ONCE(sqe->xattr_flags); + + ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL); + if (!ix->ctx.kname) + return -ENOMEM; + + ret = setxattr_copy(name, &ix->ctx); + if (ret) { + kfree(ix->ctx.kname); + return ret; + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +int io_setxattr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = io_kiocb_to_cmd(req); + const char __user *path; + int ret; + + ret = __io_setxattr_prep(req, sqe); + if (ret) + return ret; + + path = u64_to_user_ptr(READ_ONCE(sqe->addr3)); + + ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL); + if (IS_ERR(ix->filename)) { + ret = PTR_ERR(ix->filename); + ix->filename = NULL; + } + + return ret; +} + +int io_fsetxattr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + return __io_setxattr_prep(req, sqe); +} + +static int __io_setxattr(struct io_kiocb *req, unsigned int issue_flags, + struct path *path) +{ + struct io_xattr *ix = io_kiocb_to_cmd(req); + int ret; + + ret = mnt_want_write(path->mnt); + if (!ret) { + ret = do_setxattr(mnt_user_ns(path->mnt), path->dentry, &ix->ctx); + mnt_drop_write(path->mnt); + } + + return ret; +} + +int io_fsetxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = __io_setxattr(req, issue_flags, &req->file->f_path); + io_xattr_finish(req, ret); + return IOU_OK; +} + +int io_setxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = io_kiocb_to_cmd(req); + unsigned int lookup_flags = LOOKUP_FOLLOW; + struct path path; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + +retry: + ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL); + if (!ret) { + ret = __io_setxattr(req, issue_flags, &path); + path_put(&path); + if (retry_estale(ret, lookup_flags)) { + lookup_flags |= LOOKUP_REVAL; + goto retry; + } + } + + io_xattr_finish(req, ret); + return IOU_OK; +} diff --git a/io_uring/xattr.h b/io_uring/xattr.h new file mode 100644 index 000000000000..9b459d2ae90c --- /dev/null +++ b/io_uring/xattr.h @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 + +void io_xattr_cleanup(struct io_kiocb *req); + +int io_fsetxattr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_fsetxattr(struct io_kiocb *req, unsigned int issue_flags); + +int io_setxattr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_setxattr(struct io_kiocb *req, unsigned int issue_flags); + +int io_fgetxattr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags); + +int io_getxattr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_getxattr(struct io_kiocb *req, unsigned int issue_flags); diff --git a/ipc/namespace.c b/ipc/namespace.c index 754f3237194a..e1fcaedba4fa 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -64,7 +64,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, goto fail_put; if (!setup_ipc_sysctls(ns)) - goto fail_put; + goto fail_mq; sem_init_ns(ns); msg_init_ns(ns); @@ -72,6 +72,9 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, return ns; +fail_mq: + retire_mq_sysctls(ns); + fail_put: put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 5f6f3f829b36..e7961508a47d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -68,11 +68,13 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns { u8 *ptr = NULL; - if (k >= SKF_NET_OFF) + if (k >= SKF_NET_OFF) { ptr = skb_network_header(skb) + k - SKF_NET_OFF; - else if (k >= SKF_LL_OFF) + } else if (k >= SKF_LL_OFF) { + if (unlikely(!skb_mac_header_was_set(skb))) + return NULL; ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - + } if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 225806a02efb..bb1254f07667 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1497,11 +1497,12 @@ const struct bpf_func_proto bpf_dynptr_from_mem_proto = { .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, }; -BPF_CALL_4(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, u32, offset) +BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, + u32, offset, u64, flags) { int err; - if (!src->data) + if (!src->data || flags) return -EINVAL; err = bpf_dynptr_check_off_len(src, offset, len); @@ -1521,13 +1522,15 @@ const struct bpf_func_proto bpf_dynptr_read_proto = { .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_DYNPTR, .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, }; -BPF_CALL_4(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, u32, len) +BPF_CALL_5(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, + u32, len, u64, flags) { int err; - if (!dst->data || bpf_dynptr_is_rdonly(dst)) + if (!dst->data || flags || bpf_dynptr_is_rdonly(dst)) return -EINVAL; err = bpf_dynptr_check_off_len(dst, offset, len); @@ -1547,6 +1550,7 @@ const struct bpf_func_proto bpf_dynptr_write_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, + .arg5_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_dynptr_data, struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 1779ccddb734..13c8e91d7862 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -765,7 +765,8 @@ struct css_set init_css_set = { .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), .threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), - .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node), + .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node), + .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), /* @@ -1240,7 +1241,8 @@ static struct css_set *find_css_set(struct css_set *old_cset, INIT_LIST_HEAD(&cset->threaded_csets); INIT_HLIST_NODE(&cset->hlist); INIT_LIST_HEAD(&cset->cgrp_links); - INIT_LIST_HEAD(&cset->mg_preload_node); + INIT_LIST_HEAD(&cset->mg_src_preload_node); + INIT_LIST_HEAD(&cset->mg_dst_preload_node); INIT_LIST_HEAD(&cset->mg_node); /* Copy the set of subsystem state objects generated in @@ -2597,21 +2599,27 @@ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp) */ void cgroup_migrate_finish(struct cgroup_mgctx *mgctx) { - LIST_HEAD(preloaded); struct css_set *cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); - list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded); - list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded); + list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets, + mg_src_preload_node) { + cset->mg_src_cgrp = NULL; + cset->mg_dst_cgrp = NULL; + cset->mg_dst_cset = NULL; + list_del_init(&cset->mg_src_preload_node); + put_css_set_locked(cset); + } - list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) { + list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets, + mg_dst_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; - list_del_init(&cset->mg_preload_node); + list_del_init(&cset->mg_dst_preload_node); put_css_set_locked(cset); } @@ -2651,7 +2659,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset, if (src_cset->dead) return; - if (!list_empty(&src_cset->mg_preload_node)) + if (!list_empty(&src_cset->mg_src_preload_node)) return; src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); @@ -2664,7 +2672,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset, src_cset->mg_src_cgrp = src_cgrp; src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); - list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets); + list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets); } /** @@ -2689,7 +2697,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) /* look up the dst cset for each src cset and link it to src */ list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets, - mg_preload_node) { + mg_src_preload_node) { struct css_set *dst_cset; struct cgroup_subsys *ss; int ssid; @@ -2708,7 +2716,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; src_cset->mg_dst_cgrp = NULL; - list_del_init(&src_cset->mg_preload_node); + list_del_init(&src_cset->mg_src_preload_node); put_css_set(src_cset); put_css_set(dst_cset); continue; @@ -2716,8 +2724,8 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) src_cset->mg_dst_cset = dst_cset; - if (list_empty(&dst_cset->mg_preload_node)) - list_add_tail(&dst_cset->mg_preload_node, + if (list_empty(&dst_cset->mg_dst_preload_node)) + list_add_tail(&dst_cset->mg_dst_preload_node, &mgctx->preloaded_dst_csets); else put_css_set(dst_cset); @@ -2963,7 +2971,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) goto out_finish; spin_lock_irq(&css_set_lock); - list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) { + list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, + mg_src_preload_node) { struct task_struct *task, *ntask; /* all tasks in src_csets need to be migrated */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 80782cddb1da..d2b354991bf5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6253,10 +6253,10 @@ again: if (!atomic_inc_not_zero(&event->rb->mmap_count)) { /* - * Raced against perf_mmap_close() through - * perf_event_set_output(). Try again, hope for better - * luck. + * Raced against perf_mmap_close(); remove the + * event and try again. */ + ring_buffer_attach(event, NULL); mutex_unlock(&event->mmap_mutex); goto again; } @@ -11825,14 +11825,25 @@ err_size: goto out; } +static void mutex_lock_double(struct mutex *a, struct mutex *b) +{ + if (b < a) + swap(a, b); + + mutex_lock(a); + mutex_lock_nested(b, SINGLE_DEPTH_NESTING); +} + static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event) { struct perf_buffer *rb = NULL; int ret = -EINVAL; - if (!output_event) + if (!output_event) { + mutex_lock(&event->mmap_mutex); goto set; + } /* don't allow circular references */ if (event == output_event) @@ -11870,8 +11881,15 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) event->pmu != output_event->pmu) goto out; + /* + * Hold both mmap_mutex to serialize against perf_mmap_close(). Since + * output_event is already on rb->event_list, and the list iteration + * restarts after every removal, it is guaranteed this new event is + * observed *OR* if output_event is already removed, it's guaranteed we + * observe !rb->mmap_count. + */ + mutex_lock_double(&event->mmap_mutex, &output_event->mmap_mutex); set: - mutex_lock(&event->mmap_mutex); /* Can't redirect output if we've got an active mmap() */ if (atomic_read(&event->mmap_count)) goto unlock; @@ -11881,6 +11899,12 @@ set: rb = ring_buffer_get(output_event); if (!rb) goto unlock; + + /* did we race against perf_mmap_close() */ + if (!atomic_read(&rb->mmap_count)) { + ring_buffer_put(rb); + goto unlock; + } } ring_buffer_attach(event, rb); @@ -11888,20 +11912,13 @@ set: ret = 0; unlock: mutex_unlock(&event->mmap_mutex); + if (output_event) + mutex_unlock(&output_event->mmap_mutex); out: return ret; } -static void mutex_lock_double(struct mutex *a, struct mutex *b) -{ - if (b < a) - swap(a, b); - - mutex_lock(a); - mutex_lock_nested(b, SINGLE_DEPTH_NESTING); -} - static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id) { bool nmi_safe = false; diff --git a/kernel/exit.c b/kernel/exit.c index f072959fcab7..64c938ce36fe 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -766,7 +766,7 @@ void __noreturn do_exit(long code) #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); - exit_itimers(tsk->signal); + exit_itimers(tsk); #endif if (tsk->mm) setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 145321a5e798..f9261c07b048 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -29,6 +29,15 @@ #include <linux/vmalloc.h> #include "kexec_internal.h" +#ifdef CONFIG_KEXEC_SIG +static bool sig_enforce = IS_ENABLED(CONFIG_KEXEC_SIG_FORCE); + +void set_kexec_sig_enforced(void) +{ + sig_enforce = true; +} +#endif + static int kexec_calculate_store_digests(struct kimage *image); /* @@ -159,7 +168,7 @@ kimage_validate_signature(struct kimage *image) image->kernel_buf_len); if (ret) { - if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) { + if (sig_enforce) { pr_notice("Enforced kernel signature verification failed (%d).\n", ret); return ret; } diff --git a/kernel/module/internal.h b/kernel/module/internal.h index bc5507ab8450..ec104c2950c3 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -11,6 +11,7 @@ #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> +#include <linux/mm.h> #ifndef ARCH_SHF_SMALL #define ARCH_SHF_SMALL 0 @@ -30,11 +31,13 @@ * to ensure complete separation of code and data, but * only when CONFIG_STRICT_MODULE_RWX=y */ -#ifdef CONFIG_STRICT_MODULE_RWX -# define strict_align(X) PAGE_ALIGN(X) -#else -# define strict_align(X) (X) -#endif +static inline unsigned int strict_align(unsigned int size) +{ + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + return PAGE_ALIGN(size); + else + return size; +} extern struct mutex module_mutex; extern struct list_head modules; diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index 3e11523bc6f6..77e75bead569 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -137,6 +137,7 @@ void layout_symtab(struct module *mod, struct load_info *info) info->symoffs = ALIGN(mod->data_layout.size, symsect->sh_addralign ?: 1); info->stroffs = mod->data_layout.size = info->symoffs + ndst * sizeof(Elf_Sym); mod->data_layout.size += strtab_size; + /* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */ info->core_typeoffs = mod->data_layout.size; mod->data_layout.size += ndst * sizeof(char); mod->data_layout.size = strict_align(mod->data_layout.size); @@ -169,19 +170,20 @@ void add_kallsyms(struct module *mod, const struct load_info *info) Elf_Sym *dst; char *s; Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; + unsigned long strtab_size; /* Set up to point into init section. */ mod->kallsyms = (void __rcu *)mod->init_layout.base + info->mod_kallsyms_init_off; - preempt_disable(); + rcu_read_lock(); /* The following is safe since this pointer cannot change */ - rcu_dereference_sched(mod->kallsyms)->symtab = (void *)symsec->sh_addr; - rcu_dereference_sched(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym); + rcu_dereference(mod->kallsyms)->symtab = (void *)symsec->sh_addr; + rcu_dereference(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym); /* Make sure we get permanent strtab: don't use info->strtab. */ - rcu_dereference_sched(mod->kallsyms)->strtab = + rcu_dereference(mod->kallsyms)->strtab = (void *)info->sechdrs[info->index.str].sh_addr; - rcu_dereference_sched(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs; + rcu_dereference(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs; /* * Now populate the cut down core kallsyms for after init @@ -190,22 +192,29 @@ void add_kallsyms(struct module *mod, const struct load_info *info) mod->core_kallsyms.symtab = dst = mod->data_layout.base + info->symoffs; mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs; mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs; - src = rcu_dereference_sched(mod->kallsyms)->symtab; - for (ndst = i = 0; i < rcu_dereference_sched(mod->kallsyms)->num_symtab; i++) { - rcu_dereference_sched(mod->kallsyms)->typetab[i] = elf_type(src + i, info); + strtab_size = info->core_typeoffs - info->stroffs; + src = rcu_dereference(mod->kallsyms)->symtab; + for (ndst = i = 0; i < rcu_dereference(mod->kallsyms)->num_symtab; i++) { + rcu_dereference(mod->kallsyms)->typetab[i] = elf_type(src + i, info); if (i == 0 || is_livepatch_module(mod) || is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum, info->index.pcpu)) { + ssize_t ret; + mod->core_kallsyms.typetab[ndst] = - rcu_dereference_sched(mod->kallsyms)->typetab[i]; + rcu_dereference(mod->kallsyms)->typetab[i]; dst[ndst] = src[i]; dst[ndst++].st_name = s - mod->core_kallsyms.strtab; - s += strscpy(s, - &rcu_dereference_sched(mod->kallsyms)->strtab[src[i].st_name], - KSYM_NAME_LEN) + 1; + ret = strscpy(s, + &rcu_dereference(mod->kallsyms)->strtab[src[i].st_name], + strtab_size); + if (ret < 0) + break; + s += ret + 1; + strtab_size -= ret + 1; } } - preempt_enable(); + rcu_read_unlock(); mod->core_kallsyms.num_symtab = ndst; } diff --git a/kernel/module/main.c b/kernel/module/main.c index fed58d30725d..0548151dd933 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2939,24 +2939,25 @@ static void cfi_init(struct module *mod) { #ifdef CONFIG_CFI_CLANG initcall_t *init; +#ifdef CONFIG_MODULE_UNLOAD exitcall_t *exit; +#endif rcu_read_lock_sched(); mod->cfi_check = (cfi_check_fn) find_kallsyms_symbol_value(mod, "__cfi_check"); init = (initcall_t *) find_kallsyms_symbol_value(mod, "__cfi_jt_init_module"); - exit = (exitcall_t *) - find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module"); - rcu_read_unlock_sched(); - /* Fix init/exit functions to point to the CFI jump table */ if (init) mod->init = *init; #ifdef CONFIG_MODULE_UNLOAD + exit = (exitcall_t *) + find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module"); if (exit) mod->exit = *exit; #endif + rcu_read_unlock_sched(); cfi_module_add(mod, mod_tree.addr_min); #endif diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index b49c6ff6dca0..a1a81fd9889b 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3380,6 +3380,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre diff = 0; console_lock(); + for_each_console(c) { if (con && con != c) continue; @@ -3389,11 +3390,19 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre if (printk_seq < seq) diff += seq - printk_seq; } - console_unlock(); - if (diff != last_diff && reset_on_progress) + /* + * If consoles are suspended, it cannot be expected that they + * make forward progress, so timeout immediately. @diff is + * still used to return a valid flush status. + */ + if (console_suspended) + remaining = 0; + else if (diff != last_diff && reset_on_progress) remaining = timeout_ms; + console_unlock(); + if (diff == 0 || remaining == 0) break; diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 50ba70f019de..1c304fec89c0 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -511,10 +511,52 @@ static bool srcu_readers_active(struct srcu_struct *ssp) return sum; } -#define SRCU_INTERVAL 1 // Base delay if no expedited GPs pending. -#define SRCU_MAX_INTERVAL 10 // Maximum incremental delay from slow readers. -#define SRCU_MAX_NODELAY_PHASE 1 // Maximum per-GP-phase consecutive no-delay instances. -#define SRCU_MAX_NODELAY 100 // Maximum consecutive no-delay instances. +/* + * We use an adaptive strategy for synchronize_srcu() and especially for + * synchronize_srcu_expedited(). We spin for a fixed time period + * (defined below, boot time configurable) to allow SRCU readers to exit + * their read-side critical sections. If there are still some readers + * after one jiffy, we repeatedly block for one jiffy time periods. + * The blocking time is increased as the grace-period age increases, + * with max blocking time capped at 10 jiffies. + */ +#define SRCU_DEFAULT_RETRY_CHECK_DELAY 5 + +static ulong srcu_retry_check_delay = SRCU_DEFAULT_RETRY_CHECK_DELAY; +module_param(srcu_retry_check_delay, ulong, 0444); + +#define SRCU_INTERVAL 1 // Base delay if no expedited GPs pending. +#define SRCU_MAX_INTERVAL 10 // Maximum incremental delay from slow readers. + +#define SRCU_DEFAULT_MAX_NODELAY_PHASE_LO 3UL // Lowmark on default per-GP-phase + // no-delay instances. +#define SRCU_DEFAULT_MAX_NODELAY_PHASE_HI 1000UL // Highmark on default per-GP-phase + // no-delay instances. + +#define SRCU_UL_CLAMP_LO(val, low) ((val) > (low) ? (val) : (low)) +#define SRCU_UL_CLAMP_HI(val, high) ((val) < (high) ? (val) : (high)) +#define SRCU_UL_CLAMP(val, low, high) SRCU_UL_CLAMP_HI(SRCU_UL_CLAMP_LO((val), (low)), (high)) +// per-GP-phase no-delay instances adjusted to allow non-sleeping poll upto +// one jiffies time duration. Mult by 2 is done to factor in the srcu_get_delay() +// called from process_srcu(). +#define SRCU_DEFAULT_MAX_NODELAY_PHASE_ADJUSTED \ + (2UL * USEC_PER_SEC / HZ / SRCU_DEFAULT_RETRY_CHECK_DELAY) + +// Maximum per-GP-phase consecutive no-delay instances. +#define SRCU_DEFAULT_MAX_NODELAY_PHASE \ + SRCU_UL_CLAMP(SRCU_DEFAULT_MAX_NODELAY_PHASE_ADJUSTED, \ + SRCU_DEFAULT_MAX_NODELAY_PHASE_LO, \ + SRCU_DEFAULT_MAX_NODELAY_PHASE_HI) + +static ulong srcu_max_nodelay_phase = SRCU_DEFAULT_MAX_NODELAY_PHASE; +module_param(srcu_max_nodelay_phase, ulong, 0444); + +// Maximum consecutive no-delay instances. +#define SRCU_DEFAULT_MAX_NODELAY (SRCU_DEFAULT_MAX_NODELAY_PHASE > 100 ? \ + SRCU_DEFAULT_MAX_NODELAY_PHASE : 100) + +static ulong srcu_max_nodelay = SRCU_DEFAULT_MAX_NODELAY; +module_param(srcu_max_nodelay, ulong, 0444); /* * Return grace-period delay, zero if there are expedited grace @@ -522,16 +564,22 @@ static bool srcu_readers_active(struct srcu_struct *ssp) */ static unsigned long srcu_get_delay(struct srcu_struct *ssp) { + unsigned long gpstart; + unsigned long j; unsigned long jbase = SRCU_INTERVAL; if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp))) jbase = 0; - if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))) - jbase += jiffies - READ_ONCE(ssp->srcu_gp_start); - if (!jbase) { - WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1); - if (READ_ONCE(ssp->srcu_n_exp_nodelay) > SRCU_MAX_NODELAY_PHASE) - jbase = 1; + if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))) { + j = jiffies - 1; + gpstart = READ_ONCE(ssp->srcu_gp_start); + if (time_after(j, gpstart)) + jbase += j - gpstart; + if (!jbase) { + WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1); + if (READ_ONCE(ssp->srcu_n_exp_nodelay) > srcu_max_nodelay_phase) + jbase = 1; + } } return jbase > SRCU_MAX_INTERVAL ? SRCU_MAX_INTERVAL : jbase; } @@ -607,15 +655,6 @@ void __srcu_read_unlock(struct srcu_struct *ssp, int idx) EXPORT_SYMBOL_GPL(__srcu_read_unlock); /* - * We use an adaptive strategy for synchronize_srcu() and especially for - * synchronize_srcu_expedited(). We spin for a fixed time period - * (defined below) to allow SRCU readers to exit their read-side critical - * sections. If there are still some readers after a few microseconds, - * we repeatedly block for 1-millisecond time periods. - */ -#define SRCU_RETRY_CHECK_DELAY 5 - -/* * Start an SRCU grace period. */ static void srcu_gp_start(struct srcu_struct *ssp) @@ -700,7 +739,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp */ static void srcu_gp_end(struct srcu_struct *ssp) { - unsigned long cbdelay; + unsigned long cbdelay = 1; bool cbs; bool last_lvl; int cpu; @@ -720,7 +759,9 @@ static void srcu_gp_end(struct srcu_struct *ssp) spin_lock_irq_rcu_node(ssp); idx = rcu_seq_state(ssp->srcu_gp_seq); WARN_ON_ONCE(idx != SRCU_STATE_SCAN2); - cbdelay = !!srcu_get_delay(ssp); + if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp))) + cbdelay = 0; + WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns()); rcu_seq_end(&ssp->srcu_gp_seq); gpseq = rcu_seq_current(&ssp->srcu_gp_seq); @@ -921,12 +962,16 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, */ static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount) { + unsigned long curdelay; + + curdelay = !srcu_get_delay(ssp); + for (;;) { if (srcu_readers_active_idx_check(ssp, idx)) return true; - if (--trycount + !srcu_get_delay(ssp) <= 0) + if ((--trycount + curdelay) <= 0) return false; - udelay(SRCU_RETRY_CHECK_DELAY); + udelay(srcu_retry_check_delay); } } @@ -1582,7 +1627,7 @@ static void process_srcu(struct work_struct *work) j = jiffies; if (READ_ONCE(ssp->reschedule_jiffies) == j) { WRITE_ONCE(ssp->reschedule_count, READ_ONCE(ssp->reschedule_count) + 1); - if (READ_ONCE(ssp->reschedule_count) > SRCU_MAX_NODELAY) + if (READ_ONCE(ssp->reschedule_count) > srcu_max_nodelay) curdelay = 1; } else { WRITE_ONCE(ssp->reschedule_count, 1); @@ -1674,6 +1719,11 @@ static int __init srcu_bootup_announce(void) pr_info("Hierarchical SRCU implementation.\n"); if (exp_holdoff != DEFAULT_SRCU_EXP_HOLDOFF) pr_info("\tNon-default auto-expedite holdoff of %lu ns.\n", exp_holdoff); + if (srcu_retry_check_delay != SRCU_DEFAULT_RETRY_CHECK_DELAY) + pr_info("\tNon-default retry check delay of %lu us.\n", srcu_retry_check_delay); + if (srcu_max_nodelay != SRCU_DEFAULT_MAX_NODELAY) + pr_info("\tNon-default max no-delay of %lu.\n", srcu_max_nodelay); + pr_info("\tMax phase no-delay instances is %lu.\n", srcu_max_nodelay_phase); return 0; } early_initcall(srcu_bootup_announce); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index da0bf6fe9ecd..f35674e89621 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -91,7 +91,7 @@ #include "stats.h" #include "../workqueue_internal.h" -#include "../../fs/io-wq.h" +#include "../../io_uring/io-wq.h" #include "../smpboot.h" /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index b5152961b743..7bf561262cb8 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1701,7 +1701,10 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * the throttle. */ p->dl.dl_throttled = 0; - BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH); + if (!(flags & ENQUEUE_REPLENISH)) + printk_deferred_once("sched: DL de-boosted task PID %d: REPLENISH flag missing\n", + task_pid_nr(p)); + return; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e52b6e372c60..35d034219513 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -446,14 +446,14 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, if (*negp) { if (*lvalp > (unsigned long) INT_MAX + 1) return -EINVAL; - *valp = -*lvalp; + WRITE_ONCE(*valp, -*lvalp); } else { if (*lvalp > (unsigned long) INT_MAX) return -EINVAL; - *valp = *lvalp; + WRITE_ONCE(*valp, *lvalp); } } else { - int val = *valp; + int val = READ_ONCE(*valp); if (val < 0) { *negp = true; *lvalp = -(unsigned long)val; @@ -472,9 +472,9 @@ static int do_proc_douintvec_conv(unsigned long *lvalp, if (write) { if (*lvalp > UINT_MAX) return -EINVAL; - *valp = *lvalp; + WRITE_ONCE(*valp, *lvalp); } else { - unsigned int val = *valp; + unsigned int val = READ_ONCE(*valp); *lvalp = (unsigned long)val; } return 0; @@ -857,7 +857,7 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp, if ((param->min && *param->min > tmp) || (param->max && *param->max < tmp)) return -EINVAL; - *valp = tmp; + WRITE_ONCE(*valp, tmp); } return 0; @@ -923,7 +923,7 @@ static int do_proc_douintvec_minmax_conv(unsigned long *lvalp, (param->max && *param->max < tmp)) return -ERANGE; - *valp = tmp; + WRITE_ONCE(*valp, tmp); } return 0; @@ -1007,13 +1007,13 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write, tmp.maxlen = sizeof(val); tmp.data = &val; - val = *data; + val = READ_ONCE(*data); res = do_proc_douintvec(&tmp, write, buffer, lenp, ppos, do_proc_douintvec_minmax_conv, ¶m); if (res) return res; if (write) - *data = val; + WRITE_ONCE(*data, val); return 0; } EXPORT_SYMBOL_GPL(proc_dou8vec_minmax); @@ -1090,9 +1090,9 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, err = -EINVAL; break; } - *i = val; + WRITE_ONCE(*i, val); } else { - val = convdiv * (*i) / convmul; + val = convdiv * READ_ONCE(*i) / convmul; if (!first) proc_put_char(&buffer, &left, '\t'); proc_put_long(&buffer, &left, val, false); @@ -1173,9 +1173,12 @@ static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp, if (write) { if (*lvalp > INT_MAX / HZ) return 1; - *valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ); + if (*negp) + WRITE_ONCE(*valp, -*lvalp * HZ); + else + WRITE_ONCE(*valp, *lvalp * HZ); } else { - int val = *valp; + int val = READ_ONCE(*valp); unsigned long lval; if (val < 0) { *negp = true; @@ -1221,9 +1224,9 @@ static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp, if (jif > INT_MAX) return 1; - *valp = (int)jif; + WRITE_ONCE(*valp, (int)jif); } else { - int val = *valp; + int val = READ_ONCE(*valp); unsigned long lval; if (val < 0) { *negp = true; @@ -1291,8 +1294,8 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, * @ppos: the current position in the file * * Reads/writes up to table->maxlen/sizeof(unsigned int) integer - * values from/to the user buffer, treated as an ASCII string. - * The values read are assumed to be in 1/1000 seconds, and + * values from/to the user buffer, treated as an ASCII string. + * The values read are assumed to be in 1/1000 seconds, and * are converted into jiffies. * * Returns 0 on success. @@ -2091,6 +2094,17 @@ static struct ctl_table vm_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO_HUNDRED, }, +#ifdef CONFIG_NUMA + { + .procname = "numa_stat", + .data = &sysctl_vm_numa_stat, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sysctl_vm_numa_stat_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif #ifdef CONFIG_HUGETLB_PAGE { .procname = "nr_hugepages", @@ -2107,15 +2121,6 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &hugetlb_mempolicy_sysctl_handler, }, - { - .procname = "numa_stat", - .data = &sysctl_vm_numa_stat, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = sysctl_vm_numa_stat_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, #endif { .procname = "hugetlb_shm_group", diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 1cd10b102c51..5dead89308b7 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1051,15 +1051,24 @@ retry_delete: } /* - * This is called by do_exit or de_thread, only when there are no more - * references to the shared signal_struct. + * This is called by do_exit or de_thread, only when nobody else can + * modify the signal->posix_timers list. Yet we need sighand->siglock + * to prevent the race with /proc/pid/timers. */ -void exit_itimers(struct signal_struct *sig) +void exit_itimers(struct task_struct *tsk) { + struct list_head timers; struct k_itimer *tmr; - while (!list_empty(&sig->posix_timers)) { - tmr = list_entry(sig->posix_timers.next, struct k_itimer, list); + if (list_empty(&tsk->signal->posix_timers)) + return; + + spin_lock_irq(&tsk->sighand->siglock); + list_replace_init(&tsk->signal->posix_timers, &timers); + spin_unlock_irq(&tsk->sighand->siglock); + + while (!list_empty(&timers)) { + tmr = list_first_entry(&timers, struct k_itimer, list); itimer_delete(tmr); } } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index debbbb083286..ccd6a5ade3e9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -194,7 +194,8 @@ config FUNCTION_TRACER sequence is then dynamically patched into a tracer call when tracing is enabled by the administrator. If it's runtime disabled (the bootup default), then the overhead of the instructions is very - small and not measurable even in micro-benchmarks. + small and not measurable even in micro-benchmarks (at least on + x86, but may have impact on other architectures). config FUNCTION_GRAPH_TRACER bool "Kernel Function Graph Tracer" diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a8cfac0611bc..b8dd54627075 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9864,6 +9864,12 @@ void trace_init_global_iter(struct trace_iterator *iter) /* Output in nanoseconds only if we are using a clock in nanoseconds. */ if (trace_clocks[iter->tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; + + /* Can not use kmalloc for iter.temp and iter.fmt */ + iter->temp = static_temp_buf; + iter->temp_size = STATIC_TEMP_BUF_SIZE; + iter->fmt = static_fmt_buf; + iter->fmt_size = STATIC_FMT_BUF_SIZE; } void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) @@ -9896,11 +9902,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) /* Simulate the iterator */ trace_init_global_iter(&iter); - /* Can not use kmalloc for iter.temp and iter.fmt */ - iter.temp = static_temp_buf; - iter.temp_size = STATIC_TEMP_BUF_SIZE; - iter.fmt = static_fmt_buf; - iter.fmt_size = STATIC_FMT_BUF_SIZE; for_each_tracing_cpu(cpu) { atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 48e82e141d54..e87a46794079 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -4430,6 +4430,8 @@ static int parse_var_defs(struct hist_trigger_data *hist_data) s = kstrdup(field_str, GFP_KERNEL); if (!s) { + kfree(hist_data->attrs->var_defs.name[n_vars]); + hist_data->attrs->var_defs.name[n_vars] = NULL; ret = -ENOMEM; goto free; } diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 230038d4f908..bb9962b33f95 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -34,6 +34,27 @@ MODULE_LICENSE("GPL"); #define WATCH_QUEUE_NOTE_SIZE 128 #define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE) +/* + * This must be called under the RCU read-lock, which makes + * sure that the wqueue still exists. It can then take the lock, + * and check that the wqueue hasn't been destroyed, which in + * turn makes sure that the notification pipe still exists. + */ +static inline bool lock_wqueue(struct watch_queue *wqueue) +{ + spin_lock_bh(&wqueue->lock); + if (unlikely(wqueue->defunct)) { + spin_unlock_bh(&wqueue->lock); + return false; + } + return true; +} + +static inline void unlock_wqueue(struct watch_queue *wqueue) +{ + spin_unlock_bh(&wqueue->lock); +} + static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { @@ -69,6 +90,10 @@ static const struct pipe_buf_operations watch_queue_pipe_buf_ops = { /* * Post a notification to a watch queue. + * + * Must be called with the RCU lock for reading, and the + * watch_queue lock held, which guarantees that the pipe + * hasn't been released. */ static bool post_one_notification(struct watch_queue *wqueue, struct watch_notification *n) @@ -85,9 +110,6 @@ static bool post_one_notification(struct watch_queue *wqueue, spin_lock_irq(&pipe->rd_wait.lock); - if (wqueue->defunct) - goto out; - mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; @@ -203,7 +225,10 @@ void __post_watch_notification(struct watch_list *wlist, if (security_post_notification(watch->cred, cred, n) < 0) continue; - post_one_notification(wqueue, n); + if (lock_wqueue(wqueue)) { + post_one_notification(wqueue, n); + unlock_wqueue(wqueue); + } } rcu_read_unlock(); @@ -462,11 +487,12 @@ int add_watch_to_object(struct watch *watch, struct watch_list *wlist) return -EAGAIN; } - spin_lock_bh(&wqueue->lock); - kref_get(&wqueue->usage); - kref_get(&watch->usage); - hlist_add_head(&watch->queue_node, &wqueue->watches); - spin_unlock_bh(&wqueue->lock); + if (lock_wqueue(wqueue)) { + kref_get(&wqueue->usage); + kref_get(&watch->usage); + hlist_add_head(&watch->queue_node, &wqueue->watches); + unlock_wqueue(wqueue); + } hlist_add_head(&watch->list_node, &wlist->watchers); return 0; @@ -520,20 +546,15 @@ found: wqueue = rcu_dereference(watch->queue); - /* We don't need the watch list lock for the next bit as RCU is - * protecting *wqueue from deallocation. - */ - if (wqueue) { + if (lock_wqueue(wqueue)) { post_one_notification(wqueue, &n.watch); - spin_lock_bh(&wqueue->lock); - if (!hlist_unhashed(&watch->queue_node)) { hlist_del_init_rcu(&watch->queue_node); put_watch(watch); } - spin_unlock_bh(&wqueue->lock); + unlock_wqueue(wqueue); } if (wlist->release_watch) { diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index a9f7eb047768..fd15230a703b 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -84,6 +84,9 @@ config UBSAN_SHIFT config UBSAN_DIV_ZERO bool "Perform checking for integer divide-by-zero" depends on $(cc-option,-fsanitize=integer-divide-by-zero) + # https://github.com/ClangBuiltLinux/linux/issues/1657 + # https://github.com/llvm/llvm-project/issues/56289 + depends on !CC_IS_CLANG help This option enables -fsanitize=integer-divide-by-zero which checks for integer division by zero. This is effectively redundant with the diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 59e1653799f8..3c7b9d6dca95 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -336,8 +336,7 @@ static void damon_hugetlb_mkold(pte_t *pte, struct mm_struct *mm, if (pte_young(entry)) { referenced = true; entry = pte_mkold(entry); - huge_ptep_set_access_flags(vma, addr, pte, entry, - vma->vm_flags & VM_WRITE); + set_huge_pte_at(mm, addr, pte, entry); } #ifdef CONFIG_MMU_NOTIFIER diff --git a/mm/memory.c b/mm/memory.c index 7a089145cad4..4cf7d4b6c950 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4802,6 +4802,19 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf) defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) + return VM_FAULT_FALLBACK; + if (vmf->vma->vm_ops->huge_fault) + return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + return VM_FAULT_FALLBACK; +} + +static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) +{ +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + /* No support for anonymous transparent PUD pages yet */ + if (vma_is_anonymous(vmf->vma)) goto split; if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); @@ -4812,19 +4825,7 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf) split: /* COW or write-notify not handled on PUD level: split pud.*/ __split_huge_pud(vmf->vma, vmf->pud, vmf->address); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - return VM_FAULT_FALLBACK; -} - -static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - /* No support for anonymous transparent PUD pages yet */ - if (vma_is_anonymous(vmf->vma)) - return VM_FAULT_FALLBACK; - if (vmf->vma->vm_ops->huge_fault) - return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ return VM_FAULT_FALLBACK; } diff --git a/mm/rmap.c b/mm/rmap.c index 5bcb334cd6f2..746c05acad27 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1899,8 +1899,23 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); - subpage = folio_page(folio, - pte_pfn(*pvmw.pte) - folio_pfn(folio)); + if (folio_is_zone_device(folio)) { + /* + * Our PTE is a non-present device exclusive entry and + * calculating the subpage as for the common case would + * result in an invalid pointer. + * + * Since only PAGE_SIZE pages can currently be + * migrated, just set it to page. This will need to be + * changed when hugepage migrations to device private + * memory are supported. + */ + VM_BUG_ON_FOLIO(folio_nr_pages(folio) > 1, folio); + subpage = &folio->page; + } else { + subpage = folio_page(folio, + pte_pfn(*pvmw.pte) - folio_pfn(folio)); + } address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); @@ -1993,15 +2008,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, /* * No need to invalidate here it will synchronize on * against the special swap migration pte. - * - * The assignment to subpage above was computed from a - * swap PTE which results in an invalid pointer. - * Since only PAGE_SIZE pages can currently be - * migrated, just set it to page. This will need to be - * changed when hugepage migrations to device private - * memory are supported. */ - subpage = &folio->page; } else if (PageHWPoison(subpage)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index f4fa61dbbee3..dbbd1a7e65f3 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -78,6 +78,14 @@ static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) spin_lock(&init_mm.page_table_lock); if (likely(pmd_leaf(*pmd))) { + /* + * Higher order allocations from buddy allocator must be able to + * be treated as indepdenent small pages (as they can be freed + * individually). + */ + if (!PageReserved(page)) + split_page(page, get_order(PMD_SIZE)); + /* Make pte visible before pmd. See comment in pmd_install(). */ smp_wmb(); pmd_populate_kernel(&init_mm, pmd, pgtable); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 4f4892a5f767..07d3befc80e4 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -246,7 +246,10 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm, struct page *page; int ret; - ret = shmem_getpage(inode, pgoff, &page, SGP_READ); + ret = shmem_getpage(inode, pgoff, &page, SGP_NOALLOC); + /* Our caller expects us to return -EFAULT if we failed to find page. */ + if (ret == -ENOENT) + ret = -EFAULT; if (ret) goto out; if (!page) { diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 53b1955b027f..214532173536 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -182,10 +182,14 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, else if (dev->mtu > max_mtu) return -EINVAL; + /* Note: If this initial vlan_changelink() fails, we need + * to call vlan_dev_free_egress_priority() to free memory. + */ err = vlan_changelink(dev, tb, data, extack); - if (err) - return err; - err = register_vlan_dev(dev, extack); + + if (!err) + err = register_vlan_dev(dev, extack); + if (err) vlan_dev_free_egress_priority(dev); return err; diff --git a/net/compat.c b/net/compat.c index 6cd2e7683dd0..fe9be3c56ef7 100644 --- a/net/compat.c +++ b/net/compat.c @@ -34,20 +34,15 @@ #include <net/compat.h> int __get_compat_msghdr(struct msghdr *kmsg, - struct compat_msghdr __user *umsg, - struct sockaddr __user **save_addr, - compat_uptr_t *ptr, compat_size_t *len) + struct compat_msghdr *msg, + struct sockaddr __user **save_addr) { - struct compat_msghdr msg; ssize_t err; - if (copy_from_user(&msg, umsg, sizeof(*umsg))) - return -EFAULT; - - kmsg->msg_flags = msg.msg_flags; - kmsg->msg_namelen = msg.msg_namelen; + kmsg->msg_flags = msg->msg_flags; + kmsg->msg_namelen = msg->msg_namelen; - if (!msg.msg_name) + if (!msg->msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) @@ -57,15 +52,15 @@ int __get_compat_msghdr(struct msghdr *kmsg, kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_control_is_user = true; - kmsg->msg_control_user = compat_ptr(msg.msg_control); - kmsg->msg_controllen = msg.msg_controllen; + kmsg->msg_control_user = compat_ptr(msg->msg_control); + kmsg->msg_controllen = msg->msg_controllen; if (save_addr) - *save_addr = compat_ptr(msg.msg_name); + *save_addr = compat_ptr(msg->msg_name); - if (msg.msg_name && kmsg->msg_namelen) { + if (msg->msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(compat_ptr(msg.msg_name), + err = move_addr_to_kernel(compat_ptr(msg->msg_name), kmsg->msg_namelen, kmsg->msg_name); if (err < 0) @@ -76,13 +71,11 @@ int __get_compat_msghdr(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (msg.msg_iovlen > UIO_MAXIOV) + if (msg->msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; kmsg->msg_ubuf = NULL; - *ptr = msg.msg_iov; - *len = msg.msg_iovlen; return 0; } @@ -91,15 +84,17 @@ int get_compat_msghdr(struct msghdr *kmsg, struct sockaddr __user **save_addr, struct iovec **iov) { - compat_uptr_t ptr; - compat_size_t len; + struct compat_msghdr msg; ssize_t err; - err = __get_compat_msghdr(kmsg, umsg, save_addr, &ptr, &len); + if (copy_from_user(&msg, umsg, sizeof(*umsg))) + return -EFAULT; + + err = __get_compat_msghdr(kmsg, &msg, save_addr); if (err) return err; - err = import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr), len, + err = import_iovec(save_addr ? READ : WRITE, compat_ptr(msg.msg_iov), msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); return err < 0 ? err : 0; } diff --git a/net/core/dev.c b/net/core/dev.c index 8e6f22961206..30a1603a7225 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4863,7 +4863,10 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, } /* When doing generic XDP we have to bypass the qdisc layer and the - * network taps in order to match in-driver-XDP behavior. + * network taps in order to match in-driver-XDP behavior. This also means + * that XDP packets are able to starve other packets going through a qdisc, + * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX + * queues, so they do not have this starvation issue. */ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) { @@ -4875,7 +4878,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) txq = netdev_core_pick_tx(dev, skb, NULL); cpu = smp_processor_id(); HARD_TX_LOCK(dev, txq, cpu); - if (!netif_xmit_stopped(txq)) { + if (!netif_xmit_frozen_or_drv_stopped(txq)) { rc = netdev_start_xmit(skb, dev, txq, 0); if (dev_xmit_complete(rc)) free_skb = false; @@ -4883,6 +4886,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) HARD_TX_UNLOCK(dev, txq); if (free_skb) { trace_xdp_exception(dev, xdp_prog, XDP_TX); + dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); } } diff --git a/net/core/filter.c b/net/core/filter.c index 5d16d66727fc..7950f7520765 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6158,7 +6158,6 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len if (err) return err; - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); return seg6_lookup_nexthop(skb, NULL, 0); @@ -7042,7 +7041,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -EINVAL; if (!th->ack || th->rst || th->syn) @@ -7117,7 +7116,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -ENOENT; if (!th->syn || th->ack || th->fin || th->rst) diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 5f85e01d4093..b0ff6153be62 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -64,7 +64,7 @@ u32 secure_tcpv6_ts_off(const struct net *net, .daddr = *(struct in6_addr *)daddr, }; - if (net->ipv4.sysctl_tcp_timestamps != 1) + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) return 0; ts_secret_init(); @@ -120,7 +120,7 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #ifdef CONFIG_INET u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr) { - if (net->ipv4.sysctl_tcp_timestamps != 1) + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) return 0; ts_secret_init(); diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 3f00a28fe762..5daa1fa54249 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -387,7 +387,7 @@ void reuseport_stop_listen_sock(struct sock *sk) prog = rcu_dereference_protected(reuse->prog, lockdep_is_held(&reuseport_lock)); - if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req || + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req) || (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) { /* Migration capable, move sk from the listening section * to the closed section. @@ -545,7 +545,7 @@ struct sock *reuseport_migrate_sock(struct sock *sk, hash = migrating_sk->sk_hash; prog = rcu_dereference(reuse->prog); if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) { - if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req) + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req)) goto select_by_hash; goto failure; } diff --git a/net/dsa/port.c b/net/dsa/port.c index 3738f2d40a0b..2dd76eb1621c 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -248,6 +248,7 @@ static void dsa_port_reset_vlan_filtering(struct dsa_port *dp, struct netlink_ext_ack extack = {0}; bool change_vlan_filtering = false; struct dsa_switch *ds = dp->ds; + struct dsa_port *other_dp; bool vlan_filtering; int err; @@ -270,8 +271,8 @@ static void dsa_port_reset_vlan_filtering(struct dsa_port *dp, * VLAN-aware bridge. */ if (change_vlan_filtering && ds->vlan_filtering_is_global) { - dsa_switch_for_each_port(dp, ds) { - struct net_device *br = dsa_port_bridge_dev_get(dp); + dsa_switch_for_each_port(other_dp, ds) { + struct net_device *br = dsa_port_bridge_dev_get(other_dp); if (br && br_vlan_enabled(br)) { change_vlan_filtering = false; @@ -799,7 +800,7 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, ds->vlan_filtering = vlan_filtering; dsa_switch_for_each_user_port(other_dp, ds) { - struct net_device *slave = dp->slave; + struct net_device *slave = other_dp->slave; /* We might be called in the unbind path, so not * all slave devices might still be registered. diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 93da9f783bec..252c8bceaba4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -217,7 +217,7 @@ int inet_listen(struct socket *sock, int backlog) * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ - tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { @@ -335,7 +335,7 @@ lookup_protocol: inet->hdrincl = 1; } - if (net->ipv4.sysctl_ip_no_pmtu_disc) + if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; @@ -1246,7 +1246,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) if (new_saddr == old_saddr) return 0; - if (sock_net(sk)->ipv4.sysctl_ip_dynaddr > 1) { + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) { pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n", __func__, &old_saddr, &new_saddr); } @@ -1301,7 +1301,7 @@ int inet_sk_rebuild_header(struct sock *sk) * Other protocols have to map its equivalent state to TCP_SYN_SENT. * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme */ - if (!sock_net(sk)->ipv4.sysctl_ip_dynaddr || + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) || sk->sk_state != TCP_SYN_SENT || (sk->sk_userlocks & SOCK_BINDADDR_LOCK) || (err = inet_sk_reselect_saddr(sk)) != 0) @@ -1710,24 +1710,14 @@ static const struct net_protocol igmp_protocol = { }; #endif -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct net_protocol tcp_protocol = { - .early_demux = tcp_v4_early_demux, - .early_demux_handler = tcp_v4_early_demux, +static const struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, .icmp_strict_tag_validation = 1, }; -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct net_protocol udp_protocol = { - .early_demux = udp_v4_early_demux, - .early_demux_handler = udp_v4_early_demux, +static const struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 6eea1e9e998d..f8ad04470d3a 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -507,7 +507,7 @@ static int ah_init_state(struct xfrm_state *x) if (aalg_desc->uinfo.auth.icv_fullbits/8 != crypto_ahash_digestsize(ahash)) { - pr_info("%s: %s digestsize %u != %hu\n", + pr_info("%s: %s digestsize %u != %u\n", __func__, x->aalg->alg_name, crypto_ahash_digestsize(ahash), aalg_desc->uinfo.auth.icv_fullbits / 8); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 62d5f99760aa..6cd3b6c559f0 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -239,7 +239,7 @@ static int cipso_v4_cache_check(const unsigned char *key, struct cipso_v4_map_cache_entry *prev_entry = NULL; u32 hash; - if (!cipso_v4_cache_enabled) + if (!READ_ONCE(cipso_v4_cache_enabled)) return -ENOENT; hash = cipso_v4_map_cache_hash(key, key_len); @@ -296,13 +296,14 @@ static int cipso_v4_cache_check(const unsigned char *key, int cipso_v4_cache_add(const unsigned char *cipso_ptr, const struct netlbl_lsm_secattr *secattr) { + int bkt_size = READ_ONCE(cipso_v4_cache_bucketsize); int ret_val = -EPERM; u32 bkt; struct cipso_v4_map_cache_entry *entry = NULL; struct cipso_v4_map_cache_entry *old_entry = NULL; u32 cipso_ptr_len; - if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0) + if (!READ_ONCE(cipso_v4_cache_enabled) || bkt_size <= 0) return 0; cipso_ptr_len = cipso_ptr[1]; @@ -322,7 +323,7 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr, bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1); spin_lock_bh(&cipso_v4_cache[bkt].lock); - if (cipso_v4_cache[bkt].size < cipso_v4_cache_bucketsize) { + if (cipso_v4_cache[bkt].size < bkt_size) { list_add(&entry->list, &cipso_v4_cache[bkt].list); cipso_v4_cache[bkt].size += 1; } else { @@ -1199,7 +1200,8 @@ static int cipso_v4_gentag_rbm(const struct cipso_v4_doi *doi_def, /* This will send packets using the "optimized" format when * possible as specified in section 3.4.2.6 of the * CIPSO draft. */ - if (cipso_v4_rbm_optfmt && ret_val > 0 && ret_val <= 10) + if (READ_ONCE(cipso_v4_rbm_optfmt) && ret_val > 0 && + ret_val <= 10) tag_len = 14; else tag_len = 4 + ret_val; @@ -1603,7 +1605,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) * all the CIPSO validations here but it doesn't * really specify _exactly_ what we need to validate * ... so, just make it a sysctl tunable. */ - if (cipso_v4_rbm_strictvalid) { + if (READ_ONCE(cipso_v4_rbm_strictvalid)) { if (cipso_v4_map_lvl_valid(doi_def, tag[3]) < 0) { err_offset = opt_iter + 3; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index b21238df3301..b694f352ce7a 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1108,7 +1108,7 @@ static int esp_init_authenc(struct xfrm_state *x) err = -EINVAL; if (aalg_desc->uinfo.auth.icv_fullbits / 8 != crypto_aead_authsize(aead)) { - pr_info("ESP: %s digestsize %u != %hu\n", + pr_info("ESP: %s digestsize %u != %u\n", x->aalg->alg_name, crypto_aead_authsize(aead), aalg_desc->uinfo.auth.icv_fullbits / 8); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index a57ba23571c9..db7b2503f068 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1230,7 +1230,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh, nh->fib_nh_dev = in_dev->dev; dev_hold_track(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); - nh->fib_nh_scope = RT_SCOPE_HOST; + nh->fib_nh_scope = RT_SCOPE_LINK; if (!netif_carrier_ok(nh->fib_nh_dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = 0; @@ -1811,7 +1811,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, goto nla_put_failure; if (nexthop_is_blackhole(fi->nh)) rtm->rtm_type = RTN_BLACKHOLE; - if (!fi->fib_net->ipv4.sysctl_nexthop_compat_mode) + if (!READ_ONCE(fi->fib_net->ipv4.sysctl_nexthop_compat_mode)) goto offload; } @@ -2216,7 +2216,7 @@ void fib_select_multipath(struct fib_result *res, int hash) } change_nexthops(fi) { - if (net->ipv4.sysctl_fib_multipath_use_neigh) { + if (READ_ONCE(net->ipv4.sysctl_fib_multipath_use_neigh)) { if (!fib_good_nh(nexthop_nh)) continue; if (!first) { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2734c3af7e24..46e8a5125853 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -498,7 +498,7 @@ static void tnode_free(struct key_vector *tn) tn = container_of(head, struct tnode, rcu)->kv; } - if (tnode_free_size >= sysctl_fib_sync_mem) { + if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) { tnode_free_size = 0; synchronize_rcu(); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index efea0e796f06..d5d745c3e345 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -253,11 +253,12 @@ bool icmp_global_allow(void) spin_lock(&icmp_global.lock); delta = min_t(u32, now - icmp_global.stamp, HZ); if (delta >= HZ / 50) { - incr = sysctl_icmp_msgs_per_sec * delta / HZ ; + incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ; if (incr) WRITE_ONCE(icmp_global.stamp, now); } - credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst); + credit = min_t(u32, icmp_global.credit + incr, + READ_ONCE(sysctl_icmp_msgs_burst)); if (credit) { /* We want to use a credit of one in average, but need to randomize * it for security reasons. @@ -281,7 +282,7 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code) return true; /* Limit if icmp type is enabled in ratemask. */ - if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask)) + if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask))) return true; return false; @@ -319,7 +320,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, vif = l3mdev_master_ifindex(dst->dev); peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1); - rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit); + rc = inet_peer_xrlim_allow(peer, + READ_ONCE(net->ipv4.sysctl_icmp_ratelimit)); if (peer) inet_putpeer(peer); out: @@ -692,7 +694,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, rcu_read_lock(); if (rt_is_input_route(rt) && - net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) + READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)) dev = dev_get_by_index_rcu(net, inet_iif(skb_in)); if (dev) @@ -879,7 +881,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb) * values please see * Documentation/networking/ip-sysctl.rst */ - switch (net->ipv4.sysctl_ip_no_pmtu_disc) { + switch (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) { default: net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n", &iph->daddr); @@ -932,7 +934,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb) * get the other vendor to fix their kit. */ - if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses && + if (!READ_ONCE(net->ipv4.sysctl_icmp_ignore_bogus_error_responses) && inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) { net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n", &ip_hdr(skb)->saddr, @@ -992,7 +994,7 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb) net = dev_net(skb_dst(skb)->dev); /* should there be an ICMP stat for ignored echos? */ - if (net->ipv4.sysctl_icmp_echo_ignore_all) + if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all)) return SKB_NOT_DROPPED_YET; icmp_param.data.icmph = *icmp_hdr(skb); @@ -1027,7 +1029,7 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) u16 ident_len; u8 status; - if (!net->ipv4.sysctl_icmp_echo_enable_probe) + if (!READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe)) return false; /* We currently only support probing interfaces on the proxy node @@ -1248,7 +1250,7 @@ int icmp_rcv(struct sk_buff *skb) */ if ((icmph->type == ICMP_ECHO || icmph->type == ICMP_TIMESTAMP) && - net->ipv4.sysctl_icmp_echo_ignore_broadcasts) { + READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_broadcasts)) { reason = SKB_DROP_REASON_INVALID_PROTO; goto error; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b65d074d9620..e3ab0cb61624 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -467,7 +467,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; - if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(pmc->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return skb; mtu = READ_ONCE(dev->mtu); @@ -593,7 +594,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) @@ -736,7 +737,8 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); - if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) @@ -825,7 +827,7 @@ static void igmp_ifc_event(struct in_device *in_dev) struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv); + WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv)); igmp_ifc_start_timer(in_dev, 1); } @@ -920,7 +922,8 @@ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) if (group == IGMP_ALL_HOSTS) return false; - if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return false; rcu_read_lock(); @@ -1006,7 +1009,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, * received value was zero, use the default or statically * configured value. */ - in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv; + in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; /* RFC3376, 8.3. Query Response Interval: @@ -1045,7 +1048,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&im->lock); if (im->tm_running) @@ -1186,7 +1189,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; - pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; @@ -1237,9 +1240,11 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) swap(im->tomb, pmc->tomb); swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) - psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + psf->sf_crcount = in_dev->mr_qrv ?: + READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + im->crcount = in_dev->mr_qrv ?: + READ_ONCE(net->ipv4.sysctl_igmp_qrv); } in_dev_put(pmc->interface); kfree_pmc(pmc); @@ -1296,7 +1301,8 @@ static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; reporter = im->reporter; @@ -1338,13 +1344,14 @@ static void igmp_group_added(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; if (in_dev->dead) return; - im->unsolicit_count = net->ipv4.sysctl_igmp_qrv; + im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); @@ -1358,7 +1365,7 @@ static void igmp_group_added(struct ip_mc_list *im) * IN() to IN(A). */ if (im->sfmode == MCAST_EXCLUDE) - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); igmp_ifc_event(in_dev); #endif @@ -1642,7 +1649,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; /* a failover is happening and switches @@ -1749,7 +1756,7 @@ static void ip_mc_reset(struct in_device *in_dev) in_dev->mr_qi = IGMP_QUERY_INTERVAL; in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; - in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; + in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv); } #else static void ip_mc_reset(struct in_device *in_dev) @@ -1883,7 +1890,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; @@ -1947,7 +1954,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST - pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; @@ -2126,7 +2133,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ - pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; @@ -2192,7 +2199,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, count++; } err = -ENOBUFS; - if (count >= net->ipv4.sysctl_igmp_max_memberships) + if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships)) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) @@ -2379,7 +2386,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct } /* else, add a new source to the filter */ - if (psl && psl->sl_count >= net->ipv4.sysctl_igmp_max_msf) { + if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { err = -ENOBUFS; goto done; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 53f5f956d948..eb31c7158b39 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -263,7 +263,7 @@ next_port: goto other_half_scan; } - if (net->ipv4.sysctl_ip_autobind_reuse && !relax) { + if (READ_ONCE(net->ipv4.sysctl_ip_autobind_reuse) && !relax) { /* We still have a chance to connect to different destinations */ relax = true; goto ports_exhausted; @@ -833,7 +833,8 @@ static void reqsk_timer_handler(struct timer_list *t) icsk = inet_csk(sk_listener); net = sock_net(sk_listener); - max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries; + max_syn_ack_retries = icsk->icsk_syn_retries ? : + READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. * If synack was not acknowledged for 1 second, it means diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 0ec501845cb3..47ccc343c9fb 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -156,7 +156,8 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, { struct inet_timewait_sock *tw; - if (refcount_read(&dr->tw_refcount) - 1 >= dr->sysctl_max_tw_buckets) + if (refcount_read(&dr->tw_refcount) - 1 >= + READ_ONCE(dr->sysctl_max_tw_buckets)) return NULL; tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab, diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index da21dfce24d7..e9fed83e9b3c 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -141,16 +141,20 @@ static void inet_peer_gc(struct inet_peer_base *base, struct inet_peer *gc_stack[], unsigned int gc_cnt) { + int peer_threshold, peer_maxttl, peer_minttl; struct inet_peer *p; __u32 delta, ttl; int i; - if (base->total >= inet_peer_threshold) + peer_threshold = READ_ONCE(inet_peer_threshold); + peer_maxttl = READ_ONCE(inet_peer_maxttl); + peer_minttl = READ_ONCE(inet_peer_minttl); + + if (base->total >= peer_threshold) ttl = 0; /* be aggressive */ else - ttl = inet_peer_maxttl - - (inet_peer_maxttl - inet_peer_minttl) / HZ * - base->total / inet_peer_threshold * HZ; + ttl = peer_maxttl - (peer_maxttl - peer_minttl) / HZ * + base->total / peer_threshold * HZ; for (i = 0; i < gc_cnt; i++) { p = gc_stack[i]; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e3aa436a1bdf..e18931a6d153 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -157,7 +157,7 @@ int ip_forward(struct sk_buff *skb) !skb_sec_path(skb)) ip_rt_send_redirect(skb); - if (net->ipv4.sysctl_ip_fwd_update_priority) + if (READ_ONCE(net->ipv4.sysctl_ip_fwd_update_priority)) skb->priority = rt_tos2priority(iph->tos); return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index b1165f717cd1..1b512390b3cf 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -312,14 +312,13 @@ static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph, ip_hdr(hint)->tos == iph->tos; } -INDIRECT_CALLABLE_DECLARE(int udp_v4_early_demux(struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(int tcp_v4_early_demux(struct sk_buff *)); +int tcp_v4_early_demux(struct sk_buff *skb); +int udp_v4_early_demux(struct sk_buff *skb); static int ip_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct sk_buff *hint) { const struct iphdr *iph = ip_hdr(skb); - int (*edemux)(struct sk_buff *skb); int err, drop_reason; struct rtable *rt; @@ -332,21 +331,29 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, goto drop_error; } - if (net->ipv4.sysctl_ip_early_demux && + if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && !skb_dst(skb) && !skb->sk && !ip_is_fragment(iph)) { - const struct net_protocol *ipprot; - int protocol = iph->protocol; - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) { - err = INDIRECT_CALL_2(edemux, tcp_v4_early_demux, - udp_v4_early_demux, skb); - if (unlikely(err)) - goto drop_error; - /* must reload iph, skb->head might have changed */ - iph = ip_hdr(skb); + switch (iph->protocol) { + case IPPROTO_TCP: + if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) { + tcp_v4_early_demux(skb); + + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } + break; + case IPPROTO_UDP: + if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) { + err = udp_v4_early_demux(skb); + if (unlikely(err)) + goto drop_error; + + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } + break; } } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 445a9ecaefa1..a8a323ecbb54 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -782,7 +782,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) /* numsrc >= (4G-140)/128 overflow in 32 bits */ err = -ENOBUFS; if (gsf->gf_numsrc >= 0x1ffffff || - gsf->gf_numsrc > sock_net(sk)->ipv4.sysctl_igmp_max_msf) + gsf->gf_numsrc > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf)) goto out_free_gsf; err = -EINVAL; @@ -832,7 +832,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, /* numsrc >= (4G-140)/128 overflow in 32 bits */ err = -ENOBUFS; - if (n > sock_net(sk)->ipv4.sysctl_igmp_max_msf) + if (n > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf)) goto out_free_gsf; err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode, &gf32->gf_group, gf32->gf_slist_flex); @@ -1244,7 +1244,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, } /* numsrc >= (1G-4) overflow in 32 bits */ if (msf->imsf_numsrc >= 0x3ffffffcU || - msf->imsf_numsrc > net->ipv4.sysctl_igmp_max_msf) { + msf->imsf_numsrc > READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { kfree(msf); err = -ENOBUFS; break; @@ -1606,7 +1606,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, { struct net *net = sock_net(sk); val = (inet->uc_ttl == -1 ? - net->ipv4.sysctl_ip_default_ttl : + READ_ONCE(net->ipv4.sysctl_ip_default_ttl) : inet->uc_ttl); break; } diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 918c61fda0f3..d640adcaf1b1 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -62,7 +62,7 @@ struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net, skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, - net->ipv4.sysctl_ip_default_ttl); + READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); niph->tot_len = htons(nskb->len); ip_send_check(niph); @@ -117,7 +117,7 @@ struct sk_buff *nf_reject_skb_v4_unreach(struct net *net, skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP, - net->ipv4.sysctl_ip_default_ttl); + READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); skb_reset_transport_header(nskb); icmph = skb_put_zero(nskb, sizeof(struct icmphdr)); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index e459a391e607..853a75a8fbaf 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1858,7 +1858,7 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) /* __ip6_del_rt does a release, so do a hold here */ fib6_info_hold(f6i); ipv6_stub->ip6_del_rt(net, f6i, - !net->ipv4.sysctl_nexthop_compat_mode); + !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)); } } @@ -2361,7 +2361,8 @@ out: if (!rc) { nh_base_seq_inc(net); nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo); - if (replace_notify && net->ipv4.sysctl_nexthop_compat_mode) + if (replace_notify && + READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)) nexthop_replace_notify(net, new_nh, &cfg->nlinfo); } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 28836071f0a6..0088a4c64d77 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -387,7 +387,7 @@ static int snmp_seq_show_ipstats(struct seq_file *seq, void *v) seq_printf(seq, "\nIp: %d %d", IPV4_DEVCONF_ALL(net, FORWARDING) ? 1 : 2, - net->ipv4.sysctl_ip_default_ttl); + READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0); snmp_get_cpu_field64_batch(buff64, snmp4_ipstats_list, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 356f535f3443..4702c61207a8 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1398,7 +1398,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) struct fib_info *fi = res->fi; u32 mtu = 0; - if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu || + if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) || fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU)) mtu = fi->fib_mtu; @@ -1929,7 +1929,7 @@ static u32 fib_multipath_custom_hash_outer(const struct net *net, const struct sk_buff *skb, bool *p_has_inner) { - u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) @@ -1958,7 +1958,7 @@ static u32 fib_multipath_custom_hash_inner(const struct net *net, const struct sk_buff *skb, bool has_inner) { - u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; /* We assume the packet carries an encapsulation, but if none was @@ -2018,7 +2018,7 @@ static u32 fib_multipath_custom_hash_skb(const struct net *net, static u32 fib_multipath_custom_hash_fl4(const struct net *net, const struct flowi4 *fl4) { - u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) @@ -2048,7 +2048,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, struct flow_keys hash_keys; u32 mhash = 0; - switch (net->ipv4.sysctl_fib_multipath_hash_policy) { + switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index f33c31dd7366..942d2dfa1115 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -247,12 +247,12 @@ bool cookie_timestamp_decode(const struct net *net, return true; } - if (!net->ipv4.sysctl_tcp_timestamps) + if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps)) return false; tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0; - if (tcp_opt->sack_ok && !net->ipv4.sysctl_tcp_sack) + if (tcp_opt->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack)) return false; if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK) @@ -261,7 +261,7 @@ bool cookie_timestamp_decode(const struct net *net, tcp_opt->wscale_ok = 1; tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK; - return net->ipv4.sysctl_tcp_window_scaling != 0; + return READ_ONCE(net->ipv4.sysctl_tcp_window_scaling) != 0; } EXPORT_SYMBOL(cookie_timestamp_decode); @@ -273,7 +273,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, if (!ecn_ok) return false; - if (net->ipv4.sysctl_tcp_ecn) + if (READ_ONCE(net->ipv4.sysctl_tcp_ecn)) return true; return dst_feature(dst, RTAX_FEATURE_ECN); @@ -340,7 +340,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) struct flowi4 fl4; u32 tsoff = 0; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) || + !th->ack || th->rst) goto out; if (tcp_synq_no_recent_overflow(sk)) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index cd448cdd3b38..5490c285668b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -84,7 +84,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, * port limit. */ if ((range[1] < range[0]) || - (range[0] < net->ipv4.sysctl_ip_prot_sock)) + (range[0] < READ_ONCE(net->ipv4.sysctl_ip_prot_sock))) ret = -EINVAL; else set_local_port_range(net, range); @@ -110,7 +110,7 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write, .extra2 = &ip_privileged_port_max, }; - pports = net->ipv4.sysctl_ip_prot_sock; + pports = READ_ONCE(net->ipv4.sysctl_ip_prot_sock); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); @@ -122,7 +122,7 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write, if (range[0] < pports) ret = -EINVAL; else - net->ipv4.sysctl_ip_prot_sock = pports; + WRITE_ONCE(net->ipv4.sysctl_ip_prot_sock, pports); } return ret; @@ -350,61 +350,6 @@ bad_key: return ret; } -static void proc_configure_early_demux(int enabled, int protocol) -{ - struct net_protocol *ipprot; -#if IS_ENABLED(CONFIG_IPV6) - struct inet6_protocol *ip6prot; -#endif - - rcu_read_lock(); - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot) - ipprot->early_demux = enabled ? ipprot->early_demux_handler : - NULL; - -#if IS_ENABLED(CONFIG_IPV6) - ip6prot = rcu_dereference(inet6_protos[protocol]); - if (ip6prot) - ip6prot->early_demux = enabled ? ip6prot->early_demux_handler : - NULL; -#endif - rcu_read_unlock(); -} - -static int proc_tcp_early_demux(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_tcp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_TCP); - } - - return ret; -} - -static int proc_udp_early_demux(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_udp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_UDP); - } - - return ret; -} - static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -599,6 +544,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "icmp_echo_enable_probe", @@ -615,6 +562,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "icmp_ignore_bogus_error_responses", @@ -622,6 +571,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "icmp_errors_use_inbound_ifaddr", @@ -629,6 +580,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "icmp_ratelimit", @@ -668,6 +621,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, }, { .procname = "tcp_ecn_fallback", @@ -675,6 +630,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "ip_dynaddr", @@ -695,14 +652,14 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_udp_early_demux, .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_udp_early_demux + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_early_demux", .data = &init_net.ipv4.sysctl_tcp_early_demux, .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_tcp_early_demux + .proc_handler = proc_dou8vec_minmax, }, { .procname = "nexthop_compat_mode", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index fdb80b9608fe..8f117f92e193 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -441,7 +441,7 @@ void tcp_init_sock(struct sock *sk) tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; - tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering; + tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering); tcp_assign_congestion_control(sk); tp->tsoffset = 0; @@ -1150,7 +1150,8 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, struct sockaddr *uaddr = msg->msg_name; int err, flags; - if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || + if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & + TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; @@ -2726,7 +2727,8 @@ static void tcp_orphan_update(struct timer_list *unused) static bool tcp_too_many_orphans(int shift) { - return READ_ONCE(tcp_orphan_cache) << shift > sysctl_tcp_max_orphans; + return READ_ONCE(tcp_orphan_cache) << shift > + READ_ONCE(sysctl_tcp_max_orphans); } bool tcp_check_oom(struct sock *sk, int shift) @@ -3627,7 +3629,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; - } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { + } else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) & + TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else @@ -3977,12 +3980,13 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; + val = icsk->icsk_syn_retries ? : + READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: val = tp->linger2; if (val >= 0) - val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ; + val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index fdbcf2a6d08e..825b216d11f5 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -332,7 +332,7 @@ static bool tcp_fastopen_no_cookie(const struct sock *sk, const struct dst_entry *dst, int flag) { - return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) || + return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) || tcp_sk(sk)->fastopen_no_cookie || (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE)); } @@ -347,7 +347,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, const struct dst_entry *dst) { bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; - int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; int ret = 0; @@ -489,7 +489,7 @@ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk); - if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)) return; /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ @@ -510,7 +510,8 @@ void tcp_fastopen_active_disable(struct sock *sk) */ bool tcp_fastopen_active_should_disable(struct sock *sk) { - unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout; + unsigned int tfo_bh_timeout = + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout); unsigned long timeout; int tfo_da_times; int multiplier; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2e2a9ece9af2..07dbcbae7782 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1051,7 +1051,7 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, tp->undo_marker ? tp->undo_retrans : 0); #endif tp->reordering = min_t(u32, (metric + mss - 1) / mss, - sock_net(sk)->ipv4.sysctl_tcp_max_reordering); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)); } /* This exciting event is worth to be remembered. 8) */ @@ -2030,7 +2030,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend) return; tp->reordering = min_t(u32, tp->packets_out + addend, - sock_net(sk)->ipv4.sysctl_tcp_max_reordering); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)); tp->reord_seen++; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER); } @@ -2095,7 +2095,8 @@ static inline void tcp_init_undo(struct tcp_sock *tp) static bool tcp_is_rack(const struct sock *sk) { - return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION; + return READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_LOSS_DETECTION; } /* If we detect SACK reneging, forget all SACK information @@ -2139,6 +2140,7 @@ void tcp_enter_loss(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; + u8 reordering; tcp_timeout_mark_lost(sk); @@ -2159,10 +2161,12 @@ void tcp_enter_loss(struct sock *sk) /* Timeout in disordered state after receiving substantial DUPACKs * suggests that the degree of reordering is over-estimated. */ + reordering = READ_ONCE(net->ipv4.sysctl_tcp_reordering); if (icsk->icsk_ca_state <= TCP_CA_Disorder && - tp->sacked_out >= net->ipv4.sysctl_tcp_reordering) + tp->sacked_out >= reordering) tp->reordering = min_t(unsigned int, tp->reordering, - net->ipv4.sysctl_tcp_reordering); + reordering); + tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; tcp_ecn_queue_cwr(tp); @@ -3464,7 +3468,8 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) * new SACK or ECE mark may first advance cwnd here and later reduce * cwnd in tcp_fastretrans_alert() based on more states. */ - if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering) + if (tcp_sk(sk)->reordering > + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering)) return flag & FLAG_FORWARD_PROGRESS; return flag & FLAG_DATA_ACKED; @@ -4056,7 +4061,7 @@ void tcp_parse_options(const struct net *net, break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && - !estab && net->ipv4.sysctl_tcp_window_scaling) { + !estab && READ_ONCE(net->ipv4.sysctl_tcp_window_scaling)) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > TCP_MAX_WSCALE) { @@ -4072,7 +4077,7 @@ void tcp_parse_options(const struct net *net, case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || - (!estab && net->ipv4.sysctl_tcp_timestamps))) { + (!estab && READ_ONCE(net->ipv4.sysctl_tcp_timestamps)))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); @@ -4080,7 +4085,7 @@ void tcp_parse_options(const struct net *net, break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && - !estab && net->ipv4.sysctl_tcp_sack) { + !estab && READ_ONCE(net->ipv4.sysctl_tcp_sack)) { opt_rx->sack_ok = TCP_SACK_SEEN; tcp_sack_reset(opt_rx); } @@ -5567,7 +5572,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) struct tcp_sock *tp = tcp_sk(sk); u32 ptr = ntohs(th->urg_ptr); - if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg) + if (ptr && !READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_stdurg)) ptr--; ptr += ntohl(th->seq); @@ -6729,7 +6734,7 @@ static void tcp_ecn_create_request(struct request_sock *req, ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield); ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK); - ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst; + ecn_ok = READ_ONCE(net->ipv4.sysctl_tcp_ecn) || ecn_ok_dst; if (((!ect || th->res1) && ecn_ok) || tcp_ca_needs_ecn(listen_sk) || (ecn_ok_dst & DST_FEATURE_ECN_CA) || @@ -6797,11 +6802,14 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; - bool want_cookie = false; struct net *net = sock_net(sk); + bool want_cookie = false; + u8 syncookies; + + syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); #ifdef CONFIG_SYN_COOKIES - if (net->ipv4.sysctl_tcp_syncookies) { + if (syncookies) { msg = "Sending cookies"; want_cookie = true; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); @@ -6809,8 +6817,7 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) #endif __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - if (!queue->synflood_warned && - net->ipv4.sysctl_tcp_syncookies != 2 && + if (!queue->synflood_warned && syncookies != 2 && xchg(&queue->synflood_warned, 1) == 0) net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", proto, sk->sk_num, msg); @@ -6859,7 +6866,7 @@ u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, struct tcp_sock *tp = tcp_sk(sk); u16 mss; - if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 && + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) != 2 && !inet_csk_reqsk_queue_is_full(sk)) return 0; @@ -6893,13 +6900,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, bool want_cookie = false; struct dst_entry *dst; struct flowi fl; + u8 syncookies; + + syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); /* TW buckets are converted to open requests without * limitations, they conserve resources and peer is * evidently real one. */ - if ((net->ipv4.sysctl_tcp_syncookies == 2 || - inet_csk_reqsk_queue_is_full(sk)) && !isn) { + if ((syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) { want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name); if (!want_cookie) goto drop; @@ -6948,10 +6957,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb); if (!want_cookie && !isn) { + int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog); + /* Kill the following clause, if you dislike this way. */ - if (!net->ipv4.sysctl_tcp_syncookies && - (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < - (net->ipv4.sysctl_max_syn_backlog >> 2)) && + if (!syncookies && + (max_syn_backlog - inet_csk_reqsk_queue_len(sk) < + (max_syn_backlog >> 2)) && !tcp_peer_is_proven(req, dst)) { /* Without syncookies last quarter of * backlog is filled with destinations, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index da5a3c44c4fb..d16e6e40f47b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -108,10 +108,10 @@ static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) { + int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse); const struct inet_timewait_sock *tw = inet_twsk(sktw); const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); - int reuse = sock_net(sk)->ipv4.sysctl_tcp_tw_reuse; if (reuse == 2) { /* Still does not detect *everything* that goes through diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 7029b0e98edb..a501150deaa3 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -428,7 +428,8 @@ void tcp_update_metrics(struct sock *sk) if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) { val = tcp_metric_get(tm, TCP_METRIC_REORDERING); if (val < tp->reordering && - tp->reordering != net->ipv4.sysctl_tcp_reordering) + tp->reordering != + READ_ONCE(net->ipv4.sysctl_tcp_reordering)) tcp_metric_set(tm, TCP_METRIC_REORDERING, tp->reordering); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6854bb1fb32b..cb95d88497ae 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -173,7 +173,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, * Oh well... nobody has a sufficient solution to this * protocol bug yet. */ - if (twsk_net(tw)->ipv4.sysctl_tcp_rfc1337 == 0) { + if (!READ_ONCE(twsk_net(tw)->ipv4.sysctl_tcp_rfc1337)) { kill: inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; @@ -781,7 +781,7 @@ listen_overflow: if (sk != req->rsk_listener) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); - if (!sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow) { + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow)) { inet_rsk(req)->acked = 1; return NULL; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1c054431e358..c38e07b50639 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -324,7 +324,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk); - bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 || + bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 || tcp_ca_needs_ecn(sk) || bpf_needs_ecn; if (!use_ecn) { @@ -346,7 +346,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) { - if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback) + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)) /* tp->ecn_flags are cleared at a later point in time when * SYN ACK is ultimatively being received. */ @@ -791,18 +791,18 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) { + if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } - if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) { + if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling))) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } - if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) { + if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_sack))) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; @@ -1719,7 +1719,8 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) mss_now -= icsk->icsk_ext_hdr_len; /* Then reserve room for full set of TCP options and 8 bytes of data */ - mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss); + mss_now = max(mss_now, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss)); return mss_now; } @@ -1762,10 +1763,10 @@ void tcp_mtup_init(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); - icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1; + icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; - icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss); + icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, READ_ONCE(net->ipv4.sysctl_tcp_base_mss)); icsk->icsk_mtup.probe_size = 0; if (icsk->icsk_mtup.enabled) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; @@ -1897,7 +1898,7 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; - if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle && + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) && (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && !ca_ops->cong_control) tcp_cwnd_application_limited(sk); @@ -2282,7 +2283,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk) u32 interval; s32 delta; - interval = net->ipv4.sysctl_tcp_probe_interval; + interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval); delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp; if (unlikely(delta >= interval * HZ)) { int mss = tcp_current_mss(sk); @@ -2366,7 +2367,7 @@ static int tcp_mtu_probe(struct sock *sk) * probing process by not resetting search range to its orignal. */ if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) || - interval < net->ipv4.sysctl_tcp_probe_threshold) { + interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) { /* Check whether enough time has elaplased for * another round of probing. */ @@ -2740,7 +2741,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) if (rcu_access_pointer(tp->fastopen_rsk)) return false; - early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; + early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans); /* Schedule a loss probe in 2*RTT for SACK capable connections * not in loss recovery, that are either limited by cwnd or application. */ @@ -3104,7 +3105,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, struct sk_buff *skb = to, *tmp; bool first = true; - if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)) return; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; @@ -3646,7 +3647,7 @@ static void tcp_connect_init(struct sock *sk) * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr); - if (sock_net(sk)->ipv4.sysctl_tcp_timestamps) + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps)) tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG @@ -3682,7 +3683,7 @@ static void tcp_connect_init(struct sock *sk) tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, - sock_net(sk)->ipv4.sysctl_tcp_window_scaling, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling), &rcv_wscale, rcv_wnd); @@ -4089,7 +4090,7 @@ void tcp_send_probe0(struct sock *sk) icsk->icsk_probes_out++; if (err <= 0) { - if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2) + if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2)) icsk->icsk_backoff++; timeout = tcp_probe0_when(sk, TCP_RTO_MAX); } else { diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 48f30e7209f2..50abaa941387 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -14,7 +14,8 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk) return 0; if (tp->sacked_out >= tp->reordering && - !(sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_NO_DUPTHRESH)) + !(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_NO_DUPTHRESH)) return 0; } @@ -187,7 +188,8 @@ void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); - if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_STATIC_REO_WND || + if ((READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_STATIC_REO_WND) || !rs->prior_delivered) return; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 20cf4a98c69d..50bba370486e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -143,7 +143,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) */ static int tcp_orphan_retries(struct sock *sk, bool alive) { - int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */ + int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */ /* We know from an ICMP that something is wrong. */ if (sk->sk_err_soft && !alive) @@ -163,7 +163,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) int mss; /* Black hole detection */ - if (!net->ipv4.sysctl_tcp_mtu_probing) + if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing)) return; if (!icsk->icsk_mtup.enabled) { @@ -171,9 +171,9 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; - mss = min(net->ipv4.sysctl_tcp_base_mss, mss); - mss = max(mss, net->ipv4.sysctl_tcp_mtu_probe_floor); - mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss); + mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss); + mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_mtu_probe_floor)); + mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_min_snd_mss)); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); @@ -239,17 +239,18 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) __dst_negative_advice(sk); - retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; + retry_until = icsk->icsk_syn_retries ? : + READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); expired = icsk->icsk_retransmits >= retry_until; } else { - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) { + if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); __dst_negative_advice(sk); } - retry_until = net->ipv4.sysctl_tcp_retries2; + retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = icsk->icsk_rto < TCP_RTO_MAX; @@ -380,7 +381,7 @@ static void tcp_probe_timer(struct sock *sk) msecs_to_jiffies(icsk->icsk_user_timeout)) goto abort; - max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; + max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; @@ -406,12 +407,15 @@ abort: tcp_write_err(sk); static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); - int max_retries = icsk->icsk_syn_retries ? : - sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ struct tcp_sock *tp = tcp_sk(sk); + int max_retries; req->rsk_ops->syn_ack_timeout(req); + /* add one more retry for fastopen */ + max_retries = icsk->icsk_syn_retries ? : + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1; + if (req->num_timeout >= max_retries) { tcp_write_err(sk); return; @@ -574,7 +578,7 @@ out_reset_timer: * linear-timeout retransmissions into a black hole */ if (sk->sk_state == TCP_ESTABLISHED && - (tp->thin_lto || net->ipv4.sysctl_tcp_thin_linear_timeouts) && + (tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) && tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; @@ -585,7 +589,7 @@ out_reset_timer: } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX); - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0)) + if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0)) __sk_dst_reset(sk); out:; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 70564ddccc46..6f354f8be2c5 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -226,7 +226,7 @@ lookup_protocol: RCU_INIT_POINTER(inet->mc_list, NULL); inet->rcv_tos = 0; - if (net->ipv4.sysctl_ip_no_pmtu_disc) + if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 61770220774e..9d92d51c4757 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -925,7 +925,7 @@ static int icmpv6_rcv(struct sk_buff *skb) break; case ICMPV6_EXT_ECHO_REQUEST: if (!net->ipv6.sysctl.icmpv6_echo_ignore_all && - net->ipv4.sysctl_icmp_echo_enable_probe) + READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe)) icmpv6_echo_reply(skb); break; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 0322cc86b84e..e1ebf5e42ebe 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -45,20 +45,23 @@ #include <net/inet_ecn.h> #include <net/dst_metadata.h> -INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *)); static void ip6_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb) { - void (*edemux)(struct sk_buff *skb); - - if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { - const struct inet6_protocol *ipprot; - - ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); - if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) - INDIRECT_CALL_2(edemux, tcp_v6_early_demux, - udp_v6_early_demux, skb); + if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && + !skb_dst(skb) && !skb->sk) { + switch (ipv6_hdr(skb)->nexthdr) { + case IPPROTO_TCP: + if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) + tcp_v6_early_demux(skb); + break; + case IPPROTO_UDP: + if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) + udp_v6_early_demux(skb); + break; + } } + if (!skb_valid_dst(skb)) ip6_route_input(skb); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 828355710c57..916417944ec8 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5741,7 +5741,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, if (nexthop_is_blackhole(rt->nh)) rtm->rtm_type = RTN_BLACKHOLE; - if (net->ipv4.sysctl_nexthop_compat_mode && + if (READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode) && rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0) goto nla_put_failure; diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index d64855010948..e756ba705fd9 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -189,6 +189,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) } #endif + hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_postpush_rcsum(skb, hdr, tot_len); return 0; @@ -241,6 +243,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) } #endif + hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen); return 0; @@ -302,7 +306,6 @@ static int seg6_do_srh(struct sk_buff *skb) break; } - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); nf_reset_ct(skb); diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 98a34287439c..2cd4a8d3b30a 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -826,7 +826,6 @@ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt) if (err) goto drop; - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); seg6_lookup_nexthop(skb, NULL, 0); @@ -858,7 +857,6 @@ static int input_action_end_b6_encap(struct sk_buff *skb, if (err) goto drop; - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); seg6_lookup_nexthop(skb, NULL, 0); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 9cc123f000fb..5014aa663452 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -141,7 +141,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) __u8 rcv_wscale; u32 tsoff = 0; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) || + !th->ack || th->rst) goto out; if (tcp_synq_no_recent_overflow(sk)) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f37dd4aa91c6..9d3ede293258 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1822,7 +1822,7 @@ do_time_wait: goto discard_it; } -INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb) +void tcp_v6_early_demux(struct sk_buff *skb) { const struct ipv6hdr *hdr; const struct tcphdr *th; @@ -2176,12 +2176,7 @@ struct proto tcpv6_prot = { }; EXPORT_SYMBOL_GPL(tcpv6_prot); -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct inet6_protocol tcpv6_protocol = { - .early_demux = tcp_v6_early_demux, - .early_demux_handler = tcp_v6_early_demux, +static const struct inet6_protocol tcpv6_protocol = { .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 55afd7f39c04..e2f2e087a753 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1052,7 +1052,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net, return NULL; } -INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb) +void udp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); const struct udphdr *uh; @@ -1660,12 +1660,7 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname, return ipv6_getsockopt(sk, level, optname, optval, optlen); } -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct inet6_protocol udpv6_protocol = { - .early_demux = udp_v6_early_demux, - .early_demux_handler = udp_v6_early_demux, +static const struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index f7896f257e1b..4ddf297f40f2 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -4468,14 +4468,14 @@ EXPORT_SYMBOL_GPL(ieee80211_color_change_finish); void ieeee80211_obss_color_collision_notify(struct ieee80211_vif *vif, - u64 color_bitmap) + u64 color_bitmap, gfp_t gfp) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); if (sdata->vif.color_change_active || sdata->vif.csa_active) return; - cfg80211_obss_color_collision_notify(sdata->dev, color_bitmap); + cfg80211_obss_color_collision_notify(sdata->dev, color_bitmap, gfp); } EXPORT_SYMBOL_GPL(ieeee80211_obss_color_collision_notify); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 41531478437c..15a73b7fdd75 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -377,7 +377,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do bool cancel_scan; struct cfg80211_nan_func *func; + spin_lock_bh(&local->fq.lock); clear_bit(SDATA_STATE_RUNNING, &sdata->state); + spin_unlock_bh(&local->fq.lock); cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata; if (cancel_scan) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3c08ae04ddbc..1675f8cb87f1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3217,7 +3217,8 @@ ieee80211_rx_check_bss_color_collision(struct ieee80211_rx_data *rx) IEEE80211_HE_OPERATION_BSS_COLOR_MASK); if (color == bss_conf->he_bss_color.color) ieeee80211_obss_color_collision_notify(&rx->sdata->vif, - BIT_ULL(color)); + BIT_ULL(color), + GFP_ATOMIC); } } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 0e4efc08c762..c425f4fb7c2e 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2818,19 +2818,10 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, /* * If the skb is shared we need to obtain our own copy. */ - if (skb_shared(skb)) { - struct sk_buff *tmp_skb = skb; - - /* can't happen -- skb is a clone if info_id != 0 */ - WARN_ON(info_id); - - skb = skb_clone(skb, GFP_ATOMIC); - kfree_skb(tmp_skb); - - if (!skb) { - ret = -ENOMEM; - goto free; - } + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) { + ret = -ENOMEM; + goto free; } hdr.frame_control = fc; @@ -3539,15 +3530,9 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, /* after this point (skb is modified) we cannot return false */ - if (skb_shared(skb)) { - struct sk_buff *tmp_skb = skb; - - skb = skb_clone(skb, GFP_ATOMIC); - kfree_skb(tmp_skb); - - if (!skb) - return true; - } + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + return true; if ((hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) && ieee80211_amsdu_aggregate(sdata, sta, fast_tx, skb)) @@ -4437,7 +4422,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, struct net_device *dev, struct sta_info *sta, struct ieee80211_key *key, struct sk_buff *skb) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_tx_info *info; struct ieee80211_local *local = sdata->local; struct tid_ampdu_tx *tid_tx; u8 tid; @@ -4452,6 +4437,11 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) goto out_free; + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + return; + + info = IEEE80211_SKB_CB(skb); memset(info, 0, sizeof(*info)); ieee80211_aggr_check(sdata, sta, skb); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1e26b5235add..dad42d42aa84 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -301,6 +301,9 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) local_bh_disable(); spin_lock(&fq->lock); + if (!test_bit(SDATA_STATE_RUNNING, &sdata->state)) + goto out; + if (sdata->vif.type == NL80211_IFTYPE_AP) ps = &sdata->bss->ps; diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 62c6733e0792..d50480b31750 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -147,8 +147,8 @@ u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, bool qos; /* all mesh/ocb stations are required to support WME */ - if (sdata->vif.type == NL80211_IFTYPE_MESH_POINT || - sdata->vif.type == NL80211_IFTYPE_OCB) + if (sta && (sdata->vif.type == NL80211_IFTYPE_MESH_POINT || + sdata->vif.type == NL80211_IFTYPE_OCB)) qos = true; else if (sta) qos = sta->sta.wme; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index cc21fafd9726..21a3ed64226e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2919,12 +2919,12 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) static int mptcp_disconnect(struct sock *sk, int flags) { - struct mptcp_subflow_context *subflow; + struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); inet_sk_state_store(sk, TCP_CLOSE); - mptcp_for_each_subflow(msk, subflow) { + list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); __mptcp_close_ssk(sk, ssk, subflow, MPTCP_CF_FASTCLOSE); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 082a2fd8d85b..369aeabb94fe 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -729,6 +729,9 @@ static void nf_ct_gc_expired(struct nf_conn *ct) if (!refcount_inc_not_zero(&ct->ct_general.use)) return; + /* load ->status after refcount increase */ + smp_acquire__after_ctrl_dep(); + if (nf_ct_should_gc(ct)) nf_ct_kill(ct); @@ -795,6 +798,9 @@ __nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, */ ct = nf_ct_tuplehash_to_ctrack(h); if (likely(refcount_inc_not_zero(&ct->ct_general.use))) { + /* re-check key after refcount */ + smp_acquire__after_ctrl_dep(); + if (likely(nf_ct_key_equal(h, tuple, zone, net))) goto found; @@ -1387,6 +1393,9 @@ static unsigned int early_drop_list(struct net *net, if (!refcount_inc_not_zero(&tmp->ct_general.use)) continue; + /* load ->ct_net and ->status after refcount increase */ + smp_acquire__after_ctrl_dep(); + /* kill only if still in same netns -- might have moved due to * SLAB_TYPESAFE_BY_RCU rules. * @@ -1536,6 +1545,9 @@ static void gc_worker(struct work_struct *work) if (!refcount_inc_not_zero(&tmp->ct_general.use)) continue; + /* load ->status after refcount increase */ + smp_acquire__after_ctrl_dep(); + if (gc_worker_skip_ct(tmp)) { nf_ct_put(tmp); continue; @@ -1775,6 +1787,16 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, if (!exp) __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC); + /* Other CPU might have obtained a pointer to this object before it was + * released. Because refcount is 0, refcount_inc_not_zero() will fail. + * + * After refcount_set(1) it will succeed; ensure that zeroing of + * ct->status and the correct ct->net pointer are visible; else other + * core might observe CONFIRMED bit which means the entry is valid and + * in the hash table, but its not (anymore). + */ + smp_wmb(); + /* Now it is going to be associated with an sk_buff, set refcount to 1. */ refcount_set(&ct->ct_general.use, 1); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 722af5e309ba..f5905b5201a7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1203,6 +1203,7 @@ restart: hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (nf_ct_is_expired(ct)) { + /* need to defer nf_ct_kill() until lock is released */ if (i < ARRAY_SIZE(nf_ct_evict) && refcount_inc_not_zero(&ct->ct_general.use)) nf_ct_evict[i++] = ct; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 6ad7bbc90d38..05895878610c 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -306,6 +306,9 @@ static int ct_seq_show(struct seq_file *s, void *v) if (unlikely(!refcount_inc_not_zero(&ct->ct_general.use))) return 0; + /* load ->status after refcount increase */ + smp_acquire__after_ctrl_dep(); + if (nf_ct_should_gc(ct)) { nf_ct_kill(ct); goto release; diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index 77bcb10fc586..cb894f0d63e9 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -67,7 +67,7 @@ dump_arp_packet(struct nf_log_buf *m, unsigned int logflags; struct arphdr _arph; - ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); + ah = skb_header_pointer(skb, nhoff, sizeof(_arph), &_arph); if (!ah) { nf_log_buf_add(m, "TRUNCATED"); return; @@ -96,7 +96,7 @@ dump_arp_packet(struct nf_log_buf *m, ah->ar_pln != sizeof(__be32)) return; - ap = skb_header_pointer(skb, sizeof(_arph), sizeof(_arpp), &_arpp); + ap = skb_header_pointer(skb, nhoff + sizeof(_arph), sizeof(_arpp), &_arpp); if (!ap) { nf_log_buf_add(m, " INCOMPLETE [%zu bytes]", skb->len - sizeof(_arph)); @@ -149,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf, nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, prefix); - dump_arp_packet(m, loginfo, skb, 0); + dump_arp_packet(m, loginfo, skb, skb_network_offset(skb)); nf_log_buf_close(m); } @@ -850,7 +850,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf, if (in) dump_mac_header(m, loginfo, skb); - dump_ipv4_packet(net, m, loginfo, skb, 0); + dump_ipv4_packet(net, m, loginfo, skb, skb_network_offset(skb)); nf_log_buf_close(m); } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index e479dd0561c5..16915f8eef2b 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -405,7 +405,7 @@ synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr, iph->tos = 0; iph->id = 0; iph->frag_off = htons(IP_DF); - iph->ttl = net->ipv4.sysctl_ip_default_ttl; + iph->ttl = READ_ONCE(net->ipv4.sysctl_ip_default_ttl); iph->protocol = IPPROTO_TCP; iph->check = 0; iph->saddr = saddr; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d6b59beab3a9..646d5fd53604 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5833,8 +5833,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) return -EINVAL; - if (flags != 0) - nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (flags != 0) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (err < 0) + return err; + } if (set->flags & NFT_SET_MAP) { if (nla[NFTA_SET_ELEM_DATA] == NULL && @@ -5943,7 +5946,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_set_elem_expr; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + if (err < 0) + goto err_parse_key; } if (nla[NFTA_SET_ELEM_KEY_END]) { @@ -5952,22 +5957,31 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_parse_key; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + if (err < 0) + goto err_parse_key_end; } if (timeout > 0) { - nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); - if (timeout != set->timeout) - nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); + if (err < 0) + goto err_parse_key_end; + + if (timeout != set->timeout) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); + if (err < 0) + goto err_parse_key_end; + } } if (num_exprs) { for (i = 0; i < num_exprs; i++) size += expr_array[i]->ops->size; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS, - sizeof(struct nft_set_elem_expr) + - size); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS, + sizeof(struct nft_set_elem_expr) + size); + if (err < 0) + goto err_parse_key_end; } if (nla[NFTA_SET_ELEM_OBJREF] != NULL) { @@ -5982,7 +5996,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = PTR_ERR(obj); goto err_parse_key_end; } - nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); + if (err < 0) + goto err_parse_key_end; } if (nla[NFTA_SET_ELEM_DATA] != NULL) { @@ -6016,7 +6032,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, NFT_VALIDATE_NEED); } - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); + if (err < 0) + goto err_parse_data; } /* The full maximum length of userdata can exceed the maximum @@ -6026,9 +6044,12 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, ulen = 0; if (nla[NFTA_SET_ELEM_USERDATA] != NULL) { ulen = nla_len(nla[NFTA_SET_ELEM_USERDATA]); - if (ulen > 0) - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA, - ulen); + if (ulen > 0) { + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA, + ulen); + if (err < 0) + goto err_parse_data; + } } err = -ENOMEM; @@ -6256,8 +6277,11 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, nft_set_ext_prepare(&tmpl); - if (flags != 0) - nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (flags != 0) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (err < 0) + return err; + } if (nla[NFTA_SET_ELEM_KEY]) { err = nft_setelem_parse_key(ctx, set, &elem.key.val, @@ -6265,16 +6289,20 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + if (err < 0) + goto fail_elem; } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, nla[NFTA_SET_ELEM_KEY_END]); if (err < 0) - return err; + goto fail_elem; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + if (err < 0) + goto fail_elem_key_end; } err = -ENOMEM; @@ -6282,7 +6310,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, elem.key_end.val.data, NULL, 0, 0, GFP_KERNEL_ACCOUNT); if (elem.priv == NULL) - goto fail_elem; + goto fail_elem_key_end; ext = nft_set_elem_ext(set, elem.priv); if (flags) @@ -6306,6 +6334,8 @@ fail_ops: kfree(trans); fail_trans: kfree(elem.priv); +fail_elem_key_end: + nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); fail_elem: nft_data_release(&elem.key.val, NFT_DATA_VALUE); return err; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 9bb4d3dcc994..ac366c99086f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3533,7 +3533,7 @@ int tc_setup_action(struct flow_action *flow_action, struct tc_action *actions[], struct netlink_ext_ack *extack) { - int i, j, index, err = 0; + int i, j, k, index, err = 0; struct tc_action *act; BUILD_BUG_ON(TCA_ACT_HW_STATS_ANY != FLOW_ACTION_HW_STATS_ANY); @@ -3553,14 +3553,18 @@ int tc_setup_action(struct flow_action *flow_action, if (err) goto err_out_locked; - entry->hw_stats = tc_act_hw_stats(act->hw_stats); - entry->hw_index = act->tcfa_index; index = 0; err = tc_setup_offload_act(act, entry, &index, extack); - if (!err) - j += index; - else + if (err) goto err_out_locked; + + for (k = 0; k < index ; k++) { + entry[k].hw_stats = tc_act_hw_stats(act->hw_stats); + entry[k].hw_index = act->tcfa_index; + } + + j += index; + spin_unlock_bh(&act->tcfa_lock); } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 35928fefae33..1a094b087d88 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -358,7 +358,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && !sp->inet.freebind && - !net->ipv4.sysctl_ip_nonlocal_bind) + !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind)) return 0; if (ipv6_only_sock(sctp_opt2sk(sp))) diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index c4d057b2941d..0bde36b56472 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -2122,7 +2122,7 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc) init_waitqueue_head(&lgr->llc_flow_waiter); init_waitqueue_head(&lgr->llc_msg_waiter); mutex_init(&lgr->llc_conf_mutex); - lgr->llc_testlink_time = net->ipv4.sysctl_tcp_keepalive_time; + lgr->llc_testlink_time = READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } /* called after lgr was removed from lgr_list */ diff --git a/net/socket.c b/net/socket.c index 82af3882b876..ec9ef13a702e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2359,25 +2359,20 @@ struct used_address { unsigned int name_len; }; -int __copy_msghdr_from_user(struct msghdr *kmsg, - struct user_msghdr __user *umsg, - struct sockaddr __user **save_addr, - struct iovec __user **uiov, size_t *nsegs) +int __copy_msghdr(struct msghdr *kmsg, + struct user_msghdr *msg, + struct sockaddr __user **save_addr) { - struct user_msghdr msg; ssize_t err; - if (copy_from_user(&msg, umsg, sizeof(*umsg))) - return -EFAULT; - kmsg->msg_control_is_user = true; kmsg->msg_get_inq = 0; - kmsg->msg_control_user = msg.msg_control; - kmsg->msg_controllen = msg.msg_controllen; - kmsg->msg_flags = msg.msg_flags; + kmsg->msg_control_user = msg->msg_control; + kmsg->msg_controllen = msg->msg_controllen; + kmsg->msg_flags = msg->msg_flags; - kmsg->msg_namelen = msg.msg_namelen; - if (!msg.msg_name) + kmsg->msg_namelen = msg->msg_namelen; + if (!msg->msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) @@ -2387,11 +2382,11 @@ int __copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = sizeof(struct sockaddr_storage); if (save_addr) - *save_addr = msg.msg_name; + *save_addr = msg->msg_name; - if (msg.msg_name && kmsg->msg_namelen) { + if (msg->msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(msg.msg_name, + err = move_addr_to_kernel(msg->msg_name, kmsg->msg_namelen, kmsg->msg_name); if (err < 0) @@ -2402,13 +2397,11 @@ int __copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (msg.msg_iovlen > UIO_MAXIOV) + if (msg->msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; kmsg->msg_ubuf = NULL; - *uiov = msg.msg_iov; - *nsegs = msg.msg_iovlen; return 0; } @@ -2420,8 +2413,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, struct user_msghdr msg; ssize_t err; - err = __copy_msghdr_from_user(kmsg, umsg, save_addr, &msg.msg_iov, - &msg.msg_iovlen); + if (copy_from_user(&msg, umsg, sizeof(*umsg))) + return -EFAULT; + + err = __copy_msghdr(kmsg, &msg, save_addr); if (err) return err; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index ec6f4b699a2b..879b9024678e 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -97,13 +97,16 @@ static void tls_device_queue_ctx_destruction(struct tls_context *ctx) unsigned long flags; spin_lock_irqsave(&tls_device_lock, flags); + if (unlikely(!refcount_dec_and_test(&ctx->refcount))) + goto unlock; + list_move_tail(&ctx->list, &tls_device_gc_list); /* schedule_work inside the spinlock * to make sure tls_device_down waits for that work. */ schedule_work(&tls_device_gc_work); - +unlock: spin_unlock_irqrestore(&tls_device_lock, flags); } @@ -194,8 +197,7 @@ void tls_device_sk_destruct(struct sock *sk) clean_acked_data_disable(inet_csk(sk)); } - if (refcount_dec_and_test(&tls_ctx->refcount)) - tls_device_queue_ctx_destruction(tls_ctx); + tls_device_queue_ctx_destruction(tls_ctx); } EXPORT_SYMBOL_GPL(tls_device_sk_destruct); @@ -1419,9 +1421,9 @@ static struct notifier_block tls_dev_notifier = { .notifier_call = tls_dev_event, }; -void __init tls_device_init(void) +int __init tls_device_init(void) { - register_netdevice_notifier(&tls_dev_notifier); + return register_netdevice_notifier(&tls_dev_notifier); } void __exit tls_device_cleanup(void) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 2ffede463e4a..d80ab3d1764e 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -1048,7 +1048,12 @@ static int __init tls_register(void) if (err) return err; - tls_device_init(); + err = tls_device_init(); + if (err) { + unregister_pernet_subsys(&tls_proc_ops); + return err; + } + tcp_register_ulp(&tcp_tls_ulp_ops); return 0; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index ff4d48fcbfb2..607a68911047 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1031,7 +1031,8 @@ void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) { ASSERT_WDEV_LOCK(wdev); - if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) return; if (WARN_ON(!wdev->current_bss) || diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f1876ea61fdc..f1a0bab920a5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2678,8 +2678,10 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, *num_xfrms = 0; return 0; } - if (IS_ERR(pols[0])) + if (IS_ERR(pols[0])) { + *num_pols = 0; return PTR_ERR(pols[0]); + } *num_xfrms = pols[0]->xfrm_nr; @@ -2694,6 +2696,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, if (pols[1]) { if (IS_ERR(pols[1])) { xfrm_pols_put(pols, *num_pols); + *num_pols = 0; return PTR_ERR(pols[1]); } (*num_pols)++; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 08564e0eef20..ccfb172eb5b8 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2620,7 +2620,7 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload) int err; if (family == AF_INET && - xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc) + READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)) x->props.flags |= XFRM_STATE_NOPMTUDISC; err = -EPROTONOSUPPORT; diff --git a/samples/fprobe/fprobe_example.c b/samples/fprobe/fprobe_example.c index 18b1e5c4b431..e22da8573116 100644 --- a/samples/fprobe/fprobe_example.c +++ b/samples/fprobe/fprobe_example.c @@ -20,7 +20,7 @@ #define BACKTRACE_DEPTH 16 #define MAX_SYMBOL_LEN 4096 -struct fprobe sample_probe; +static struct fprobe sample_probe; static unsigned long nhit; static char symbol[MAX_SYMBOL_LEN] = "kernel_clone"; diff --git a/samples/kprobes/kprobe_example.c b/samples/kprobes/kprobe_example.c index f991a66b5b02..fd346f58ddba 100644 --- a/samples/kprobes/kprobe_example.c +++ b/samples/kprobes/kprobe_example.c @@ -16,9 +16,8 @@ #include <linux/module.h> #include <linux/kprobes.h> -#define MAX_SYMBOL_LEN 64 -static char symbol[MAX_SYMBOL_LEN] = "kernel_clone"; -module_param_string(symbol, symbol, sizeof(symbol), 0644); +static char symbol[KSYM_NAME_LEN] = "kernel_clone"; +module_param_string(symbol, symbol, KSYM_NAME_LEN, 0644); /* For each probe you need to allocate a kprobe structure */ static struct kprobe kp = { diff --git a/samples/kprobes/kretprobe_example.c b/samples/kprobes/kretprobe_example.c index 228321ecb161..cbf16542d84e 100644 --- a/samples/kprobes/kretprobe_example.c +++ b/samples/kprobes/kretprobe_example.c @@ -23,11 +23,10 @@ #include <linux/module.h> #include <linux/kprobes.h> #include <linux/ktime.h> -#include <linux/limits.h> #include <linux/sched.h> -static char func_name[NAME_MAX] = "kernel_clone"; -module_param_string(func, func_name, NAME_MAX, S_IRUGO); +static char func_name[KSYM_NAME_LEN] = "kernel_clone"; +module_param_string(func, func_name, KSYM_NAME_LEN, 0644); MODULE_PARM_DESC(func, "Function to kretprobe; this module will report the" " function's execution time"); diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index d1425778664b..3fb6a99e78c4 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -236,6 +236,7 @@ objtool_args = \ $(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount) \ $(if $(CONFIG_UNWINDER_ORC), --orc) \ $(if $(CONFIG_RETPOLINE), --retpoline) \ + $(if $(CONFIG_RETHUNK), --rethunk) \ $(if $(CONFIG_SLS), --sls) \ $(if $(CONFIG_STACK_VALIDATION), --stackval) \ $(if $(CONFIG_HAVE_STATIC_CALL_INLINE), --static-call) \ diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o index 3c97a1564947..84019814f33f 100644 --- a/scripts/Makefile.vmlinux_o +++ b/scripts/Makefile.vmlinux_o @@ -44,7 +44,7 @@ objtool-enabled := $(or $(delay-objtool),$(CONFIG_NOINSTR_VALIDATION)) objtool_args := \ $(if $(delay-objtool),$(objtool_args)) \ - $(if $(CONFIG_NOINSTR_VALIDATION), --noinstr) \ + $(if $(CONFIG_NOINSTR_VALIDATION), --noinstr $(if $(CONFIG_CPU_UNRET_ENTRY), --unret)) \ $(if $(CONFIG_GCOV_KERNEL), --no-unreachable) \ --link diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index 46f7542db08c..dc07b6d12e30 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -180,7 +180,7 @@ lx-symbols command.""" self.breakpoint.delete() self.breakpoint = None self.breakpoint = LoadModuleBreakpoint( - "kernel/module.c:do_init_module", self) + "kernel/module/main.c:do_init_module", self) else: gdb.write("Note: symbol update on module loading not supported " "with this gdb version\n") diff --git a/security/Kconfig b/security/Kconfig index f29e4c656983..e6db09a779b7 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -54,17 +54,6 @@ config SECURITY_NETWORK implement socket and networking access controls. If you are unsure how to answer this question, answer N. -config PAGE_TABLE_ISOLATION - bool "Remove the kernel mapping in user mode" - default y - depends on (X86_64 || X86_PAE) && !UML - help - This feature reduces the number of hardware side channels by - ensuring that the majority of kernel addresses are not mapped - into userspace. - - See Documentation/x86/pti.rst for more details. - config SECURITY_INFINIBAND bool "Infiniband Security Hooks" depends on SECURITY && INFINIBAND diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c index a733aff02006..708de9656bbd 100644 --- a/security/integrity/evm/evm_crypto.c +++ b/security/integrity/evm/evm_crypto.c @@ -75,7 +75,7 @@ static struct shash_desc *init_desc(char type, uint8_t hash_algo) { long rc; const char *algo; - struct crypto_shash **tfm, *tmp_tfm = NULL; + struct crypto_shash **tfm, *tmp_tfm; struct shash_desc *desc; if (type == EVM_XATTR_HMAC) { @@ -120,16 +120,13 @@ unlock: alloc: desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(*tfm), GFP_KERNEL); - if (!desc) { - crypto_free_shash(tmp_tfm); + if (!desc) return ERR_PTR(-ENOMEM); - } desc->tfm = *tfm; rc = crypto_shash_init(desc); if (rc) { - crypto_free_shash(tmp_tfm); kfree(desc); return ERR_PTR(rc); } diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index cdb84dccd24e..bde74fcecee3 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -514,7 +514,8 @@ int ima_appraise_measurement(enum ima_hooks func, goto out; } - status = evm_verifyxattr(dentry, XATTR_NAME_IMA, xattr_value, rc, iint); + status = evm_verifyxattr(dentry, XATTR_NAME_IMA, xattr_value, + rc < 0 ? 0 : rc, iint); switch (status) { case INTEGRITY_PASS: case INTEGRITY_PASS_IMMUTABLE: diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index a7206cc1d7d1..64499056648a 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -205,6 +205,7 @@ out_array: crypto_free_shash(ima_algo_array[i].tfm); } + kfree(ima_algo_array); out: crypto_free_shash(ima_shash_tfm); return rc; diff --git a/security/integrity/ima/ima_efi.c b/security/integrity/ima/ima_efi.c index 71786d01946f..9db66fe310d4 100644 --- a/security/integrity/ima/ima_efi.c +++ b/security/integrity/ima/ima_efi.c @@ -67,6 +67,8 @@ const char * const *arch_get_ima_policy(void) if (IS_ENABLED(CONFIG_IMA_ARCH_POLICY) && arch_ima_get_secureboot()) { if (IS_ENABLED(CONFIG_MODULE_SIG)) set_module_sig_enforced(); + if (IS_ENABLED(CONFIG_KEXEC_SIG)) + set_kexec_sig_enforced(); return sb_arch_rules; } return NULL; diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 73917413365b..a8802b8da946 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -2247,6 +2247,10 @@ bool ima_appraise_signature(enum kernel_read_file_id id) if (id >= READING_MAX_ID) return false; + if (id == READING_KEXEC_IMAGE && !(ima_appraise & IMA_APPRAISE_ENFORCE) + && security_locked_down(LOCKDOWN_KEXEC)) + return false; + func = read_idmap[id] ?: FILE_CHECK; rcu_read_lock(); diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index c877f01a5471..7bf9b1507220 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -323,10 +323,10 @@ static int ima_eventdigest_init_common(const u8 *digest, u32 digestsize, else /* * If digest is NULL, the event being recorded is a violation. - * Make room for the digest by increasing the offset of - * IMA_DIGEST_SIZE. + * Make room for the digest by increasing the offset by the + * hash algorithm digest size. */ - offset += IMA_DIGEST_SIZE; + offset += hash_digest_size[hash_algo]; return ima_write_template_field_data(buffer, offset + digestsize, fmt, field_data); diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 3e541a4c0423..83ae21a01bbf 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -944,6 +944,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x828c, "HP EliteBook 840 G4", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x103c, 0x82b4, "HP ProDesk 600 G3", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x836e, "HP ProBook 455 G5", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x837f, "HP ProBook 470 G5", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x83b2, "HP EliteBook 840 G5", CXT_FIXUP_HP_DOCK), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 007dd8b5e1f2..2f55bc43bfa9 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6901,6 +6901,7 @@ enum { ALC298_FIXUP_LENOVO_SPK_VOLUME, ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER, ALC269_FIXUP_ATIV_BOOK_8, + ALC221_FIXUP_HP_288PRO_MIC_NO_PRESENCE, ALC221_FIXUP_HP_MIC_NO_PRESENCE, ALC256_FIXUP_ASUS_HEADSET_MODE, ALC256_FIXUP_ASUS_MIC, @@ -7837,6 +7838,16 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_NO_SHUTUP }, + [ALC221_FIXUP_HP_288PRO_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */ + { 0x1a, 0x01813030 }, /* use as headphone mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE + }, [ALC221_FIXUP_HP_MIC_NO_PRESENCE] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -8886,6 +8897,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x129c, "Acer SWIFT SF314-55", ALC256_FIXUP_ACER_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x129d, "Acer SWIFT SF313-51", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1300, "Acer SWIFT SF314-56", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC), @@ -8895,6 +8907,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), + SND_PCI_QUIRK(0x1028, 0x053c, "Dell Latitude E5430", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS), SND_PCI_QUIRK(0x1028, 0x05bd, "Dell Latitude E6440", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x05be, "Dell Latitude E6540", ALC292_FIXUP_DELL_E7X), @@ -9010,6 +9023,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2b5e, "HP 288 Pro G2 MT", ALC221_FIXUP_HP_288PRO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x802e, "HP Z240 SFF", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x802f, "HP Z240", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8077, "HP", ALC256_FIXUP_HP_HEADSET_MIC), @@ -9096,6 +9110,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x89c6, "Zbook Fury 17 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8a78, "HP Dev One", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x103c, 0x8aa0, "HP ProBook 440 G9 (MB 8A9E)", ALC236_FIXUP_HP_GPIO_LED), + 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(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -9355,6 +9373,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED), @@ -11217,6 +11236,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x103c, 0x8719, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x873e, "HP", ALC671_FIXUP_HP_HEADSET_MIC2), + SND_PCI_QUIRK(0x103c, 0x877e, "HP 288 Pro G6", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x885f, "HP 288 Pro G8", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x1043, 0x1080, "Asus UX501VW", ALC668_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_ASUS_Nx50), diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c index e32871b3f68a..7434aeeda292 100644 --- a/sound/soc/codecs/arizona.c +++ b/sound/soc/codecs/arizona.c @@ -1760,8 +1760,8 @@ static bool arizona_aif_cfg_changed(struct snd_soc_component *component, if (bclk != (val & ARIZONA_AIF1_BCLK_FREQ_MASK)) return true; - val = snd_soc_component_read(component, base + ARIZONA_AIF_TX_BCLK_RATE); - if (lrclk != (val & ARIZONA_AIF1TX_BCPF_MASK)) + val = snd_soc_component_read(component, base + ARIZONA_AIF_RX_BCLK_RATE); + if (lrclk != (val & ARIZONA_AIF1RX_BCPF_MASK)) return true; val = snd_soc_component_read(component, base + ARIZONA_AIF_FRAME_CTRL_1); diff --git a/sound/soc/codecs/cs47l92.c b/sound/soc/codecs/cs47l92.c index a1b8dcdb9f7b..444026b7d54b 100644 --- a/sound/soc/codecs/cs47l92.c +++ b/sound/soc/codecs/cs47l92.c @@ -119,7 +119,13 @@ static int cs47l92_put_demux(struct snd_kcontrol *kcontrol, end: snd_soc_dapm_mutex_unlock(dapm); - return snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); + ret = snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); + if (ret < 0) { + dev_err(madera->dev, "Failed to update demux power state: %d\n", ret); + return ret; + } + + return change; } static SOC_ENUM_SINGLE_DECL(cs47l92_outdemux_enum, diff --git a/sound/soc/codecs/max98396.c b/sound/soc/codecs/max98396.c index 56eb62bb041f..34db38812807 100644 --- a/sound/soc/codecs/max98396.c +++ b/sound/soc/codecs/max98396.c @@ -342,12 +342,15 @@ static int max98396_dai_set_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) { struct snd_soc_component *component = codec_dai->component; struct max98396_priv *max98396 = snd_soc_component_get_drvdata(component); - unsigned int format = 0; + unsigned int format_mask, format = 0; unsigned int bclk_pol = 0; int ret, status; int reg; bool update = false; + format_mask = MAX98396_PCM_MODE_CFG_FORMAT_MASK | + MAX98396_PCM_MODE_CFG_LRCLKEDGE; + dev_dbg(component->dev, "%s: fmt 0x%08X\n", __func__, fmt); switch (fmt & SND_SOC_DAIFMT_INV_MASK) { @@ -395,7 +398,7 @@ static int max98396_dai_set_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) ret = regmap_read(max98396->regmap, MAX98396_R2041_PCM_MODE_CFG, ®); if (ret < 0) return -EINVAL; - if (format != (reg & MAX98396_PCM_BCLKEDGE_BSEL_MASK)) { + if (format != (reg & format_mask)) { update = true; } else { ret = regmap_read(max98396->regmap, @@ -412,8 +415,7 @@ static int max98396_dai_set_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) regmap_update_bits(max98396->regmap, MAX98396_R2041_PCM_MODE_CFG, - MAX98396_PCM_BCLKEDGE_BSEL_MASK, - format); + format_mask, format); regmap_update_bits(max98396->regmap, MAX98396_R2042_PCM_CLK_SETUP, diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index 69c80d80ed9d..18b3da9211e3 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -1984,7 +1984,12 @@ static int rt5640_set_bias_level(struct snd_soc_component *component, snd_soc_component_write(component, RT5640_PWR_DIG2, 0x0000); snd_soc_component_write(component, RT5640_PWR_VOL, 0x0000); snd_soc_component_write(component, RT5640_PWR_MIXER, 0x0000); - snd_soc_component_write(component, RT5640_PWR_ANLG1, 0x0000); + if (rt5640->jd_src == RT5640_JD_SRC_HDA_HEADER) + snd_soc_component_write(component, RT5640_PWR_ANLG1, + 0x0018); + else + snd_soc_component_write(component, RT5640_PWR_ANLG1, + 0x0000); snd_soc_component_write(component, RT5640_PWR_ANLG2, 0x0000); break; @@ -2393,9 +2398,15 @@ static void rt5640_jack_work(struct work_struct *work) static irqreturn_t rt5640_irq(int irq, void *data) { struct rt5640_priv *rt5640 = data; + int delay = 0; + + if (rt5640->jd_src == RT5640_JD_SRC_HDA_HEADER) { + cancel_delayed_work_sync(&rt5640->jack_work); + delay = 100; + } if (rt5640->jack) - queue_delayed_work(system_long_wq, &rt5640->jack_work, 0); + queue_delayed_work(system_long_wq, &rt5640->jack_work, delay); return IRQ_HANDLED; } @@ -2580,6 +2591,12 @@ static void rt5640_enable_hda_jack_detect( snd_soc_component_update_bits(component, RT5640_DUMMY1, 0x400, 0x0); + snd_soc_component_update_bits(component, RT5640_PWR_ANLG1, + RT5640_PWR_VREF2, RT5640_PWR_VREF2); + usleep_range(10000, 15000); + snd_soc_component_update_bits(component, RT5640_PWR_ANLG1, + RT5640_PWR_FV2, RT5640_PWR_FV2); + rt5640->jack = jack; ret = request_irq(rt5640->irq, rt5640_irq, @@ -2696,16 +2713,13 @@ static int rt5640_probe(struct snd_soc_component *component) if (device_property_read_u32(component->dev, "realtek,jack-detect-source", &val) == 0) { - if (val <= RT5640_JD_SRC_GPIO4) { + if (val <= RT5640_JD_SRC_GPIO4) rt5640->jd_src = val << RT5640_JD_SFT; - } else if (val == RT5640_JD_SRC_HDA_HEADER) { + else if (val == RT5640_JD_SRC_HDA_HEADER) rt5640->jd_src = RT5640_JD_SRC_HDA_HEADER; - snd_soc_component_update_bits(component, RT5640_DUMMY1, - 0x0300, 0x0); - } else { + else dev_warn(component->dev, "Warning: Invalid jack-detect-source value: %d, leaving jack-detect disabled\n", val); - } } if (!device_property_read_bool(component->dev, "realtek,jack-detect-not-inverted")) diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index 2aa48aef6a97..3363d1696ad7 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -1795,6 +1795,9 @@ static int sgtl5000_i2c_remove(struct i2c_client *client) { struct sgtl5000_priv *sgtl5000 = i2c_get_clientdata(client); + regmap_write(sgtl5000->regmap, SGTL5000_CHIP_DIG_POWER, SGTL5000_DIG_POWER_DEFAULT); + regmap_write(sgtl5000->regmap, SGTL5000_CHIP_ANA_POWER, SGTL5000_ANA_POWER_DEFAULT); + clk_disable_unprepare(sgtl5000->mclk); regulator_bulk_disable(sgtl5000->num_supplies, sgtl5000->supplies); regulator_bulk_free(sgtl5000->num_supplies, sgtl5000->supplies); @@ -1802,6 +1805,11 @@ static int sgtl5000_i2c_remove(struct i2c_client *client) return 0; } +static void sgtl5000_i2c_shutdown(struct i2c_client *client) +{ + sgtl5000_i2c_remove(client); +} + static const struct i2c_device_id sgtl5000_id[] = { {"sgtl5000", 0}, {}, @@ -1822,6 +1830,7 @@ static struct i2c_driver sgtl5000_i2c_driver = { }, .probe_new = sgtl5000_i2c_probe, .remove = sgtl5000_i2c_remove, + .shutdown = sgtl5000_i2c_shutdown, .id_table = sgtl5000_id, }; diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h index 56ec5863f250..3a808c762299 100644 --- a/sound/soc/codecs/sgtl5000.h +++ b/sound/soc/codecs/sgtl5000.h @@ -80,6 +80,7 @@ /* * SGTL5000_CHIP_DIG_POWER */ +#define SGTL5000_DIG_POWER_DEFAULT 0x0000 #define SGTL5000_ADC_EN 0x0040 #define SGTL5000_DAC_EN 0x0020 #define SGTL5000_DAP_POWERUP 0x0010 diff --git a/sound/soc/codecs/tas2764.c b/sound/soc/codecs/tas2764.c index d395feffb30b..4cb788f3e5f7 100644 --- a/sound/soc/codecs/tas2764.c +++ b/sound/soc/codecs/tas2764.c @@ -42,10 +42,12 @@ static void tas2764_reset(struct tas2764_priv *tas2764) gpiod_set_value_cansleep(tas2764->reset_gpio, 0); msleep(20); gpiod_set_value_cansleep(tas2764->reset_gpio, 1); + usleep_range(1000, 2000); } snd_soc_component_write(tas2764->component, TAS2764_SW_RST, TAS2764_RST); + usleep_range(1000, 2000); } static int tas2764_set_bias_level(struct snd_soc_component *component, @@ -107,8 +109,10 @@ static int tas2764_codec_resume(struct snd_soc_component *component) struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component); int ret; - if (tas2764->sdz_gpio) + if (tas2764->sdz_gpio) { gpiod_set_value_cansleep(tas2764->sdz_gpio, 1); + usleep_range(1000, 2000); + } ret = snd_soc_component_update_bits(component, TAS2764_PWR_CTRL, TAS2764_PWR_CTRL_MASK, @@ -131,7 +135,8 @@ static const char * const tas2764_ASI1_src[] = { }; static SOC_ENUM_SINGLE_DECL( - tas2764_ASI1_src_enum, TAS2764_TDM_CFG2, 4, tas2764_ASI1_src); + tas2764_ASI1_src_enum, TAS2764_TDM_CFG2, TAS2764_TDM_CFG2_SCFG_SHIFT, + tas2764_ASI1_src); static const struct snd_kcontrol_new tas2764_asi1_mux = SOC_DAPM_ENUM("ASI1 Source", tas2764_ASI1_src_enum); @@ -329,20 +334,22 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) { struct snd_soc_component *component = dai->component; struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component); - u8 tdm_rx_start_slot = 0, asi_cfg_1 = 0; - int iface; + u8 tdm_rx_start_slot = 0, asi_cfg_0 = 0, asi_cfg_1 = 0; int ret; switch (fmt & SND_SOC_DAIFMT_INV_MASK) { + case SND_SOC_DAIFMT_NB_IF: + asi_cfg_0 ^= TAS2764_TDM_CFG0_FRAME_START; + fallthrough; case SND_SOC_DAIFMT_NB_NF: asi_cfg_1 = TAS2764_TDM_CFG1_RX_RISING; break; + case SND_SOC_DAIFMT_IB_IF: + asi_cfg_0 ^= TAS2764_TDM_CFG0_FRAME_START; + fallthrough; case SND_SOC_DAIFMT_IB_NF: asi_cfg_1 = TAS2764_TDM_CFG1_RX_FALLING; break; - default: - dev_err(tas2764->dev, "ASI format Inverse is not found\n"); - return -EINVAL; } ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG1, @@ -353,13 +360,13 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_I2S: + asi_cfg_0 ^= TAS2764_TDM_CFG0_FRAME_START; + fallthrough; case SND_SOC_DAIFMT_DSP_A: - iface = TAS2764_TDM_CFG2_SCFG_I2S; tdm_rx_start_slot = 1; break; case SND_SOC_DAIFMT_DSP_B: case SND_SOC_DAIFMT_LEFT_J: - iface = TAS2764_TDM_CFG2_SCFG_LEFT_J; tdm_rx_start_slot = 0; break; default: @@ -368,14 +375,15 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) return -EINVAL; } - ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG1, - TAS2764_TDM_CFG1_MASK, - (tdm_rx_start_slot << TAS2764_TDM_CFG1_51_SHIFT)); + ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG0, + TAS2764_TDM_CFG0_FRAME_START, + asi_cfg_0); if (ret < 0) return ret; - ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG2, - TAS2764_TDM_CFG2_SCFG_MASK, iface); + ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG1, + TAS2764_TDM_CFG1_MASK, + (tdm_rx_start_slot << TAS2764_TDM_CFG1_51_SHIFT)); if (ret < 0) return ret; @@ -501,8 +509,10 @@ static int tas2764_codec_probe(struct snd_soc_component *component) tas2764->component = component; - if (tas2764->sdz_gpio) + if (tas2764->sdz_gpio) { gpiod_set_value_cansleep(tas2764->sdz_gpio, 1); + usleep_range(1000, 2000); + } tas2764_reset(tas2764); @@ -526,12 +536,12 @@ static int tas2764_codec_probe(struct snd_soc_component *component) } static DECLARE_TLV_DB_SCALE(tas2764_digital_tlv, 1100, 50, 0); -static DECLARE_TLV_DB_SCALE(tas2764_playback_volume, -10000, 50, 0); +static DECLARE_TLV_DB_SCALE(tas2764_playback_volume, -10050, 50, 1); static const struct snd_kcontrol_new tas2764_snd_controls[] = { SOC_SINGLE_TLV("Speaker Volume", TAS2764_DVC, 0, TAS2764_DVC_MAX, 1, tas2764_playback_volume), - SOC_SINGLE_TLV("Amp Gain Volume", TAS2764_CHNL_0, 0, 0x14, 0, + SOC_SINGLE_TLV("Amp Gain Volume", TAS2764_CHNL_0, 1, 0x14, 0, tas2764_digital_tlv), }; @@ -556,7 +566,7 @@ static const struct reg_default tas2764_reg_defaults[] = { { TAS2764_SW_RST, 0x00 }, { TAS2764_PWR_CTRL, 0x1a }, { TAS2764_DVC, 0x00 }, - { TAS2764_CHNL_0, 0x00 }, + { TAS2764_CHNL_0, 0x28 }, { TAS2764_TDM_CFG0, 0x09 }, { TAS2764_TDM_CFG1, 0x02 }, { TAS2764_TDM_CFG2, 0x0a }, diff --git a/sound/soc/codecs/tas2764.h b/sound/soc/codecs/tas2764.h index 67d6fd903c42..f015f22a083b 100644 --- a/sound/soc/codecs/tas2764.h +++ b/sound/soc/codecs/tas2764.h @@ -47,6 +47,7 @@ #define TAS2764_TDM_CFG0_MASK GENMASK(3, 1) #define TAS2764_TDM_CFG0_44_1_48KHZ BIT(3) #define TAS2764_TDM_CFG0_88_2_96KHZ (BIT(3) | BIT(1)) +#define TAS2764_TDM_CFG0_FRAME_START BIT(0) /* TDM Configuration Reg1 */ #define TAS2764_TDM_CFG1 TAS2764_REG(0X0, 0x09) @@ -66,10 +67,7 @@ #define TAS2764_TDM_CFG2_RXS_16BITS 0x0 #define TAS2764_TDM_CFG2_RXS_24BITS BIT(0) #define TAS2764_TDM_CFG2_RXS_32BITS BIT(1) -#define TAS2764_TDM_CFG2_SCFG_MASK GENMASK(5, 4) -#define TAS2764_TDM_CFG2_SCFG_I2S 0x0 -#define TAS2764_TDM_CFG2_SCFG_LEFT_J BIT(4) -#define TAS2764_TDM_CFG2_SCFG_RIGHT_J BIT(5) +#define TAS2764_TDM_CFG2_SCFG_SHIFT 4 /* TDM Configuration Reg3 */ #define TAS2764_TDM_CFG3 TAS2764_REG(0X0, 0x0c) diff --git a/sound/soc/codecs/tlv320adcx140.c b/sound/soc/codecs/tlv320adcx140.c index b55f0b836932..0b729658fde8 100644 --- a/sound/soc/codecs/tlv320adcx140.c +++ b/sound/soc/codecs/tlv320adcx140.c @@ -33,7 +33,6 @@ struct adcx140_priv { bool micbias_vg; unsigned int dai_fmt; - unsigned int tdm_delay; unsigned int slot_width; }; @@ -792,12 +791,13 @@ static int adcx140_set_dai_tdm_slot(struct snd_soc_dai *codec_dai, { struct snd_soc_component *component = codec_dai->component; struct adcx140_priv *adcx140 = snd_soc_component_get_drvdata(component); - unsigned int lsb; - /* TDM based on DSP mode requires slots to be adjacent */ - lsb = __ffs(tx_mask); - if ((lsb + 1) != __fls(tx_mask)) { - dev_err(component->dev, "Invalid mask, slots must be adjacent\n"); + /* + * The chip itself supports arbitrary masks, but the driver currently + * only supports adjacent slots beginning at the first slot. + */ + if (tx_mask != GENMASK(__fls(tx_mask), 0)) { + dev_err(component->dev, "Only lower adjacent slots are supported\n"); return -EINVAL; } @@ -812,7 +812,6 @@ static int adcx140_set_dai_tdm_slot(struct snd_soc_dai *codec_dai, return -EINVAL; } - adcx140->tdm_delay = lsb; adcx140->slot_width = slot_width; return 0; diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c index d9f135200688..3cb7a3eab8c7 100644 --- a/sound/soc/codecs/wcd9335.c +++ b/sound/soc/codecs/wcd9335.c @@ -342,7 +342,7 @@ struct wcd9335_codec { struct regulator_bulk_data supplies[WCD9335_MAX_SUPPLY]; unsigned int rx_port_value[WCD9335_RX_MAX]; - unsigned int tx_port_value; + unsigned int tx_port_value[WCD9335_TX_MAX]; int hph_l_gain; int hph_r_gain; u32 rx_bias_count; @@ -1334,8 +1334,13 @@ static int slim_tx_mixer_get(struct snd_kcontrol *kc, struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kc); struct wcd9335_codec *wcd = dev_get_drvdata(dapm->dev); + struct snd_soc_dapm_widget *widget = snd_soc_dapm_kcontrol_widget(kc); + struct soc_mixer_control *mixer = + (struct soc_mixer_control *)kc->private_value; + int dai_id = widget->shift; + int port_id = mixer->shift; - ucontrol->value.integer.value[0] = wcd->tx_port_value; + ucontrol->value.integer.value[0] = wcd->tx_port_value[port_id] == dai_id; return 0; } @@ -1358,12 +1363,12 @@ static int slim_tx_mixer_put(struct snd_kcontrol *kc, case AIF2_CAP: case AIF3_CAP: /* only add to the list if value not set */ - if (enable && !(wcd->tx_port_value & BIT(port_id))) { - wcd->tx_port_value |= BIT(port_id); + if (enable && wcd->tx_port_value[port_id] != dai_id) { + wcd->tx_port_value[port_id] = dai_id; list_add_tail(&wcd->tx_chs[port_id].list, &wcd->dai[dai_id].slim_ch_list); - } else if (!enable && (wcd->tx_port_value & BIT(port_id))) { - wcd->tx_port_value &= ~BIT(port_id); + } else if (!enable && wcd->tx_port_value[port_id] == dai_id) { + wcd->tx_port_value[port_id] = -1; list_del_init(&wcd->tx_chs[port_id].list); } break; diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c index da2f8998df87..b034df47a5ef 100644 --- a/sound/soc/codecs/wm5102.c +++ b/sound/soc/codecs/wm5102.c @@ -680,12 +680,17 @@ static int wm5102_out_comp_coeff_put(struct snd_kcontrol *kcontrol, { struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol); struct arizona *arizona = dev_get_drvdata(component->dev->parent); + uint16_t dac_comp_coeff = get_unaligned_be16(ucontrol->value.bytes.data); + int ret = 0; mutex_lock(&arizona->dac_comp_lock); - arizona->dac_comp_coeff = get_unaligned_be16(ucontrol->value.bytes.data); + if (arizona->dac_comp_coeff != dac_comp_coeff) { + arizona->dac_comp_coeff = dac_comp_coeff; + ret = 1; + } mutex_unlock(&arizona->dac_comp_lock); - return 0; + return ret; } static int wm5102_out_comp_switch_get(struct snd_kcontrol *kcontrol, @@ -706,12 +711,20 @@ static int wm5102_out_comp_switch_put(struct snd_kcontrol *kcontrol, { struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol); struct arizona *arizona = dev_get_drvdata(component->dev->parent); + struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value; + int ret = 0; + + if (ucontrol->value.integer.value[0] > mc->max) + return -EINVAL; mutex_lock(&arizona->dac_comp_lock); - arizona->dac_comp_enabled = ucontrol->value.integer.value[0]; + if (arizona->dac_comp_enabled != ucontrol->value.integer.value[0]) { + arizona->dac_comp_enabled = ucontrol->value.integer.value[0]; + ret = 1; + } mutex_unlock(&arizona->dac_comp_lock); - return 0; + return ret; } static const char * const wm5102_osr_text[] = { diff --git a/sound/soc/codecs/wm8998.c b/sound/soc/codecs/wm8998.c index 00b59fc9b1fe..ab5481187c71 100644 --- a/sound/soc/codecs/wm8998.c +++ b/sound/soc/codecs/wm8998.c @@ -108,6 +108,7 @@ static int wm8998_inmux_put(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mode_reg, mode_index; unsigned int mux, inmode, src_val, mode_val; + int change, ret; mux = ucontrol->value.enumerated.item[0]; if (mux > 1) @@ -137,14 +138,20 @@ static int wm8998_inmux_put(struct snd_kcontrol *kcontrol, snd_soc_component_update_bits(component, mode_reg, ARIZONA_IN1_MODE_MASK, mode_val); - snd_soc_component_update_bits(component, e->reg, - ARIZONA_IN1L_SRC_MASK | - ARIZONA_IN1L_SRC_SE_MASK, - src_val); + change = snd_soc_component_update_bits(component, e->reg, + ARIZONA_IN1L_SRC_MASK | + ARIZONA_IN1L_SRC_SE_MASK, + src_val); - return snd_soc_dapm_mux_update_power(dapm, kcontrol, - ucontrol->value.enumerated.item[0], - e, NULL); + ret = snd_soc_dapm_mux_update_power(dapm, kcontrol, + ucontrol->value.enumerated.item[0], + e, NULL); + if (ret < 0) { + dev_err(arizona->dev, "Failed to update demux power state: %d\n", ret); + return ret; + } + + return change; } static const char * const wm8998_inmux_texts[] = { diff --git a/sound/soc/generic/audio-graph-card2.c b/sound/soc/generic/audio-graph-card2.c index 77ac4051b827..d34b29a49268 100644 --- a/sound/soc/generic/audio-graph-card2.c +++ b/sound/soc/generic/audio-graph-card2.c @@ -90,12 +90,12 @@ links indicates connection part of CPU side (= A). ports@0 { (X) (A) mcpu: port@0 { mcpu0_ep: endpoint { remote-endpoint = <&mcodec0_ep>; }; }; (y) port@1 { mcpu1_ep: endpoint { remote-endpoint = <&cpu1_ep>; }; }; -(y) port@1 { mcpu2_ep: endpoint { remote-endpoint = <&cpu2_ep>; }; }; +(y) port@2 { mcpu2_ep: endpoint { remote-endpoint = <&cpu2_ep>; }; }; }; ports@1 { (X) port@0 { mcodec0_ep: endpoint { remote-endpoint = <&mcpu0_ep>; }; }; -(y) port@0 { mcodec1_ep: endpoint { remote-endpoint = <&codec1_ep>; }; }; -(y) port@1 { mcodec2_ep: endpoint { remote-endpoint = <&codec2_ep>; }; }; +(y) port@1 { mcodec1_ep: endpoint { remote-endpoint = <&codec1_ep>; }; }; +(y) port@2 { mcodec2_ep: endpoint { remote-endpoint = <&codec2_ep>; }; }; }; }; }; diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c index 5d67a2c87a1d..4a90a0a5d831 100644 --- a/sound/soc/intel/boards/sof_rt5682.c +++ b/sound/soc/intel/boards/sof_rt5682.c @@ -69,11 +69,10 @@ static unsigned long sof_rt5682_quirk = SOF_RT5682_MCLK_EN | static int is_legacy_cpu; -static struct snd_soc_jack sof_hdmi[3]; - struct sof_hdmi_pcm { struct list_head head; struct snd_soc_dai *codec_dai; + struct snd_soc_jack hdmi_jack; int device; }; @@ -434,7 +433,6 @@ static int sof_card_late_probe(struct snd_soc_card *card) char jack_name[NAME_SIZE]; struct sof_hdmi_pcm *pcm; int err; - int i = 0; /* HDMI is not supported by SOF on Baytrail/CherryTrail */ if (is_legacy_cpu || !ctx->idisp_codec) @@ -455,17 +453,15 @@ static int sof_card_late_probe(struct snd_soc_card *card) snprintf(jack_name, sizeof(jack_name), "HDMI/DP, pcm=%d Jack", pcm->device); err = snd_soc_card_jack_new(card, jack_name, - SND_JACK_AVOUT, &sof_hdmi[i]); + SND_JACK_AVOUT, &pcm->hdmi_jack); if (err) return err; err = hdac_hdmi_jack_init(pcm->codec_dai, pcm->device, - &sof_hdmi[i]); + &pcm->hdmi_jack); if (err < 0) return err; - - i++; } if (sof_rt5682_quirk & SOF_MAX98373_SPEAKER_AMP_PRESENT) { diff --git a/sound/soc/intel/skylake/skl-nhlt.c b/sound/soc/intel/skylake/skl-nhlt.c index 2439a574ac2f..deb7b820325e 100644 --- a/sound/soc/intel/skylake/skl-nhlt.c +++ b/sound/soc/intel/skylake/skl-nhlt.c @@ -99,7 +99,6 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks, struct nhlt_fmt_cfg *fmt_cfg; struct wav_fmt_ext *wav_fmt; unsigned long rate; - bool present = false; int rate_index = 0; u16 channels, bps; u8 clk_src; @@ -112,9 +111,12 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks, if (fmt->fmt_count == 0) return; + fmt_cfg = (struct nhlt_fmt_cfg *)fmt->fmt_config; for (i = 0; i < fmt->fmt_count; i++) { - fmt_cfg = &fmt->fmt_config[i]; - wav_fmt = &fmt_cfg->fmt_ext; + struct nhlt_fmt_cfg *saved_fmt_cfg = fmt_cfg; + bool present = false; + + wav_fmt = &saved_fmt_cfg->fmt_ext; channels = wav_fmt->fmt.channels; bps = wav_fmt->fmt.bits_per_sample; @@ -132,12 +134,18 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks, * derive the rate. */ for (j = i; j < fmt->fmt_count; j++) { - fmt_cfg = &fmt->fmt_config[j]; - wav_fmt = &fmt_cfg->fmt_ext; + struct nhlt_fmt_cfg *tmp_fmt_cfg = fmt_cfg; + + wav_fmt = &tmp_fmt_cfg->fmt_ext; if ((fs == wav_fmt->fmt.samples_per_sec) && - (bps == wav_fmt->fmt.bits_per_sample)) + (bps == wav_fmt->fmt.bits_per_sample)) { channels = max_t(u16, channels, wav_fmt->fmt.channels); + saved_fmt_cfg = tmp_fmt_cfg; + } + /* Move to the next nhlt_fmt_cfg */ + tmp_fmt_cfg = (struct nhlt_fmt_cfg *)(tmp_fmt_cfg->config.caps + + tmp_fmt_cfg->config.size); } rate = channels * bps * fs; @@ -153,8 +161,11 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks, /* Fill rate and parent for sclk/sclkfs */ if (!present) { + struct nhlt_fmt_cfg *first_fmt_cfg; + + first_fmt_cfg = (struct nhlt_fmt_cfg *)fmt->fmt_config; i2s_config_ext = (struct skl_i2s_config_blob_ext *) - fmt->fmt_config[0].config.caps; + first_fmt_cfg->config.caps; /* MCLK Divider Source Select */ if (is_legacy_blob(i2s_config_ext->hdr.sig)) { @@ -168,6 +179,9 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks, parent = skl_get_parent_clk(clk_src); + /* Move to the next nhlt_fmt_cfg */ + fmt_cfg = (struct nhlt_fmt_cfg *)(fmt_cfg->config.caps + + fmt_cfg->config.size); /* * Do not copy the config data if there is no parent * clock available for this clock source select @@ -176,9 +190,9 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks, continue; sclk[id].rate_cfg[rate_index].rate = rate; - sclk[id].rate_cfg[rate_index].config = fmt_cfg; + sclk[id].rate_cfg[rate_index].config = saved_fmt_cfg; sclkfs[id].rate_cfg[rate_index].rate = rate; - sclkfs[id].rate_cfg[rate_index].config = fmt_cfg; + sclkfs[id].rate_cfg[rate_index].config = saved_fmt_cfg; sclk[id].parent_name = parent->name; sclkfs[id].parent_name = parent->name; @@ -192,13 +206,13 @@ static void skl_get_mclk(struct skl_dev *skl, struct skl_ssp_clk *mclk, { struct skl_i2s_config_blob_ext *i2s_config_ext; struct skl_i2s_config_blob_legacy *i2s_config; - struct nhlt_specific_cfg *fmt_cfg; + struct nhlt_fmt_cfg *fmt_cfg; struct skl_clk_parent_src *parent; u32 clkdiv, div_ratio; u8 clk_src; - fmt_cfg = &fmt->fmt_config[0].config; - i2s_config_ext = (struct skl_i2s_config_blob_ext *)fmt_cfg->caps; + fmt_cfg = (struct nhlt_fmt_cfg *)fmt->fmt_config; + i2s_config_ext = (struct skl_i2s_config_blob_ext *)fmt_cfg->config.caps; /* MCLK Divider Source Select and divider */ if (is_legacy_blob(i2s_config_ext->hdr.sig)) { @@ -227,7 +241,7 @@ static void skl_get_mclk(struct skl_dev *skl, struct skl_ssp_clk *mclk, return; mclk[id].rate_cfg[0].rate = parent->rate/div_ratio; - mclk[id].rate_cfg[0].config = &fmt->fmt_config[0]; + mclk[id].rate_cfg[0].config = fmt_cfg; mclk[id].parent_name = parent->name; } diff --git a/sound/soc/qcom/qdsp6/q6apm.c b/sound/soc/qcom/qdsp6/q6apm.c index f424d7aa389a..794019286c70 100644 --- a/sound/soc/qcom/qdsp6/q6apm.c +++ b/sound/soc/qcom/qdsp6/q6apm.c @@ -75,6 +75,7 @@ static struct audioreach_graph *q6apm_get_audioreach_graph(struct q6apm *apm, ui id = idr_alloc(&apm->graph_idr, graph, graph_id, graph_id + 1, GFP_KERNEL); if (id < 0) { dev_err(apm->dev, "Unable to allocate graph id (%d)\n", graph_id); + kfree(graph->graph); kfree(graph); mutex_unlock(&apm->lock); return ERR_PTR(id); diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c index 99a128a666fb..4ce5d2579387 100644 --- a/sound/soc/rockchip/rockchip_i2s.c +++ b/sound/soc/rockchip/rockchip_i2s.c @@ -13,7 +13,6 @@ #include <linux/of_gpio.h> #include <linux/of_device.h> #include <linux/clk.h> -#include <linux/pinctrl/consumer.h> #include <linux/pm_runtime.h> #include <linux/regmap.h> #include <linux/spinlock.h> @@ -55,40 +54,8 @@ struct rk_i2s_dev { const struct rk_i2s_pins *pins; unsigned int bclk_ratio; spinlock_t lock; /* tx/rx lock */ - struct pinctrl *pinctrl; - struct pinctrl_state *bclk_on; - struct pinctrl_state *bclk_off; }; -static int i2s_pinctrl_select_bclk_on(struct rk_i2s_dev *i2s) -{ - int ret = 0; - - if (!IS_ERR(i2s->pinctrl) && !IS_ERR_OR_NULL(i2s->bclk_on)) - ret = pinctrl_select_state(i2s->pinctrl, - i2s->bclk_on); - - if (ret) - dev_err(i2s->dev, "bclk enable failed %d\n", ret); - - return ret; -} - -static int i2s_pinctrl_select_bclk_off(struct rk_i2s_dev *i2s) -{ - - int ret = 0; - - if (!IS_ERR(i2s->pinctrl) && !IS_ERR_OR_NULL(i2s->bclk_off)) - ret = pinctrl_select_state(i2s->pinctrl, - i2s->bclk_off); - - if (ret) - dev_err(i2s->dev, "bclk disable failed %d\n", ret); - - return ret; -} - static int i2s_runtime_suspend(struct device *dev) { struct rk_i2s_dev *i2s = dev_get_drvdata(dev); @@ -125,49 +92,38 @@ static inline struct rk_i2s_dev *to_info(struct snd_soc_dai *dai) return snd_soc_dai_get_drvdata(dai); } -static int rockchip_snd_txctrl(struct rk_i2s_dev *i2s, int on) +static void rockchip_snd_txctrl(struct rk_i2s_dev *i2s, int on) { unsigned int val = 0; int retry = 10; - int ret = 0; spin_lock(&i2s->lock); if (on) { - ret = regmap_update_bits(i2s->regmap, I2S_DMACR, - I2S_DMACR_TDE_ENABLE, I2S_DMACR_TDE_ENABLE); - if (ret < 0) - goto end; + regmap_update_bits(i2s->regmap, I2S_DMACR, + I2S_DMACR_TDE_ENABLE, I2S_DMACR_TDE_ENABLE); - ret = regmap_update_bits(i2s->regmap, I2S_XFER, - I2S_XFER_TXS_START | I2S_XFER_RXS_START, - I2S_XFER_TXS_START | I2S_XFER_RXS_START); - if (ret < 0) - goto end; + regmap_update_bits(i2s->regmap, I2S_XFER, + I2S_XFER_TXS_START | I2S_XFER_RXS_START, + I2S_XFER_TXS_START | I2S_XFER_RXS_START); i2s->tx_start = true; } else { i2s->tx_start = false; - ret = regmap_update_bits(i2s->regmap, I2S_DMACR, - I2S_DMACR_TDE_ENABLE, I2S_DMACR_TDE_DISABLE); - if (ret < 0) - goto end; + regmap_update_bits(i2s->regmap, I2S_DMACR, + I2S_DMACR_TDE_ENABLE, I2S_DMACR_TDE_DISABLE); if (!i2s->rx_start) { - ret = regmap_update_bits(i2s->regmap, I2S_XFER, - I2S_XFER_TXS_START | - I2S_XFER_RXS_START, - I2S_XFER_TXS_STOP | - I2S_XFER_RXS_STOP); - if (ret < 0) - goto end; + regmap_update_bits(i2s->regmap, I2S_XFER, + I2S_XFER_TXS_START | + I2S_XFER_RXS_START, + I2S_XFER_TXS_STOP | + I2S_XFER_RXS_STOP); udelay(150); - ret = regmap_update_bits(i2s->regmap, I2S_CLR, - I2S_CLR_TXC | I2S_CLR_RXC, - I2S_CLR_TXC | I2S_CLR_RXC); - if (ret < 0) - goto end; + regmap_update_bits(i2s->regmap, I2S_CLR, + I2S_CLR_TXC | I2S_CLR_RXC, + I2S_CLR_TXC | I2S_CLR_RXC); regmap_read(i2s->regmap, I2S_CLR, &val); @@ -182,57 +138,44 @@ static int rockchip_snd_txctrl(struct rk_i2s_dev *i2s, int on) } } } -end: spin_unlock(&i2s->lock); - if (ret < 0) - dev_err(i2s->dev, "lrclk update failed\n"); - - return ret; } -static int rockchip_snd_rxctrl(struct rk_i2s_dev *i2s, int on) +static void rockchip_snd_rxctrl(struct rk_i2s_dev *i2s, int on) { unsigned int val = 0; int retry = 10; - int ret = 0; spin_lock(&i2s->lock); if (on) { - ret = regmap_update_bits(i2s->regmap, I2S_DMACR, + regmap_update_bits(i2s->regmap, I2S_DMACR, I2S_DMACR_RDE_ENABLE, I2S_DMACR_RDE_ENABLE); - if (ret < 0) - goto end; - ret = regmap_update_bits(i2s->regmap, I2S_XFER, + regmap_update_bits(i2s->regmap, I2S_XFER, I2S_XFER_TXS_START | I2S_XFER_RXS_START, I2S_XFER_TXS_START | I2S_XFER_RXS_START); - if (ret < 0) - goto end; i2s->rx_start = true; } else { i2s->rx_start = false; - ret = regmap_update_bits(i2s->regmap, I2S_DMACR, + regmap_update_bits(i2s->regmap, I2S_DMACR, I2S_DMACR_RDE_ENABLE, I2S_DMACR_RDE_DISABLE); - if (ret < 0) - goto end; if (!i2s->tx_start) { - ret = regmap_update_bits(i2s->regmap, I2S_XFER, + regmap_update_bits(i2s->regmap, I2S_XFER, I2S_XFER_TXS_START | I2S_XFER_RXS_START, I2S_XFER_TXS_STOP | I2S_XFER_RXS_STOP); - if (ret < 0) - goto end; + udelay(150); - ret = regmap_update_bits(i2s->regmap, I2S_CLR, + regmap_update_bits(i2s->regmap, I2S_CLR, I2S_CLR_TXC | I2S_CLR_RXC, I2S_CLR_TXC | I2S_CLR_RXC); - if (ret < 0) - goto end; + regmap_read(i2s->regmap, I2S_CLR, &val); + /* Should wait for clear operation to finish */ while (val) { regmap_read(i2s->regmap, I2S_CLR, &val); @@ -244,12 +187,7 @@ static int rockchip_snd_rxctrl(struct rk_i2s_dev *i2s, int on) } } } -end: spin_unlock(&i2s->lock); - if (ret < 0) - dev_err(i2s->dev, "lrclk update failed\n"); - - return ret; } static int rockchip_i2s_set_fmt(struct snd_soc_dai *cpu_dai, @@ -487,26 +425,17 @@ static int rockchip_i2s_trigger(struct snd_pcm_substream *substream, case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) - ret = rockchip_snd_rxctrl(i2s, 1); + rockchip_snd_rxctrl(i2s, 1); else - ret = rockchip_snd_txctrl(i2s, 1); - /* Do not turn on bclk if lrclk open fails. */ - if (ret < 0) - return ret; - i2s_pinctrl_select_bclk_on(i2s); + rockchip_snd_txctrl(i2s, 1); break; case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) { - if (!i2s->tx_start) - i2s_pinctrl_select_bclk_off(i2s); - ret = rockchip_snd_rxctrl(i2s, 0); - } else { - if (!i2s->rx_start) - i2s_pinctrl_select_bclk_off(i2s); - ret = rockchip_snd_txctrl(i2s, 0); - } + if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) + rockchip_snd_rxctrl(i2s, 0); + else + rockchip_snd_txctrl(i2s, 0); break; default: ret = -EINVAL; @@ -807,33 +736,6 @@ static int rockchip_i2s_probe(struct platform_device *pdev) } i2s->bclk_ratio = 64; - i2s->pinctrl = devm_pinctrl_get(&pdev->dev); - if (IS_ERR(i2s->pinctrl)) - dev_err(&pdev->dev, "failed to find i2s pinctrl\n"); - - i2s->bclk_on = pinctrl_lookup_state(i2s->pinctrl, - "bclk_on"); - if (IS_ERR_OR_NULL(i2s->bclk_on)) - dev_err(&pdev->dev, "failed to find i2s default state\n"); - else - dev_dbg(&pdev->dev, "find i2s bclk state\n"); - - i2s->bclk_off = pinctrl_lookup_state(i2s->pinctrl, - "bclk_off"); - if (IS_ERR_OR_NULL(i2s->bclk_off)) - dev_err(&pdev->dev, "failed to find i2s gpio state\n"); - else - dev_dbg(&pdev->dev, "find i2s bclk_off state\n"); - - i2s_pinctrl_select_bclk_off(i2s); - - i2s->playback_dma_data.addr = res->start + I2S_TXDR; - i2s->playback_dma_data.addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - i2s->playback_dma_data.maxburst = 4; - - i2s->capture_dma_data.addr = res->start + I2S_RXDR; - i2s->capture_dma_data.addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - i2s->capture_dma_data.maxburst = 4; dev_set_drvdata(&pdev->dev, i2s); diff --git a/sound/soc/ti/omap-mcbsp-priv.h b/sound/soc/ti/omap-mcbsp-priv.h index 7865cda4bf0a..da519ea1f303 100644 --- a/sound/soc/ti/omap-mcbsp-priv.h +++ b/sound/soc/ti/omap-mcbsp-priv.h @@ -316,8 +316,6 @@ static inline int omap_mcbsp_read(struct omap_mcbsp *mcbsp, u16 reg, /* Sidetone specific API */ int omap_mcbsp_st_init(struct platform_device *pdev); -void omap_mcbsp_st_cleanup(struct platform_device *pdev); - int omap_mcbsp_st_start(struct omap_mcbsp *mcbsp); int omap_mcbsp_st_stop(struct omap_mcbsp *mcbsp); diff --git a/sound/soc/ti/omap-mcbsp-st.c b/sound/soc/ti/omap-mcbsp-st.c index 0bc7d26c660a..7e8179cae92e 100644 --- a/sound/soc/ti/omap-mcbsp-st.c +++ b/sound/soc/ti/omap-mcbsp-st.c @@ -347,7 +347,7 @@ int omap_mcbsp_st_init(struct platform_device *pdev) if (!st_data) return -ENOMEM; - st_data->mcbsp_iclk = clk_get(mcbsp->dev, "ick"); + st_data->mcbsp_iclk = devm_clk_get(mcbsp->dev, "ick"); if (IS_ERR(st_data->mcbsp_iclk)) { dev_warn(mcbsp->dev, "Failed to get ick, sidetone might be broken\n"); @@ -359,7 +359,7 @@ int omap_mcbsp_st_init(struct platform_device *pdev) if (!st_data->io_base_st) return -ENOMEM; - ret = sysfs_create_group(&mcbsp->dev->kobj, &sidetone_attr_group); + ret = devm_device_add_group(mcbsp->dev, &sidetone_attr_group); if (ret) return ret; @@ -368,16 +368,6 @@ int omap_mcbsp_st_init(struct platform_device *pdev) return 0; } -void omap_mcbsp_st_cleanup(struct platform_device *pdev) -{ - struct omap_mcbsp *mcbsp = platform_get_drvdata(pdev); - - if (mcbsp->st_data) { - sysfs_remove_group(&mcbsp->dev->kobj, &sidetone_attr_group); - clk_put(mcbsp->st_data->mcbsp_iclk); - } -} - static int omap_mcbsp_st_info_volsw(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { diff --git a/sound/soc/ti/omap-mcbsp.c b/sound/soc/ti/omap-mcbsp.c index 4479d74f0a45..9933b33c80ca 100644 --- a/sound/soc/ti/omap-mcbsp.c +++ b/sound/soc/ti/omap-mcbsp.c @@ -702,8 +702,7 @@ static int omap_mcbsp_init(struct platform_device *pdev) mcbsp->max_tx_thres = max_thres(mcbsp) - 0x10; mcbsp->max_rx_thres = max_thres(mcbsp) - 0x10; - ret = sysfs_create_group(&mcbsp->dev->kobj, - &additional_attr_group); + ret = devm_device_add_group(mcbsp->dev, &additional_attr_group); if (ret) { dev_err(mcbsp->dev, "Unable to create additional controls\n"); @@ -711,16 +710,7 @@ static int omap_mcbsp_init(struct platform_device *pdev) } } - ret = omap_mcbsp_st_init(pdev); - if (ret) - goto err_st; - - return 0; - -err_st: - if (mcbsp->pdata->buffer_size) - sysfs_remove_group(&mcbsp->dev->kobj, &additional_attr_group); - return ret; + return omap_mcbsp_st_init(pdev); } /* @@ -1431,11 +1421,6 @@ static int asoc_mcbsp_remove(struct platform_device *pdev) if (cpu_latency_qos_request_active(&mcbsp->pm_qos_req)) cpu_latency_qos_remove_request(&mcbsp->pm_qos_req); - if (mcbsp->pdata->buffer_size) - sysfs_remove_group(&mcbsp->dev->kobj, &additional_attr_group); - - omap_mcbsp_st_cleanup(pdev); - return 0; } diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 03acc823838a..00f5227c8459 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -203,8 +203,8 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ @@ -296,6 +296,12 @@ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ #define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ #define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ +#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */ +#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */ +#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ +#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ @@ -316,6 +322,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ @@ -447,5 +454,6 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 36369e76cc63..33d2cd04d254 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -50,6 +50,25 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif +#ifdef CONFIG_RETPOLINE +# define DISABLE_RETPOLINE 0 +#else +# define DISABLE_RETPOLINE ((1 << (X86_FEATURE_RETPOLINE & 31)) | \ + (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31))) +#endif + +#ifdef CONFIG_RETHUNK +# define DISABLE_RETHUNK 0 +#else +# define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) +#endif + +#ifdef CONFIG_CPU_UNRET_ENTRY +# define DISABLE_UNRET 0 +#else +# define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -82,7 +101,7 @@ #define DISABLED_MASK8 (DISABLE_TDX_GUEST) #define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 -#define DISABLED_MASK11 0 +#define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET) #define DISABLED_MASK12 0 #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index d27e0581b777..cc615be27a54 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -51,6 +51,8 @@ #define SPEC_CTRL_STIBP BIT(SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */ #define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ +#define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ +#define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -93,6 +95,7 @@ #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a #define ARCH_CAP_RDCL_NO BIT(0) /* Not susceptible to Meltdown */ #define ARCH_CAP_IBRS_ALL BIT(1) /* Enhanced IBRS support */ +#define ARCH_CAP_RSBA BIT(2) /* RET may use alternative branch predictors */ #define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH BIT(3) /* Skip L1D flush on vmentry */ #define ARCH_CAP_SSB_NO BIT(4) /* * Not susceptible to Speculative Store Bypass @@ -140,6 +143,13 @@ * bit available to control VERW * behavior. */ +#define ARCH_CAP_RRSBA BIT(19) /* + * Indicates RET may use predictors + * other than the RSB. With eIBRS + * enabled predictions in kernel mode + * are restricted to targets in + * kernel. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -567,6 +577,9 @@ /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 +#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3 +#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1) + /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 15b940ec1eac..10bc88cc3bf6 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -32,11 +32,16 @@ struct unwind_hint { * * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 #ifdef CONFIG_OBJTOOL @@ -124,7 +129,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -177,7 +182,7 @@ struct unwind_hint { #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f4009dbdf62d..ef78e0e1a754 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5222,22 +5222,25 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset) + * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length - * of *src*'s data, -EINVAL if *src* is an invalid dynptr. + * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if + * *flags* is not 0. * - * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len) + * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* - * is a read-only dynptr. + * is a read-only dynptr or if *flags* is not 0. * * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) * Description diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 5088bd9f1922..860f867c50c0 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -2083,7 +2083,8 @@ struct kvm_stats_header { #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) -#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES +#define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN #define KVM_STATS_BASE_SHIFT 8 #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 8b990a52aada..c260006106be 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -787,3 +787,8 @@ bool arch_is_retpoline(struct symbol *sym) { return !strncmp(sym->name, "__x86_indirect_", 15); } + +bool arch_is_rethunk(struct symbol *sym) +{ + return !strcmp(sym->name, "__x86_return_thunk"); +} diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index f4c3a5091737..24fbe803a0d3 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -68,6 +68,8 @@ const struct option check_options[] = { OPT_BOOLEAN('n', "noinstr", &opts.noinstr, "validate noinstr rules"), OPT_BOOLEAN('o', "orc", &opts.orc, "generate ORC metadata"), OPT_BOOLEAN('r', "retpoline", &opts.retpoline, "validate and annotate retpoline usage"), + OPT_BOOLEAN(0, "rethunk", &opts.rethunk, "validate and annotate rethunk usage"), + OPT_BOOLEAN(0, "unret", &opts.unret, "validate entry unret placement"), OPT_BOOLEAN('l', "sls", &opts.sls, "validate straight-line-speculation mitigations"), OPT_BOOLEAN('s', "stackval", &opts.stackval, "validate frame pointer rules"), OPT_BOOLEAN('t', "static-call", &opts.static_call, "annotate static calls"), @@ -123,6 +125,7 @@ static bool opts_valid(void) opts.noinstr || opts.orc || opts.retpoline || + opts.rethunk || opts.sls || opts.stackval || opts.static_call || @@ -135,6 +138,11 @@ static bool opts_valid(void) return true; } + if (opts.unret && !opts.rethunk) { + ERROR("--unret requires --rethunk"); + return false; + } + if (opts.dump_orc) return true; @@ -163,6 +171,11 @@ static bool link_opts_valid(struct objtool_file *file) return false; } + if (opts.unret) { + ERROR("--unret requires --link"); + return false; + } + return true; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 57153e00349c..b341f8a8c7c5 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -376,7 +376,8 @@ static int decode_instructions(struct objtool_file *file) sec->text = true; if (!strcmp(sec->name, ".noinstr.text") || - !strcmp(sec->name, ".entry.text")) + !strcmp(sec->name, ".entry.text") || + !strncmp(sec->name, ".text.__x86.", 12)) sec->noinstr = true; for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) { @@ -749,6 +750,52 @@ static int create_retpoline_sites_sections(struct objtool_file *file) return 0; } +static int create_return_sites_sections(struct objtool_file *file) +{ + struct instruction *insn; + struct section *sec; + int idx; + + sec = find_section_by_name(file->elf, ".return_sites"); + if (sec) { + WARN("file already has .return_sites, skipping"); + return 0; + } + + idx = 0; + list_for_each_entry(insn, &file->return_thunk_list, call_node) + idx++; + + if (!idx) + return 0; + + sec = elf_create_section(file->elf, ".return_sites", 0, + sizeof(int), idx); + if (!sec) { + WARN("elf_create_section: .return_sites"); + return -1; + } + + idx = 0; + list_for_each_entry(insn, &file->return_thunk_list, call_node) { + + int *site = (int *)sec->data->d_buf + idx; + *site = 0; + + if (elf_add_reloc_to_insn(file->elf, sec, + idx * sizeof(int), + R_X86_64_PC32, + insn->sec, insn->offset)) { + WARN("elf_add_reloc_to_insn: .return_sites"); + return -1; + } + + idx++; + } + + return 0; +} + static int create_ibt_endbr_seal_sections(struct objtool_file *file) { struct instruction *insn; @@ -1083,6 +1130,11 @@ __weak bool arch_is_retpoline(struct symbol *sym) return false; } +__weak bool arch_is_rethunk(struct symbol *sym) +{ + return false; +} + #define NEGATIVE_RELOC ((void *)-1L) static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *insn) @@ -1250,6 +1302,19 @@ static void add_retpoline_call(struct objtool_file *file, struct instruction *in annotate_call_site(file, insn, false); } +static void add_return_call(struct objtool_file *file, struct instruction *insn, bool add) +{ + /* + * Return thunk tail calls are really just returns in disguise, + * so convert them accordingly. + */ + insn->type = INSN_RETURN; + insn->retpoline_safe = true; + + if (add) + list_add_tail(&insn->call_node, &file->return_thunk_list); +} + static bool same_function(struct instruction *insn1, struct instruction *insn2) { return insn1->func->pfunc == insn2->func->pfunc; @@ -1302,6 +1367,9 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->retpoline_thunk) { add_retpoline_call(file, insn); continue; + } else if (reloc->sym->return_thunk) { + add_return_call(file, insn, true); + continue; } else if (insn->func) { /* * External sibling call or internal sibling call with @@ -1320,6 +1388,21 @@ static int add_jump_destinations(struct objtool_file *file) jump_dest = find_insn(file, dest_sec, dest_off); if (!jump_dest) { + struct symbol *sym = find_symbol_by_offset(dest_sec, dest_off); + + /* + * This is a special case for zen_untrain_ret(). + * It jumps to __x86_return_thunk(), but objtool + * can't find the thunk's starting RET + * instruction, because the RET is also in the + * middle of another instruction. Objtool only + * knows about the outer instruction. + */ + if (sym && sym->return_thunk) { + add_return_call(file, insn, false); + continue; + } + WARN_FUNC("can't find jump dest instruction at %s+0x%lx", insn->sec, insn->offset, dest_sec->name, dest_off); @@ -1949,16 +2032,35 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true; - if (opts.ibt && hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) { + if (hint->type == UNWIND_HINT_TYPE_SAVE) { + insn->hint = false; + insn->save = true; + continue; + } + + if (hint->type == UNWIND_HINT_TYPE_RESTORE) { + insn->restore = true; + continue; + } + + if (hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) { struct symbol *sym = find_symbol_by_offset(insn->sec, insn->offset); - if (sym && sym->bind == STB_GLOBAL && - insn->type != INSN_ENDBR && !insn->noendbr) { - WARN_FUNC("UNWIND_HINT_IRET_REGS without ENDBR", - insn->sec, insn->offset); + if (sym && sym->bind == STB_GLOBAL) { + if (opts.ibt && insn->type != INSN_ENDBR && !insn->noendbr) { + WARN_FUNC("UNWIND_HINT_IRET_REGS without ENDBR", + insn->sec, insn->offset); + } + + insn->entry = 1; } } + if (hint->type == UNWIND_HINT_TYPE_ENTRY) { + hint->type = UNWIND_HINT_TYPE_CALL; + insn->entry = 1; + } + if (hint->type == UNWIND_HINT_TYPE_FUNC) { insn->cfi = &func_cfi; continue; @@ -2032,8 +2134,10 @@ static int read_retpoline_hints(struct objtool_file *file) } if (insn->type != INSN_JUMP_DYNAMIC && - insn->type != INSN_CALL_DYNAMIC) { - WARN_FUNC("retpoline_safe hint not an indirect jump/call", + insn->type != INSN_CALL_DYNAMIC && + insn->type != INSN_RETURN && + insn->type != INSN_NOP) { + WARN_FUNC("retpoline_safe hint not an indirect jump/call/ret/nop", insn->sec, insn->offset); return -1; } @@ -2184,6 +2288,9 @@ static int classify_symbols(struct objtool_file *file) if (arch_is_retpoline(func)) func->retpoline_thunk = true; + if (arch_is_rethunk(func)) + func->return_thunk = true; + if (!strcmp(func->name, "__fentry__")) func->fentry = true; @@ -3218,8 +3325,8 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 1; } - visited = 1 << state.uaccess; - if (insn->visited) { + visited = VISITED_BRANCH << state.uaccess; + if (insn->visited & VISITED_BRANCH_MASK) { if (!insn->hint && !insn_cfi_match(insn, &state.cfi)) return 1; @@ -3233,6 +3340,35 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, state.instr += insn->instr; if (insn->hint) { + if (insn->restore) { + struct instruction *save_insn, *i; + + i = insn; + save_insn = NULL; + + sym_for_each_insn_continue_reverse(file, func, i) { + if (i->save) { + save_insn = i; + break; + } + } + + if (!save_insn) { + WARN_FUNC("no corresponding CFI save for CFI restore", + sec, insn->offset); + return 1; + } + + if (!save_insn->visited) { + WARN_FUNC("objtool isn't smart enough to handle this CFI save/restore combo", + sec, insn->offset); + return 1; + } + + insn->cfi = save_insn->cfi; + nr_cfi_reused++; + } + state.cfi = *insn->cfi; } else { /* XXX track if we actually changed state.cfi */ @@ -3433,6 +3569,145 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) return warnings; } +/* + * Validate rethunk entry constraint: must untrain RET before the first RET. + * + * Follow every branch (intra-function) and ensure ANNOTATE_UNRET_END comes + * before an actual RET instruction. + */ +static int validate_entry(struct objtool_file *file, struct instruction *insn) +{ + struct instruction *next, *dest; + int ret, warnings = 0; + + for (;;) { + next = next_insn_to_validate(file, insn); + + if (insn->visited & VISITED_ENTRY) + return 0; + + insn->visited |= VISITED_ENTRY; + + if (!insn->ignore_alts && !list_empty(&insn->alts)) { + struct alternative *alt; + bool skip_orig = false; + + list_for_each_entry(alt, &insn->alts, list) { + if (alt->skip_orig) + skip_orig = true; + + ret = validate_entry(file, alt->insn); + if (ret) { + if (opts.backtrace) + BT_FUNC("(alt)", insn); + return ret; + } + } + + if (skip_orig) + return 0; + } + + switch (insn->type) { + + case INSN_CALL_DYNAMIC: + case INSN_JUMP_DYNAMIC: + case INSN_JUMP_DYNAMIC_CONDITIONAL: + WARN_FUNC("early indirect call", insn->sec, insn->offset); + return 1; + + case INSN_JUMP_UNCONDITIONAL: + case INSN_JUMP_CONDITIONAL: + if (!is_sibling_call(insn)) { + if (!insn->jump_dest) { + WARN_FUNC("unresolved jump target after linking?!?", + insn->sec, insn->offset); + return -1; + } + ret = validate_entry(file, insn->jump_dest); + if (ret) { + if (opts.backtrace) { + BT_FUNC("(branch%s)", insn, + insn->type == INSN_JUMP_CONDITIONAL ? "-cond" : ""); + } + return ret; + } + + if (insn->type == INSN_JUMP_UNCONDITIONAL) + return 0; + + break; + } + + /* fallthrough */ + case INSN_CALL: + dest = find_insn(file, insn->call_dest->sec, + insn->call_dest->offset); + if (!dest) { + WARN("Unresolved function after linking!?: %s", + insn->call_dest->name); + return -1; + } + + ret = validate_entry(file, dest); + if (ret) { + if (opts.backtrace) + BT_FUNC("(call)", insn); + return ret; + } + /* + * If a call returns without error, it must have seen UNTRAIN_RET. + * Therefore any non-error return is a success. + */ + return 0; + + case INSN_RETURN: + WARN_FUNC("RET before UNTRAIN", insn->sec, insn->offset); + return 1; + + case INSN_NOP: + if (insn->retpoline_safe) + return 0; + break; + + default: + break; + } + + if (!next) { + WARN_FUNC("teh end!", insn->sec, insn->offset); + return -1; + } + insn = next; + } + + return warnings; +} + +/* + * Validate that all branches starting at 'insn->entry' encounter UNRET_END + * before RET. + */ +static int validate_unret(struct objtool_file *file) +{ + struct instruction *insn; + int ret, warnings = 0; + + for_each_insn(file, insn) { + if (!insn->entry) + continue; + + ret = validate_entry(file, insn); + if (ret < 0) { + WARN_FUNC("Failed UNRET validation", insn->sec, insn->offset); + return ret; + } + warnings += ret; + } + + return warnings; +} + static int validate_retpoline(struct objtool_file *file) { struct instruction *insn; @@ -3440,7 +3715,8 @@ static int validate_retpoline(struct objtool_file *file) for_each_insn(file, insn) { if (insn->type != INSN_JUMP_DYNAMIC && - insn->type != INSN_CALL_DYNAMIC) + insn->type != INSN_CALL_DYNAMIC && + insn->type != INSN_RETURN) continue; if (insn->retpoline_safe) @@ -3455,9 +3731,17 @@ static int validate_retpoline(struct objtool_file *file) if (!strcmp(insn->sec->name, ".init.text") && !opts.module) continue; - WARN_FUNC("indirect %s found in RETPOLINE build", - insn->sec, insn->offset, - insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); + if (insn->type == INSN_RETURN) { + if (opts.rethunk) { + WARN_FUNC("'naked' return found in RETHUNK build", + insn->sec, insn->offset); + } else + continue; + } else { + WARN_FUNC("indirect %s found in RETPOLINE build", + insn->sec, insn->offset, + insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); + } warnings++; } @@ -3945,6 +4229,17 @@ int check(struct objtool_file *file) warnings += ret; } + if (opts.unret) { + /* + * Must be after validate_branch() and friends, it plays + * further games with insn->visited. + */ + ret = validate_unret(file); + if (ret < 0) + return ret; + warnings += ret; + } + if (opts.ibt) { ret = validate_ibt(file); if (ret < 0) @@ -3973,6 +4268,13 @@ int check(struct objtool_file *file) warnings += ret; } + if (opts.rethunk) { + ret = create_return_sites_sections(file); + if (ret < 0) + goto out; + warnings += ret; + } + if (opts.mcount) { ret = create_mcount_loc_sections(file); if (ret < 0) diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h index 9b19cc304195..beb2f3aa94ff 100644 --- a/tools/objtool/include/objtool/arch.h +++ b/tools/objtool/include/objtool/arch.h @@ -89,6 +89,7 @@ const char *arch_ret_insn(int len); int arch_decode_hint_reg(u8 sp_reg, int *base); bool arch_is_retpoline(struct symbol *sym); +bool arch_is_rethunk(struct symbol *sym); int arch_rewrite_retpolines(struct objtool_file *file); diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h index 280ea18b7f2b..42a52f1a0add 100644 --- a/tools/objtool/include/objtool/builtin.h +++ b/tools/objtool/include/objtool/builtin.h @@ -19,6 +19,8 @@ struct opts { bool noinstr; bool orc; bool retpoline; + bool rethunk; + bool unret; bool sls; bool stackval; bool static_call; diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index f10d7374f388..036129cebeee 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -46,16 +46,19 @@ struct instruction { enum insn_type type; unsigned long immediate; - u8 dead_end : 1, - ignore : 1, - ignore_alts : 1, - hint : 1, - retpoline_safe : 1, - noendbr : 1; - /* 2 bit hole */ + u16 dead_end : 1, + ignore : 1, + ignore_alts : 1, + hint : 1, + save : 1, + restore : 1, + retpoline_safe : 1, + noendbr : 1, + entry : 1; + /* 7 bit hole */ + s8 instr; u8 visited; - /* u8 hole */ struct alt_group *alt_group; struct symbol *call_dest; @@ -69,6 +72,11 @@ struct instruction { struct cfi_state *cfi; }; +#define VISITED_BRANCH 0x01 +#define VISITED_BRANCH_UACCESS 0x02 +#define VISITED_BRANCH_MASK 0x03 +#define VISITED_ENTRY 0x04 + static inline bool is_static_jump(struct instruction *insn) { return insn->type == INSN_JUMP_CONDITIONAL || diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index adebfbc2b518..16f4067b82ae 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -57,6 +57,7 @@ struct symbol { u8 uaccess_safe : 1; u8 static_call_tramp : 1; u8 retpoline_thunk : 1; + u8 return_thunk : 1; u8 fentry : 1; u8 profiling_func : 1; struct list_head pv_target; diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h index a6e72d916807..7f2d1b095333 100644 --- a/tools/objtool/include/objtool/objtool.h +++ b/tools/objtool/include/objtool/objtool.h @@ -24,6 +24,7 @@ struct objtool_file { struct list_head insn_list; DECLARE_HASHTABLE(insn_hash, 20); struct list_head retpoline_call_list; + struct list_head return_thunk_list; struct list_head static_call_list; struct list_head mcount_loc_list; struct list_head endbr_list; diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index 512669ce064c..a7ecc32e3512 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -102,6 +102,7 @@ struct objtool_file *objtool_open_read(const char *_objname) INIT_LIST_HEAD(&file.insn_list); hash_init(file.insn_hash); INIT_LIST_HEAD(&file.retpoline_call_list); + INIT_LIST_HEAD(&file.return_thunk_list); INIT_LIST_HEAD(&file.static_call_list); INIT_LIST_HEAD(&file.mcount_loc_list); INIT_LIST_HEAD(&file.endbr_list); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 897fc504918b..f075cf37a65e 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -4280,6 +4280,7 @@ static int trace__replay(struct trace *trace) goto out; evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_enter"); + trace->syscalls.events.sys_enter = evsel; /* older kernels have syscalls tp versus raw_syscalls */ if (evsel == NULL) evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_enter"); @@ -4292,6 +4293,7 @@ static int trace__replay(struct trace *trace) } evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_exit"); + trace->syscalls.events.sys_exit = evsel; if (evsel == NULL) evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_exit"); if (evsel && diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 4ad0dfbc8b21..7c7d20fc503a 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -20,8 +20,6 @@ #include "tsc.h" #include "mmap.h" #include "tests.h" -#include "pmu.h" -#include "pmu-hybrid.h" /* * Except x86_64/i386 and Arm64, other archs don't support TSC in perf. Just @@ -106,28 +104,21 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su evlist__config(evlist, &opts, NULL); - evsel = evlist__first(evlist); - - evsel->core.attr.comm = 1; - evsel->core.attr.disabled = 1; - evsel->core.attr.enable_on_exec = 0; - - /* - * For hybrid "cycles:u", it creates two events. - * Init the second evsel here. - */ - if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) { - evsel = evsel__next(evsel); + /* For hybrid "cycles:u", it creates two events */ + evlist__for_each_entry(evlist, evsel) { evsel->core.attr.comm = 1; evsel->core.attr.disabled = 1; evsel->core.attr.enable_on_exec = 0; } - if (evlist__open(evlist) == -ENOENT) { - err = TEST_SKIP; + ret = evlist__open(evlist); + if (ret < 0) { + if (ret == -ENOENT) + err = TEST_SKIP; + else + pr_debug("evlist__open() failed\n"); goto out_err; } - CHECK__(evlist__open(evlist)); CHECK__(evlist__mmap(evlist, UINT_MAX)); @@ -167,10 +158,12 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su goto next_event; if (strcmp(event->comm.comm, comm1) == 0) { + CHECK_NOT_NULL__(evsel = evlist__event2evsel(evlist, event)); CHECK__(evsel__parse_sample(evsel, event, &sample)); comm1_time = sample.time; } if (strcmp(event->comm.comm, comm2) == 0) { + CHECK_NOT_NULL__(evsel = evlist__event2evsel(evlist, event)); CHECK__(evsel__parse_sample(evsel, event, &sample)); comm2_time = sample.time; } diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index d811cff73597..0a26c243e6e9 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -140,12 +140,12 @@ int use_after_invalid(void *ctx) bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(read_data), 0, &ptr); - bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); bpf_ringbuf_submit_dynptr(&ptr, 0); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); return 0; } @@ -338,7 +338,7 @@ int invalid_helper2(void *ctx) get_map_val_dynptr(&ptr); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 8, 0); + bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 8, 0, 0); return 0; } @@ -377,7 +377,7 @@ int invalid_write2(void *ctx) memcpy((void *)&ptr + 8, &x, sizeof(x)); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); bpf_ringbuf_submit_dynptr(&ptr, 0); @@ -473,7 +473,7 @@ int invalid_read2(void *ctx) get_map_val_dynptr(&ptr); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 1, 0); + bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 1, 0, 0); return 0; } diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index d67be48df4b2..a3a6103c8569 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -43,10 +43,10 @@ int test_read_write(void *ctx) bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(write_data), 0, &ptr); /* Write data into the dynptr */ - err = err ?: bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data)); + err = bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0); /* Read the data that was written into the dynptr */ - err = err ?: bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + err = err ?: bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); /* Ensure the data we read matches the data we wrote */ for (i = 0; i < sizeof(read_data); i++) { diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile index 71b306602368..616ed4019655 100644 --- a/tools/testing/selftests/gpio/Makefile +++ b/tools/testing/selftests/gpio/Makefile @@ -3,6 +3,6 @@ TEST_PROGS := gpio-mockup.sh gpio-sim.sh TEST_FILES := gpio-mockup-sysfs.sh TEST_GEN_PROGS_EXTENDED := gpio-mockup-cdev gpio-chip-info gpio-line-name -CFLAGS += -O2 -g -Wall -I../../../../usr/include/ +CFLAGS += -O2 -g -Wall -I../../../../usr/include/ $(KHDR_INCLUDES) include ../lib.mk diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index 4158da0da2bb..2237d1aac801 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -82,8 +82,9 @@ static int next_cpu(int cpu) return cpu; } -static void *migration_worker(void *ign) +static void *migration_worker(void *__rseq_tid) { + pid_t rseq_tid = (pid_t)(unsigned long)__rseq_tid; cpu_set_t allowed_mask; int r, i, cpu; @@ -106,7 +107,7 @@ static void *migration_worker(void *ign) * stable, i.e. while changing affinity is in-progress. */ smp_wmb(); - r = sched_setaffinity(0, sizeof(allowed_mask), &allowed_mask); + r = sched_setaffinity(rseq_tid, sizeof(allowed_mask), &allowed_mask); TEST_ASSERT(!r, "sched_setaffinity failed, errno = %d (%s)", errno, strerror(errno)); smp_wmb(); @@ -231,7 +232,8 @@ int main(int argc, char *argv[]) vm = vm_create_default(VCPU_ID, 0, guest_code); ucall_init(vm, NULL); - pthread_create(&migration_thread, NULL, migration_worker, 0); + pthread_create(&migration_thread, NULL, migration_worker, + (void *)(unsigned long)gettid()); for (i = 0; !done; i++) { vcpu_run(vm, VCPU_ID); diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index a29f79618934..ffc35a22e914 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -36,4 +36,5 @@ test_unix_oob gro ioam6_parser toeplitz +tun cmsg_sender diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index ddad703ace34..db05b3764b77 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -11,7 +11,7 @@ TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh ipv6_flowlabel.sh TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh traceroute.sh -TEST_PROGS += fin_ack_lat.sh fib_nexthop_multiprefix.sh fib_nexthops.sh +TEST_PROGS += fin_ack_lat.sh fib_nexthop_multiprefix.sh fib_nexthops.sh fib_nexthop_nongw.sh TEST_PROGS += altnames.sh icmp.sh icmp_redirect.sh ip6_gre_headroom.sh TEST_PROGS += route_localnet.sh TEST_PROGS += reuseaddr_ports_exhausted.sh diff --git a/tools/testing/selftests/net/fib_nexthop_nongw.sh b/tools/testing/selftests/net/fib_nexthop_nongw.sh new file mode 100755 index 000000000000..b7b928b38ce4 --- /dev/null +++ b/tools/testing/selftests/net/fib_nexthop_nongw.sh @@ -0,0 +1,119 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# ns: h1 | ns: h2 +# 192.168.0.1/24 | +# eth0 | +# | 192.168.1.1/32 +# veth0 <---|---> veth1 +# Validate source address selection for route without gateway + +PAUSE_ON_FAIL=no +VERBOSE=0 +ret=0 + +################################################################################ +# helpers + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf "TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf "TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + [ "$VERBOSE" = "1" ] && echo +} + +run_cmd() +{ + local cmd="$*" + local out + local rc + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: $cmd" + fi + + out=$(eval $cmd 2>&1) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo "$out" + fi + + [ "$VERBOSE" = "1" ] && echo + + return $rc +} + +################################################################################ +# config +setup() +{ + ip netns add h1 + ip -n h1 link set lo up + ip netns add h2 + ip -n h2 link set lo up + + # Add a fake eth0 to support an ip address + ip -n h1 link add name eth0 type dummy + ip -n h1 link set eth0 up + ip -n h1 address add 192.168.0.1/24 dev eth0 + + # Configure veths (same @mac, arp off) + ip -n h1 link add name veth0 type veth peer name veth1 netns h2 + ip -n h1 link set veth0 up + + ip -n h2 link set veth1 up + + # Configure @IP in the peer netns + ip -n h2 address add 192.168.1.1/32 dev veth1 + ip -n h2 route add default dev veth1 + + # Add a nexthop without @gw and use it in a route + ip -n h1 nexthop add id 1 dev veth0 + ip -n h1 route add 192.168.1.1 nhid 1 +} + +cleanup() +{ + ip netns del h1 2>/dev/null + ip netns del h2 2>/dev/null +} + +trap cleanup EXIT + +################################################################################ +# main + +while getopts :pv o +do + case $o in + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=1;; + esac +done + +cleanup +setup + +run_cmd ip -netns h1 route get 192.168.1.1 +log_test $? 0 "nexthop: get route with nexthop without gw" +run_cmd ip netns exec h1 ping -c1 192.168.1.1 +log_test $? 0 "nexthop: ping through nexthop without gw" + +exit $ret diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 8f481218a492..57b84e0c879e 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -37,6 +37,7 @@ TEST_PROGS = bridge_igmp.sh \ ipip_hier_gre_key.sh \ ipip_hier_gre_keys.sh \ ipip_hier_gre.sh \ + local_termination.sh \ loopback.sh \ mirror_gre_bound.sh \ mirror_gre_bridge_1d.sh \ @@ -52,6 +53,7 @@ TEST_PROGS = bridge_igmp.sh \ mirror_gre_vlan_bridge_1q.sh \ mirror_gre_vlan.sh \ mirror_vlan.sh \ + no_forwarding.sh \ pedit_dsfield.sh \ pedit_ip.sh \ pedit_l4port.sh \ diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index f905d5358e68..48a99e1453e1 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -6,7 +6,7 @@ KSFT_KHDR_INSTALL := 1 CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ - simult_flows.sh mptcp_sockopt.sh + simult_flows.sh mptcp_sockopt.sh userspace_pm.sh TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq |