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>

CREDITS

@@ -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

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

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
 ===================

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,
+and kernel/module/main.c make use the namespace at build time or module load
-respectively.
+time, respectively.
 
 2.2 Using the DEFAULT_SYMBOL_NAMESPACE define
 =============================================

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:

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.

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

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:

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
+   It may unlock and discard the folio it was given and set the caller's folio
-   regrabbed and any other error code to abort the operation.
+   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``
 

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
 ---------------------------------

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
+in kernel/module/kallsyms.c). For livepatch modules, the symbol table copied
-on module load must be exactly the same as the symbol table produced when the
+into memory on module load must be exactly the same as the symbol table produced
-patch module was compiled. This is because the relocations in each livepatch
+when the patch module was compiled. This is because the relocations in each
-relocation section refer to their respective symbols with their symbol indices,
+livepatch relocation section refer to their respective symbols with their symbol
-and the original symbol indices (and thus the symtab ordering) must be
+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:::

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
+Probing, registration and device lifetime
-of drivers to probe for. ``unregister_switch_driver()`` does the exact opposite.
+-----------------------------------------
 
-Unless requested differently by setting the priv_size member accordingly, DSA
+DSA switches are regular ``device`` structures on buses (be they platform, SPI,
-does not allocate any driver private context space.
+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,
+- ``get_tag_protocol``: this is to indicate what kind of tagging protocol is
-  should be a valid value from the ``dsa_tag_protocol`` enum
+  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
+- ``change_tag_protocol``: when the default tagging protocol has compatibility
-  registration to test for the presence/absence of a switch device. For MDIO
+  problems with the master or other issues, the driver may support changing it
-  devices, it is recommended to issue a read towards internal registers using
+  at runtime, either through a device tree property or through sysfs. In that
-  the switch pseudo-PHY and return whether this is a supported device. For other
+  case, further calls to ``get_tag_protocol`` should report the protocol in
-  buses, return a non-NULL string
+  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
+  remaining bridge members.
-  out at the switch hardware for the switch to (re) learn MAC addresses behind
-  this port.
 
 - ``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
+  hardware to forward/block/learn traffic.
-  computing a STP state change based on current and asked parameters and perform
-  the relevant ageing based on the intersection results
 
 - ``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_fast_age``: bridge layer function invoked when flushing the
-  ``port_bridge_join`` when a driver sets ``ds->num_fwd_offloading_bridges`` to
+  dynamically learned FDB entries on the port is necessary. This is called when
-  a non-zero value. Returning success in this function activates the TX
+  transitioning from an STP state where learning should take place to an STP
-  forwarding offload bridge feature for this port, which enables the tagging
+  state where it shouldn't, or when leaving a bridge, or when address learning
-  protocol driver to inject data plane packets towards the bridging domain that
+  is turned off via ``port_bridge_flags``.
-  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.
 
 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
+  (tagged or untagged) for the given switch port. The CPU port becomes a member
-  supported by the hardware, this function should return ``-EOPNOTSUPP`` to
+  of a VLAN only if a foreign bridge port is also a member of it (and
-  inform the bridge code to fallback to a software implementation.
+  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
+  associated with this VLAN ID.
-  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.
 
 - ``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
+- ``port_fdb_dump``: bridge bypass function invoked by ``ndo_fdb_dump`` on the
-  function that the driver has to call for each MAC address known to be behind
+  physical DSA port interfaces. Since DSA does not attempt to keep in sync its
-  the given port. A switchdev object is used to carry the VID and FDB info.
+  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
+  a multicast database entry. The switch hardware should be programmed with the
-  should return ``-EOPNOTSUPP`` to inform the bridge code to fallback to a
-  software implementation. 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
 ----------------
 

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.
+	UDP does not have tx memory accounting and this tunable has no effect.
-	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
 
 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

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

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
+di base. Il programma ``modpost`` e il codice in kernel/module/main.c usano lo
-dei nomi, rispettivamente, durante la compilazione e durante il caricamento
+spazio dei nomi, rispettivamente, durante la compilazione e durante il
-di un modulo.
+caricamento di un modulo.
 
 2.2 Usare il simbolo di preprocessore DEFAULT_SYMBOL_NAMESPACE
 ==============================================================

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
 ========

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
 ====================================

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
+    [pow(2, N-2), pow(2, N-1)).
-    in the bucket's range.
 
 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

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
+S:	Orphan
-W:	http://hackndev.com
 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:	io_uring/
-F:	fs/io-wq.h
-F:	fs/io_uring.c
 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
 

Makefile

@@ -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) \

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

arch/arm/boot/dts/imx6qdl-ts7970.dtsi

@@ -226,7 +226,7 @@ gpio8: gpio@28 {
 		reg = <0x28>;
 		#gpio-cells = <2>;
 		gpio-controller;
-		ngpio = <32>;
+		ngpios = <62>;
 	};
 
 	sgtl5000: codec@a {

arch/arm/boot/dts/imx6ull-colibri.dtsi

@@ -166,7 +166,7 @@ &i2c1 {
 	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 @@ MX6UL_PAD_ENET1_TX_EN__GPIO2_IO05       0xb0a0  /* SODIMM 30 */
 	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 @@ MX6UL_PAD_LCD_RESET__WDOG1_WDOG_ANY    0x30b0
 };
 
 &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 */

arch/arm/boot/dts/lan966x-kontron-kswitch-d10-mmt.dtsi

@@ -87,22 +87,22 @@ &mdio0 {
 
 	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>;
 	};
 };
 

arch/arm/boot/dts/qcom-msm8974.dtsi

@@ -506,6 +506,8 @@ blsp1_uart2: serial@f991e000 {
 			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 @@ blsp2_uart1: serial@f995d000 {
 			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 @@ blsp2_uart4: serial@f9960000 {
 			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 @@ blsp2_i2c6: i2c@f9968000 {
 			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 @@ cd {
 				};
 			};
 
-			blsp1_uart2_active: blsp1-uart2-active {
+			blsp1_uart2_default: blsp1-uart2-default {
 				rx {
 					pins = "gpio5";
 					function = "blsp_uart2";
@@ -1272,7 +1282,7 @@ tx {
 				};
 			};
 
-			blsp2_uart1_active: blsp2-uart1-active {
+			blsp2_uart1_default: blsp2-uart1-default {
 				tx-rts {
 					pins = "gpio41", "gpio44";
 					function = "blsp_uart7";
@@ -1295,7 +1305,7 @@ blsp2_uart1_sleep: blsp2-uart1-sleep {
 				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 @@ blsp2_i2c5_sleep: blsp2-i2c5-sleep {
 				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 {

arch/arm/boot/dts/sama5d2.dtsi

@@ -1124,7 +1124,7 @@ AT91_XDMAC_DT_PERID(33))>,
 				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";
 			};
 

arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts

@@ -169,7 +169,7 @@ &spi0 {
 	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>;
 	};

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)

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,

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

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

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);
 }

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"

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:

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);
 	}
 

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",
+	pr_info_once("Spectre V2: workarounds disabled by configuration\n");
-		smp_processor_id());
 
 	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",
+		pr_info("CPU%u: Spectre BHB: enabling %s workaround for all CPUs\n",
 			smp_processor_id(), spectre_bhb_method_name(method));
+	}
 
 	return SPECTRE_MITIGATED;
 }

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;

arch/arm64/boot/dts/broadcom/bcm4908/bcm4906.dtsi

@@ -9,6 +9,14 @@ cpus {
 		/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>,

arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi

@@ -29,6 +29,8 @@ cpu0: cpu@0 {
 			device_type = "cpu";
 			compatible = "brcm,brahma-b53";
 			reg = <0x0>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x0 0xfff8>;
 			next-level-cache = <&l2>;
 		};
 

arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi

@@ -224,9 +224,12 @@ rst: syscon@1e60000 {
 			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>;
 

arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi

@@ -376,7 +376,8 @@ &cru {
 		<&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 @@ &cru {
 		<400000000>,
 		<200000000>,
 		<200000000>,
+		<400000000>,
 		<400000000>;
 };
 

arch/arm64/boot/dts/rockchip/rk3399.dtsi

@@ -1462,7 +1462,8 @@ cru: clock-controller@ff760000 {
 			<&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 @@ cru: clock-controller@ff760000 {
 			 <100000000>,   <50000000>,
 			 <400000000>, <400000000>,
 			 <200000000>,
-			 <200000000>;
+			 <200000000>,
+			 <400000000>;
 	};
 
 	grf: syscon@ff770000 {

arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts

@@ -687,6 +687,7 @@ &usb_host1_ohci {
 };
 
 &usb_host0_xhci {
+	dr_mode = "host";
 	status = "okay";
 };
 

arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts

@@ -133,7 +133,7 @@ &gmac1 {
 	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

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 */

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

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);

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

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

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

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

arch/riscv/boot/dts/canaan/canaan_kd233.dts

@@ -35,7 +35,7 @@ led1 {
 	gpio-keys {
 		compatible = "gpio-keys";
 
-		key0 {
+		key {
 			label = "KEY0";
 			linux,code = <BTN_0>;
 			gpios = <&gpio0 10 GPIO_ACTIVE_LOW>;

arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts

@@ -47,7 +47,7 @@ led2 {
 	gpio-keys {
 		compatible = "gpio-keys";
 
-		boot {
+		key-boot {
 			label = "BOOT";
 			linux,code = <BTN_0>;
 			gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;

arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts

@@ -52,7 +52,7 @@ led2 {
 	gpio-keys {
 		compatible = "gpio-keys";
 
-		boot {
+		key-boot {
 			label = "BOOT";
 			linux,code = <BTN_0>;
 			gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;

arch/riscv/boot/dts/canaan/sipeed_maix_go.dts

@@ -46,19 +46,19 @@ led2 {
 	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>;

arch/riscv/boot/dts/canaan/sipeed_maixduino.dts

@@ -23,7 +23,7 @@ chosen {
 	gpio-keys {
 		compatible = "gpio-keys";
 
-		boot {
+		key-boot {
 			label = "BOOT";
 			linux,code = <BTN_0>;
 			gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;

arch/riscv/boot/dts/microchip/mpfs.dtsi

@@ -50,6 +50,7 @@ cpu1: cpu@1 {
 			riscv,isa = "rv64imafdc";
 			clocks = <&clkcfg CLK_CPU>;
 			tlb-split;
+			next-level-cache = <&cctrllr>;
 			status = "okay";
 
 			cpu1_intc: interrupt-controller {
@@ -77,6 +78,7 @@ cpu2: cpu@2 {
 			riscv,isa = "rv64imafdc";
 			clocks = <&clkcfg CLK_CPU>;
 			tlb-split;
+			next-level-cache = <&cctrllr>;
 			status = "okay";
 
 			cpu2_intc: interrupt-controller {
@@ -104,6 +106,7 @@ cpu3: cpu@3 {
 			riscv,isa = "rv64imafdc";
 			clocks = <&clkcfg CLK_CPU>;
 			tlb-split;
+			next-level-cache = <&cctrllr>;
 			status = "okay";
 
 			cpu3_intc: interrupt-controller {
@@ -131,6 +134,7 @@ cpu4: cpu@4 {
 			riscv,isa = "rv64imafdc";
 			clocks = <&clkcfg CLK_CPU>;
 			tlb-split;
+			next-level-cache = <&cctrllr>;
 			status = "okay";
 			cpu4_intc: interrupt-controller {
 				#interrupt-cells = <1>;

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);
 }

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)
 

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)
 {

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
 

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 */

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)

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) {
 				/*

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

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

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__

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

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/

arch/s390/lib/expoline/Makefile

@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-y += expoline.o

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)
+static inline void __iomem *ioremap(phys_addr_t offset, size_t size)
-#define ioremap(offset, size)	((void __iomem *)(unsigned long)(offset))
+{
+	return (void __iomem *)(unsigned long)offset;
+}
+
+static inline void iounmap(volatile void __iomem *addr) { }
 #endif /* CONFIG_MMU */
 
 #define ioremap_uc	ioremap

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

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()
 
 /*

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 __pa(virt) uml_to_phys((void *) (unsigned long) (virt))
-#define __va(phys) to_virt((unsigned long) (phys))
+#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)

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);
 }

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)
 {
 }

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

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

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
 

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/

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>
 
 /*
 
@@ -282,6 +284,66 @@ 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.
  *

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

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

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(xen_error_entry)
-SYM_CODE_START_LOCAL(push_and_clear_regs)
 	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
 

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

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.

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
 

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
+ * For format LBR_FORMAT_EIP_FLAGS2, bits 61:62 in MSR_LAST_BRANCH_FROM_x
- * MSR_LAST_BRANCH_FROM_x are the TSX flags when TSX is supported, but when
+ * are the TSX flags when TSX is supported, but when TSX is not supported
- * TSX is not supported they have no consistent behavior:
+ * 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;

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;

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_KERNEL_IBRS		( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */
-#define X86_FEATURE_RETPOLINE_LFENCE	( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */
+#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 */

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

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__ */
 

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

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
 
@@ -75,6 +76,23 @@
 	.popsection
 .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
@@ -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,			\
-									\
+			      spec_ctrl_current(),			\
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
 			      X86_FEATURE_USE_IBRS_FW);			\
 	preempt_enable();						\
 } while (0)

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 */

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);
 

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 \

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;

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