Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

No conflicts. Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-06-16 20:13:52 -07:00 · 2022-06-16 20:13:52 -07:00 · 9cbc991126
parent 5dcb50c009 48a23ec6ff
commit 9cbc991126
201 changed files with 2493 additions and 1676 deletions
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@ -526,6 +526,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/srbds
 		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
 		/sys/devices/system/cpu/vulnerabilities/itlb_multihit
+		/sys/devices/system/cpu/vulnerabilities/mmio_stale_data
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
--- a/Documentation/admin-guide/hw-vuln/index.rst
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@ -17,3 +17,4 @@ are configurable at compile, boot or run time.
   special-register-buffer-data-sampling.rst
   core-scheduling.rst
   l1d_flush.rst
+   processor_mmio_stale_data.rst
--- a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
+++ b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
@ -0,0 +1,246 @@
+=========================================
+Processor MMIO Stale Data Vulnerabilities
+=========================================
+
+Processor MMIO Stale Data Vulnerabilities are a class of memory-mapped I/O
+(MMIO) vulnerabilities that can expose data. The sequences of operations for
+exposing data range from simple to very complex. Because most of the
+vulnerabilities require the attacker to have access to MMIO, many environments
+are not affected. System environments using virtualization where MMIO access is
+provided to untrusted guests may need mitigation. These vulnerabilities are
+not transient execution attacks. However, these vulnerabilities may propagate
+stale data into core fill buffers where the data can subsequently be inferred
+by an unmitigated transient execution attack. Mitigation for these
+vulnerabilities includes a combination of microcode update and software
+changes, depending on the platform and usage model. Some of these mitigations
+are similar to those used to mitigate Microarchitectural Data Sampling (MDS) or
+those used to mitigate Special Register Buffer Data Sampling (SRBDS).
+
+Data Propagators
+================
+Propagators are operations that result in stale data being copied or moved from
+one microarchitectural buffer or register to another. Processor MMIO Stale Data
+Vulnerabilities are operations that may result in stale data being directly
+read into an architectural, software-visible state or sampled from a buffer or
+register.
+
+Fill Buffer Stale Data Propagator (FBSDP)
+-----------------------------------------
+Stale data may propagate from fill buffers (FB) into the non-coherent portion
+of the uncore on some non-coherent writes. Fill buffer propagation by itself
+does not make stale data architecturally visible. Stale data must be propagated
+to a location where it is subject to reading or sampling.
+
+Sideband Stale Data Propagator (SSDP)
+-------------------------------------
+The sideband stale data propagator (SSDP) is limited to the client (including
+Intel Xeon server E3) uncore implementation. The sideband response buffer is
+shared by all client cores. For non-coherent reads that go to sideband
+destinations, the uncore logic returns 64 bytes of data to the core, including
+both requested data and unrequested stale data, from a transaction buffer and
+the sideband response buffer. As a result, stale data from the sideband
+response and transaction buffers may now reside in a core fill buffer.
+
+Primary Stale Data Propagator (PSDP)
+------------------------------------
+The primary stale data propagator (PSDP) is limited to the client (including
+Intel Xeon server E3) uncore implementation. Similar to the sideband response
+buffer, the primary response buffer is shared by all client cores. For some
+processors, MMIO primary reads will return 64 bytes of data to the core fill
+buffer including both requested data and unrequested stale data. This is
+similar to the sideband stale data propagator.
+
+Vulnerabilities
+===============
+Device Register Partial Write (DRPW) (CVE-2022-21166)
+-----------------------------------------------------
+Some endpoint MMIO registers incorrectly handle writes that are smaller than
+the register size. Instead of aborting the write or only copying the correct
+subset of bytes (for example, 2 bytes for a 2-byte write), more bytes than
+specified by the write transaction may be written to the register. On
+processors affected by FBSDP, this may expose stale data from the fill buffers
+of the core that created the write transaction.
+
+Shared Buffers Data Sampling (SBDS) (CVE-2022-21125)
+----------------------------------------------------
+After propagators may have moved data around the uncore and copied stale data
+into client core fill buffers, processors affected by MFBDS can leak data from
+the fill buffer. It is limited to the client (including Intel Xeon server E3)
+uncore implementation.
+
+Shared Buffers Data Read (SBDR) (CVE-2022-21123)
+------------------------------------------------
+It is similar to Shared Buffer Data Sampling (SBDS) except that the data is
+directly read into the architectural software-visible state. It is limited to
+the client (including Intel Xeon server E3) uncore implementation.
+
+Affected Processors
+===================
+Not all the CPUs are affected by all the variants. For instance, most
+processors for the server market (excluding Intel Xeon E3 processors) are
+impacted by only Device Register Partial Write (DRPW).
+
+Below is the list of affected Intel processors [#f1]_:
+
+   ===================  ============  =========
+   Common name          Family_Model  Steppings
+   ===================  ============  =========
+   HASWELL_X            06_3FH        2,4
+   SKYLAKE_L            06_4EH        3
+   BROADWELL_X          06_4FH        All
+   SKYLAKE_X            06_55H        3,4,6,7,11
+   BROADWELL_D          06_56H        3,4,5
+   SKYLAKE              06_5EH        3
+   ICELAKE_X            06_6AH        4,5,6
+   ICELAKE_D            06_6CH        1
+   ICELAKE_L            06_7EH        5
+   ATOM_TREMONT_D       06_86H        All
+   LAKEFIELD            06_8AH        1
+   KABYLAKE_L           06_8EH        9 to 12
+   ATOM_TREMONT         06_96H        1
+   ATOM_TREMONT_L       06_9CH        0
+   KABYLAKE             06_9EH        9 to 13
+   COMETLAKE            06_A5H        2,3,5
+   COMETLAKE_L          06_A6H        0,1
+   ROCKETLAKE           06_A7H        1
+   ===================  ============  =========
+
+If a CPU is in the affected processor list, but not affected by a variant, it
+is indicated by new bits in MSR IA32_ARCH_CAPABILITIES. As described in a later
+section, mitigation largely remains the same for all the variants, i.e. to
+clear the CPU fill buffers via VERW instruction.
+
+New bits in MSRs
+================
+Newer processors and microcode update on existing affected processors added new
+bits to IA32_ARCH_CAPABILITIES MSR. These bits can be used to enumerate
+specific variants of Processor MMIO Stale Data vulnerabilities and mitigation
+capability.
+
+MSR IA32_ARCH_CAPABILITIES
+--------------------------
+Bit 13 - SBDR_SSDP_NO - When set, processor is not affected by either the
+	 Shared Buffers Data Read (SBDR) vulnerability or the sideband stale
+	 data propagator (SSDP).
+Bit 14 - FBSDP_NO - When set, processor is not affected by the Fill Buffer
+	 Stale Data Propagator (FBSDP).
+Bit 15 - PSDP_NO - When set, processor is not affected by Primary Stale Data
+	 Propagator (PSDP).
+Bit 17 - FB_CLEAR - When set, VERW instruction will overwrite CPU fill buffer
+	 values as part of MD_CLEAR operations. Processors that do not
+	 enumerate MDS_NO (meaning they are affected by MDS) but that do
+	 enumerate support for both L1D_FLUSH and MD_CLEAR implicitly enumerate
+	 FB_CLEAR as part of their MD_CLEAR support.
+Bit 18 - FB_CLEAR_CTRL - Processor supports read and write to MSR
+	 IA32_MCU_OPT_CTRL[FB_CLEAR_DIS]. On such processors, the FB_CLEAR_DIS
+	 bit can be set to cause the VERW instruction to not perform the
+	 FB_CLEAR action. Not all processors that support FB_CLEAR will support
+	 FB_CLEAR_CTRL.
+
+MSR IA32_MCU_OPT_CTRL
+---------------------
+Bit 3 - FB_CLEAR_DIS - When set, VERW instruction does not perform the FB_CLEAR
+action. This may be useful to reduce the performance impact of FB_CLEAR in
+cases where system software deems it warranted (for example, when performance
+is more critical, or the untrusted software has no MMIO access). Note that
+FB_CLEAR_DIS has no impact on enumeration (for example, it does not change
+FB_CLEAR or MD_CLEAR enumeration) and it may not be supported on all processors
+that enumerate FB_CLEAR.
+
+Mitigation
+==========
+Like MDS, all variants of Processor MMIO Stale Data vulnerabilities  have the
+same mitigation strategy to force the CPU to clear the affected buffers before
+an attacker can extract the secrets.
+
+This is achieved by using the otherwise unused and obsolete VERW instruction in
+combination with a microcode update. The microcode clears the affected CPU
+buffers when the VERW instruction is executed.
+
+Kernel reuses the MDS function to invoke the buffer clearing:
+
+	mds_clear_cpu_buffers()
+
+On MDS affected CPUs, the kernel already invokes CPU buffer clear on
+kernel/userspace, hypervisor/guest and C-state (idle) transitions. No
+additional mitigation is needed on such CPUs.
+
+For CPUs not affected by MDS or TAA, mitigation is needed only for the attacker
+with MMIO capability. Therefore, VERW is not required for kernel/userspace. For
+virtualization case, VERW is only needed at VMENTER for a guest with MMIO
+capability.
+
+Mitigation points
+-----------------
+Return to user space
+^^^^^^^^^^^^^^^^^^^^
+Same mitigation as MDS when affected by MDS/TAA, otherwise no mitigation
+needed.
+
+C-State transition
+^^^^^^^^^^^^^^^^^^
+Control register writes by CPU during C-state transition can propagate data
+from fill buffer to uncore buffers. Execute VERW before C-state transition to
+clear CPU fill buffers.
+
+Guest entry point
+^^^^^^^^^^^^^^^^^
+Same mitigation as MDS when processor is also affected by MDS/TAA, otherwise
+execute VERW at VMENTER only for MMIO capable guests. On CPUs not affected by
+MDS/TAA, guest without MMIO access cannot extract secrets using Processor MMIO
+Stale Data vulnerabilities, so there is no need to execute VERW for such guests.
+
+Mitigation control on the kernel command line
+---------------------------------------------
+The kernel command line allows to control the Processor MMIO Stale Data
+mitigations at boot time with the option "mmio_stale_data=". The valid
+arguments for this option are:
+
+  ==========  =================================================================
+  full        If the CPU is vulnerable, enable mitigation; CPU buffer clearing
+              on exit to userspace and when entering a VM. Idle transitions are
+              protected as well. It does not automatically disable SMT.
+  full,nosmt  Same as full, with SMT disabled on vulnerable CPUs. This is the
+              complete mitigation.
+  off         Disables mitigation completely.
+  ==========  =================================================================
+
+If the CPU is affected and mmio_stale_data=off is not supplied on the kernel
+command line, then the kernel selects the appropriate mitigation.
+
+Mitigation status information
+-----------------------------
+The Linux kernel provides a sysfs interface to enumerate the current
+vulnerability status of the system: whether the system is vulnerable, and
+which mitigations are active. The relevant sysfs file is:
+
+	/sys/devices/system/cpu/vulnerabilities/mmio_stale_data
+
+The possible values in this file are:
+
+  .. list-table::
+
+     * - 'Not affected'
+       - The processor is not vulnerable
+     * - 'Vulnerable'
+       - The processor is vulnerable, but no mitigation enabled
+     * - 'Vulnerable: Clear CPU buffers attempted, no microcode'
+       - The processor is vulnerable, but microcode is not updated. The
+         mitigation is enabled on a best effort basis.
+     * - 'Mitigation: Clear CPU buffers'
+       - The processor is vulnerable and the CPU buffer clearing mitigation is
+         enabled.
+
+If the processor is vulnerable then the following information is appended to
+the above information:
+
+  ========================  ===========================================
+  'SMT vulnerable'          SMT is enabled
+  'SMT disabled'            SMT is disabled
+  'SMT Host state unknown'  Kernel runs in a VM, Host SMT state unknown
+  ========================  ===========================================
+
+References
+----------
+.. [#f1] Affected Processors
+   https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@ -2469,7 +2469,6 @@

 			protected: nVHE-based mode with support for guests whose
 				   state is kept private from the host.
-				   Not valid if the kernel is running in EL2.

 			Defaults to VHE/nVHE based on hardware support. Setting
 			mode to "protected" will disable kexec and hibernation
@ -3176,6 +3175,7 @@
 					       srbds=off [X86,INTEL]
 					       no_entry_flush [PPC]
 					       no_uaccess_flush [PPC]
+					       mmio_stale_data=off [X86]

 				Exceptions:
 					       This does not have any effect on
@ -3197,6 +3197,7 @@
 				Equivalent to: l1tf=flush,nosmt [X86]
 					       mds=full,nosmt [X86]
 					       tsx_async_abort=full,nosmt [X86]
+					       mmio_stale_data=full,nosmt [X86]

 	mminit_loglevel=
 			[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
@ -3206,6 +3207,40 @@
 			log everything. Information is printed at KERN_DEBUG
 			so loglevel=8 may also need to be specified.

+	mmio_stale_data=
+			[X86,INTEL] Control mitigation for the Processor
+			MMIO Stale Data vulnerabilities.
+
+			Processor MMIO Stale Data is a class of
+			vulnerabilities that may expose data after an MMIO
+			operation. Exposed data could originate or end in
+			the same CPU buffers as affected by MDS and TAA.
+			Therefore, similar to MDS and TAA, the mitigation
+			is to clear the affected CPU buffers.
+
+			This parameter controls the mitigation. The
+			options are:
+
+			full       - Enable mitigation on vulnerable CPUs
+
+			full,nosmt - Enable mitigation and disable SMT on
+				     vulnerable CPUs.
+
+			off        - Unconditionally disable mitigation
+
+			On MDS or TAA affected machines,
+			mmio_stale_data=off can be prevented by an active
+			MDS or TAA mitigation as these vulnerabilities are
+			mitigated with the same mechanism so in order to
+			disable this mitigation, you need to specify
+			mds=off and tsx_async_abort=off too.
+
+			Not specifying this option is equivalent to
+			mmio_stale_data=full.
+
+			For details see:
+			Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
+
 	module.sig_enforce
 			[KNL] When CONFIG_MODULE_SIG is set, this means that
 			modules without (valid) signatures will fail to load.
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@ -79,7 +79,7 @@ To help deal with the per-inode context, a number helper functions are
 provided.  Firstly, a function to perform basic initialisation on a context and
 set the operations table pointer::

-	void netfs_inode_init(struct inode *inode,
+	void netfs_inode_init(struct netfs_inode *ctx,
 			      const struct netfs_request_ops *ops);

 then a function to cast from the VFS inode structure to the netfs context::
@ -89,7 +89,7 @@ then a function to cast from the VFS inode structure to the netfs context::
 and finally, a function to get the cache cookie pointer from the context
 attached to an inode (or NULL if fscache is disabled)::

-	struct fscache_cookie *netfs_i_cookie(struct inode *inode);
+	struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx);


 Buffered Read Helpers
@ -136,8 +136,9 @@ Three read helpers are provided::

 	void netfs_readahead(struct readahead_control *ractl);
 	int netfs_read_folio(struct file *file,
-			   struct folio *folio);
-	int netfs_write_begin(struct file *file,
+			     struct folio *folio);
+	int netfs_write_begin(struct netfs_inode *ctx,
+			      struct file *file,
 			      struct address_space *mapping,
 			      loff_t pos,
 			      unsigned int len,
@ -157,9 +158,10 @@ The helpers manage the read request, calling back into the network filesystem
 through the suppplied table of operations.  Waits will be performed as
 necessary before returning for helpers that are meant to be synchronous.

-If an error occurs and netfs_priv is non-NULL, ops->cleanup() will be called to
-deal with it.  If some parts of the request are in progress when an error
-occurs, the request will get partially completed if sufficient data is read.
+If an error occurs, the ->free_request() will be called to clean up the
+netfs_io_request struct allocated.  If some parts of the request are in
+progress when an error occurs, the request will get partially completed if
+sufficient data is read.

 Additionally, there is::

@ -207,8 +209,7 @@ The above fields are the ones the netfs can use.  They are:
 * ``netfs_priv``

   The network filesystem's private data.  The value for this can be passed in
-   to the helper functions or set during the request.  The ->cleanup() op will
-   be called if this is non-NULL at the end.
+   to the helper functions or set during the request.

 * ``start``
 * ``len``
@ -293,6 +294,7 @@ through which it can issue requests and negotiate::

 	struct netfs_request_ops {
 		void (*init_request)(struct netfs_io_request *rreq, struct file *file);
+		void (*free_request)(struct netfs_io_request *rreq);
 		int (*begin_cache_operation)(struct netfs_io_request *rreq);
 		void (*expand_readahead)(struct netfs_io_request *rreq);
 		bool (*clamp_length)(struct netfs_io_subrequest *subreq);
@ -301,7 +303,6 @@ through which it can issue requests and negotiate::
 		int (*check_write_begin)(struct file *file, loff_t pos, unsigned len,
 					 struct folio *folio, void **_fsdata);
 		void (*done)(struct netfs_io_request *rreq);
-		void (*cleanup)(struct address_space *mapping, void *netfs_priv);
 	};

 The operations are as follows:
@ -309,7 +310,12 @@ The operations are as follows:
 * ``init_request()``

   [Optional] This is called to initialise the request structure.  It is given
-   the file for reference and can modify the ->netfs_priv value.
+   the file for reference.
+
+ * ``free_request()``
+
+   [Optional] This is called as the request is being deallocated so that the
+   filesystem can clean up any state it has attached there.

 * ``begin_cache_operation()``

@ -383,11 +389,6 @@ The operations are as follows:
   [Optional] This is called after the folios in the request have all been
   unlocked (and marked uptodate if applicable).

- * ``cleanup``
-
-   [Optional] This is called as the request is being deallocated so that the
-   filesystem can clean up ->netfs_priv.
-


 Read Helper Procedure
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@ -2925,6 +2925,43 @@ plpmtud_probe_interval - INTEGER

 	Default: 0

+reconf_enable - BOOLEAN
+        Enable or disable extension of Stream Reconfiguration functionality
+        specified in RFC6525. This extension provides the ability to "reset"
+        a stream, and it includes the Parameters of "Outgoing/Incoming SSN
+        Reset", "SSN/TSN Reset" and "Add Outgoing/Incoming Streams".
+
+	- 1: Enable extension.
+	- 0: Disable extension.
+
+	Default: 0
+
+intl_enable - BOOLEAN
+        Enable or disable extension of User Message Interleaving functionality
+        specified in RFC8260. This extension allows the interleaving of user
+        messages sent on different streams. With this feature enabled, I-DATA
+        chunk will replace DATA chunk to carry user messages if also supported
+        by the peer. Note that to use this feature, one needs to set this option
+        to 1 and also needs to set socket options SCTP_FRAGMENT_INTERLEAVE to 2
+        and SCTP_INTERLEAVING_SUPPORTED to 1.
+
+	- 1: Enable extension.
+	- 0: Disable extension.
+
+	Default: 0
+
+ecn_enable - BOOLEAN
+        Control use of Explicit Congestion Notification (ECN) by SCTP.
+        Like in TCP, ECN is used only when both ends of the SCTP connection
+        indicate support for it. This feature is useful in avoiding losses
+        due to congestion by allowing supporting routers to signal congestion
+        before having to drop packets.
+
+        1: Enable ecn.
+        0: Disable ecn.
+
+        Default: 1
+

 ``/proc/sys/net/core/*``
 ========================
--- a/Documentation/networking/phy.rst
+++ b/Documentation/networking/phy.rst
@ -104,7 +104,7 @@ Whenever possible, use the PHY side RGMII delay for these reasons:

 * PHY device drivers in PHYLIB being reusable by nature, being able to
  configure correctly a specified delay enables more designs with similar delay
-  requirements to be operate correctly
+  requirements to be operated correctly

 For cases where the PHY is not capable of providing this delay, but the
 Ethernet MAC driver is capable of doing so, the correct phy_interface_t value
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@ -32,6 +32,7 @@ you probably needn't concern yourself with pcmciautils.
 GNU C                  5.1              gcc --version
 Clang/LLVM (optional)  11.0.0           clang --version
 GNU make               3.81             make --version
+bash                   4.2              bash --version
 binutils               2.23             ld -v
 flex                   2.5.35           flex --version
 bison                  2.0              bison --version
@ -84,6 +85,12 @@ Make

 You will need GNU make 3.81 or later to build the kernel.

+Bash
+----
+
+Some bash scripts are used for the kernel build.
+Bash 4.2 or newer is needed.
+
 Binutils
 --------

@ -362,6 +369,11 @@ Make

 - <ftp://ftp.gnu.org/gnu/make/>

+Bash
+----
+
+- <ftp://ftp.gnu.org/gnu/bash/>
+
 Binutils
 --------

--- a/4
+++ b/4
@ -7653,6 +7653,7 @@ F:	include/uapi/scsi/fc/

 FILE LOCKING (flock() and fcntl()/lockf())
 M:	Jeff Layton <jlayton@kernel.org>
+M:	Chuck Lever <chuck.lever@oracle.com>
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 F:	fs/fcntl.c
@ -10745,6 +10746,7 @@ W:	http://kernelnewbies.org/KernelJanitors

 KERNEL NFSD, SUNRPC, AND LOCKD SERVERS
 M:	Chuck Lever <chuck.lever@oracle.com>
+M:	Jeff Layton <jlayton@kernel.org>
 L:	linux-nfs@vger.kernel.org
 S:	Supported
 W:	http://nfs.sourceforge.net/
@ -10869,7 +10871,6 @@ F:	arch/riscv/include/asm/kvm*
 F:	arch/riscv/include/uapi/asm/kvm*
 F:	arch/riscv/kvm/
 F:	tools/testing/selftests/kvm/*/riscv/
-F:	tools/testing/selftests/kvm/riscv/

 KERNEL VIRTUAL MACHINE for s390 (KVM/s390)
 M:	Christian Borntraeger <borntraeger@linux.ibm.com>
@ -13798,6 +13799,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
 F:	Documentation/devicetree/bindings/net/
 F:	drivers/connector/
 F:	drivers/net/
+F:	include/dt-bindings/net/
 F:	include/linux/etherdevice.h
 F:	include/linux/fcdevice.h
 F:	include/linux/fddidevice.h
--- a/2
+++ b/2
@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 19
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Superb Owl

 # *DOCUMENTATION*
--- a/arch/arm/boot/dts/at91-sama5d3_ksz9477_evb.dts
+++ b/arch/arm/boot/dts/at91-sama5d3_ksz9477_evb.dts
@ -120,26 +120,31 @@
 			port@0 {
 				reg = <0>;
 				label = "lan1";
+				phy-mode = "internal";
 			};

 			port@1 {
 				reg = <1>;
 				label = "lan2";
+				phy-mode = "internal";
 			};

 			port@2 {
 				reg = <2>;
 				label = "lan3";
+				phy-mode = "internal";
 			};

 			port@3 {
 				reg = <3>;
 				label = "lan4";
+				phy-mode = "internal";
 			};

 			port@4 {
 				reg = <4>;
 				label = "lan5";
+				phy-mode = "internal";
 			};

 			port@5 {
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@ -362,11 +362,6 @@ struct kvm_vcpu_arch {
 	struct arch_timer_cpu timer_cpu;
 	struct kvm_pmu pmu;

-	/*
-	 * Anything that is not used directly from assembly code goes
-	 * here.
-	 */
-
 	/*
 	 * Guest registers we preserve during guest debugging.
 	 *
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@ -113,6 +113,9 @@ static __always_inline bool has_vhe(void)
 	/*
 	 * Code only run in VHE/NVHE hyp context can assume VHE is present or
 	 * absent. Otherwise fall back to caps.
+	 * This allows the compiler to discard VHE-specific code from the
+	 * nVHE object, reducing the number of external symbol references
+	 * needed to link.
 	 */
 	if (is_vhe_hyp_code())
 		return true;
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@ -1974,15 +1974,7 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap)
 #ifdef CONFIG_KVM
 static bool is_kvm_protected_mode(const struct arm64_cpu_capabilities *entry, int __unused)
 {
-	if (kvm_get_mode() != KVM_MODE_PROTECTED)
-		return false;
-
-	if (is_kernel_in_hyp_mode()) {
-		pr_warn("Protected KVM not available with VHE\n");
-		return false;
-	}
-
-	return true;
+	return kvm_get_mode() == KVM_MODE_PROTECTED;
 }
 #endif /* CONFIG_KVM */

--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@ -1230,6 +1230,9 @@ bool kvm_arch_timer_get_input_level(int vintid)
 	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 	struct arch_timer_context *timer;

+	if (WARN(!vcpu, "No vcpu context!\n"))
+		return false;
+
 	if (vintid == vcpu_vtimer(vcpu)->irq.irq)
 		timer = vcpu_vtimer(vcpu);
 	else if (vintid == vcpu_ptimer(vcpu)->irq.irq)
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@ -150,8 +150,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out_free_stage2_pgd;

-	if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL)) {
+		ret = -ENOMEM;
 		goto out_free_stage2_pgd;
+	}
 	cpumask_copy(kvm->arch.supported_cpus, cpu_possible_mask);

 	kvm_vgic_early_init(kvm);
@ -2271,7 +2273,11 @@ static int __init early_kvm_mode_cfg(char *arg)
 		return -EINVAL;

 	if (strcmp(arg, "protected") == 0) {
-		kvm_mode = KVM_MODE_PROTECTED;
+		if (!is_kernel_in_hyp_mode())
+			kvm_mode = KVM_MODE_PROTECTED;
+		else
+			pr_warn_once("Protected KVM not available with VHE\n");
+
 		return 0;
 	}

--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@ -80,6 +80,7 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 	vcpu->arch.flags &= ~KVM_ARM64_FP_ENABLED;
 	vcpu->arch.flags |= KVM_ARM64_FP_HOST;

+	vcpu->arch.flags &= ~KVM_ARM64_HOST_SVE_ENABLED;
 	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
 		vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED;

@ -93,6 +94,7 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 	 * operations. Do this for ZA as well for now for simplicity.
 	 */
 	if (system_supports_sme()) {
+		vcpu->arch.flags &= ~KVM_ARM64_HOST_SME_ENABLED;
 		if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN)
 			vcpu->arch.flags |= KVM_ARM64_HOST_SME_ENABLED;

--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@ -314,15 +314,11 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size,
 			     enum kvm_pgtable_prot prot)
 {
-	hyp_assert_lock_held(&host_kvm.lock);
-
 	return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot);
 }

 int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
 {
-	hyp_assert_lock_held(&host_kvm.lock);
-
 	return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_kvm.pgt,
 			       addr, size, &host_s2_pool, owner_id);
 }
--- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c
+++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
@ -243,15 +243,9 @@ u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id)
 	case SYS_ID_AA64MMFR2_EL1:
 		return get_pvm_id_aa64mmfr2(vcpu);
 	default:
-		/*
-		 * Should never happen because all cases are covered in
-		 * pvm_sys_reg_descs[].
-		 */
-		WARN_ON(1);
-		break;
+		/* Unhandled ID register, RAZ */
+		return 0;
 	}
-
-	return 0;
 }

 static u64 read_id_reg(const struct kvm_vcpu *vcpu,
@ -332,6 +326,16 @@ static bool pvm_gic_read_sre(struct kvm_vcpu *vcpu,
 /* Mark the specified system register as an AArch64 feature id register. */
 #define AARCH64(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch64 }

+/*
+ * sys_reg_desc initialiser for architecturally unallocated cpufeature ID
+ * register with encoding Op0=3, Op1=0, CRn=0, CRm=crm, Op2=op2
+ * (1 <= crm < 8, 0 <= Op2 < 8).
+ */
+#define ID_UNALLOCATED(crm, op2) {			\
+	Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2),	\
+	.access = pvm_access_id_aarch64,		\
+}
+
 /* Mark the specified system register as Read-As-Zero/Write-Ignored */
 #define RAZ_WI(REG) { SYS_DESC(REG), .access = pvm_access_raz_wi }

@ -375,24 +379,46 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
 	AARCH32(SYS_MVFR0_EL1),
 	AARCH32(SYS_MVFR1_EL1),
 	AARCH32(SYS_MVFR2_EL1),
+	ID_UNALLOCATED(3,3),
 	AARCH32(SYS_ID_PFR2_EL1),
 	AARCH32(SYS_ID_DFR1_EL1),
 	AARCH32(SYS_ID_MMFR5_EL1),
+	ID_UNALLOCATED(3,7),

 	/* AArch64 ID registers */
 	/* CRm=4 */
 	AARCH64(SYS_ID_AA64PFR0_EL1),
 	AARCH64(SYS_ID_AA64PFR1_EL1),
+	ID_UNALLOCATED(4,2),
+	ID_UNALLOCATED(4,3),
 	AARCH64(SYS_ID_AA64ZFR0_EL1),
+	ID_UNALLOCATED(4,5),
+	ID_UNALLOCATED(4,6),
+	ID_UNALLOCATED(4,7),
 	AARCH64(SYS_ID_AA64DFR0_EL1),
 	AARCH64(SYS_ID_AA64DFR1_EL1),
+	ID_UNALLOCATED(5,2),
+	ID_UNALLOCATED(5,3),
 	AARCH64(SYS_ID_AA64AFR0_EL1),
 	AARCH64(SYS_ID_AA64AFR1_EL1),
+	ID_UNALLOCATED(5,6),
+	ID_UNALLOCATED(5,7),
 	AARCH64(SYS_ID_AA64ISAR0_EL1),
 	AARCH64(SYS_ID_AA64ISAR1_EL1),
+	AARCH64(SYS_ID_AA64ISAR2_EL1),
+	ID_UNALLOCATED(6,3),
+	ID_UNALLOCATED(6,4),
+	ID_UNALLOCATED(6,5),
+	ID_UNALLOCATED(6,6),
+	ID_UNALLOCATED(6,7),
 	AARCH64(SYS_ID_AA64MMFR0_EL1),
 	AARCH64(SYS_ID_AA64MMFR1_EL1),
 	AARCH64(SYS_ID_AA64MMFR2_EL1),
+	ID_UNALLOCATED(7,3),
+	ID_UNALLOCATED(7,4),
+	ID_UNALLOCATED(7,5),
+	ID_UNALLOCATED(7,6),
+	ID_UNALLOCATED(7,7),

 	/* Scalable Vector Registers are restricted. */

--- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c
@ -429,11 +429,11 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = {
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET,
 		vgic_mmio_read_pending, vgic_mmio_write_spending,
-		NULL, vgic_uaccess_write_spending, 1,
+		vgic_uaccess_read_pending, vgic_uaccess_write_spending, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR,
 		vgic_mmio_read_pending, vgic_mmio_write_cpending,
-		NULL, vgic_uaccess_write_cpending, 1,
+		vgic_uaccess_read_pending, vgic_uaccess_write_cpending, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET,
 		vgic_mmio_read_active, vgic_mmio_write_sactive,
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@ -353,42 +353,6 @@ static unsigned long vgic_mmio_read_v3_idregs(struct kvm_vcpu *vcpu,
 	return 0;
 }

-static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu,
-						  gpa_t addr, unsigned int len)
-{
-	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	u32 value = 0;
-	int i;
-
-	/*
-	 * pending state of interrupt is latched in pending_latch variable.
-	 * Userspace will save and restore pending state and line_level
-	 * separately.
-	 * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst
-	 * for handling of ISPENDR and ICPENDR.
-	 */
-	for (i = 0; i < len * 8; i++) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-		bool state = irq->pending_latch;
-
-		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
-			int err;
-
-			err = irq_get_irqchip_state(irq->host_irq,
-						    IRQCHIP_STATE_PENDING,
-						    &state);
-			WARN_ON(err);
-		}
-
-		if (state)
-			value |= (1U << i);
-
-		vgic_put_irq(vcpu->kvm, irq);
-	}
-
-	return value;
-}
-
 static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu,
 					 gpa_t addr, unsigned int len,
 					 unsigned long val)
@ -666,7 +630,7 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = {
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR,
 		vgic_mmio_read_pending, vgic_mmio_write_spending,
-		vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1,
+		vgic_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICPENDR,
 		vgic_mmio_read_pending, vgic_mmio_write_cpending,
@ -750,7 +714,7 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = {
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0,
 		vgic_mmio_read_pending, vgic_mmio_write_spending,
-		vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4,
+		vgic_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICPENDR0,
 		vgic_mmio_read_pending, vgic_mmio_write_cpending,
--- a/arch/arm64/kvm/vgic/vgic-mmio.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio.c
@ -226,8 +226,9 @@ int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu,
 	return 0;
 }

-unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
-				     gpa_t addr, unsigned int len)
+static unsigned long __read_pending(struct kvm_vcpu *vcpu,
+				    gpa_t addr, unsigned int len,
+				    bool is_user)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	u32 value = 0;
@ -239,6 +240,15 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 		unsigned long flags;
 		bool val;

+		/*
+		 * When used from userspace with a GICv3 model:
+		 *
+		 * Pending state of interrupt is latched in pending_latch
+		 * variable.  Userspace will save and restore pending state
+		 * and line_level separately.
+		 * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst
+		 * for handling of ISPENDR and ICPENDR.
+		 */
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
 			int err;
@ -248,10 +258,20 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 						    IRQCHIP_STATE_PENDING,
 						    &val);
 			WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);
-		} else if (vgic_irq_is_mapped_level(irq)) {
+		} else if (!is_user && vgic_irq_is_mapped_level(irq)) {
 			val = vgic_get_phys_line_level(irq);
 		} else {
-			val = irq_is_pending(irq);
+			switch (vcpu->kvm->arch.vgic.vgic_model) {
+			case KVM_DEV_TYPE_ARM_VGIC_V3:
+				if (is_user) {
+					val = irq->pending_latch;
+					break;
+				}
+				fallthrough;
+			default:
+				val = irq_is_pending(irq);
+				break;
+			}
 		}

 		value |= ((u32)val << i);
@ -263,6 +283,18 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 	return value;
 }

+unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
+				     gpa_t addr, unsigned int len)
+{
+	return __read_pending(vcpu, addr, len, false);
+}
+
+unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu,
+					gpa_t addr, unsigned int len)
+{
+	return __read_pending(vcpu, addr, len, true);
+}
+
 static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
 {
 	return (vgic_irq_is_sgi(irq->intid) &&
--- a/arch/arm64/kvm/vgic/vgic-mmio.h
+++ b/arch/arm64/kvm/vgic/vgic-mmio.h
@ -149,6 +149,9 @@ int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu,
 unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 				     gpa_t addr, unsigned int len);

+unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu,
+					gpa_t addr, unsigned int len);
+
 void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val);
--- a/arch/arm64/kvm/vmid.c
+++ b/arch/arm64/kvm/vmid.c
@ -66,7 +66,7 @@ static void flush_context(void)
 	 * the next context-switch, we broadcast TLB flush + I-cache
 	 * invalidation over the inner shareable domain on rollover.
 	 */
-	 kvm_call_hyp(__kvm_flush_vm_context);
+	kvm_call_hyp(__kvm_flush_vm_context);
 }

 static bool check_update_reserved_vmid(u64 vmid, u64 newvmid)
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@ -343,6 +343,7 @@ config NR_CPUS

 config NUMA
 	bool "NUMA Support"
+	select SMP
 	select ACPI_NUMA if ACPI
 	help
 	  Say Y to compile the kernel with NUMA (Non-Uniform Memory Access)
--- a/arch/loongarch/include/asm/hardirq.h
+++ b/arch/loongarch/include/asm/hardirq.h
@ -19,7 +19,7 @@ typedef struct {
 	unsigned int __softirq_pending;
 } ____cacheline_aligned irq_cpustat_t;

-DECLARE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat);
+DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);

 #define __ARCH_IRQ_STAT

--- a/arch/loongarch/include/asm/percpu.h
+++ b/arch/loongarch/include/asm/percpu.h
@ -6,6 +6,7 @@
 #define __ASM_PERCPU_H

 #include <asm/cmpxchg.h>
+#include <asm/loongarch.h>

 /* Use r21 for fast access */
 register unsigned long __my_cpu_offset __asm__("$r21");
--- a/arch/loongarch/include/asm/smp.h
+++ b/arch/loongarch/include/asm/smp.h
@ -9,10 +9,16 @@
 #include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/linkage.h>
-#include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/cpumask.h>

+extern int smp_num_siblings;
+extern int num_processors;
+extern int disabled_cpus;
+extern cpumask_t cpu_sibling_map[];
+extern cpumask_t cpu_core_map[];
+extern cpumask_t cpu_foreign_map[];
+
 void loongson3_smp_setup(void);
 void loongson3_prepare_cpus(unsigned int max_cpus);
 void loongson3_boot_secondary(int cpu, struct task_struct *idle);
@ -25,26 +31,11 @@ int loongson3_cpu_disable(void);
 void loongson3_cpu_die(unsigned int cpu);
 #endif

-#ifdef CONFIG_SMP
-
 static inline void plat_smp_setup(void)
 {
 	loongson3_smp_setup();
 }

-#else /* !CONFIG_SMP */
-
-static inline void plat_smp_setup(void) { }
-
-#endif /* !CONFIG_SMP */
-
-extern int smp_num_siblings;
-extern int num_processors;
-extern int disabled_cpus;
-extern cpumask_t cpu_sibling_map[];
-extern cpumask_t cpu_core_map[];
-extern cpumask_t cpu_foreign_map[];
-
 static inline int raw_smp_processor_id(void)
 {
 #if defined(__VDSO__)
--- a/arch/loongarch/include/asm/timex.h
+++ b/arch/loongarch/include/asm/timex.h
@ -12,13 +12,6 @@
 #include <asm/cpu.h>
 #include <asm/cpu-features.h>

-/*
- * Standard way to access the cycle counter.
- * Currently only used on SMP for scheduling.
- *
- * We know that all SMP capable CPUs have cycle counters.
- */
-
 typedef unsigned long cycles_t;

 #define get_cycles get_cycles
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@ -138,6 +138,7 @@ void __init acpi_boot_table_init(void)
 	}
 }

+#ifdef CONFIG_SMP
 static int set_processor_mask(u32 id, u32 flags)
 {

@ -166,15 +167,18 @@ static int set_processor_mask(u32 id, u32 flags)

 	return cpu;
 }
+#endif

 static void __init acpi_process_madt(void)
 {
+#ifdef CONFIG_SMP
 	int i;

 	for (i = 0; i < NR_CPUS; i++) {
 		__cpu_number_map[i] = -1;
 		__cpu_logical_map[i] = -1;
 	}
+#endif

 	loongson_sysconf.nr_cpus = num_processors;
 }
--- a/arch/loongarch/kernel/cacheinfo.c
+++ b/arch/loongarch/kernel/cacheinfo.c
@ -4,6 +4,7 @@
 *
 * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
 */
+#include <asm/cpu-info.h>
 #include <linux/cacheinfo.h>

 /* Populates leaf and increments to next leaf */
--- a/arch/loongarch/kernel/irq.c
+++ b/arch/loongarch/kernel/irq.c
@ -22,6 +22,8 @@
 #include <asm/setup.h>

 DEFINE_PER_CPU(unsigned long, irq_stack);
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);

 struct irq_domain *cpu_domain;
 struct irq_domain *liointc_domain;
@ -56,8 +58,11 @@ int arch_show_interrupts(struct seq_file *p, int prec)

 void __init init_IRQ(void)
 {
-	int i, r, ipi_irq;
+	int i;
+#ifdef CONFIG_SMP
+	int r, ipi_irq;
 	static int ipi_dummy_dev;
+#endif
 	unsigned int order = get_order(IRQ_STACK_SIZE);
 	struct page *page;

--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@ -120,10 +120,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 /*
 * Copy architecture-specific thread state
 */
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-	unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long childksp;
+	unsigned long tls = args->tls;
+	unsigned long usp = args->stack;
+	unsigned long clone_flags = args->flags;
 	struct pt_regs *childregs, *regs = current_pt_regs();

 	childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
@ -136,12 +138,12 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	p->thread.csr_crmd = csr_read32(LOONGARCH_CSR_CRMD);
 	p->thread.csr_prmd = csr_read32(LOONGARCH_CSR_PRMD);
 	p->thread.csr_ecfg = csr_read32(LOONGARCH_CSR_ECFG);
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* kernel thread */
-		p->thread.reg23 = usp; /* fn */
-		p->thread.reg24 = kthread_arg;
 		p->thread.reg03 = childksp;
-		p->thread.reg01 = (unsigned long) ret_from_kernel_thread;
+		p->thread.reg23 = (unsigned long)args->fn;
+		p->thread.reg24 = (unsigned long)args->fn_arg;
+		p->thread.reg01 = (unsigned long)ret_from_kernel_thread;
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->csr_euen = p->thread.csr_euen;
 		childregs->csr_crmd = p->thread.csr_crmd;
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@ -39,7 +39,6 @@
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
-#include <asm/smp.h>
 #include <asm/time.h>

 #define SMBIOS_BIOSSIZE_OFFSET		0x09
@ -349,8 +348,6 @@ static void __init prefill_possible_map(void)

 	nr_cpu_ids = possible;
 }
-#else
-static inline void prefill_possible_map(void) {}
 #endif

 void __init setup_arch(char **cmdline_p)
@ -367,8 +364,10 @@ void __init setup_arch(char **cmdline_p)
 	arch_mem_init(cmdline_p);

 	resource_init();
+#ifdef CONFIG_SMP
 	plat_smp_setup();
 	prefill_possible_map();
+#endif

 	paging_init();
 }
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@ -66,8 +66,6 @@ static cpumask_t cpu_core_setup_map;

 struct secondary_data cpuboot_data;
 static DEFINE_PER_CPU(int, cpu_state);
-DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
-EXPORT_PER_CPU_SYMBOL(irq_stat);

 enum ipi_msg_type {
 	IPI_RESCHEDULE,
--- a/arch/riscv/kvm/vmid.c
+++ b/arch/riscv/kvm/vmid.c
@ -97,7 +97,7 @@ void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu)
 		 * We ran out of VMIDs so we increment vmid_version and
 		 * start assigning VMIDs from 1.
 		 *
-		 * This also means existing VMIDs assignement to all Guest
+		 * This also means existing VMIDs assignment to all Guest
 		 * instances is invalid and we have force VMID re-assignement
 		 * for all Guest instances. The Guest instances that were not
 		 * running will automatically pick-up new VMIDs because will
--- a/arch/um/drivers/virt-pci.c
+++ b/arch/um/drivers/virt-pci.c
@ -544,6 +544,8 @@ static int um_pci_init_vqs(struct um_pci_device *dev)
 	dev->cmd_vq = vqs[0];
 	dev->irq_vq = vqs[1];

+	virtio_device_ready(dev->vdev);
+
 	for (i = 0; i < NUM_IRQ_MSGS; i++) {
 		void *msg = kzalloc(MAX_IRQ_MSG_SIZE, GFP_KERNEL);

@ -587,7 +589,7 @@ static int um_pci_virtio_probe(struct virtio_device *vdev)
 	dev->irq = irq_alloc_desc(numa_node_id());
 	if (dev->irq < 0) {
 		err = dev->irq;
-		goto error;
+		goto err_reset;
 	}
 	um_pci_devices[free].dev = dev;
 	vdev->priv = dev;
@ -604,6 +606,9 @@ static int um_pci_virtio_probe(struct virtio_device *vdev)

 	um_pci_rescan();
 	return 0;
+err_reset:
+	virtio_reset_device(vdev);
+	vdev->config->del_vqs(vdev);
 error:
 	mutex_unlock(&um_pci_mtx);
 	kfree(dev);
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@ -446,5 +446,6 @@
 #define X86_BUG_TAA			X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
 #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 */

 #endif /* _ASM_X86_CPUFEATURES_H */
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@ -1047,14 +1047,77 @@ struct kvm_x86_msr_filter {
 };

 enum kvm_apicv_inhibit {
+
+	/********************************************************************/
+	/* INHIBITs that are relevant to both Intel's APICv and AMD's AVIC. */
+	/********************************************************************/
+
+	/*
+	 * APIC acceleration is disabled by a module parameter
+	 * and/or not supported in hardware.
+	 */
 	APICV_INHIBIT_REASON_DISABLE,
+
+	/*
+	 * APIC acceleration is inhibited because AutoEOI feature is
+	 * being used by a HyperV guest.
+	 */
 	APICV_INHIBIT_REASON_HYPERV,
-	APICV_INHIBIT_REASON_NESTED,
-	APICV_INHIBIT_REASON_IRQWIN,
-	APICV_INHIBIT_REASON_PIT_REINJ,
-	APICV_INHIBIT_REASON_X2APIC,
-	APICV_INHIBIT_REASON_BLOCKIRQ,
+
+	/*
+	 * APIC acceleration is inhibited because the userspace didn't yet
+	 * enable the kernel/split irqchip.
+	 */
 	APICV_INHIBIT_REASON_ABSENT,
+
+	/* APIC acceleration is inhibited because KVM_GUESTDBG_BLOCKIRQ
+	 * (out of band, debug measure of blocking all interrupts on this vCPU)
+	 * was enabled, to avoid AVIC/APICv bypassing it.
+	 */
+	APICV_INHIBIT_REASON_BLOCKIRQ,
+
+	/*
+	 * For simplicity, the APIC acceleration is inhibited
+	 * first time either APIC ID or APIC base are changed by the guest
+	 * from their reset values.
+	 */
+	APICV_INHIBIT_REASON_APIC_ID_MODIFIED,
+	APICV_INHIBIT_REASON_APIC_BASE_MODIFIED,
+
+	/******************************************************/
+	/* INHIBITs that are relevant only to the AMD's AVIC. */
+	/******************************************************/
+
+	/*
+	 * AVIC is inhibited on a vCPU because it runs a nested guest.
+	 *
+	 * This is needed because unlike APICv, the peers of this vCPU
+	 * cannot use the doorbell mechanism to signal interrupts via AVIC when
+	 * a vCPU runs nested.
+	 */
+	APICV_INHIBIT_REASON_NESTED,
+
+	/*
+	 * On SVM, the wait for the IRQ window is implemented with pending vIRQ,
+	 * which cannot be injected when the AVIC is enabled, thus AVIC
+	 * is inhibited while KVM waits for IRQ window.
+	 */
+	APICV_INHIBIT_REASON_IRQWIN,
+
+	/*
+	 * PIT (i8254) 're-inject' mode, relies on EOI intercept,
+	 * which AVIC doesn't support for edge triggered interrupts.
+	 */
+	APICV_INHIBIT_REASON_PIT_REINJ,
+
+	/*
+	 * AVIC is inhibited because the guest has x2apic in its CPUID.
+	 */
+	APICV_INHIBIT_REASON_X2APIC,
+
+	/*
+	 * AVIC is disabled because SEV doesn't support it.
+	 */
 	APICV_INHIBIT_REASON_SEV,
 };

--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@ -116,6 +116,30 @@
 						 * Not susceptible to
 						 * TSX Async Abort (TAA) vulnerabilities.
 						 */
+#define ARCH_CAP_SBDR_SSDP_NO		BIT(13)	/*
+						 * Not susceptible to SBDR and SSDP
+						 * variants of Processor MMIO stale data
+						 * vulnerabilities.
+						 */
+#define ARCH_CAP_FBSDP_NO		BIT(14)	/*
+						 * Not susceptible to FBSDP variant of
+						 * Processor MMIO stale data
+						 * vulnerabilities.
+						 */
+#define ARCH_CAP_PSDP_NO		BIT(15)	/*
+						 * Not susceptible to PSDP variant of
+						 * Processor MMIO stale data
+						 * vulnerabilities.
+						 */
+#define ARCH_CAP_FB_CLEAR		BIT(17)	/*
+						 * VERW clears CPU fill buffer
+						 * even on MDS_NO CPUs.
+						 */
+#define ARCH_CAP_FB_CLEAR_CTRL		BIT(18)	/*
+						 * MSR_IA32_MCU_OPT_CTRL[FB_CLEAR_DIS]
+						 * bit available to control VERW
+						 * behavior.
+						 */

 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
@ -133,6 +157,7 @@
 #define MSR_IA32_MCU_OPT_CTRL		0x00000123
 #define RNGDS_MITG_DIS			BIT(0)	/* SRBDS support */
 #define RTM_ALLOW			BIT(1)	/* TSX development mode */
+#define FB_CLEAR_DIS			BIT(3)	/* CPU Fill buffer clear disable */

 #define MSR_IA32_SYSENTER_CS		0x00000174
 #define MSR_IA32_SYSENTER_ESP		0x00000175
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@ -269,6 +269,8 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear);

 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);

+DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
+
 #include <asm/segment.h>

 /**
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@ -41,8 +41,10 @@ static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
-static void __init mds_print_mitigation(void);
+static void __init md_clear_update_mitigation(void);
+static void __init md_clear_select_mitigation(void);
 static void __init taa_select_mitigation(void);
+static void __init mmio_select_mitigation(void);
 static void __init srbds_select_mitigation(void);
 static void __init l1d_flush_select_mitigation(void);

@ -85,6 +87,10 @@ EXPORT_SYMBOL_GPL(mds_idle_clear);
 */
 DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);

+/* Controls CPU Fill buffer clear before KVM guest MMIO accesses */
+DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear);
+EXPORT_SYMBOL_GPL(mmio_stale_data_clear);
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@ -117,17 +123,10 @@ void __init check_bugs(void)
 	spectre_v2_select_mitigation();
 	ssb_select_mitigation();
 	l1tf_select_mitigation();
-	mds_select_mitigation();
-	taa_select_mitigation();
+	md_clear_select_mitigation();
 	srbds_select_mitigation();
 	l1d_flush_select_mitigation();

-	/*
-	 * As MDS and TAA mitigations are inter-related, print MDS
-	 * mitigation until after TAA mitigation selection is done.
-	 */
-	mds_print_mitigation();
-
 	arch_smt_update();

 #ifdef CONFIG_X86_32
@ -267,14 +266,6 @@ static void __init mds_select_mitigation(void)
 	}
 }

-static void __init mds_print_mitigation(void)
-{
-	if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off())
-		return;
-
-	pr_info("%s\n", mds_strings[mds_mitigation]);
-}
-
 static int __init mds_cmdline(char *str)
 {
 	if (!boot_cpu_has_bug(X86_BUG_MDS))
@ -329,7 +320,7 @@ static void __init taa_select_mitigation(void)
 	/* TSX previously disabled by tsx=off */
 	if (!boot_cpu_has(X86_FEATURE_RTM)) {
 		taa_mitigation = TAA_MITIGATION_TSX_DISABLED;
-		goto out;
+		return;
 	}

 	if (cpu_mitigations_off()) {
@ -343,7 +334,7 @@ static void __init taa_select_mitigation(void)
 	 */
 	if (taa_mitigation == TAA_MITIGATION_OFF &&
 	    mds_mitigation == MDS_MITIGATION_OFF)
-		goto out;
+		return;

 	if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
 		taa_mitigation = TAA_MITIGATION_VERW;
@ -375,18 +366,6 @@ static void __init taa_select_mitigation(void)

 	if (taa_nosmt || cpu_mitigations_auto_nosmt())
 		cpu_smt_disable(false);
-
-	/*
-	 * Update MDS mitigation, if necessary, as the mds_user_clear is
-	 * now enabled for TAA mitigation.
-	 */
-	if (mds_mitigation == MDS_MITIGATION_OFF &&
-	    boot_cpu_has_bug(X86_BUG_MDS)) {
-		mds_mitigation = MDS_MITIGATION_FULL;
-		mds_select_mitigation();
-	}
-out:
-	pr_info("%s\n", taa_strings[taa_mitigation]);
 }

 static int __init tsx_async_abort_parse_cmdline(char *str)
@ -410,6 +389,151 @@ static int __init tsx_async_abort_parse_cmdline(char *str)
 }
 early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);

+#undef pr_fmt
+#define pr_fmt(fmt)	"MMIO Stale Data: " fmt
+
+enum mmio_mitigations {
+	MMIO_MITIGATION_OFF,
+	MMIO_MITIGATION_UCODE_NEEDED,
+	MMIO_MITIGATION_VERW,
+};
+
+/* Default mitigation for Processor MMIO Stale Data vulnerabilities */
+static enum mmio_mitigations mmio_mitigation __ro_after_init = MMIO_MITIGATION_VERW;
+static bool mmio_nosmt __ro_after_init = false;
+
+static const char * const mmio_strings[] = {
+	[MMIO_MITIGATION_OFF]		= "Vulnerable",
+	[MMIO_MITIGATION_UCODE_NEEDED]	= "Vulnerable: Clear CPU buffers attempted, no microcode",
+	[MMIO_MITIGATION_VERW]		= "Mitigation: Clear CPU buffers",
+};
+
+static void __init mmio_select_mitigation(void)
+{
+	u64 ia32_cap;
+
+	if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
+	    cpu_mitigations_off()) {
+		mmio_mitigation = MMIO_MITIGATION_OFF;
+		return;
+	}
+
+	if (mmio_mitigation == MMIO_MITIGATION_OFF)
+		return;
+
+	ia32_cap = x86_read_arch_cap_msr();
+
+	/*
+	 * Enable CPU buffer clear mitigation for host and VMM, if also affected
+	 * by MDS or TAA. Otherwise, enable mitigation for VMM only.
+	 */
+	if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) &&
+					      boot_cpu_has(X86_FEATURE_RTM)))
+		static_branch_enable(&mds_user_clear);
+	else
+		static_branch_enable(&mmio_stale_data_clear);
+
+	/*
+	 * If Processor-MMIO-Stale-Data bug is present and Fill Buffer data can
+	 * be propagated to uncore buffers, clearing the Fill buffers on idle
+	 * is required irrespective of SMT state.
+	 */
+	if (!(ia32_cap & ARCH_CAP_FBSDP_NO))
+		static_branch_enable(&mds_idle_clear);
+
+	/*
+	 * Check if the system has the right microcode.
+	 *
+	 * CPU Fill buffer clear mitigation is enumerated by either an explicit
+	 * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS
+	 * affected systems.
+	 */
+	if ((ia32_cap & ARCH_CAP_FB_CLEAR) ||
+	    (boot_cpu_has(X86_FEATURE_MD_CLEAR) &&
+	     boot_cpu_has(X86_FEATURE_FLUSH_L1D) &&
+	     !(ia32_cap & ARCH_CAP_MDS_NO)))
+		mmio_mitigation = MMIO_MITIGATION_VERW;
+	else
+		mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED;
+
+	if (mmio_nosmt || cpu_mitigations_auto_nosmt())
+		cpu_smt_disable(false);
+}
+
+static int __init mmio_stale_data_parse_cmdline(char *str)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
+		return 0;
+
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off")) {
+		mmio_mitigation = MMIO_MITIGATION_OFF;
+	} else if (!strcmp(str, "full")) {
+		mmio_mitigation = MMIO_MITIGATION_VERW;
+	} else if (!strcmp(str, "full,nosmt")) {
+		mmio_mitigation = MMIO_MITIGATION_VERW;
+		mmio_nosmt = true;
+	}
+
+	return 0;
+}
+early_param("mmio_stale_data", mmio_stale_data_parse_cmdline);
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "" fmt
+
+static void __init md_clear_update_mitigation(void)
+{
+	if (cpu_mitigations_off())
+		return;
+
+	if (!static_key_enabled(&mds_user_clear))
+		goto out;
+
+	/*
+	 * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data
+	 * mitigation, if necessary.
+	 */
+	if (mds_mitigation == MDS_MITIGATION_OFF &&
+	    boot_cpu_has_bug(X86_BUG_MDS)) {
+		mds_mitigation = MDS_MITIGATION_FULL;
+		mds_select_mitigation();
+	}
+	if (taa_mitigation == TAA_MITIGATION_OFF &&
+	    boot_cpu_has_bug(X86_BUG_TAA)) {
+		taa_mitigation = TAA_MITIGATION_VERW;
+		taa_select_mitigation();
+	}
+	if (mmio_mitigation == MMIO_MITIGATION_OFF &&
+	    boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) {
+		mmio_mitigation = MMIO_MITIGATION_VERW;
+		mmio_select_mitigation();
+	}
+out:
+	if (boot_cpu_has_bug(X86_BUG_MDS))
+		pr_info("MDS: %s\n", mds_strings[mds_mitigation]);
+	if (boot_cpu_has_bug(X86_BUG_TAA))
+		pr_info("TAA: %s\n", taa_strings[taa_mitigation]);
+	if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
+		pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]);
+}
+
+static void __init md_clear_select_mitigation(void)
+{
+	mds_select_mitigation();
+	taa_select_mitigation();
+	mmio_select_mitigation();
+
+	/*
+	 * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update
+	 * and print their mitigation after MDS, TAA and MMIO Stale Data
+	 * mitigation selection is done.
+	 */
+	md_clear_update_mitigation();
+}
+
 #undef pr_fmt
 #define pr_fmt(fmt)	"SRBDS: " fmt

@ -478,11 +602,13 @@ static void __init srbds_select_mitigation(void)
 		return;

 	/*
-	 * Check to see if this is one of the MDS_NO systems supporting
-	 * TSX that are only exposed to SRBDS when TSX is enabled.
+	 * Check to see if this is one of the MDS_NO systems supporting TSX that
+	 * are only exposed to SRBDS when TSX is enabled or when CPU is affected
+	 * by Processor MMIO Stale Data vulnerability.
 	 */
 	ia32_cap = x86_read_arch_cap_msr();
-	if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM))
+	if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) &&
+	    !boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
 		srbds_mitigation = SRBDS_MITIGATION_TSX_OFF;
 	else if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR;
@ -1116,6 +1242,8 @@ static void update_indir_branch_cond(void)
 /* Update the static key controlling the MDS CPU buffer clear in idle */
 static void update_mds_branch_idle(void)
 {
+	u64 ia32_cap = x86_read_arch_cap_msr();
+
 	/*
 	 * Enable the idle clearing if SMT is active on CPUs which are
 	 * affected only by MSBDS and not any other MDS variant.
@ -1127,14 +1255,17 @@ static void update_mds_branch_idle(void)
 	if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY))
 		return;

-	if (sched_smt_active())
+	if (sched_smt_active()) {
 		static_branch_enable(&mds_idle_clear);
-	else
+	} else if (mmio_mitigation == MMIO_MITIGATION_OFF ||
+		   (ia32_cap & ARCH_CAP_FBSDP_NO)) {
 		static_branch_disable(&mds_idle_clear);
+	}
 }

 #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
 #define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n"
+#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n"

 void cpu_bugs_smt_update(void)
 {
@ -1179,6 +1310,16 @@ void cpu_bugs_smt_update(void)
 		break;
 	}

+	switch (mmio_mitigation) {
+	case MMIO_MITIGATION_VERW:
+	case MMIO_MITIGATION_UCODE_NEEDED:
+		if (sched_smt_active())
+			pr_warn_once(MMIO_MSG_SMT);
+		break;
+	case MMIO_MITIGATION_OFF:
+		break;
+	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }

@ -1781,6 +1922,20 @@ static ssize_t tsx_async_abort_show_state(char *buf)
 		       sched_smt_active() ? "vulnerable" : "disabled");
 }

+static ssize_t mmio_stale_data_show_state(char *buf)
+{
+	if (mmio_mitigation == MMIO_MITIGATION_OFF)
+		return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]);
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		return sysfs_emit(buf, "%s; SMT Host state unknown\n",
+				  mmio_strings[mmio_mitigation]);
+	}
+
+	return sysfs_emit(buf, "%s; SMT %s\n", mmio_strings[mmio_mitigation],
+			  sched_smt_active() ? "vulnerable" : "disabled");
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled))
@ -1881,6 +2036,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_SRBDS:
 		return srbds_show_state(buf);

+	case X86_BUG_MMIO_STALE_DATA:
+		return mmio_stale_data_show_state(buf);
+
 	default:
 		break;
 	}
@ -1932,4 +2090,9 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS);
 }
+
+ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
+}
 #endif
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@ -1211,18 +1211,42 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 					    X86_FEATURE_ANY, issues)

 #define SRBDS		BIT(0)
+/* CPU is affected by X86_BUG_MMIO_STALE_DATA */
+#define MMIO		BIT(1)
+/* CPU is affected by Shared Buffers Data Sampling (SBDS), a variant of X86_BUG_MMIO_STALE_DATA */
+#define MMIO_SBDS	BIT(2)

 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPPINGS(IVYBRIDGE,	X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(HASWELL,		X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(HASWELL_L,	X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(HASWELL_G,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(HASWELL_X,	BIT(2) | BIT(4),		MMIO),
+	VULNBL_INTEL_STEPPINGS(BROADWELL_D,	X86_STEPPINGS(0x3, 0x5),	MMIO),
 	VULNBL_INTEL_STEPPINGS(BROADWELL_G,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(BROADWELL_X,	X86_STEPPING_ANY,		MMIO),
 	VULNBL_INTEL_STEPPINGS(BROADWELL,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_L,	X86_STEPPINGS(0x3, 0x3),	SRBDS | MMIO),
 	VULNBL_INTEL_STEPPINGS(SKYLAKE_L,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_X,	BIT(3) | BIT(4) | BIT(6) |
+						BIT(7) | BIT(0xB),              MMIO),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE,		X86_STEPPINGS(0x3, 0x3),	SRBDS | MMIO),
 	VULNBL_INTEL_STEPPINGS(SKYLAKE,		X86_STEPPING_ANY,		SRBDS),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPINGS(0x0, 0xC),	SRBDS),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPINGS(0x0, 0xD),	SRBDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPINGS(0x9, 0xC),	SRBDS | MMIO),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPINGS(0x0, 0x8),	SRBDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPINGS(0x9, 0xD),	SRBDS | MMIO),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPINGS(0x0, 0x8),	SRBDS),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_L,	X86_STEPPINGS(0x5, 0x5),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_D,	X86_STEPPINGS(0x1, 0x1),	MMIO),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_X,	X86_STEPPINGS(0x4, 0x6),	MMIO),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE,	BIT(2) | BIT(3) | BIT(5),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPINGS(0x1, 0x1),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPINGS(0x0, 0x0),	MMIO),
+	VULNBL_INTEL_STEPPINGS(LAKEFIELD,	X86_STEPPINGS(0x1, 0x1),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(ROCKETLAKE,	X86_STEPPINGS(0x1, 0x1),	MMIO),
+	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT,	X86_STEPPINGS(0x1, 0x1),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D,	X86_STEPPING_ANY,		MMIO),
+	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L,	X86_STEPPINGS(0x0, 0x0),	MMIO | MMIO_SBDS),
 	{}
 };

@ -1243,6 +1267,13 @@ u64 x86_read_arch_cap_msr(void)
 	return ia32_cap;
 }

+static bool arch_cap_mmio_immune(u64 ia32_cap)
+{
+	return (ia32_cap & ARCH_CAP_FBSDP_NO &&
+		ia32_cap & ARCH_CAP_PSDP_NO &&
+		ia32_cap & ARCH_CAP_SBDR_SSDP_NO);
+}
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = x86_read_arch_cap_msr();
@ -1296,12 +1327,27 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	/*
 	 * SRBDS affects CPUs which support RDRAND or RDSEED and are listed
 	 * in the vulnerability blacklist.
+	 *
+	 * Some of the implications and mitigation of Shared Buffers Data
+	 * Sampling (SBDS) are similar to SRBDS. Give SBDS same treatment as
+	 * SRBDS.
 	 */
 	if ((cpu_has(c, X86_FEATURE_RDRAND) ||
 	     cpu_has(c, X86_FEATURE_RDSEED)) &&
-	    cpu_matches(cpu_vuln_blacklist, SRBDS))
+	    cpu_matches(cpu_vuln_blacklist, SRBDS | MMIO_SBDS))
 		    setup_force_cpu_bug(X86_BUG_SRBDS);

+	/*
+	 * Processor MMIO Stale Data bug enumeration
+	 *
+	 * Affected CPU list is generally enough to enumerate the vulnerability,
+	 * but for virtualization case check for ARCH_CAP MSR bits also, VMM may
+	 * not want the guest to enumerate the bug.
+	 */
+	if (cpu_matches(cpu_vuln_blacklist, MMIO) &&
+	    !arch_cap_mmio_immune(ia32_cap))
+		setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;

--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@ -2039,6 +2039,19 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
 	}
 }

+static void kvm_lapic_xapic_id_updated(struct kvm_lapic *apic)
+{
+	struct kvm *kvm = apic->vcpu->kvm;
+
+	if (KVM_BUG_ON(apic_x2apic_mode(apic), kvm))
+		return;
+
+	if (kvm_xapic_id(apic) == apic->vcpu->vcpu_id)
+		return;
+
+	kvm_set_apicv_inhibit(apic->vcpu->kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED);
+}
+
 static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 {
 	int ret = 0;
@ -2047,10 +2060,12 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)

 	switch (reg) {
 	case APIC_ID:		/* Local APIC ID */
-		if (!apic_x2apic_mode(apic))
+		if (!apic_x2apic_mode(apic)) {
 			kvm_apic_set_xapic_id(apic, val >> 24);
-		else
+			kvm_lapic_xapic_id_updated(apic);
+		} else {
 			ret = 1;
+		}
 		break;

 	case APIC_TASKPRI:
@ -2336,8 +2351,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 			     MSR_IA32_APICBASE_BASE;

 	if ((value & MSR_IA32_APICBASE_ENABLE) &&
-	     apic->base_address != APIC_DEFAULT_PHYS_BASE)
-		pr_warn_once("APIC base relocation is unsupported by KVM");
+	     apic->base_address != APIC_DEFAULT_PHYS_BASE) {
+		kvm_set_apicv_inhibit(apic->vcpu->kvm,
+				      APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);
+	}
 }

 void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
@ -2648,6 +2665,8 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
 			icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR);
 			__kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32);
 		}
+	} else {
+		kvm_lapic_xapic_id_updated(vcpu->arch.apic);
 	}

 	return 0;
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@ -3411,7 +3411,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 			root = mmu_alloc_root(vcpu, i << (30 - PAGE_SHIFT),
 					      i << 30, PT32_ROOT_LEVEL, true);
 			mmu->pae_root[i] = root | PT_PRESENT_MASK |
-					   shadow_me_mask;
+					   shadow_me_value;
 		}
 		mmu->root.hpa = __pa(mmu->pae_root);
 	} else {
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@ -291,58 +291,91 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu)
 static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source,
 				       u32 icrl, u32 icrh, u32 index)
 {
-	u32 dest, apic_id;
-	struct kvm_vcpu *vcpu;
+	u32 l1_physical_id, dest;
+	struct kvm_vcpu *target_vcpu;
 	int dest_mode = icrl & APIC_DEST_MASK;
 	int shorthand = icrl & APIC_SHORT_MASK;
 	struct kvm_svm *kvm_svm = to_kvm_svm(kvm);
-	u32 *avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page);

 	if (shorthand != APIC_DEST_NOSHORT)
 		return -EINVAL;

-	/*
-	 * The AVIC incomplete IPI #vmexit info provides index into
-	 * the physical APIC ID table, which can be used to derive
-	 * guest physical APIC ID.
-	 */
-	if (dest_mode == APIC_DEST_PHYSICAL) {
-		apic_id = index;
-	} else {
-		if (!apic_x2apic_mode(source)) {
-			/* For xAPIC logical mode, the index is for logical APIC table. */
-			apic_id = avic_logical_id_table[index] & 0x1ff;
-		} else {
-			return -EINVAL;
-		}
-	}
-
-	/*
-	 * Assuming vcpu ID is the same as physical apic ID,
-	 * and use it to retrieve the target vCPU.
-	 */
-	vcpu = kvm_get_vcpu_by_id(kvm, apic_id);
-	if (!vcpu)
-		return -EINVAL;
-
-	if (apic_x2apic_mode(vcpu->arch.apic))
+	if (apic_x2apic_mode(source))
 		dest = icrh;
 	else
 		dest = GET_APIC_DEST_FIELD(icrh);

-	/*
-	 * Try matching the destination APIC ID with the vCPU.
-	 */
-	if (kvm_apic_match_dest(vcpu, source, shorthand, dest, dest_mode)) {
-		vcpu->arch.apic->irr_pending = true;
-		svm_complete_interrupt_delivery(vcpu,
-						icrl & APIC_MODE_MASK,
-						icrl & APIC_INT_LEVELTRIG,
-						icrl & APIC_VECTOR_MASK);
-		return 0;
+	if (dest_mode == APIC_DEST_PHYSICAL) {
+		/* broadcast destination, use slow path */
+		if (apic_x2apic_mode(source) && dest == X2APIC_BROADCAST)
+			return -EINVAL;
+		if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST)
+			return -EINVAL;
+
+		l1_physical_id = dest;
+
+		if (WARN_ON_ONCE(l1_physical_id != index))
+			return -EINVAL;
+
+	} else {
+		u32 bitmap, cluster;
+		int logid_index;
+
+		if (apic_x2apic_mode(source)) {
+			/* 16 bit dest mask, 16 bit cluster id */
+			bitmap = dest & 0xFFFF0000;
+			cluster = (dest >> 16) << 4;
+		} else if (kvm_lapic_get_reg(source, APIC_DFR) == APIC_DFR_FLAT) {
+			/* 8 bit dest mask*/
+			bitmap = dest;
+			cluster = 0;
+		} else {
+			/* 4 bit desk mask, 4 bit cluster id */
+			bitmap = dest & 0xF;
+			cluster = (dest >> 4) << 2;
+		}
+
+		if (unlikely(!bitmap))
+			/* guest bug: nobody to send the logical interrupt to */
+			return 0;
+
+		if (!is_power_of_2(bitmap))
+			/* multiple logical destinations, use slow path */
+			return -EINVAL;
+
+		logid_index = cluster + __ffs(bitmap);
+
+		if (apic_x2apic_mode(source)) {
+			l1_physical_id = logid_index;
+		} else {
+			u32 *avic_logical_id_table =
+				page_address(kvm_svm->avic_logical_id_table_page);
+
+			u32 logid_entry = avic_logical_id_table[logid_index];
+
+			if (WARN_ON_ONCE(index != logid_index))
+				return -EINVAL;
+
+			/* guest bug: non existing/reserved logical destination */
+			if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK)))
+				return 0;
+
+			l1_physical_id = logid_entry &
+					 AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK;
+		}
 	}

-	return -EINVAL;
+	target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id);
+	if (unlikely(!target_vcpu))
+		/* guest bug: non existing vCPU is a target of this IPI*/
+		return 0;
+
+	target_vcpu->arch.apic->irr_pending = true;
+	svm_complete_interrupt_delivery(target_vcpu,
+					icrl & APIC_MODE_MASK,
+					icrl & APIC_INT_LEVELTRIG,
+					icrl & APIC_VECTOR_MASK);
+	return 0;
 }

 static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source,
@ -508,35 +541,6 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 	return ret;
 }

-static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu)
-{
-	u64 *old, *new;
-	struct vcpu_svm *svm = to_svm(vcpu);
-	u32 id = kvm_xapic_id(vcpu->arch.apic);
-
-	if (vcpu->vcpu_id == id)
-		return 0;
-
-	old = avic_get_physical_id_entry(vcpu, vcpu->vcpu_id);
-	new = avic_get_physical_id_entry(vcpu, id);
-	if (!new || !old)
-		return 1;
-
-	/* We need to move physical_id_entry to new offset */
-	*new = *old;
-	*old = 0ULL;
-	to_svm(vcpu)->avic_physical_id_cache = new;
-
-	/*
-	 * Also update the guest physical APIC ID in the logical
-	 * APIC ID table entry if already setup the LDR.
-	 */
-	if (svm->ldr_reg)
-		avic_handle_ldr_update(vcpu);
-
-	return 0;
-}
-
 static void avic_handle_dfr_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@ -555,10 +559,6 @@ static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu)
 				AVIC_UNACCEL_ACCESS_OFFSET_MASK;

 	switch (offset) {
-	case APIC_ID:
-		if (avic_handle_apic_id_update(vcpu))
-			return 0;
-		break;
 	case APIC_LDR:
 		if (avic_handle_ldr_update(vcpu))
 			return 0;
@ -650,8 +650,6 @@ int avic_init_vcpu(struct vcpu_svm *svm)

 void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 {
-	if (avic_handle_apic_id_update(vcpu) != 0)
-		return;
 	avic_handle_dfr_update(vcpu);
 	avic_handle_ldr_update(vcpu);
 }
@ -910,7 +908,9 @@ bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
 			  BIT(APICV_INHIBIT_REASON_PIT_REINJ) |
 			  BIT(APICV_INHIBIT_REASON_X2APIC) |
 			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |
-			  BIT(APICV_INHIBIT_REASON_SEV);
+			  BIT(APICV_INHIBIT_REASON_SEV)      |
+			  BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |
+			  BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);

 	return supported & BIT(reason);
 }
@ -946,7 +946,7 @@ out:
 	return ret;
 }

-void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	u64 entry;
 	int h_physical_id = kvm_cpu_get_apicid(cpu);
@ -978,7 +978,7 @@ void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
 }

-void __avic_vcpu_put(struct kvm_vcpu *vcpu)
+void avic_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	u64 entry;
 	struct vcpu_svm *svm = to_svm(vcpu);
@ -997,25 +997,6 @@ void __avic_vcpu_put(struct kvm_vcpu *vcpu)
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
 }

-static void avic_vcpu_load(struct kvm_vcpu *vcpu)
-{
-	int cpu = get_cpu();
-
-	WARN_ON(cpu != vcpu->cpu);
-
-	__avic_vcpu_load(vcpu, cpu);
-
-	put_cpu();
-}
-
-static void avic_vcpu_put(struct kvm_vcpu *vcpu)
-{
-	preempt_disable();
-
-	__avic_vcpu_put(vcpu);
-
-	preempt_enable();
-}

 void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 {
@ -1042,7 +1023,7 @@ void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 	vmcb_mark_dirty(vmcb, VMCB_AVIC);

 	if (activated)
-		avic_vcpu_load(vcpu);
+		avic_vcpu_load(vcpu, vcpu->cpu);
 	else
 		avic_vcpu_put(vcpu);

@ -1075,5 +1056,5 @@ void avic_vcpu_unblocking(struct kvm_vcpu *vcpu)
 	if (!kvm_vcpu_apicv_active(vcpu))
 		return;

-	avic_vcpu_load(vcpu);
+	avic_vcpu_load(vcpu, vcpu->cpu);
 }
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@ -616,6 +616,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	struct vmcb *vmcb01 = svm->vmcb01.ptr;
 	struct vmcb *vmcb02 = svm->nested.vmcb02.ptr;
+	u32 pause_count12;
+	u32 pause_thresh12;

 	/*
 	 * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2,
@ -671,27 +673,25 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 	if (!nested_vmcb_needs_vls_intercept(svm))
 		vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;

+	pause_count12 = svm->pause_filter_enabled ? svm->nested.ctl.pause_filter_count : 0;
+	pause_thresh12 = svm->pause_threshold_enabled ? svm->nested.ctl.pause_filter_thresh : 0;
 	if (kvm_pause_in_guest(svm->vcpu.kvm)) {
-		/* use guest values since host doesn't use them */
-		vmcb02->control.pause_filter_count =
-				svm->pause_filter_enabled ?
-				svm->nested.ctl.pause_filter_count : 0;
+		/* use guest values since host doesn't intercept PAUSE */
+		vmcb02->control.pause_filter_count = pause_count12;
+		vmcb02->control.pause_filter_thresh = pause_thresh12;

-		vmcb02->control.pause_filter_thresh =
-				svm->pause_threshold_enabled ?
-				svm->nested.ctl.pause_filter_thresh : 0;
-
-	} else if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) {
-		/* use host values when guest doesn't use them */
+	} else {
+		/* start from host values otherwise */
 		vmcb02->control.pause_filter_count = vmcb01->control.pause_filter_count;
 		vmcb02->control.pause_filter_thresh = vmcb01->control.pause_filter_thresh;
-	} else {
-		/*
-		 * Intercept every PAUSE otherwise and
-		 * ignore both host and guest values
-		 */
-		vmcb02->control.pause_filter_count = 0;
-		vmcb02->control.pause_filter_thresh = 0;
+
+		/* ... but ensure filtering is disabled if so requested.  */
+		if (vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) {
+			if (!pause_count12)
+				vmcb02->control.pause_filter_count = 0;
+			if (!pause_thresh12)
+				vmcb02->control.pause_filter_thresh = 0;
+		}
 	}

 	nested_svm_transition_tlb_flush(vcpu);
@ -951,8 +951,11 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	vmcb12->control.event_inj         = svm->nested.ctl.event_inj;
 	vmcb12->control.event_inj_err     = svm->nested.ctl.event_inj_err;

-	if (!kvm_pause_in_guest(vcpu->kvm) && vmcb02->control.pause_filter_count)
+	if (!kvm_pause_in_guest(vcpu->kvm)) {
 		vmcb01->control.pause_filter_count = vmcb02->control.pause_filter_count;
+		vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS);
+
+	}

 	nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr);

--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@ -921,7 +921,7 @@ static void grow_ple_window(struct kvm_vcpu *vcpu)
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	int old = control->pause_filter_count;

-	if (kvm_pause_in_guest(vcpu->kvm) || !old)
+	if (kvm_pause_in_guest(vcpu->kvm))
 		return;

 	control->pause_filter_count = __grow_ple_window(old,
@ -942,7 +942,7 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	int old = control->pause_filter_count;

-	if (kvm_pause_in_guest(vcpu->kvm) || !old)
+	if (kvm_pause_in_guest(vcpu->kvm))
 		return;

 	control->pause_filter_count =
@ -1400,13 +1400,13 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		indirect_branch_prediction_barrier();
 	}
 	if (kvm_vcpu_apicv_active(vcpu))
-		__avic_vcpu_load(vcpu, cpu);
+		avic_vcpu_load(vcpu, cpu);
 }

 static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	if (kvm_vcpu_apicv_active(vcpu))
-		__avic_vcpu_put(vcpu);
+		avic_vcpu_put(vcpu);

 	svm_prepare_host_switch(vcpu);

--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@ -610,8 +610,8 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb);
 int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu);
 int avic_unaccelerated_access_interception(struct kvm_vcpu *vcpu);
 int avic_init_vcpu(struct vcpu_svm *svm);
-void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
-void __avic_vcpu_put(struct kvm_vcpu *vcpu);
+void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
+void avic_vcpu_put(struct kvm_vcpu *vcpu);
 void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu);
 void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
 void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu);
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@ -229,6 +229,9 @@ static const struct {
 #define L1D_CACHE_ORDER 4
 static void *vmx_l1d_flush_pages;

+/* Control for disabling CPU Fill buffer clear */
+static bool __read_mostly vmx_fb_clear_ctrl_available;
+
 static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 {
 	struct page *page;
@ -360,6 +363,60 @@ static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
 	return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
 }

+static void vmx_setup_fb_clear_ctrl(void)
+{
+	u64 msr;
+
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) &&
+	    !boot_cpu_has_bug(X86_BUG_MDS) &&
+	    !boot_cpu_has_bug(X86_BUG_TAA)) {
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
+		if (msr & ARCH_CAP_FB_CLEAR_CTRL)
+			vmx_fb_clear_ctrl_available = true;
+	}
+}
+
+static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx)
+{
+	u64 msr;
+
+	if (!vmx->disable_fb_clear)
+		return;
+
+	rdmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
+	msr |= FB_CLEAR_DIS;
+	wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
+	/* Cache the MSR value to avoid reading it later */
+	vmx->msr_ia32_mcu_opt_ctrl = msr;
+}
+
+static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
+{
+	if (!vmx->disable_fb_clear)
+		return;
+
+	vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS;
+	wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl);
+}
+
+static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
+{
+	vmx->disable_fb_clear = vmx_fb_clear_ctrl_available;
+
+	/*
+	 * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS
+	 * at VMEntry. Skip the MSR read/write when a guest has no use case to
+	 * execute VERW.
+	 */
+	if ((vcpu->arch.arch_capabilities & ARCH_CAP_FB_CLEAR) ||
+	   ((vcpu->arch.arch_capabilities & ARCH_CAP_MDS_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_TAA_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_PSDP_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_FBSDP_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_SBDR_SSDP_NO)))
+		vmx->disable_fb_clear = false;
+}
+
 static const struct kernel_param_ops vmentry_l1d_flush_ops = {
 	.set = vmentry_l1d_flush_set,
 	.get = vmentry_l1d_flush_get,
@ -2252,6 +2309,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			ret = kvm_set_msr_common(vcpu, msr_info);
 	}

+	/* FB_CLEAR may have changed, also update the FB_CLEAR_DIS behavior */
+	if (msr_index == MSR_IA32_ARCH_CAPABILITIES)
+		vmx_update_fb_clear_dis(vcpu, vmx);
+
 	return ret;
 }

@ -4553,6 +4614,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);

 	vpid_sync_context(vmx->vpid);
+
+	vmx_update_fb_clear_dis(vcpu, vmx);
 }

 static void vmx_enable_irq_window(struct kvm_vcpu *vcpu)
@ -6772,6 +6835,11 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 		vmx_l1d_flush(vcpu);
 	else if (static_branch_unlikely(&mds_user_clear))
 		mds_clear_cpu_buffers();
+	else if (static_branch_unlikely(&mmio_stale_data_clear) &&
+		 kvm_arch_has_assigned_device(vcpu->kvm))
+		mds_clear_cpu_buffers();
+
+	vmx_disable_fb_clear(vmx);

 	if (vcpu->arch.cr2 != native_read_cr2())
 		native_write_cr2(vcpu->arch.cr2);
@ -6781,6 +6849,8 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,

 	vcpu->arch.cr2 = native_read_cr2();

+	vmx_enable_fb_clear(vmx);
+
 	guest_state_exit_irqoff();
 }

@ -7709,7 +7779,9 @@ static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
 	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
 			  BIT(APICV_INHIBIT_REASON_ABSENT) |
 			  BIT(APICV_INHIBIT_REASON_HYPERV) |
-			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
+			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |
+			  BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |
+			  BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);

 	return supported & BIT(reason);
 }
@ -8212,6 +8284,8 @@ static int __init vmx_init(void)
 		return r;
 	}

+	vmx_setup_fb_clear_ctrl();
+
 	for_each_possible_cpu(cpu) {
 		INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));

--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@ -348,6 +348,8 @@ struct vcpu_vmx {
 	u64 msr_ia32_feature_control_valid_bits;
 	/* SGX Launch Control public key hash */
 	u64 msr_ia32_sgxlepubkeyhash[4];
+	u64 msr_ia32_mcu_opt_ctrl;
+	bool disable_fb_clear;

 	struct pt_desc pt_desc;
 	struct lbr_desc lbr_desc;
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@ -1617,6 +1617,9 @@ static u64 kvm_get_arch_capabilities(void)
 		 */
 	}

+	/* Guests don't need to know "Fill buffer clear control" exists */
+	data &= ~ARCH_CAP_FB_CLEAR_CTRL;
+
 	return data;
 }

@ -9850,6 +9853,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
 		return;

 	down_read(&vcpu->kvm->arch.apicv_update_lock);
+	preempt_disable();

 	activate = kvm_vcpu_apicv_activated(vcpu);

@ -9870,6 +9874,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
 		kvm_make_request(KVM_REQ_EVENT, vcpu);

 out:
+	preempt_enable();
 	up_read(&vcpu->kvm->arch.apicv_update_lock);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv);
--- a/block/bio.c
+++ b/block/bio.c
@ -1747,26 +1747,6 @@ bad:
 }
 EXPORT_SYMBOL(bioset_init);

-/*
- * Initialize and setup a new bio_set, based on the settings from
- * another bio_set.
- */
-int bioset_init_from_src(struct bio_set *bs, struct bio_set *src)
-{
-	int flags;
-
-	flags = 0;
-	if (src->bvec_pool.min_nr)
-		flags |= BIOSET_NEED_BVECS;
-	if (src->rescue_workqueue)
-		flags |= BIOSET_NEED_RESCUER;
-	if (src->cache)
-		flags |= BIOSET_PERCPU_CACHE;
-
-	return bioset_init(bs, src->bio_pool.min_nr, src->front_pad, flags);
-}
-EXPORT_SYMBOL(bioset_init_from_src);
-
 static int __init init_bio(void)
 {
 	int i;
--- a/certs/.gitignore
+++ b/certs/.gitignore
@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-/blacklist_hashes_checked
+/blacklist_hash_list
 /extract-cert
 /x509_certificate_list
 /x509_revocation_list
--- a/certs/Makefile
+++ b/certs/Makefile
@ -7,22 +7,22 @@ obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o c
 obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o common.o
 obj-$(CONFIG_SYSTEM_REVOCATION_LIST) += revocation_certificates.o
 ifneq ($(CONFIG_SYSTEM_BLACKLIST_HASH_LIST),)
-quiet_cmd_check_blacklist_hashes = CHECK   $(patsubst "%",%,$(2))
-      cmd_check_blacklist_hashes = $(AWK) -f $(srctree)/scripts/check-blacklist-hashes.awk $(2); touch $@

-$(eval $(call config_filename,SYSTEM_BLACKLIST_HASH_LIST))
+$(obj)/blacklist_hashes.o: $(obj)/blacklist_hash_list
+CFLAGS_blacklist_hashes.o := -I $(obj)

-$(obj)/blacklist_hashes.o: $(obj)/blacklist_hashes_checked
+quiet_cmd_check_and_copy_blacklist_hash_list = GEN     $@
+      cmd_check_and_copy_blacklist_hash_list = \
+	$(AWK) -f $(srctree)/scripts/check-blacklist-hashes.awk $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST) >&2; \
+	cat $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST) > $@

-CFLAGS_blacklist_hashes.o += -I$(srctree)
-
-targets += blacklist_hashes_checked
-$(obj)/blacklist_hashes_checked: $(SYSTEM_BLACKLIST_HASH_LIST_SRCPREFIX)$(SYSTEM_BLACKLIST_HASH_LIST_FILENAME) scripts/check-blacklist-hashes.awk FORCE
-	$(call if_changed,check_blacklist_hashes,$(SYSTEM_BLACKLIST_HASH_LIST_SRCPREFIX)$(CONFIG_SYSTEM_BLACKLIST_HASH_LIST))
+$(obj)/blacklist_hash_list: $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST) FORCE
+	$(call if_changed,check_and_copy_blacklist_hash_list)
 obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_hashes.o
 else
 obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_nohashes.o
 endif
+targets += blacklist_hash_list

 quiet_cmd_extract_certs  = CERT    $@
      cmd_extract_certs  = $(obj)/extract-cert $(extract-cert-in) $@
@ -33,7 +33,7 @@ $(obj)/system_certificates.o: $(obj)/x509_certificate_list
 $(obj)/x509_certificate_list: $(CONFIG_SYSTEM_TRUSTED_KEYS) $(obj)/extract-cert FORCE
 	$(call if_changed,extract_certs)

-targets += x509_certificate_list blacklist_hashes_checked
+targets += x509_certificate_list

 # If module signing is requested, say by allyesconfig, but a key has not been
 # supplied, then one will need to be generated to make sure the build does not
--- a/certs/blacklist_hashes.c
+++ b/certs/blacklist_hashes.c
@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "blacklist.h"

-const char __initdata *const blacklist_hashes[] = {
-#include CONFIG_SYSTEM_BLACKLIST_HASH_LIST
+const char __initconst *const blacklist_hashes[] = {
+#include "blacklist_hash_list"
 	, NULL
 };
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@ -564,6 +564,12 @@ ssize_t __weak cpu_show_srbds(struct device *dev,
 	return sysfs_emit(buf, "Not affected\n");
 }

+ssize_t __weak cpu_show_mmio_stale_data(struct device *dev,
+					struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
@ -573,6 +579,7 @@ static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL);
 static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL);
 static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL);
 static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL);
+static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL);

 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@ -584,6 +591,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_tsx_async_abort.attr,
 	&dev_attr_itlb_multihit.attr,
 	&dev_attr_srbds.attr,
+	&dev_attr_mmio_stale_data.attr,
 	NULL
 };

--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@ -429,28 +429,40 @@ config ADI
 	  driver include crash and makedumpfile.

 config RANDOM_TRUST_CPU
-	bool "Trust the CPU manufacturer to initialize Linux's CRNG"
+	bool "Initialize RNG using CPU RNG instructions"
+	default y
 	depends on ARCH_RANDOM
-	default n
 	help
-	Assume that CPU manufacturer (e.g., Intel or AMD for RDSEED or
-	RDRAND, IBM for the S390 and Power PC architectures) is trustworthy
-	for the purposes of initializing Linux's CRNG.  Since this is not
-	something that can be independently audited, this amounts to trusting
-	that CPU manufacturer (perhaps with the insistence or mandate
-	of a Nation State's intelligence or law enforcement agencies)
-	has not installed a hidden back door to compromise the CPU's
-	random number generation facilities. This can also be configured
-	at boot with "random.trust_cpu=on/off".
+	  Initialize the RNG using random numbers supplied by the CPU's
+	  RNG instructions (e.g. RDRAND), if supported and available. These
+	  random numbers are never used directly, but are rather hashed into
+	  the main input pool, and this happens regardless of whether or not
+	  this option is enabled. Instead, this option controls whether the
+	  they are credited and hence can initialize the RNG. Additionally,
+	  other sources of randomness are always used, regardless of this
+	  setting.  Enabling this implies trusting that the CPU can supply high
+	  quality and non-backdoored random numbers.
+
+	  Say Y here unless you have reason to mistrust your CPU or believe
+	  its RNG facilities may be faulty. This may also be configured at
+	  boot time with "random.trust_cpu=on/off".

 config RANDOM_TRUST_BOOTLOADER
-	bool "Trust the bootloader to initialize Linux's CRNG"
+	bool "Initialize RNG using bootloader-supplied seed"
+	default y
 	help
-	Some bootloaders can provide entropy to increase the kernel's initial
-	device randomness. Say Y here to assume the entropy provided by the
-	booloader is trustworthy so it will be added to the kernel's entropy
-	pool. Otherwise, say N here so it will be regarded as device input that
-	only mixes the entropy pool. This can also be configured at boot with
-	"random.trust_bootloader=on/off".
+	  Initialize the RNG using a seed supplied by the bootloader or boot
+	  environment (e.g. EFI or a bootloader-generated device tree). This
+	  seed is not used directly, but is rather hashed into the main input
+	  pool, and this happens regardless of whether or not this option is
+	  enabled. Instead, this option controls whether the seed is credited
+	  and hence can initialize the RNG. Additionally, other sources of
+	  randomness are always used, regardless of this setting. Enabling
+	  this implies trusting that the bootloader can supply high quality and
+	  non-backdoored seeds.
+
+	  Say Y here unless you have reason to mistrust your bootloader or
+	  believe its RNG facilities may be faulty. This may also be configured
+	  at boot time with "random.trust_bootloader=on/off".

 endmenu
--- a/drivers/char/hw_random/virtio-rng.c
+++ b/drivers/char/hw_random/virtio-rng.c
@ -159,6 +159,8 @@ static int probe_common(struct virtio_device *vdev)
 		goto err_find;
 	}

+	virtio_device_ready(vdev);
+
 	/* we always have a pending entropy request */
 	request_entropy(vi);

--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@ -650,7 +650,8 @@ static void __cold _credit_init_bits(size_t bits)

 	if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) {
 		crng_reseed(); /* Sets crng_init to CRNG_READY under base_crng.lock. */
-		execute_in_process_context(crng_set_ready, &set_ready);
+		if (static_key_initialized)
+			execute_in_process_context(crng_set_ready, &set_ready);
 		wake_up_interruptible(&crng_init_wait);
 		kill_fasync(&fasync, SIGIO, POLL_IN);
 		pr_notice("crng init done\n");
@ -724,9 +725,8 @@ static void __cold _credit_init_bits(size_t bits)
 *
 **********************************************************************/

-static bool used_arch_random;
-static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU);
-static bool trust_bootloader __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER);
+static bool trust_cpu __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU);
+static bool trust_bootloader __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER);
 static int __init parse_trust_cpu(char *arg)
 {
 	return kstrtobool(arg, &trust_cpu);
@ -776,7 +776,7 @@ static struct notifier_block pm_notifier = { .notifier_call = random_pm_notifica
 int __init random_init(const char *command_line)
 {
 	ktime_t now = ktime_get_real();
-	unsigned int i, arch_bytes;
+	unsigned int i, arch_bits;
 	unsigned long entropy;

 #if defined(LATENT_ENTROPY_PLUGIN)
@ -784,12 +784,12 @@ int __init random_init(const char *command_line)
 	_mix_pool_bytes(compiletime_seed, sizeof(compiletime_seed));
 #endif

-	for (i = 0, arch_bytes = BLAKE2S_BLOCK_SIZE;
+	for (i = 0, arch_bits = BLAKE2S_BLOCK_SIZE * 8;
 	     i < BLAKE2S_BLOCK_SIZE; i += sizeof(entropy)) {
 		if (!arch_get_random_seed_long_early(&entropy) &&
 		    !arch_get_random_long_early(&entropy)) {
 			entropy = random_get_entropy();
-			arch_bytes -= sizeof(entropy);
+			arch_bits -= sizeof(entropy) * 8;
 		}
 		_mix_pool_bytes(&entropy, sizeof(entropy));
 	}
@ -798,11 +798,18 @@ int __init random_init(const char *command_line)
 	_mix_pool_bytes(command_line, strlen(command_line));
 	add_latent_entropy();

+	/*
+	 * If we were initialized by the bootloader before jump labels are
+	 * initialized, then we should enable the static branch here, where
+	 * it's guaranteed that jump labels have been initialized.
+	 */
+	if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY)
+		crng_set_ready(NULL);
+
 	if (crng_ready())
 		crng_reseed();
 	else if (trust_cpu)
-		credit_init_bits(arch_bytes * 8);
-	used_arch_random = arch_bytes * 8 >= POOL_READY_BITS;
+		_credit_init_bits(arch_bits);

 	WARN_ON(register_pm_notifier(&pm_notifier));

@ -811,17 +818,6 @@ int __init random_init(const char *command_line)
 	return 0;
 }

-/*
- * Returns whether arch randomness has been mixed into the initial
- * state of the RNG, regardless of whether or not that randomness
- * was credited. Knowing this is only good for a very limited set
- * of uses, such as early init printk pointer obfuscation.
- */
-bool rng_has_arch_random(void)
-{
-	return used_arch_random;
-}
-
 /*
 * Add device- or boot-specific data to the input pool to help
 * initialize it.
@ -865,13 +861,12 @@ EXPORT_SYMBOL_GPL(add_hwgenerator_randomness);
 * Handle random seed passed by bootloader, and credit it if
 * CONFIG_RANDOM_TRUST_BOOTLOADER is set.
 */
-void __cold add_bootloader_randomness(const void *buf, size_t len)
+void __init add_bootloader_randomness(const void *buf, size_t len)
 {
 	mix_pool_bytes(buf, len);
 	if (trust_bootloader)
 		credit_init_bits(len * 8);
 }
-EXPORT_SYMBOL_GPL(add_bootloader_randomness);

 #if IS_ENABLED(CONFIG_VMGENID)
 static BLOCKING_NOTIFIER_HEAD(vmfork_chain);
--- a/drivers/gpio/gpio-crystalcove.c
+++ b/drivers/gpio/gpio-crystalcove.c
@ -15,6 +15,7 @@
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/seq_file.h>
+#include <linux/types.h>

 #define CRYSTALCOVE_GPIO_NUM	16
 #define CRYSTALCOVE_VGPIO_NUM	95
@ -110,8 +111,7 @@ static inline int to_reg(int gpio, enum ctrl_register reg_type)
 	return reg + gpio % 8;
 }

-static void crystalcove_update_irq_mask(struct crystalcove_gpio *cg,
-					int gpio)
+static void crystalcove_update_irq_mask(struct crystalcove_gpio *cg, int gpio)
 {
 	u8 mirqs0 = gpio < 8 ? MGPIO0IRQS0 : MGPIO1IRQS0;
 	int mask = BIT(gpio % 8);
@ -140,8 +140,7 @@ static int crystalcove_gpio_dir_in(struct gpio_chip *chip, unsigned int gpio)
 	return regmap_write(cg->regmap, reg, CTLO_INPUT_SET);
 }

-static int crystalcove_gpio_dir_out(struct gpio_chip *chip, unsigned int gpio,
-				    int value)
+static int crystalcove_gpio_dir_out(struct gpio_chip *chip, unsigned int gpio, int value)
 {
 	struct crystalcove_gpio *cg = gpiochip_get_data(chip);
 	int reg = to_reg(gpio, CTRL_OUT);
@ -168,8 +167,7 @@ static int crystalcove_gpio_get(struct gpio_chip *chip, unsigned int gpio)
 	return val & 0x1;
 }

-static void crystalcove_gpio_set(struct gpio_chip *chip,
-				 unsigned int gpio, int value)
+static void crystalcove_gpio_set(struct gpio_chip *chip, unsigned int gpio, int value)
 {
 	struct crystalcove_gpio *cg = gpiochip_get_data(chip);
 	int reg = to_reg(gpio, CTRL_OUT);
@ -185,10 +183,10 @@ static void crystalcove_gpio_set(struct gpio_chip *chip,

 static int crystalcove_irq_type(struct irq_data *data, unsigned int type)
 {
-	struct crystalcove_gpio *cg =
-		gpiochip_get_data(irq_data_get_irq_chip_data(data));
+	struct crystalcove_gpio *cg = gpiochip_get_data(irq_data_get_irq_chip_data(data));
+	irq_hw_number_t hwirq = irqd_to_hwirq(data);

-	if (data->hwirq >= CRYSTALCOVE_GPIO_NUM)
+	if (hwirq >= CRYSTALCOVE_GPIO_NUM)
 		return 0;

 	switch (type) {
@ -215,22 +213,20 @@ static int crystalcove_irq_type(struct irq_data *data, unsigned int type)

 static void crystalcove_bus_lock(struct irq_data *data)
 {
-	struct crystalcove_gpio *cg =
-		gpiochip_get_data(irq_data_get_irq_chip_data(data));
+	struct crystalcove_gpio *cg = gpiochip_get_data(irq_data_get_irq_chip_data(data));

 	mutex_lock(&cg->buslock);
 }

 static void crystalcove_bus_sync_unlock(struct irq_data *data)
 {
-	struct crystalcove_gpio *cg =
-		gpiochip_get_data(irq_data_get_irq_chip_data(data));
-	int gpio = data->hwirq;
+	struct crystalcove_gpio *cg = gpiochip_get_data(irq_data_get_irq_chip_data(data));
+	irq_hw_number_t hwirq = irqd_to_hwirq(data);

 	if (cg->update & UPDATE_IRQ_TYPE)
-		crystalcove_update_irq_ctrl(cg, gpio);
+		crystalcove_update_irq_ctrl(cg, hwirq);
 	if (cg->update & UPDATE_IRQ_MASK)
-		crystalcove_update_irq_mask(cg, gpio);
+		crystalcove_update_irq_mask(cg, hwirq);
 	cg->update = 0;

 	mutex_unlock(&cg->buslock);
@ -238,34 +234,43 @@ static void crystalcove_bus_sync_unlock(struct irq_data *data)

 static void crystalcove_irq_unmask(struct irq_data *data)
 {
-	struct crystalcove_gpio *cg =
-		gpiochip_get_data(irq_data_get_irq_chip_data(data));
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct crystalcove_gpio *cg = gpiochip_get_data(gc);
+	irq_hw_number_t hwirq = irqd_to_hwirq(data);

-	if (data->hwirq < CRYSTALCOVE_GPIO_NUM) {
-		cg->set_irq_mask = false;
-		cg->update |= UPDATE_IRQ_MASK;
-	}
+	if (hwirq >= CRYSTALCOVE_GPIO_NUM)
+		return;
+
+	gpiochip_enable_irq(gc, hwirq);
+
+	cg->set_irq_mask = false;
+	cg->update |= UPDATE_IRQ_MASK;
 }

 static void crystalcove_irq_mask(struct irq_data *data)
 {
-	struct crystalcove_gpio *cg =
-		gpiochip_get_data(irq_data_get_irq_chip_data(data));
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct crystalcove_gpio *cg = gpiochip_get_data(gc);
+	irq_hw_number_t hwirq = irqd_to_hwirq(data);

-	if (data->hwirq < CRYSTALCOVE_GPIO_NUM) {
-		cg->set_irq_mask = true;
-		cg->update |= UPDATE_IRQ_MASK;
-	}
+	if (hwirq >= CRYSTALCOVE_GPIO_NUM)
+		return;
+
+	cg->set_irq_mask = true;
+	cg->update |= UPDATE_IRQ_MASK;
+
+	gpiochip_disable_irq(gc, hwirq);
 }

-static struct irq_chip crystalcove_irqchip = {
+static const struct irq_chip crystalcove_irqchip = {
 	.name			= "Crystal Cove",
 	.irq_mask		= crystalcove_irq_mask,
 	.irq_unmask		= crystalcove_irq_unmask,
 	.irq_set_type		= crystalcove_irq_type,
 	.irq_bus_lock		= crystalcove_bus_lock,
 	.irq_bus_sync_unlock	= crystalcove_bus_sync_unlock,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
+	.flags			= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };

 static irqreturn_t crystalcove_gpio_irq_handler(int irq, void *data)
@ -293,8 +298,7 @@ static irqreturn_t crystalcove_gpio_irq_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }

-static void crystalcove_gpio_dbg_show(struct seq_file *s,
-				      struct gpio_chip *chip)
+static void crystalcove_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 {
 	struct crystalcove_gpio *cg = gpiochip_get_data(chip);
 	int gpio, offset;
@ -353,7 +357,7 @@ static int crystalcove_gpio_probe(struct platform_device *pdev)
 	cg->regmap = pmic->regmap;

 	girq = &cg->chip.irq;
-	girq->chip = &crystalcove_irqchip;
+	gpio_irq_chip_set_chip(girq, &crystalcove_irqchip);
 	/* This will let us handle the parent IRQ in the driver */
 	girq->parent_handler = NULL;
 	girq->num_parents = 0;
--- a/drivers/gpio/gpio-dln2.c
+++ b/drivers/gpio/gpio-dln2.c
@ -46,7 +46,6 @@
 struct dln2_gpio {
 	struct platform_device *pdev;
 	struct gpio_chip gpio;
-	struct irq_chip irqchip;

 	/*
 	 * Cache pin direction to save us one transfer, since the hardware has
@ -306,6 +305,7 @@ static void dln2_irq_unmask(struct irq_data *irqd)
 	struct dln2_gpio *dln2 = gpiochip_get_data(gc);
 	int pin = irqd_to_hwirq(irqd);

+	gpiochip_enable_irq(gc, pin);
 	set_bit(pin, dln2->unmasked_irqs);
 }

@ -316,6 +316,7 @@ static void dln2_irq_mask(struct irq_data *irqd)
 	int pin = irqd_to_hwirq(irqd);

 	clear_bit(pin, dln2->unmasked_irqs);
+	gpiochip_disable_irq(gc, pin);
 }

 static int dln2_irq_set_type(struct irq_data *irqd, unsigned type)
@ -384,6 +385,17 @@ static void dln2_irq_bus_unlock(struct irq_data *irqd)
 	mutex_unlock(&dln2->irq_lock);
 }

+static const struct irq_chip dln2_irqchip = {
+	.name = "dln2-irq",
+	.irq_mask = dln2_irq_mask,
+	.irq_unmask = dln2_irq_unmask,
+	.irq_set_type = dln2_irq_set_type,
+	.irq_bus_lock = dln2_irq_bus_lock,
+	.irq_bus_sync_unlock = dln2_irq_bus_unlock,
+	.flags = IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
 static void dln2_gpio_event(struct platform_device *pdev, u16 echo,
 			    const void *data, int len)
 {
@ -465,15 +477,8 @@ static int dln2_gpio_probe(struct platform_device *pdev)
 	dln2->gpio.direction_output = dln2_gpio_direction_output;
 	dln2->gpio.set_config = dln2_gpio_set_config;

-	dln2->irqchip.name = "dln2-irq",
-	dln2->irqchip.irq_mask = dln2_irq_mask,
-	dln2->irqchip.irq_unmask = dln2_irq_unmask,
-	dln2->irqchip.irq_set_type = dln2_irq_set_type,
-	dln2->irqchip.irq_bus_lock = dln2_irq_bus_lock,
-	dln2->irqchip.irq_bus_sync_unlock = dln2_irq_bus_unlock,
-
 	girq = &dln2->gpio.irq;
-	girq->chip = &dln2->irqchip;
+	gpio_irq_chip_set_chip(girq, &dln2_irqchip);
 	/* The event comes from the outside so no parent handler */
 	girq->parent_handler = NULL;
 	girq->num_parents = 0;
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@ -662,10 +662,9 @@ static int dwapb_get_clks(struct dwapb_gpio *gpio)
 	gpio->clks[1].id = "db";
 	err = devm_clk_bulk_get_optional(gpio->dev, DWAPB_NR_CLOCKS,
 					 gpio->clks);
-	if (err) {
-		dev_err(gpio->dev, "Cannot get APB/Debounce clocks\n");
-		return err;
-	}
+	if (err)
+		return dev_err_probe(gpio->dev, err,
+				     "Cannot get APB/Debounce clocks\n");

 	err = clk_bulk_prepare_enable(DWAPB_NR_CLOCKS, gpio->clks);
 	if (err) {
--- a/drivers/gpio/gpio-merrifield.c
+++ b/drivers/gpio/gpio-merrifield.c
@ -220,10 +220,8 @@ static void mrfld_irq_ack(struct irq_data *d)
 	raw_spin_unlock_irqrestore(&priv->lock, flags);
 }

-static void mrfld_irq_unmask_mask(struct irq_data *d, bool unmask)
+static void mrfld_irq_unmask_mask(struct mrfld_gpio *priv, u32 gpio, bool unmask)
 {
-	struct mrfld_gpio *priv = irq_data_get_irq_chip_data(d);
-	u32 gpio = irqd_to_hwirq(d);
 	void __iomem *gimr = gpio_reg(&priv->chip, gpio, GIMR);
 	unsigned long flags;
 	u32 value;
@ -241,12 +239,20 @@ static void mrfld_irq_unmask_mask(struct irq_data *d, bool unmask)

 static void mrfld_irq_mask(struct irq_data *d)
 {
-	mrfld_irq_unmask_mask(d, false);
+	struct mrfld_gpio *priv = irq_data_get_irq_chip_data(d);
+	u32 gpio = irqd_to_hwirq(d);
+
+	mrfld_irq_unmask_mask(priv, gpio, false);
+	gpiochip_disable_irq(&priv->chip, gpio);
 }

 static void mrfld_irq_unmask(struct irq_data *d)
 {
-	mrfld_irq_unmask_mask(d, true);
+	struct mrfld_gpio *priv = irq_data_get_irq_chip_data(d);
+	u32 gpio = irqd_to_hwirq(d);
+
+	gpiochip_enable_irq(&priv->chip, gpio);
+	mrfld_irq_unmask_mask(priv, gpio, true);
 }

 static int mrfld_irq_set_type(struct irq_data *d, unsigned int type)
@ -329,13 +335,15 @@ static int mrfld_irq_set_wake(struct irq_data *d, unsigned int on)
 	return 0;
 }

-static struct irq_chip mrfld_irqchip = {
+static const struct irq_chip mrfld_irqchip = {
 	.name		= "gpio-merrifield",
 	.irq_ack	= mrfld_irq_ack,
 	.irq_mask	= mrfld_irq_mask,
 	.irq_unmask	= mrfld_irq_unmask,
 	.irq_set_type	= mrfld_irq_set_type,
 	.irq_set_wake	= mrfld_irq_set_wake,
+	.flags		= IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };

 static void mrfld_irq_handler(struct irq_desc *desc)
@ -482,7 +490,7 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 		return retval;

 	girq = &priv->chip.irq;
-	girq->chip = &mrfld_irqchip;
+	gpio_irq_chip_set_chip(girq, &mrfld_irqchip);
 	girq->init_hw = mrfld_irq_init_hw;
 	girq->parent_handler = mrfld_irq_handler;
 	girq->num_parents = 1;
--- a/drivers/gpio/gpio-sch.c
+++ b/drivers/gpio/gpio-sch.c
@ -38,7 +38,6 @@

 struct sch_gpio {
 	struct gpio_chip chip;
-	struct irq_chip irqchip;
 	spinlock_t lock;
 	unsigned short iobase;
 	unsigned short resume_base;
@ -218,11 +217,9 @@ static void sch_irq_ack(struct irq_data *d)
 	spin_unlock_irqrestore(&sch->lock, flags);
 }

-static void sch_irq_mask_unmask(struct irq_data *d, int val)
+static void sch_irq_mask_unmask(struct gpio_chip *gc, irq_hw_number_t gpio_num, int val)
 {
-	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct sch_gpio *sch = gpiochip_get_data(gc);
-	irq_hw_number_t gpio_num = irqd_to_hwirq(d);
 	unsigned long flags;

 	spin_lock_irqsave(&sch->lock, flags);
@ -232,14 +229,32 @@ static void sch_irq_mask_unmask(struct irq_data *d, int val)

 static void sch_irq_mask(struct irq_data *d)
 {
-	sch_irq_mask_unmask(d, 0);
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	irq_hw_number_t gpio_num = irqd_to_hwirq(d);
+
+	sch_irq_mask_unmask(gc, gpio_num, 0);
+	gpiochip_disable_irq(gc, gpio_num);
 }

 static void sch_irq_unmask(struct irq_data *d)
 {
-	sch_irq_mask_unmask(d, 1);
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	irq_hw_number_t gpio_num = irqd_to_hwirq(d);
+
+	gpiochip_enable_irq(gc, gpio_num);
+	sch_irq_mask_unmask(gc, gpio_num, 1);
 }

+static const struct irq_chip sch_irqchip = {
+	.name = "sch_gpio",
+	.irq_ack = sch_irq_ack,
+	.irq_mask = sch_irq_mask,
+	.irq_unmask = sch_irq_unmask,
+	.irq_set_type = sch_irq_type,
+	.flags = IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
 static u32 sch_gpio_gpe_handler(acpi_handle gpe_device, u32 gpe, void *context)
 {
 	struct sch_gpio *sch = context;
@ -367,14 +382,8 @@ static int sch_gpio_probe(struct platform_device *pdev)

 	platform_set_drvdata(pdev, sch);

-	sch->irqchip.name = "sch_gpio";
-	sch->irqchip.irq_ack = sch_irq_ack;
-	sch->irqchip.irq_mask = sch_irq_mask;
-	sch->irqchip.irq_unmask = sch_irq_unmask;
-	sch->irqchip.irq_set_type = sch_irq_type;
-
 	girq = &sch->chip.irq;
-	girq->chip = &sch->irqchip;
+	gpio_irq_chip_set_chip(girq, &sch_irqchip);
 	girq->num_parents = 0;
 	girq->parents = NULL;
 	girq->parent_handler = NULL;
--- a/drivers/gpio/gpio-wcove.c
+++ b/drivers/gpio/gpio-wcove.c
@ -299,6 +299,8 @@ static void wcove_irq_unmask(struct irq_data *data)
 	if (gpio >= WCOVE_GPIO_NUM)
 		return;

+	gpiochip_enable_irq(chip, gpio);
+
 	wg->set_irq_mask = false;
 	wg->update |= UPDATE_IRQ_MASK;
 }
@ -314,15 +316,19 @@ static void wcove_irq_mask(struct irq_data *data)

 	wg->set_irq_mask = true;
 	wg->update |= UPDATE_IRQ_MASK;
+
+	gpiochip_disable_irq(chip, gpio);
 }

-static struct irq_chip wcove_irqchip = {
+static const struct irq_chip wcove_irqchip = {
 	.name			= "Whiskey Cove",
 	.irq_mask		= wcove_irq_mask,
 	.irq_unmask		= wcove_irq_unmask,
 	.irq_set_type		= wcove_irq_type,
 	.irq_bus_lock		= wcove_bus_lock,
 	.irq_bus_sync_unlock	= wcove_bus_sync_unlock,
+	.flags			= IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };

 static irqreturn_t wcove_gpio_irq_handler(int irq, void *data)
@ -452,7 +458,7 @@ static int wcove_gpio_probe(struct platform_device *pdev)
 	}

 	girq = &wg->chip.irq;
-	girq->chip = &wcove_irqchip;
+	gpio_irq_chip_set_chip(girq, &wcove_irqchip);
 	/* This will let us handle the parent IRQ in the driver */
 	girq->parent_handler = NULL;
 	girq->num_parents = 0;
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@ -33,6 +33,14 @@ struct dm_kobject_holder {
 * access their members!
 */

+/*
+ * For mempools pre-allocation at the table loading time.
+ */
+struct dm_md_mempools {
+	struct bio_set bs;
+	struct bio_set io_bs;
+};
+
 struct mapped_device {
 	struct mutex suspend_lock;

@ -110,8 +118,7 @@ struct mapped_device {
 	/*
 	 * io objects are allocated from here.
 	 */
-	struct bio_set io_bs;
-	struct bio_set bs;
+	struct dm_md_mempools *mempools;

 	/* kobject and completion */
 	struct dm_kobject_holder kobj_holder;
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@ -319,7 +319,7 @@ static int setup_clone(struct request *clone, struct request *rq,
 {
 	int r;

-	r = blk_rq_prep_clone(clone, rq, &tio->md->bs, gfp_mask,
+	r = blk_rq_prep_clone(clone, rq, &tio->md->mempools->bs, gfp_mask,
 			      dm_rq_bio_constructor, tio);
 	if (r)
 		return r;
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@ -1038,17 +1038,6 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
 	return 0;
 }

-void dm_table_free_md_mempools(struct dm_table *t)
-{
-	dm_free_md_mempools(t->mempools);
-	t->mempools = NULL;
-}
-
-struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t)
-{
-	return t->mempools;
-}
-
 static int setup_indexes(struct dm_table *t)
 {
 	int i;
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@ -136,14 +136,6 @@ static int get_swap_bios(void)
 	return latch;
 }

-/*
- * For mempools pre-allocation at the table loading time.
- */
-struct dm_md_mempools {
-	struct bio_set bs;
-	struct bio_set io_bs;
-};
-
 struct table_device {
 	struct list_head list;
 	refcount_t count;
@ -581,7 +573,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
 	struct dm_target_io *tio;
 	struct bio *clone;

-	clone = bio_alloc_clone(NULL, bio, GFP_NOIO, &md->io_bs);
+	clone = bio_alloc_clone(NULL, bio, GFP_NOIO, &md->mempools->io_bs);
 	/* Set default bdev, but target must bio_set_dev() before issuing IO */
 	clone->bi_bdev = md->disk->part0;

@ -628,7 +620,8 @@ static struct bio *alloc_tio(struct clone_info *ci, struct dm_target *ti,
 	} else {
 		struct mapped_device *md = ci->io->md;

-		clone = bio_alloc_clone(NULL, ci->bio, gfp_mask, &md->bs);
+		clone = bio_alloc_clone(NULL, ci->bio, gfp_mask,
+					&md->mempools->bs);
 		if (!clone)
 			return NULL;
 		/* Set default bdev, but target must bio_set_dev() before issuing IO */
@ -1023,23 +1016,19 @@ static void clone_endio(struct bio *bio)
 	struct dm_io *io = tio->io;
 	struct mapped_device *md = io->md;

-	if (likely(bio->bi_bdev != md->disk->part0)) {
-		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-
-		if (unlikely(error == BLK_STS_TARGET)) {
-			if (bio_op(bio) == REQ_OP_DISCARD &&
-			    !bdev_max_discard_sectors(bio->bi_bdev))
-				disable_discard(md);
-			else if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
-				 !q->limits.max_write_zeroes_sectors)
-				disable_write_zeroes(md);
-		}
-
-		if (static_branch_unlikely(&zoned_enabled) &&
-		    unlikely(blk_queue_is_zoned(q)))
-			dm_zone_endio(io, bio);
+	if (unlikely(error == BLK_STS_TARGET)) {
+		if (bio_op(bio) == REQ_OP_DISCARD &&
+		    !bdev_max_discard_sectors(bio->bi_bdev))
+			disable_discard(md);
+		else if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
+			 !bdev_write_zeroes_sectors(bio->bi_bdev))
+			disable_write_zeroes(md);
 	}

+	if (static_branch_unlikely(&zoned_enabled) &&
+	    unlikely(blk_queue_is_zoned(bdev_get_queue(bio->bi_bdev))))
+		dm_zone_endio(io, bio);
+
 	if (endio) {
 		int r = endio(ti, bio, &error);
 		switch (r) {
@ -1876,8 +1865,7 @@ static void cleanup_mapped_device(struct mapped_device *md)
 {
 	if (md->wq)
 		destroy_workqueue(md->wq);
-	bioset_exit(&md->bs);
-	bioset_exit(&md->io_bs);
+	dm_free_md_mempools(md->mempools);

 	if (md->dax_dev) {
 		dax_remove_host(md->disk);
@ -2049,48 +2037,6 @@ static void free_dev(struct mapped_device *md)
 	kvfree(md);
 }

-static int __bind_mempools(struct mapped_device *md, struct dm_table *t)
-{
-	struct dm_md_mempools *p = dm_table_get_md_mempools(t);
-	int ret = 0;
-
-	if (dm_table_bio_based(t)) {
-		/*
-		 * The md may already have mempools that need changing.
-		 * If so, reload bioset because front_pad may have changed
-		 * because a different table was loaded.
-		 */
-		bioset_exit(&md->bs);
-		bioset_exit(&md->io_bs);
-
-	} else if (bioset_initialized(&md->bs)) {
-		/*
-		 * There's no need to reload with request-based dm
-		 * because the size of front_pad doesn't change.
-		 * Note for future: If you are to reload bioset,
-		 * prep-ed requests in the queue may refer
-		 * to bio from the old bioset, so you must walk
-		 * through the queue to unprep.
-		 */
-		goto out;
-	}
-
-	BUG_ON(!p ||
-	       bioset_initialized(&md->bs) ||
-	       bioset_initialized(&md->io_bs));
-
-	ret = bioset_init_from_src(&md->bs, &p->bs);
-	if (ret)
-		goto out;
-	ret = bioset_init_from_src(&md->io_bs, &p->io_bs);
-	if (ret)
-		bioset_exit(&md->bs);
-out:
-	/* mempool bind completed, no longer need any mempools in the table */
-	dm_table_free_md_mempools(t);
-	return ret;
-}
-
 /*
 * Bind a table to the device.
 */
@ -2144,12 +2090,28 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 		 * immutable singletons - used to optimize dm_mq_queue_rq.
 		 */
 		md->immutable_target = dm_table_get_immutable_target(t);
-	}

-	ret = __bind_mempools(md, t);
-	if (ret) {
-		old_map = ERR_PTR(ret);
-		goto out;
+		/*
+		 * There is no need to reload with request-based dm because the
+		 * size of front_pad doesn't change.
+		 *
+		 * Note for future: If you are to reload bioset, prep-ed
+		 * requests in the queue may refer to bio from the old bioset,
+		 * so you must walk through the queue to unprep.
+		 */
+		if (!md->mempools) {
+			md->mempools = t->mempools;
+			t->mempools = NULL;
+		}
+	} else {
+		/*
+		 * The md may already have mempools that need changing.
+		 * If so, reload bioset because front_pad may have changed
+		 * because a different table was loaded.
+		 */
+		dm_free_md_mempools(md->mempools);
+		md->mempools = t->mempools;
+		t->mempools = NULL;
 	}

 	ret = dm_table_set_restrictions(t, md->queue, limits);
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@ -71,8 +71,6 @@ struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
 struct dm_target *dm_table_get_wildcard_target(struct dm_table *t);
 bool dm_table_bio_based(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
-void dm_table_free_md_mempools(struct dm_table *t);
-struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);

 void dm_lock_md_type(struct mapped_device *md);
 void dm_unlock_md_type(struct mapped_device *md);
--- a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
@ -338,7 +338,7 @@ static int xgbe_platform_probe(struct platform_device *pdev)
 		 *   the PHY resources listed last
 		 */
 		phy_memnum = xgbe_resource_count(pdev, IORESOURCE_MEM) - 3;
-		phy_irqnum = xgbe_resource_count(pdev, IORESOURCE_IRQ) - 1;
+		phy_irqnum = platform_irq_count(pdev) - 1;
 		dma_irqnum = 1;
 		dma_irqend = phy_irqnum;
 	} else {
@ -348,7 +348,7 @@ static int xgbe_platform_probe(struct platform_device *pdev)
 		phy_memnum = 0;
 		phy_irqnum = 0;
 		dma_irqnum = 1;
-		dma_irqend = xgbe_resource_count(pdev, IORESOURCE_IRQ);
+		dma_irqend = platform_irq_count(pdev);
 	}

 	/* Obtain the mmio areas for the device */
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@ -332,7 +332,6 @@ static void bgmac_remove(struct bcma_device *core)
 	bcma_mdio_mii_unregister(bgmac->mii_bus);
 	bgmac_enet_remove(bgmac);
 	bcma_set_drvdata(core, NULL);
-	kfree(bgmac);
 }

 static struct bcma_driver bgmac_bcma_driver = {
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@ -769,6 +769,7 @@ struct hnae3_tc_info {
 	u8 prio_tc[HNAE3_MAX_USER_PRIO]; /* TC indexed by prio */
 	u16 tqp_count[HNAE3_MAX_TC];
 	u16 tqp_offset[HNAE3_MAX_TC];
+	u8 max_tc; /* Total number of TCs */
 	u8 num_tc; /* Total number of enabled TCs */
 	bool mqprio_active;
 };
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@ -1129,7 +1129,7 @@ hns3_is_ringparam_changed(struct net_device *ndev,
 	if (old_ringparam->tx_desc_num == new_ringparam->tx_desc_num &&
 	    old_ringparam->rx_desc_num == new_ringparam->rx_desc_num &&
 	    old_ringparam->rx_buf_len == new_ringparam->rx_buf_len) {
-		netdev_info(ndev, "ringparam not changed\n");
+		netdev_info(ndev, "descriptor number and rx buffer length not changed\n");
 		return false;
 	}

--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@ -3268,7 +3268,7 @@ static int hclge_tp_port_init(struct hclge_dev *hdev)
 static int hclge_update_port_info(struct hclge_dev *hdev)
 {
 	struct hclge_mac *mac = &hdev->hw.mac;
-	int speed = HCLGE_MAC_SPEED_UNKNOWN;
+	int speed;
 	int ret;

 	/* get the port info from SFP cmd if not copper port */
@ -3279,10 +3279,13 @@ static int hclge_update_port_info(struct hclge_dev *hdev)
 	if (!hdev->support_sfp_query)
 		return 0;

-	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2)
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
+		speed = mac->speed;
 		ret = hclge_get_sfp_info(hdev, mac);
-	else
+	} else {
+		speed = HCLGE_MAC_SPEED_UNKNOWN;
 		ret = hclge_get_sfp_speed(hdev, &speed);
+	}

 	if (ret == -EOPNOTSUPP) {
 		hdev->support_sfp_query = false;
@ -3294,6 +3297,8 @@ static int hclge_update_port_info(struct hclge_dev *hdev)
 	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
 		if (mac->speed_type == QUERY_ACTIVE_SPEED) {
 			hclge_update_port_capability(hdev, mac);
+			if (mac->speed != speed)
+				(void)hclge_tm_port_shaper_cfg(hdev);
 			return 0;
 		}
 		return hclge_cfg_mac_speed_dup(hdev, mac->speed,
@ -3376,6 +3381,12 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf,
 	link_state_old = vport->vf_info.link_state;
 	vport->vf_info.link_state = link_state;

+	/* return success directly if the VF is unalive, VF will
+	 * query link state itself when it starts work.
+	 */
+	if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+		return 0;
+
 	ret = hclge_push_vf_link_status(vport);
 	if (ret) {
 		vport->vf_info.link_state = link_state_old;
@ -10117,6 +10128,7 @@ static int hclge_modify_port_base_vlan_tag(struct hclge_vport *vport,
 	if (ret)
 		return ret;

+	vport->port_base_vlan_cfg.tbl_sta = false;
 	/* remove old VLAN tag */
 	if (old_info->vlan_tag == 0)
 		ret = hclge_set_vf_vlan_common(hdev, vport->vport_id,
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@ -282,8 +282,8 @@ static int hclge_tm_pg_to_pri_map_cfg(struct hclge_dev *hdev,
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }

-static int hclge_tm_qs_to_pri_map_cfg(struct hclge_dev *hdev,
-				      u16 qs_id, u8 pri)
+static int hclge_tm_qs_to_pri_map_cfg(struct hclge_dev *hdev, u16 qs_id, u8 pri,
+				      bool link_vld)
 {
 	struct hclge_qs_to_pri_link_cmd *map;
 	struct hclge_desc desc;
@ -294,7 +294,7 @@ static int hclge_tm_qs_to_pri_map_cfg(struct hclge_dev *hdev,

 	map->qs_id = cpu_to_le16(qs_id);
 	map->priority = pri;
-	map->link_vld = HCLGE_TM_QS_PRI_LINK_VLD_MSK;
+	map->link_vld = link_vld ? HCLGE_TM_QS_PRI_LINK_VLD_MSK : 0;

 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
@ -420,7 +420,7 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev,
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }

-static int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev)
+int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev)
 {
 	struct hclge_port_shapping_cmd *shap_cfg_cmd;
 	struct hclge_shaper_ir_para ir_para;
@ -642,11 +642,13 @@ static void hclge_tm_update_kinfo_rss_size(struct hclge_vport *vport)
 	 * one tc for VF for simplicity. VF's vport_id is non zero.
 	 */
 	if (vport->vport_id) {
+		kinfo->tc_info.max_tc = 1;
 		kinfo->tc_info.num_tc = 1;
 		vport->qs_offset = HNAE3_MAX_TC +
 				   vport->vport_id - HCLGE_VF_VPORT_START_NUM;
 		vport_max_rss_size = hdev->vf_rss_size_max;
 	} else {
+		kinfo->tc_info.max_tc = hdev->tc_max;
 		kinfo->tc_info.num_tc =
 			min_t(u16, vport->alloc_tqps, hdev->tm_info.num_tc);
 		vport->qs_offset = 0;
@ -679,7 +681,9 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport)
 	kinfo->num_tqps = hclge_vport_get_tqp_num(vport);
 	vport->dwrr = 100;  /* 100 percent as init */
 	vport->bw_limit = hdev->tm_info.pg_info[0].bw_limit;
-	hdev->rss_cfg.rss_size = kinfo->rss_size;
+
+	if (vport->vport_id == PF_VPORT_ID)
+		hdev->rss_cfg.rss_size = kinfo->rss_size;

 	/* when enable mqprio, the tc_info has been updated. */
 	if (kinfo->tc_info.mqprio_active)
@ -714,14 +718,22 @@ static void hclge_tm_vport_info_update(struct hclge_dev *hdev)

 static void hclge_tm_tc_info_init(struct hclge_dev *hdev)
 {
-	u8 i;
+	u8 i, tc_sch_mode;
+	u32 bw_limit;
+
+	for (i = 0; i < hdev->tc_max; i++) {
+		if (i < hdev->tm_info.num_tc) {
+			tc_sch_mode = HCLGE_SCH_MODE_DWRR;
+			bw_limit = hdev->tm_info.pg_info[0].bw_limit;
+		} else {
+			tc_sch_mode = HCLGE_SCH_MODE_SP;
+			bw_limit = 0;
+		}

-	for (i = 0; i < hdev->tm_info.num_tc; i++) {
 		hdev->tm_info.tc_info[i].tc_id = i;
-		hdev->tm_info.tc_info[i].tc_sch_mode = HCLGE_SCH_MODE_DWRR;
+		hdev->tm_info.tc_info[i].tc_sch_mode = tc_sch_mode;
 		hdev->tm_info.tc_info[i].pgid = 0;
-		hdev->tm_info.tc_info[i].bw_limit =
-			hdev->tm_info.pg_info[0].bw_limit;
+		hdev->tm_info.tc_info[i].bw_limit = bw_limit;
 	}

 	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++)
@ -926,10 +938,13 @@ static int hclge_tm_pri_q_qs_cfg_tc_base(struct hclge_dev *hdev)
 	for (k = 0; k < hdev->num_alloc_vport; k++) {
 		struct hnae3_knic_private_info *kinfo = &vport[k].nic.kinfo;

-		for (i = 0; i < kinfo->tc_info.num_tc; i++) {
+		for (i = 0; i < kinfo->tc_info.max_tc; i++) {
+			u8 pri = i < kinfo->tc_info.num_tc ? i : 0;
+			bool link_vld = i < kinfo->tc_info.num_tc;
+
 			ret = hclge_tm_qs_to_pri_map_cfg(hdev,
 							 vport[k].qs_offset + i,
-							 i);
+							 pri, link_vld);
 			if (ret)
 				return ret;
 		}
@ -949,7 +964,7 @@ static int hclge_tm_pri_q_qs_cfg_vnet_base(struct hclge_dev *hdev)
 		for (i = 0; i < HNAE3_MAX_TC; i++) {
 			ret = hclge_tm_qs_to_pri_map_cfg(hdev,
 							 vport[k].qs_offset + i,
-							 k);
+							 k, true);
 			if (ret)
 				return ret;
 		}
@ -989,33 +1004,39 @@ static int hclge_tm_pri_tc_base_shaper_cfg(struct hclge_dev *hdev)
 {
 	u32 max_tm_rate = hdev->ae_dev->dev_specs.max_tm_rate;
 	struct hclge_shaper_ir_para ir_para;
-	u32 shaper_para;
+	u32 shaper_para_c, shaper_para_p;
 	int ret;
 	u32 i;

-	for (i = 0; i < hdev->tm_info.num_tc; i++) {
+	for (i = 0; i < hdev->tc_max; i++) {
 		u32 rate = hdev->tm_info.tc_info[i].bw_limit;

-		ret = hclge_shaper_para_calc(rate, HCLGE_SHAPER_LVL_PRI,
-					     &ir_para, max_tm_rate);
-		if (ret)
-			return ret;
+		if (rate) {
+			ret = hclge_shaper_para_calc(rate, HCLGE_SHAPER_LVL_PRI,
+						     &ir_para, max_tm_rate);
+			if (ret)
+				return ret;
+
+			shaper_para_c = hclge_tm_get_shapping_para(0, 0, 0,
+								   HCLGE_SHAPER_BS_U_DEF,
+								   HCLGE_SHAPER_BS_S_DEF);
+			shaper_para_p = hclge_tm_get_shapping_para(ir_para.ir_b,
+								   ir_para.ir_u,
+								   ir_para.ir_s,
+								   HCLGE_SHAPER_BS_U_DEF,
+								   HCLGE_SHAPER_BS_S_DEF);
+		} else {
+			shaper_para_c = 0;
+			shaper_para_p = 0;
+		}

-		shaper_para = hclge_tm_get_shapping_para(0, 0, 0,
-							 HCLGE_SHAPER_BS_U_DEF,
-							 HCLGE_SHAPER_BS_S_DEF);
 		ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_C_BUCKET, i,
-						shaper_para, rate);
+						shaper_para_c, rate);
 		if (ret)
 			return ret;

-		shaper_para = hclge_tm_get_shapping_para(ir_para.ir_b,
-							 ir_para.ir_u,
-							 ir_para.ir_s,
-							 HCLGE_SHAPER_BS_U_DEF,
-							 HCLGE_SHAPER_BS_S_DEF);
 		ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_P_BUCKET, i,
-						shaper_para, rate);
+						shaper_para_p, rate);
 		if (ret)
 			return ret;
 	}
@ -1125,7 +1146,7 @@ static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev)
 	int ret;
 	u32 i, k;

-	for (i = 0; i < hdev->tm_info.num_tc; i++) {
+	for (i = 0; i < hdev->tc_max; i++) {
 		pg_info =
 			&hdev->tm_info.pg_info[hdev->tm_info.tc_info[i].pgid];
 		dwrr = pg_info->tc_dwrr[i];
@ -1135,9 +1156,15 @@ static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev)
 			return ret;

 		for (k = 0; k < hdev->num_alloc_vport; k++) {
+			struct hnae3_knic_private_info *kinfo = &vport[k].nic.kinfo;
+
+			if (i >= kinfo->tc_info.max_tc)
+				continue;
+
+			dwrr = i < kinfo->tc_info.num_tc ? vport[k].dwrr : 0;
 			ret = hclge_tm_qs_weight_cfg(
 				hdev, vport[k].qs_offset + i,
-				vport[k].dwrr);
+				dwrr);
 			if (ret)
 				return ret;
 		}
@ -1303,6 +1330,7 @@ static int hclge_tm_schd_mode_tc_base_cfg(struct hclge_dev *hdev, u8 pri_id)
 {
 	struct hclge_vport *vport = hdev->vport;
 	int ret;
+	u8 mode;
 	u16 i;

 	ret = hclge_tm_pri_schd_mode_cfg(hdev, pri_id);
@ -1310,9 +1338,16 @@ static int hclge_tm_schd_mode_tc_base_cfg(struct hclge_dev *hdev, u8 pri_id)
 		return ret;

 	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		struct hnae3_knic_private_info *kinfo = &vport[i].nic.kinfo;
+
+		if (pri_id >= kinfo->tc_info.max_tc)
+			continue;
+
+		mode = pri_id < kinfo->tc_info.num_tc ? HCLGE_SCH_MODE_DWRR :
+		       HCLGE_SCH_MODE_SP;
 		ret = hclge_tm_qs_schd_mode_cfg(hdev,
 						vport[i].qs_offset + pri_id,
-						HCLGE_SCH_MODE_DWRR);
+						mode);
 		if (ret)
 			return ret;
 	}
@ -1353,7 +1388,7 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
 	u8 i;

 	if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) {
-		for (i = 0; i < hdev->tm_info.num_tc; i++) {
+		for (i = 0; i < hdev->tc_max; i++) {
 			ret = hclge_tm_schd_mode_tc_base_cfg(hdev, i);
 			if (ret)
 				return ret;
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@ -237,6 +237,7 @@ int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr);
 void hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats);
 void hclge_pfc_tx_stats_get(struct hclge_dev *hdev, u64 *stats);
 int hclge_tm_qs_shaper_cfg(struct hclge_vport *vport, int max_tx_rate);
+int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev);
 int hclge_tm_get_qset_num(struct hclge_dev *hdev, u16 *qset_num);
 int hclge_tm_get_pri_num(struct hclge_dev *hdev, u8 *pri_num);
 int hclge_tm_get_qset_map_pri(struct hclge_dev *hdev, u16 qset_id, u8 *priority,
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@ -2588,15 +2588,16 @@ static void i40e_diag_test(struct net_device *netdev,

 		set_bit(__I40E_TESTING, pf->state);

+		if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
+		    test_bit(__I40E_RESET_INTR_RECEIVED, pf->state)) {
+			dev_warn(&pf->pdev->dev,
+				 "Cannot start offline testing when PF is in reset state.\n");
+			goto skip_ol_tests;
+		}
+
 		if (i40e_active_vfs(pf) || i40e_active_vmdqs(pf)) {
 			dev_warn(&pf->pdev->dev,
 				 "Please take active VFs and Netqueues offline and restart the adapter before running NIC diagnostics\n");
-			data[I40E_ETH_TEST_REG]		= 1;
-			data[I40E_ETH_TEST_EEPROM]	= 1;
-			data[I40E_ETH_TEST_INTR]	= 1;
-			data[I40E_ETH_TEST_LINK]	= 1;
-			eth_test->flags |= ETH_TEST_FL_FAILED;
-			clear_bit(__I40E_TESTING, pf->state);
 			goto skip_ol_tests;
 		}

@ -2643,9 +2644,17 @@ static void i40e_diag_test(struct net_device *netdev,
 		data[I40E_ETH_TEST_INTR] = 0;
 	}

-skip_ol_tests:
-
 	netif_info(pf, drv, netdev, "testing finished\n");
+	return;
+
+skip_ol_tests:
+	data[I40E_ETH_TEST_REG]		= 1;
+	data[I40E_ETH_TEST_EEPROM]	= 1;
+	data[I40E_ETH_TEST_INTR]	= 1;
+	data[I40E_ETH_TEST_LINK]	= 1;
+	eth_test->flags |= ETH_TEST_FL_FAILED;
+	clear_bit(__I40E_TESTING, pf->state);
+	netif_info(pf, drv, netdev, "testing failed\n");
 }

 static void i40e_get_wol(struct net_device *netdev,
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@ -8667,6 +8667,11 @@ static int i40e_configure_clsflower(struct i40e_vsi *vsi,
 		return -EOPNOTSUPP;
 	}

+	if (!tc) {
+		dev_err(&pf->pdev->dev, "Unable to add filter because of invalid destination");
+		return -EINVAL;
+	}
+
 	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
 	    test_bit(__I40E_RESET_INTR_RECEIVED, pf->state))
 		return -EBUSY;
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@ -2282,7 +2282,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 	}

 	if (vf->adq_enabled) {
-		for (i = 0; i < I40E_MAX_VF_VSI; i++)
+		for (i = 0; i < vf->num_tc; i++)
 			num_qps_all += vf->ch[i].num_qps;
 		if (num_qps_all != qci->num_queue_pairs) {
 			aq_ret = I40E_ERR_PARAM;
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@ -985,7 +985,7 @@ struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
 		f->add = true;
 		f->add_handled = false;
 		f->is_new_mac = true;
-		f->is_primary = false;
+		f->is_primary = ether_addr_equal(macaddr, adapter->hw.mac.addr);
 		adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER;
 	} else {
 		f->remove = false;
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@ -5763,25 +5763,38 @@ static netdev_features_t
 ice_fix_features(struct net_device *netdev, netdev_features_t features)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
-	netdev_features_t supported_vlan_filtering;
-	netdev_features_t requested_vlan_filtering;
-	struct ice_vsi *vsi = np->vsi;
+	netdev_features_t req_vlan_fltr, cur_vlan_fltr;
+	bool cur_ctag, cur_stag, req_ctag, req_stag;

-	requested_vlan_filtering = features & NETIF_VLAN_FILTERING_FEATURES;
+	cur_vlan_fltr = netdev->features & NETIF_VLAN_FILTERING_FEATURES;
+	cur_ctag = cur_vlan_fltr & NETIF_F_HW_VLAN_CTAG_FILTER;
+	cur_stag = cur_vlan_fltr & NETIF_F_HW_VLAN_STAG_FILTER;

-	/* make sure supported_vlan_filtering works for both SVM and DVM */
-	supported_vlan_filtering = NETIF_F_HW_VLAN_CTAG_FILTER;
-	if (ice_is_dvm_ena(&vsi->back->hw))
-		supported_vlan_filtering |= NETIF_F_HW_VLAN_STAG_FILTER;
+	req_vlan_fltr = features & NETIF_VLAN_FILTERING_FEATURES;
+	req_ctag = req_vlan_fltr & NETIF_F_HW_VLAN_CTAG_FILTER;
+	req_stag = req_vlan_fltr & NETIF_F_HW_VLAN_STAG_FILTER;

-	if (requested_vlan_filtering &&
-	    requested_vlan_filtering != supported_vlan_filtering) {
-		if (requested_vlan_filtering & NETIF_F_HW_VLAN_CTAG_FILTER) {
-			netdev_warn(netdev, "cannot support requested VLAN filtering settings, enabling all supported VLAN filtering settings\n");
-			features |= supported_vlan_filtering;
+	if (req_vlan_fltr != cur_vlan_fltr) {
+		if (ice_is_dvm_ena(&np->vsi->back->hw)) {
+			if (req_ctag && req_stag) {
+				features |= NETIF_VLAN_FILTERING_FEATURES;
+			} else if (!req_ctag && !req_stag) {
+				features &= ~NETIF_VLAN_FILTERING_FEATURES;
+			} else if ((!cur_ctag && req_ctag && !cur_stag) ||
+				   (!cur_stag && req_stag && !cur_ctag)) {
+				features |= NETIF_VLAN_FILTERING_FEATURES;
+				netdev_warn(netdev,  "802.1Q and 802.1ad VLAN filtering must be either both on or both off. VLAN filtering has been enabled for both types.\n");
+			} else if ((cur_ctag && !req_ctag && cur_stag) ||
+				   (cur_stag && !req_stag && cur_ctag)) {
+				features &= ~NETIF_VLAN_FILTERING_FEATURES;
+				netdev_warn(netdev,  "802.1Q and 802.1ad VLAN filtering must be either both on or both off. VLAN filtering has been disabled for both types.\n");
+			}
 		} else {
-			netdev_warn(netdev, "cannot support requested VLAN filtering settings, clearing all supported VLAN filtering settings\n");
-			features &= ~supported_vlan_filtering;
+			if (req_vlan_fltr & NETIF_F_HW_VLAN_STAG_FILTER)
+				netdev_warn(netdev, "cannot support requested 802.1ad filtering setting in SVM mode\n");
+
+			if (req_vlan_fltr & NETIF_F_HW_VLAN_CTAG_FILTER)
+				features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 		}
 	}

--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@ -2271,7 +2271,7 @@ static int
 ice_ptp_init_tx_e822(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
 {
 	tx->quad = port / ICE_PORTS_PER_QUAD;
-	tx->quad_offset = tx->quad * INDEX_PER_PORT;
+	tx->quad_offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT;
 	tx->len = INDEX_PER_PORT;

 	return ice_ptp_alloc_tx_tracker(tx);
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@ -49,6 +49,37 @@ struct ice_perout_channel {
 * To allow multiple ports to access the shared register block independently,
 * the blocks are split up so that indexes are assigned to each port based on
 * hardware logical port number.
+ *
+ * The timestamp blocks are handled differently for E810- and E822-based
+ * devices. In E810 devices, each port has its own block of timestamps, while in
+ * E822 there is a need to logically break the block of registers into smaller
+ * chunks based on the port number to avoid collisions.
+ *
+ * Example for port 5 in E810:
+ *  +--------+--------+--------+--------+--------+--------+--------+--------+
+ *  |register|register|register|register|register|register|register|register|
+ *  | block  | block  | block  | block  | block  | block  | block  | block  |
+ *  |  for   |  for   |  for   |  for   |  for   |  for   |  for   |  for   |
+ *  | port 0 | port 1 | port 2 | port 3 | port 4 | port 5 | port 6 | port 7 |
+ *  +--------+--------+--------+--------+--------+--------+--------+--------+
+ *                                               ^^
+ *                                               ||
+ *                                               |---  quad offset is always 0
+ *                                               ---- quad number
+ *
+ * Example for port 5 in E822:
+ * +-----------------------------+-----------------------------+
+ * |  register block for quad 0  |  register block for quad 1  |
+ * |+------+------+------+------+|+------+------+------+------+|
+ * ||port 0|port 1|port 2|port 3|||port 0|port 1|port 2|port 3||
+ * |+------+------+------+------+|+------+------+------+------+|
+ * +-----------------------------+-------^---------------------+
+ *                                ^      |
+ *                                |      --- quad offset*
+ *                                ---- quad number
+ *
+ *   * PHY port 5 is port 1 in quad 1
+ *
 */

 /**
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@ -504,6 +504,11 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 	}

 	if (ice_is_vf_disabled(vf)) {
+		vsi = ice_get_vf_vsi(vf);
+		if (WARN_ON(!vsi))
+			return -EINVAL;
+		ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id);
+		ice_vsi_stop_all_rx_rings(vsi);
 		dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n",
 			vf->vf_id);
 		return 0;
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@ -1592,35 +1592,27 @@ error_param:
 */
 static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 {
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_vsi_queue_config_info *qci =
 	    (struct virtchnl_vsi_queue_config_info *)msg;
 	struct virtchnl_queue_pair_info *qpi;
 	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
-	int i, q_idx;
+	int i = -1, q_idx;

-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
 		goto error_param;
-	}

-	if (!ice_vc_isvalid_vsi_id(vf, qci->vsi_id)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	if (!ice_vc_isvalid_vsi_id(vf, qci->vsi_id))
 		goto error_param;
-	}

 	vsi = ice_get_vf_vsi(vf);
-	if (!vsi) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	if (!vsi)
 		goto error_param;
-	}

 	if (qci->num_queue_pairs > ICE_MAX_RSS_QS_PER_VF ||
 	    qci->num_queue_pairs > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
 		dev_err(ice_pf_to_dev(pf), "VF-%d requesting more than supported number of queues: %d\n",
 			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}

@ -1633,7 +1625,6 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 		    !ice_vc_isvalid_ring_len(qpi->txq.ring_len) ||
 		    !ice_vc_isvalid_ring_len(qpi->rxq.ring_len) ||
 		    !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) {
-			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto error_param;
 		}

@ -1643,7 +1634,6 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 		 * for selected "vsi"
 		 */
 		if (q_idx >= vsi->alloc_txq || q_idx >= vsi->alloc_rxq) {
-			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto error_param;
 		}

@ -1653,14 +1643,13 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 			vsi->tx_rings[i]->count = qpi->txq.ring_len;

 			/* Disable any existing queue first */
-			if (ice_vf_vsi_dis_single_txq(vf, vsi, q_idx)) {
-				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			if (ice_vf_vsi_dis_single_txq(vf, vsi, q_idx))
 				goto error_param;
-			}

 			/* Configure a queue with the requested settings */
 			if (ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx)) {
-				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+				dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure TX queue %d\n",
+					 vf->vf_id, i);
 				goto error_param;
 			}
 		}
@ -1674,17 +1663,13 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)

 			if (qpi->rxq.databuffer_size != 0 &&
 			    (qpi->rxq.databuffer_size > ((16 * 1024) - 128) ||
-			     qpi->rxq.databuffer_size < 1024)) {
-				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			     qpi->rxq.databuffer_size < 1024))
 				goto error_param;
-			}
 			vsi->rx_buf_len = qpi->rxq.databuffer_size;
 			vsi->rx_rings[i]->rx_buf_len = vsi->rx_buf_len;
 			if (qpi->rxq.max_pkt_size > max_frame_size ||
-			    qpi->rxq.max_pkt_size < 64) {
-				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			    qpi->rxq.max_pkt_size < 64)
 				goto error_param;
-			}

 			vsi->max_frame = qpi->rxq.max_pkt_size;
 			/* add space for the port VLAN since the VF driver is
@ -1695,16 +1680,30 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 				vsi->max_frame += VLAN_HLEN;

 			if (ice_vsi_cfg_single_rxq(vsi, q_idx)) {
-				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+				dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure RX queue %d\n",
+					 vf->vf_id, i);
 				goto error_param;
 			}
 		}
 	}

-error_param:
 	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, v_ret,
-				     NULL, 0);
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES,
+				     VIRTCHNL_STATUS_SUCCESS, NULL, 0);
+error_param:
+	/* disable whatever we can */
+	for (; i >= 0; i--) {
+		if (ice_vsi_ctrl_one_rx_ring(vsi, false, i, true))
+			dev_err(ice_pf_to_dev(pf), "VF-%d could not disable RX queue %d\n",
+				vf->vf_id, i);
+		if (ice_vf_vsi_dis_single_txq(vf, vsi, i))
+			dev_err(ice_pf_to_dev(pf), "VF-%d could not disable TX queue %d\n",
+				vf->vf_id, i);
+	}
+
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES,
+				     VIRTCHNL_STATUS_ERR_PARAM, NULL, 0);
 }

 /**
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@ -1390,7 +1390,8 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev,

 static const struct ethtool_ops otx2vf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
-				     ETHTOOL_COALESCE_MAX_FRAMES,
+				     ETHTOOL_COALESCE_MAX_FRAMES |
+				     ETHTOOL_COALESCE_USE_ADAPTIVE,
 	.supported_ring_params  = ETHTOOL_RING_USE_RX_BUF_LEN |
 				  ETHTOOL_RING_USE_CQE_SIZE,
 	.get_link		= otx2_get_link,
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
@ -8,8 +8,8 @@
 #include "spectrum.h"

 enum mlxsw_sp_counter_sub_pool_id {
-	MLXSW_SP_COUNTER_SUB_POOL_FLOW,
 	MLXSW_SP_COUNTER_SUB_POOL_RIF,
+	MLXSW_SP_COUNTER_SUB_POOL_FLOW,
 };

 int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp,
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@ -547,6 +547,57 @@ static inline void axienet_iow(struct axienet_local *lp, off_t offset,
 	iowrite32(value, lp->regs + offset);
 }

+/**
+ * axienet_dma_out32 - Memory mapped Axi DMA register write.
+ * @lp:		Pointer to axienet local structure
+ * @reg:	Address offset from the base address of the Axi DMA core
+ * @value:	Value to be written into the Axi DMA register
+ *
+ * This function writes the desired value into the corresponding Axi DMA
+ * register.
+ */
+
+static inline void axienet_dma_out32(struct axienet_local *lp,
+				     off_t reg, u32 value)
+{
+	iowrite32(value, lp->dma_regs + reg);
+}
+
+#if defined(CONFIG_64BIT) && defined(iowrite64)
+/**
+ * axienet_dma_out64 - Memory mapped Axi DMA register write.
+ * @lp:		Pointer to axienet local structure
+ * @reg:	Address offset from the base address of the Axi DMA core
+ * @value:	Value to be written into the Axi DMA register
+ *
+ * This function writes the desired value into the corresponding Axi DMA
+ * register.
+ */
+static inline void axienet_dma_out64(struct axienet_local *lp,
+				     off_t reg, u64 value)
+{
+	iowrite64(value, lp->dma_regs + reg);
+}
+
+static inline void axienet_dma_out_addr(struct axienet_local *lp, off_t reg,
+					dma_addr_t addr)
+{
+	if (lp->features & XAE_FEATURE_DMA_64BIT)
+		axienet_dma_out64(lp, reg, addr);
+	else
+		axienet_dma_out32(lp, reg, lower_32_bits(addr));
+}
+
+#else /* CONFIG_64BIT */
+
+static inline void axienet_dma_out_addr(struct axienet_local *lp, off_t reg,
+				 dma_addr_t addr)
+{
+	axienet_dma_out32(lp, reg, lower_32_bits(addr));
+}
+
+#endif /* CONFIG_64BIT */
+
 /* Function prototypes visible in xilinx_axienet_mdio.c for other files */
 int axienet_mdio_enable(struct axienet_local *lp);
 void axienet_mdio_disable(struct axienet_local *lp);
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@ -133,30 +133,6 @@ static inline u32 axienet_dma_in32(struct axienet_local *lp, off_t reg)
 	return ioread32(lp->dma_regs + reg);
 }

-/**
- * axienet_dma_out32 - Memory mapped Axi DMA register write.
- * @lp:		Pointer to axienet local structure
- * @reg:	Address offset from the base address of the Axi DMA core
- * @value:	Value to be written into the Axi DMA register
- *
- * This function writes the desired value into the corresponding Axi DMA
- * register.
- */
-static inline void axienet_dma_out32(struct axienet_local *lp,
-				     off_t reg, u32 value)
-{
-	iowrite32(value, lp->dma_regs + reg);
-}
-
-static void axienet_dma_out_addr(struct axienet_local *lp, off_t reg,
-				 dma_addr_t addr)
-{
-	axienet_dma_out32(lp, reg, lower_32_bits(addr));
-
-	if (lp->features & XAE_FEATURE_DMA_64BIT)
-		axienet_dma_out32(lp, reg + 4, upper_32_bits(addr));
-}
-
 static void desc_set_phys_addr(struct axienet_local *lp, dma_addr_t addr,
 			       struct axidma_bd *desc)
 {
@ -2061,6 +2037,11 @@ static int axienet_probe(struct platform_device *pdev)
 			iowrite32(0x0, desc);
 		}
 	}
+	if (!IS_ENABLED(CONFIG_64BIT) && lp->features & XAE_FEATURE_DMA_64BIT) {
+		dev_err(&pdev->dev, "64-bit addressable DMA is not compatible with 32-bit archecture\n");
+		ret = -EINVAL;
+		goto cleanup_clk;
+	}

 	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(addr_width));
 	if (ret) {
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@ -1750,7 +1750,7 @@ static const struct driver_info ax88179_info = {
 	.link_reset = ax88179_link_reset,
 	.reset = ax88179_reset,
 	.stop = ax88179_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1763,7 +1763,7 @@ static const struct driver_info ax88178a_info = {
 	.link_reset = ax88179_link_reset,
 	.reset = ax88179_reset,
 	.stop = ax88179_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1776,7 +1776,7 @@ static const struct driver_info cypress_GX3_info = {
 	.link_reset = ax88179_link_reset,
 	.reset = ax88179_reset,
 	.stop = ax88179_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1789,7 +1789,7 @@ static const struct driver_info dlink_dub1312_info = {
 	.link_reset = ax88179_link_reset,
 	.reset = ax88179_reset,
 	.stop = ax88179_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1802,7 +1802,7 @@ static const struct driver_info sitecom_info = {
 	.link_reset = ax88179_link_reset,
 	.reset = ax88179_reset,
 	.stop = ax88179_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1815,7 +1815,7 @@ static const struct driver_info samsung_info = {
 	.link_reset = ax88179_link_reset,
 	.reset = ax88179_reset,
 	.stop = ax88179_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1828,7 +1828,7 @@ static const struct driver_info lenovo_info = {
 	.link_reset = ax88179_link_reset,
 	.reset = ax88179_reset,
 	.stop = ax88179_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1841,7 +1841,7 @@ static const struct driver_info belkin_info = {
 	.link_reset = ax88179_link_reset,
 	.reset	= ax88179_reset,
 	.stop	= ax88179_stop,
-	.flags	= FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags	= FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1854,7 +1854,7 @@ static const struct driver_info toshiba_info = {
 	.link_reset = ax88179_link_reset,
 	.reset	= ax88179_reset,
 	.stop = ax88179_stop,
-	.flags	= FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags	= FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1867,7 +1867,7 @@ static const struct driver_info mct_info = {
 	.link_reset = ax88179_link_reset,
 	.reset	= ax88179_reset,
 	.stop	= ax88179_stop,
-	.flags	= FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags	= FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1880,7 +1880,7 @@ static const struct driver_info at_umc2000_info = {
 	.link_reset = ax88179_link_reset,
 	.reset  = ax88179_reset,
 	.stop   = ax88179_stop,
-	.flags  = FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags  = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1893,7 +1893,7 @@ static const struct driver_info at_umc200_info = {
 	.link_reset = ax88179_link_reset,
 	.reset  = ax88179_reset,
 	.stop   = ax88179_stop,
-	.flags  = FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags  = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
@ -1906,7 +1906,7 @@ static const struct driver_info at_umc2000sp_info = {
 	.link_reset = ax88179_link_reset,
 	.reset  = ax88179_reset,
 	.stop   = ax88179_stop,
-	.flags  = FLAG_ETHER | FLAG_FRAMING_AX,
+	.flags  = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
 };
--- a/drivers/platform/mellanox/Kconfig
+++ b/drivers/platform/mellanox/Kconfig
@ -85,7 +85,7 @@ config NVSW_SN2201
 	depends on I2C
 	depends on REGMAP_I2C
 	help
-	  This driver provides support for the Nvidia SN2201 platfom.
+	  This driver provides support for the Nvidia SN2201 platform.
 	  The SN2201 is a highly integrated for one rack unit system with
 	  L3 management switches. It has 48 x 1Gbps RJ45 + 4 x 100G QSFP28
 	  ports in a compact 1RU form factor. The system also including a
--- a/drivers/platform/mellanox/nvsw-sn2201.c
+++ b/drivers/platform/mellanox/nvsw-sn2201.c
@ -326,7 +326,7 @@ static struct resource nvsw_sn2201_lpc_res[] = {
 };

 /* SN2201 I2C platform data. */
-struct mlxreg_core_hotplug_platform_data nvsw_sn2201_i2c_data = {
+static struct mlxreg_core_hotplug_platform_data nvsw_sn2201_i2c_data = {
 	.irq = NVSW_SN2201_CPLD_SYSIRQ,
 };

--- a/drivers/platform/x86/barco-p50-gpio.c
+++ b/drivers/platform/x86/barco-p50-gpio.c
@ -405,11 +405,14 @@ MODULE_DEVICE_TABLE(dmi, dmi_ids);
 static int __init p50_module_init(void)
 {
 	struct resource res = DEFINE_RES_IO(P50_GPIO_IO_PORT_BASE, P50_PORT_CMD + 1);
+	int ret;

 	if (!dmi_first_match(dmi_ids))
 		return -ENODEV;

-	platform_driver_register(&p50_gpio_driver);
+	ret = platform_driver_register(&p50_gpio_driver);
+	if (ret)
+		return ret;

 	gpio_pdev = platform_device_register_simple(DRIVER_NAME, PLATFORM_DEVID_NONE, &res, 1);
 	if (IS_ERR(gpio_pdev)) {
--- a/drivers/platform/x86/gigabyte-wmi.c
+++ b/drivers/platform/x86/gigabyte-wmi.c
@ -140,6 +140,7 @@ static u8 gigabyte_wmi_detect_sensor_usability(struct wmi_device *wdev)
 	}}

 static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = {
+	DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H-CF"),
 	DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M S2H V2"),
 	DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE AX V2"),
 	DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"),
@ -156,6 +157,7 @@ static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = {
 	DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 GAMING X"),
 	DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 I AORUS PRO WIFI"),
 	DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 UD"),
+	DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("Z690M AORUS ELITE AX DDR4"),
 	{ }
 };

--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@ -38,6 +38,7 @@ MODULE_ALIAS("wmi:5FB7F034-2C63-45e9-BE91-3D44E2C707E4");
 #define HPWMI_EVENT_GUID "95F24279-4D7B-4334-9387-ACCDC67EF61C"
 #define HPWMI_BIOS_GUID "5FB7F034-2C63-45e9-BE91-3D44E2C707E4"
 #define HP_OMEN_EC_THERMAL_PROFILE_OFFSET 0x95
+#define zero_if_sup(tmp) (zero_insize_support?0:sizeof(tmp)) // use when zero insize is required

 /* DMI board names of devices that should use the omen specific path for
 * thermal profiles.
@ -220,6 +221,7 @@ static struct input_dev *hp_wmi_input_dev;
 static struct platform_device *hp_wmi_platform_dev;
 static struct platform_profile_handler platform_profile_handler;
 static bool platform_profile_support;
+static bool zero_insize_support;

 static struct rfkill *wifi_rfkill;
 static struct rfkill *bluetooth_rfkill;
@ -290,14 +292,16 @@ static int hp_wmi_perform_query(int query, enum hp_wmi_command command,
 	struct bios_return *bios_return;
 	union acpi_object *obj = NULL;
 	struct bios_args *args = NULL;
-	int mid, actual_outsize, ret;
+	int mid, actual_insize, actual_outsize;
 	size_t bios_args_size;
+	int ret;

 	mid = encode_outsize_for_pvsz(outsize);
 	if (WARN_ON(mid < 0))
 		return mid;

-	bios_args_size = struct_size(args, data, insize);
+	actual_insize = max(insize, 128);
+	bios_args_size = struct_size(args, data, actual_insize);
 	args = kmalloc(bios_args_size, GFP_KERNEL);
 	if (!args)
 		return -ENOMEM;
@ -374,7 +378,7 @@ static int hp_wmi_read_int(int query)
 	int val = 0, ret;

 	ret = hp_wmi_perform_query(query, HPWMI_READ, &val,
-				   0, sizeof(val));
+				   zero_if_sup(val), sizeof(val));

 	if (ret)
 		return ret < 0 ? ret : -EINVAL;
@ -410,7 +414,8 @@ static int hp_wmi_get_tablet_mode(void)
 		return -ENODEV;

 	ret = hp_wmi_perform_query(HPWMI_SYSTEM_DEVICE_MODE, HPWMI_READ,
-				   system_device_mode, 0, sizeof(system_device_mode));
+				   system_device_mode, zero_if_sup(system_device_mode),
+				   sizeof(system_device_mode));
 	if (ret < 0)
 		return ret;

@ -497,7 +502,7 @@ static int hp_wmi_fan_speed_max_get(void)
 	int val = 0, ret;

 	ret = hp_wmi_perform_query(HPWMI_FAN_SPEED_MAX_GET_QUERY, HPWMI_GM,
-				   &val, 0, sizeof(val));
+				   &val, zero_if_sup(val), sizeof(val));

 	if (ret)
 		return ret < 0 ? ret : -EINVAL;
@ -509,7 +514,7 @@ static int __init hp_wmi_bios_2008_later(void)
 {
 	int state = 0;
 	int ret = hp_wmi_perform_query(HPWMI_FEATURE_QUERY, HPWMI_READ, &state,
-				       0, sizeof(state));
+				       zero_if_sup(state), sizeof(state));
 	if (!ret)
 		return 1;

@ -520,7 +525,7 @@ static int __init hp_wmi_bios_2009_later(void)
 {
 	u8 state[128];
 	int ret = hp_wmi_perform_query(HPWMI_FEATURE2_QUERY, HPWMI_READ, &state,
-				       0, sizeof(state));
+				       zero_if_sup(state), sizeof(state));
 	if (!ret)
 		return 1;

@ -598,7 +603,7 @@ static int hp_wmi_rfkill2_refresh(void)
 	int err, i;

 	err = hp_wmi_perform_query(HPWMI_WIRELESS2_QUERY, HPWMI_READ, &state,
-				   0, sizeof(state));
+				   zero_if_sup(state), sizeof(state));
 	if (err)
 		return err;

@ -1007,7 +1012,7 @@ static int __init hp_wmi_rfkill2_setup(struct platform_device *device)
 	int err, i;

 	err = hp_wmi_perform_query(HPWMI_WIRELESS2_QUERY, HPWMI_READ, &state,
-				   0, sizeof(state));
+				   zero_if_sup(state), sizeof(state));
 	if (err)
 		return err < 0 ? err : -EINVAL;

@ -1483,11 +1488,15 @@ static int __init hp_wmi_init(void)
 {
 	int event_capable = wmi_has_guid(HPWMI_EVENT_GUID);
 	int bios_capable = wmi_has_guid(HPWMI_BIOS_GUID);
-	int err;
+	int err, tmp = 0;

 	if (!bios_capable && !event_capable)
 		return -ENODEV;

+	if (hp_wmi_perform_query(HPWMI_HARDWARE_QUERY, HPWMI_READ, &tmp,
+				 sizeof(tmp), sizeof(tmp)) == HPWMI_RET_INVALID_PARAMETERS)
+		zero_insize_support = true;
+
 	if (event_capable) {
 		err = hp_wmi_input_setup();
 		if (err)
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@ -122,6 +122,12 @@ static const struct dmi_system_id dmi_vgbs_allow_list[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP Spectre x360 Convertible 15-df0xxx"),
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go"),
+		},
+	},
 	{ }
 };

--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@ -1912,6 +1912,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&tgl_reg_map),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&tgl_reg_map),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&adl_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,        &tgl_reg_map),
 	{}
 };

--- a/drivers/platform/x86/intel/pmt/crashlog.c
+++ b/drivers/platform/x86/intel/pmt/crashlog.c
@ -282,7 +282,7 @@ static int pmt_crashlog_probe(struct auxiliary_device *auxdev,
 	auxiliary_set_drvdata(auxdev, priv);

 	for (i = 0; i < intel_vsec_dev->num_resources; i++) {
-		struct intel_pmt_entry *entry = &priv->entry[i].entry;
+		struct intel_pmt_entry *entry = &priv->entry[priv->num_entries].entry;

 		ret = intel_pmt_dev_create(entry, &pmt_crashlog_ns, intel_vsec_dev, i);
 		if (ret < 0)
--- a/Show More
+++ b/Show More