Merge 5.16-rc4 into tty-next

We need the tty/serial driver fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Documentation/arm64/pointer-authentication.rst

@@ -53,11 +53,10 @@ The number of bits that the PAC occupies in a pointer is 55 minus the
 virtual address size configured by the kernel. For example, with a
 virtual address size of 48, the PAC is 7 bits wide.
 
-Recent versions of GCC can compile code with APIAKey-based return
+When ARM64_PTR_AUTH_KERNEL is selected, the kernel will be compiled
-address protection when passed the -msign-return-address option. This
+with HINT space pointer authentication instructions protecting
-uses instructions in the HINT space (unless -march=armv8.3-a or higher
+function returns. Kernels built with this option will work on hardware
-is also passed), and such code can run on systems without the pointer
+with or without pointer authentication support.
-authentication extension.
 
 In addition to exec(), keys can also be reinitialized to random values
 using the PR_PAC_RESET_KEYS prctl. A bitmask of PR_PAC_APIAKEY,

Documentation/cpu-freq/core.rst

@@ -73,12 +73,12 @@ CPUFREQ_POSTCHANGE.
 The third argument is a struct cpufreq_freqs with the following
 values:
 
-=====	===========================
+======	======================================
-cpu	number of the affected CPU
+policy	a pointer to the struct cpufreq_policy
 old	old frequency
 new	new frequency
 flags	flags of the cpufreq driver
-=====	===========================
+======	======================================
 
 3. CPUFreq Table Generation with Operating Performance Point (OPP)
 ==================================================================

Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml

@@ -17,9 +17,10 @@ properties:
     oneOf:
       - enum:
           - fsl,imx7ulp-lpi2c
-          - fsl,imx8qm-lpi2c
       - items:
-          - const: fsl,imx8qxp-lpi2c
+          - enum:
+              - fsl,imx8qxp-lpi2c
+              - fsl,imx8qm-lpi2c
           - const: fsl,imx7ulp-lpi2c
 
   reg:

Documentation/filesystems/cifs/ksmbd.rst

@@ -50,11 +50,11 @@ ksmbd.mountd (user space daemon)
 --------------------------------
 
 ksmbd.mountd is userspace process to, transfer user account and password that
-are registered using ksmbd.adduser(part of utils for user space). Further it
+are registered using ksmbd.adduser (part of utils for user space). Further it
 allows sharing information parameters that parsed from smb.conf to ksmbd in
 kernel. For the execution part it has a daemon which is continuously running
 and connected to the kernel interface using netlink socket, it waits for the
-requests(dcerpc and share/user info). It handles RPC calls (at a minimum few
+requests (dcerpc and share/user info). It handles RPC calls (at a minimum few
 dozen) that are most important for file server from NetShareEnum and
 NetServerGetInfo. Complete DCE/RPC response is prepared from the user space
 and passed over to the associated kernel thread for the client.
@@ -154,11 +154,11 @@ Each layer
 1. Enable all component prints
 	# sudo ksmbd.control -d "all"
 
-2. Enable one of components(smb, auth, vfs, oplock, ipc, conn, rdma)
+2. Enable one of components (smb, auth, vfs, oplock, ipc, conn, rdma)
 	# sudo ksmbd.control -d "smb"
 
-3. Show what prints are enable.
+3. Show what prints are enabled.
-	# cat/sys/class/ksmbd-control/debug
+	# cat /sys/class/ksmbd-control/debug
 	  [smb] auth vfs oplock ipc conn [rdma]
 
 4. Disable prints:

Documentation/filesystems/netfs_library.rst

@@ -1,7 +1,7 @@
 .. SPDX-License-Identifier: GPL-2.0
 
 =================================
-NETWORK FILESYSTEM HELPER LIBRARY
+Network Filesystem Helper Library
 =================================
 
 .. Contents:
@@ -37,22 +37,22 @@ into a common call framework.
 
 The following services are provided:
 
- * Handles transparent huge pages (THPs).
+ * Handle folios that span multiple pages.
 
- * Insulates the netfs from VM interface changes.
+ * Insulate the netfs from VM interface changes.
 
- * Allows the netfs to arbitrarily split reads up into pieces, even ones that
+ * Allow the netfs to arbitrarily split reads up into pieces, even ones that
-   don't match page sizes or page alignments and that may cross pages.
+   don't match folio sizes or folio alignments and that may cross folios.
 
- * Allows the netfs to expand a readahead request in both directions to meet
+ * Allow the netfs to expand a readahead request in both directions to meet its
-   its needs.
+   needs.
 
- * Allows the netfs to partially fulfil a read, which will then be resubmitted.
+ * Allow the netfs to partially fulfil a read, which will then be resubmitted.
 
- * Handles local caching, allowing cached data and server-read data to be
+ * Handle local caching, allowing cached data and server-read data to be
    interleaved for a single request.
 
- * Handles clearing of bufferage that aren't on the server.
+ * Handle clearing of bufferage that aren't on the server.
 
  * Handle retrying of reads that failed, switching reads from the cache to the
    server as necessary.
@@ -70,22 +70,22 @@ Read Helper Functions
 
 Three read helpers are provided::
 
- * void netfs_readahead(struct readahead_control *ractl,
+	void netfs_readahead(struct readahead_control *ractl,
-			const struct netfs_read_request_ops *ops,
+			     const struct netfs_read_request_ops *ops,
-			void *netfs_priv);``
+			     void *netfs_priv);
- * int netfs_readpage(struct file *file,
+	int netfs_readpage(struct file *file,
-		      struct page *page,
+			   struct folio *folio,
-		      const struct netfs_read_request_ops *ops,
+			   const struct netfs_read_request_ops *ops,
-		      void *netfs_priv);
+			   void *netfs_priv);
- * int netfs_write_begin(struct file *file,
+	int netfs_write_begin(struct file *file,
-			 struct address_space *mapping,
+			      struct address_space *mapping,
-			 loff_t pos,
+			      loff_t pos,
-			 unsigned int len,
+			      unsigned int len,
-			 unsigned int flags,
+			      unsigned int flags,
-			 struct page **_page,
+			      struct folio **_folio,
-			 void **_fsdata,
+			      void **_fsdata,
-			 const struct netfs_read_request_ops *ops,
+			      const struct netfs_read_request_ops *ops,
-			 void *netfs_priv);
+			      void *netfs_priv);
 
 Each corresponds to a VM operation, with the addition of a couple of parameters
 for the use of the read helpers:
@@ -103,8 +103,8 @@ Both of these values will be stored into the read request structure.
 For ->readahead() and ->readpage(), the network filesystem should just jump
 into the corresponding read helper; whereas for ->write_begin(), it may be a
 little more complicated as the network filesystem might want to flush
-conflicting writes or track dirty data and needs to put the acquired page if an
+conflicting writes or track dirty data and needs to put the acquired folio if
-error occurs after calling the helper.
+an error occurs after calling the helper.
 
 The helpers manage the read request, calling back into the network filesystem
 through the suppplied table of operations.  Waits will be performed as
@@ -253,7 +253,7 @@ through which it can issue requests and negotiate::
 		void (*issue_op)(struct netfs_read_subrequest *subreq);
 		bool (*is_still_valid)(struct netfs_read_request *rreq);
 		int (*check_write_begin)(struct file *file, loff_t pos, unsigned len,
-					 struct page *page, void **_fsdata);
+					 struct folio *folio, void **_fsdata);
 		void (*done)(struct netfs_read_request *rreq);
 		void (*cleanup)(struct address_space *mapping, void *netfs_priv);
 	};
@@ -313,13 +313,14 @@ The operations are as follows:
 
    There is no return value; the netfs_subreq_terminated() function should be
    called to indicate whether or not the operation succeeded and how much data
-   it transferred.  The filesystem also should not deal with setting pages
+   it transferred.  The filesystem also should not deal with setting folios
    uptodate, unlocking them or dropping their refs - the helpers need to deal
    with this as they have to coordinate with copying to the local cache.
 
-   Note that the helpers have the pages locked, but not pinned.  It is possible
+   Note that the helpers have the folios locked, but not pinned.  It is
-   to use the ITER_XARRAY iov iterator to refer to the range of the inode that
+   possible to use the ITER_XARRAY iov iterator to refer to the range of the
-   is being operated upon without the need to allocate large bvec tables.
+   inode that is being operated upon without the need to allocate large bvec
+   tables.
 
  * ``is_still_valid()``
 
@@ -330,15 +331,15 @@ The operations are as follows:
  * ``check_write_begin()``
 
    [Optional] This is called from the netfs_write_begin() helper once it has
-   allocated/grabbed the page to be modified to allow the filesystem to flush
+   allocated/grabbed the folio to be modified to allow the filesystem to flush
    conflicting state before allowing it to be modified.
 
-   It should return 0 if everything is now fine, -EAGAIN if the page should be
+   It should return 0 if everything is now fine, -EAGAIN if the folio should be
    regrabbed and any other error code to abort the operation.
 
  * ``done``
 
-   [Optional] This is called after the pages in the request have all been
+   [Optional] This is called after the folios in the request have all been
    unlocked (and marked uptodate if applicable).
 
  * ``cleanup``
@@ -390,7 +391,7 @@ The read helpers work by the following general procedure:
      * If NETFS_SREQ_CLEAR_TAIL was set, a short read will be cleared to the
        end of the slice instead of reissuing.
 
- * Once the data is read, the pages that have been fully read/cleared:
+ * Once the data is read, the folios that have been fully read/cleared:
 
    * Will be marked uptodate.
 
@@ -398,11 +399,11 @@ The read helpers work by the following general procedure:
 
    * Unlocked
 
- * Any pages that need writing to the cache will then have DIO writes issued.
+ * Any folios that need writing to the cache will then have DIO writes issued.
 
  * Synchronous operations will wait for reading to be complete.
 
- * Writes to the cache will proceed asynchronously and the pages will have the
+ * Writes to the cache will proceed asynchronously and the folios will have the
    PG_fscache mark removed when that completes.
 
  * The request structures will be cleaned up when everything has completed.
@@ -452,6 +453,9 @@ operation table looks like the following::
 			    netfs_io_terminated_t term_func,
 			    void *term_func_priv);
 
+		int (*prepare_write)(struct netfs_cache_resources *cres,
+				     loff_t *_start, size_t *_len, loff_t i_size);
+
 		int (*write)(struct netfs_cache_resources *cres,
 			     loff_t start_pos,
 			     struct iov_iter *iter,
@@ -509,6 +513,14 @@ The methods defined in the table are:
    indicating whether the termination is definitely happening in the caller's
    context.
 
+ * ``prepare_write()``
+
+   [Required] Called to adjust a write to the cache and check that there is
+   sufficient space in the cache.  The start and length values indicate the
+   size of the write that netfslib is proposing, and this can be adjusted by
+   the cache to respect DIO boundaries.  The file size is passed for
+   information.
+
  * ``write()``
 
    [Required] Called to write to the cache.  The start file offset is given
@@ -525,4 +537,9 @@ not the read request structure as they could be used in other situations where
 there isn't a read request structure as well, such as writing dirty data to the
 cache.
 
+
+API Function Reference
+======================
+
 .. kernel-doc:: include/linux/netfs.h
+.. kernel-doc:: fs/netfs/read_helper.c

Documentation/i2c/smbus-protocol.rst

@@ -36,6 +36,8 @@ Key to symbols
 
 =============== =============================================================
 S               Start condition
+Sr              Repeated start condition, used to switch from write to
+                read mode.
 P               Stop condition
 Rd/Wr (1 bit)   Read/Write bit. Rd equals 1, Wr equals 0.
 A, NA (1 bit)   Acknowledge (ACK) and Not Acknowledge (NACK) bit
@@ -100,7 +102,7 @@ Implemented by i2c_smbus_read_byte_data()
 This reads a single byte from a device, from a designated register.
 The register is specified through the Comm byte::
 
-  S Addr Wr [A] Comm [A] S Addr Rd [A] [Data] NA P
+  S Addr Wr [A] Comm [A] Sr Addr Rd [A] [Data] NA P
 
 Functionality flag: I2C_FUNC_SMBUS_READ_BYTE_DATA
 
@@ -114,7 +116,7 @@ This operation is very like Read Byte; again, data is read from a
 device, from a designated register that is specified through the Comm
 byte. But this time, the data is a complete word (16 bits)::
 
-  S Addr Wr [A] Comm [A] S Addr Rd [A] [DataLow] A [DataHigh] NA P
+  S Addr Wr [A] Comm [A] Sr Addr Rd [A] [DataLow] A [DataHigh] NA P
 
 Functionality flag: I2C_FUNC_SMBUS_READ_WORD_DATA
 
@@ -164,7 +166,7 @@ This command selects a device register (through the Comm byte), sends
 16 bits of data to it, and reads 16 bits of data in return::
 
   S Addr Wr [A] Comm [A] DataLow [A] DataHigh [A]
-                               S Addr Rd [A] [DataLow] A [DataHigh] NA P
+                              Sr Addr Rd [A] [DataLow] A [DataHigh] NA P
 
 Functionality flag: I2C_FUNC_SMBUS_PROC_CALL
 
@@ -181,7 +183,7 @@ of data is specified by the device in the Count byte.
 ::
 
   S Addr Wr [A] Comm [A]
-             S Addr Rd [A] [Count] A [Data] A [Data] A ... A [Data] NA P
+            Sr Addr Rd [A] [Count] A [Data] A [Data] A ... A [Data] NA P
 
 Functionality flag: I2C_FUNC_SMBUS_READ_BLOCK_DATA
 
@@ -212,7 +214,7 @@ This command selects a device register (through the Comm byte), sends
 1 to 31 bytes of data to it, and reads 1 to 31 bytes of data in return::
 
   S Addr Wr [A] Comm [A] Count [A] Data [A] ...
-                               S Addr Rd [A] [Count] A [Data] ... A P
+                              Sr Addr Rd [A] [Count] A [Data] ... A P
 
 Functionality flag: I2C_FUNC_SMBUS_BLOCK_PROC_CALL
 
@@ -300,7 +302,7 @@ This command reads a block of bytes from a device, from a
 designated register that is specified through the Comm byte::
 
   S Addr Wr [A] Comm [A]
-             S Addr Rd [A] [Data] A [Data] A ... A [Data] NA P
+            Sr Addr Rd [A] [Data] A [Data] A ... A [Data] NA P
 
 Functionality flag: I2C_FUNC_SMBUS_READ_I2C_BLOCK
 

Documentation/networking/ipvs-sysctl.rst

@@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER
 
 	0: disable any special handling on port reuse. The new
 	connection will be delivered to the same real server that was
-	servicing the previous connection. This will effectively
+	servicing the previous connection.
-	disable expire_nodest_conn.
 
 	bit 1: enable rescheduling of new connections when it is safe.
 	That is, whenever expire_nodest_conn and for TCP sockets, when

Documentation/networking/timestamping.rst

@@ -486,8 +486,8 @@ of packets.
 Drivers are free to use a more permissive configuration than the requested
 configuration. It is expected that drivers should only implement directly the
 most generic mode that can be supported. For example if the hardware can
-support HWTSTAMP_FILTER_V2_EVENT, then it should generally always upscale
+support HWTSTAMP_FILTER_PTP_V2_EVENT, then it should generally always upscale
-HWTSTAMP_FILTER_V2_L2_SYNC_MESSAGE, and so forth, as HWTSTAMP_FILTER_V2_EVENT
+HWTSTAMP_FILTER_PTP_V2_L2_SYNC, and so forth, as HWTSTAMP_FILTER_PTP_V2_EVENT
 is more generic (and more useful to applications).
 
 A driver which supports hardware time stamping shall update the struct

MAINTAINERS

@@ -2263,6 +2263,15 @@ L:	linux-iio@vger.kernel.org
 S:	Maintained
 F:	drivers/counter/microchip-tcb-capture.c
 
+ARM/MILBEAUT ARCHITECTURE
+M:	Taichi Sugaya <sugaya.taichi@socionext.com>
+M:	Takao Orito <orito.takao@socionext.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/boot/dts/milbeaut*
+F:	arch/arm/mach-milbeaut/
+N:	milbeaut
+
 ARM/MIOA701 MACHINE SUPPORT
 M:	Robert Jarzmik <robert.jarzmik@free.fr>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -2729,10 +2738,11 @@ S:	Maintained
 F:	drivers/memory/*emif*
 
 ARM/TEXAS INSTRUMENT KEYSTONE ARCHITECTURE
+M:	Nishanth Menon <nm@ti.com>
 M:	Santosh Shilimkar <ssantosh@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ti/linux.git
 F:	arch/arm/boot/dts/keystone-*
 F:	arch/arm/mach-keystone/
 
@@ -3570,13 +3580,14 @@ L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/broadcom/b44.*
 
-BROADCOM B53 ETHERNET SWITCH DRIVER
+BROADCOM B53/SF2 ETHERNET SWITCH DRIVER
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	netdev@vger.kernel.org
 L:	openwrt-devel@lists.openwrt.org (subscribers-only)
 S:	Supported
 F:	Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml
 F:	drivers/net/dsa/b53/*
+F:	drivers/net/dsa/bcm_sf2*
 F:	include/linux/dsa/brcm.h
 F:	include/linux/platform_data/b53.h
 
@@ -15968,6 +15979,7 @@ F:	arch/mips/generic/board-ranchu.c
 
 RANDOM NUMBER DRIVER
 M:	"Theodore Ts'o" <tytso@mit.edu>
+M:	Jason A. Donenfeld <Jason@zx2c4.com>
 S:	Maintained
 F:	drivers/char/random.c
 
@@ -16490,6 +16502,12 @@ T:	git git://linuxtv.org/media_tree.git
 F:	Documentation/devicetree/bindings/media/allwinner,sun8i-a83t-de2-rotate.yaml
 F:	drivers/media/platform/sunxi/sun8i-rotate/
 
+RPMSG TTY DRIVER
+M:	Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
+L:	linux-remoteproc@vger.kernel.org
+S:	Maintained
+F:	drivers/tty/rpmsg_tty.c
+
 RTL2830 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
@@ -16612,7 +16630,8 @@ F:	drivers/iommu/s390-iommu.c
 
 S390 IUCV NETWORK LAYER
 M:	Julian Wiedmann <jwi@linux.ibm.com>
-M:	Karsten Graul <kgraul@linux.ibm.com>
+M:	Alexandra Winter <wintera@linux.ibm.com>
+M:	Wenjia Zhang <wenjia@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -16623,7 +16642,8 @@ F:	net/iucv/
 
 S390 NETWORK DRIVERS
 M:	Julian Wiedmann <jwi@linux.ibm.com>
-M:	Karsten Graul <kgraul@linux.ibm.com>
+M:	Alexandra Winter <wintera@linux.ibm.com>
+M:	Wenjia Zhang <wenjia@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -18483,6 +18503,7 @@ F:	include/uapi/linux/pkt_sched.h
 F:	include/uapi/linux/tc_act/
 F:	include/uapi/linux/tc_ematch/
 F:	net/sched/
+F:	tools/testing/selftests/tc-testing
 
 TC90522 MEDIA DRIVER
 M:	Akihiro Tsukada <tskd08@gmail.com>
@@ -19031,11 +19052,12 @@ F:	drivers/mmc/host/tifm_sd.c
 F:	include/linux/tifm.h
 
 TI KEYSTONE MULTICORE NAVIGATOR DRIVERS
+M:	Nishanth Menon <nm@ti.com>
 M:	Santosh Shilimkar <ssantosh@kernel.org>
 L:	linux-kernel@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ti/linux.git
 F:	drivers/soc/ti/*
 
 TI LM49xxx FAMILY ASoC CODEC DRIVERS

Makefile

@@ -2,8 +2,8 @@
 VERSION = 5
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
-NAME = Trick or Treat
+NAME = Gobble Gobble
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"

arch/Kconfig

@@ -991,6 +991,16 @@ config HAVE_ARCH_COMPAT_MMAP_BASES
 	  and vice-versa 32-bit applications to call 64-bit mmap().
 	  Required for applications doing different bitness syscalls.
 
+config PAGE_SIZE_LESS_THAN_64KB
+	def_bool y
+	depends on !ARM64_64K_PAGES
+	depends on !IA64_PAGE_SIZE_64KB
+	depends on !PAGE_SIZE_64KB
+	depends on !PARISC_PAGE_SIZE_64KB
+	depends on !PPC_64K_PAGES
+	depends on !PPC_256K_PAGES
+	depends on !PAGE_SIZE_256KB
+
 # This allows to use a set of generic functions to determine mmap base
 # address by giving priority to top-down scheme only if the process
 # is not in legacy mode (compat task, unlimited stack size or

arch/alpha/kernel/syscalls/syscall.tbl

@@ -488,3 +488,4 @@
 556	common	landlock_restrict_self		sys_landlock_restrict_self
 # 557 reserved for memfd_secret
 558	common	process_mrelease		sys_process_mrelease
+559	common  futex_waitv                     sys_futex_waitv

arch/arc/include/asm/cacheflush.h

@@ -36,7 +36,6 @@ void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr);
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 
 void flush_dcache_page(struct page *page);
-void flush_dcache_folio(struct folio *folio);
 
 void dma_cache_wback_inv(phys_addr_t start, unsigned long sz);
 void dma_cache_inv(phys_addr_t start, unsigned long sz);

arch/arm/boot/dts/bcm2711.dtsi

@@ -506,11 +506,17 @@
 			#address-cells = <3>;
 			#interrupt-cells = <1>;
 			#size-cells = <2>;
-			interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "pcie", "msi";
 			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
 			interrupt-map = <0 0 0 1 &gicv2 GIC_SPI 143
+							IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 2 &gicv2 GIC_SPI 144
+							IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 3 &gicv2 GIC_SPI 145
+							IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 4 &gicv2 GIC_SPI 146
 							IRQ_TYPE_LEVEL_HIGH>;
 			msi-controller;
 			msi-parent = <&pcie0>;

arch/arm/boot/dts/bcm5301x.dtsi

@@ -242,6 +242,8 @@
 
 			gpio-controller;
 			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
 		};
 
 		pcie0: pcie@12000 {
@@ -408,7 +410,7 @@
 	i2c0: i2c@18009000 {
 		compatible = "brcm,iproc-i2c";
 		reg = <0x18009000 0x50>;
-		interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clock-frequency = <100000>;

arch/arm/include/asm/cacheflush.h

@@ -290,7 +290,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
  */
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
-void flush_dcache_folio(struct folio *folio);
 
 #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1
 static inline void flush_kernel_vmap_range(void *addr, int size)

arch/arm/mach-socfpga/core.h

@@ -33,7 +33,7 @@ extern void __iomem *sdr_ctl_base_addr;
 u32 socfpga_sdram_self_refresh(u32 sdr_base);
 extern unsigned int socfpga_sdram_self_refresh_sz;
 
-extern char secondary_trampoline, secondary_trampoline_end;
+extern char secondary_trampoline[], secondary_trampoline_end[];
 
 extern unsigned long socfpga_cpu1start_addr;
 

arch/arm/mach-socfpga/platsmp.c

@@ -20,14 +20,14 @@
 
 static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	int trampoline_size = &secondary_trampoline_end - &secondary_trampoline;
+	int trampoline_size = secondary_trampoline_end - secondary_trampoline;
 
 	if (socfpga_cpu1start_addr) {
 		/* This will put CPU #1 into reset. */
 		writel(RSTMGR_MPUMODRST_CPU1,
 		       rst_manager_base_addr + SOCFPGA_RSTMGR_MODMPURST);
 
-		memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size);
+		memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size);
 
 		writel(__pa_symbol(secondary_startup),
 		       sys_manager_base_addr + (socfpga_cpu1start_addr & 0x000000ff));
@@ -45,12 +45,12 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 static int socfpga_a10_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	int trampoline_size = &secondary_trampoline_end - &secondary_trampoline;
+	int trampoline_size = secondary_trampoline_end - secondary_trampoline;
 
 	if (socfpga_cpu1start_addr) {
 		writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr +
 		       SOCFPGA_A10_RSTMGR_MODMPURST);
-		memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size);
+		memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size);
 
 		writel(__pa_symbol(secondary_startup),
 		       sys_manager_base_addr + (socfpga_cpu1start_addr & 0x00000fff));

arch/arm64/boot/dts/exynos/exynosautov9.dtsi

@@ -296,8 +296,7 @@
 			pinctrl-0 = <&ufs_rst_n &ufs_refclk_out>;
 			phys = <&ufs_0_phy>;
 			phy-names = "ufs-phy";
-			samsung,sysreg = <&syscon_fsys2>;
+			samsung,sysreg = <&syscon_fsys2 0x710>;
-			samsung,ufs-shareability-reg-offset = <0x710>;
 			status = "disabled";
 		};
 	};

arch/arm64/include/asm/ftrace.h

@@ -12,6 +12,17 @@
 
 #define HAVE_FUNCTION_GRAPH_FP_TEST
 
+/*
+ * HAVE_FUNCTION_GRAPH_RET_ADDR_PTR means that the architecture can provide a
+ * "return address pointer" which can be used to uniquely identify a return
+ * address which has been overwritten.
+ *
+ * On arm64 we use the address of the caller's frame record, which remains the
+ * same for the lifetime of the instrumented function, unlike the return
+ * address in the LR.
+ */
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #else

arch/arm64/include/asm/kvm_arm.h

@@ -91,7 +91,7 @@
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */
-#define TCR_EL2_RES1		((1 << 31) | (1 << 23))
+#define TCR_EL2_RES1		((1U << 31) | (1 << 23))
 #define TCR_EL2_TBI		(1 << 20)
 #define TCR_EL2_PS_SHIFT	16
 #define TCR_EL2_PS_MASK		(7 << TCR_EL2_PS_SHIFT)
@@ -276,7 +276,7 @@
 #define CPTR_EL2_TFP_SHIFT 10
 
 /* Hyp Coprocessor Trap Register */
-#define CPTR_EL2_TCPAC	(1 << 31)
+#define CPTR_EL2_TCPAC	(1U << 31)
 #define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)

arch/arm64/include/asm/pgalloc.h

@@ -76,7 +76,7 @@ static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep,
 static inline void
 pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
 {
-	VM_BUG_ON(mm != &init_mm);
+	VM_BUG_ON(mm && mm != &init_mm);
 	__pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE | PMD_TABLE_UXN);
 }
 

arch/arm64/include/asm/stacktrace.h

@@ -47,9 +47,6 @@ struct stack_info {
  * @prev_type:   The type of stack this frame record was on, or a synthetic
  *               value of STACK_TYPE_UNKNOWN. This is used to detect a
  *               transition from one stack to another.
- *
- * @graph:       When FUNCTION_GRAPH_TRACER is selected, holds the index of a
- *               replacement lr value in the ftrace graph stack.
  */
 struct stackframe {
 	unsigned long fp;
@@ -57,9 +54,6 @@ struct stackframe {
 	DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES);
 	unsigned long prev_fp;
 	enum stack_type prev_type;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	int graph;
-#endif
 #ifdef CONFIG_KRETPROBES
 	struct llist_node *kr_cur;
 #endif

arch/arm64/include/asm/uaccess.h

@@ -281,12 +281,22 @@ do {									\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
 } while (0)
 
+/*
+ * We must not call into the scheduler between uaccess_ttbr0_enable() and
+ * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions,
+ * we must evaluate these outside of the critical section.
+ */
 #define __raw_get_user(x, ptr, err)					\
 do {									\
+	__typeof__(*(ptr)) __user *__rgu_ptr = (ptr);			\
+	__typeof__(x) __rgu_val;					\
 	__chk_user_ptr(ptr);						\
+									\
 	uaccess_ttbr0_enable();						\
-	__raw_get_mem("ldtr", x, ptr, err);				\
+	__raw_get_mem("ldtr", __rgu_val, __rgu_ptr, err);		\
 	uaccess_ttbr0_disable();					\
+									\
+	(x) = __rgu_val;						\
 } while (0)
 
 #define __get_user_error(x, ptr, err)					\
@@ -310,14 +320,22 @@ do {									\
 
 #define get_user	__get_user
 
+/*
+ * We must not call into the scheduler between __uaccess_enable_tco_async() and
+ * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking
+ * functions, we must evaluate these outside of the critical section.
+ */
 #define __get_kernel_nofault(dst, src, type, err_label)			\
 do {									\
+	__typeof__(dst) __gkn_dst = (dst);				\
+	__typeof__(src) __gkn_src = (src);				\
 	int __gkn_err = 0;						\
 									\
 	__uaccess_enable_tco_async();					\
-	__raw_get_mem("ldr", *((type *)(dst)),				\
+	__raw_get_mem("ldr", *((type *)(__gkn_dst)),			\
-		      (__force type *)(src), __gkn_err);		\
+		      (__force type *)(__gkn_src), __gkn_err);		\
 	__uaccess_disable_tco_async();					\
+									\
 	if (unlikely(__gkn_err))					\
 		goto err_label;						\
 } while (0)
@@ -351,11 +369,19 @@ do {									\
 	}								\
 } while (0)
 
+/*
+ * We must not call into the scheduler between uaccess_ttbr0_enable() and
+ * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions,
+ * we must evaluate these outside of the critical section.
+ */
 #define __raw_put_user(x, ptr, err)					\
 do {									\
-	__chk_user_ptr(ptr);						\
+	__typeof__(*(ptr)) __user *__rpu_ptr = (ptr);			\
+	__typeof__(*(ptr)) __rpu_val = (x);				\
+	__chk_user_ptr(__rpu_ptr);					\
+									\
 	uaccess_ttbr0_enable();						\
-	__raw_put_mem("sttr", x, ptr, err);				\
+	__raw_put_mem("sttr", __rpu_val, __rpu_ptr, err);		\
 	uaccess_ttbr0_disable();					\
 } while (0)
 
@@ -380,14 +406,22 @@ do {									\
 
 #define put_user	__put_user
 
+/*
+ * We must not call into the scheduler between __uaccess_enable_tco_async() and
+ * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking
+ * functions, we must evaluate these outside of the critical section.
+ */
 #define __put_kernel_nofault(dst, src, type, err_label)			\
 do {									\
+	__typeof__(dst) __pkn_dst = (dst);				\
+	__typeof__(src) __pkn_src = (src);				\
 	int __pkn_err = 0;						\
 									\
 	__uaccess_enable_tco_async();					\
-	__raw_put_mem("str", *((type *)(src)),				\
+	__raw_put_mem("str", *((type *)(__pkn_src)),			\
-		      (__force type *)(dst), __pkn_err);		\
+		      (__force type *)(__pkn_dst), __pkn_err);		\
 	__uaccess_disable_tco_async();					\
+									\
 	if (unlikely(__pkn_err))					\
 		goto err_label;						\
 } while(0)

arch/arm64/kernel/entry-ftrace.S

@@ -77,11 +77,17 @@
 	.endm
 
 SYM_CODE_START(ftrace_regs_caller)
+#ifdef BTI_C
+	BTI_C
+#endif
 	ftrace_regs_entry	1
 	b	ftrace_common
 SYM_CODE_END(ftrace_regs_caller)
 
 SYM_CODE_START(ftrace_caller)
+#ifdef BTI_C
+	BTI_C
+#endif
 	ftrace_regs_entry	0
 	b	ftrace_common
 SYM_CODE_END(ftrace_caller)

arch/arm64/kernel/ftrace.c

@@ -244,8 +244,6 @@ void arch_ftrace_update_code(int command)
  * on the way back to parent. For this purpose, this function is called
  * in _mcount() or ftrace_caller() to replace return address (*parent) on
  * the call stack to return_to_handler.
- *
- * Note that @frame_pointer is used only for sanity check later.
  */
 void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 			   unsigned long frame_pointer)
@@ -263,8 +261,10 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 	 */
 	old = *parent;
 
-	if (!function_graph_enter(old, self_addr, frame_pointer, NULL))
+	if (!function_graph_enter(old, self_addr, frame_pointer,
+	    (void *)frame_pointer)) {
 		*parent = return_hooker;
+	}
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE

arch/arm64/kernel/machine_kexec.c

@@ -147,7 +147,7 @@ int machine_kexec_post_load(struct kimage *kimage)
 	if (rc)
 		return rc;
 	kimage->arch.ttbr1 = __pa(trans_pgd);
-	kimage->arch.zero_page = __pa(empty_zero_page);
+	kimage->arch.zero_page = __pa_symbol(empty_zero_page);
 
 	reloc_size = __relocate_new_kernel_end - __relocate_new_kernel_start;
 	memcpy(reloc_code, __relocate_new_kernel_start, reloc_size);

arch/arm64/kernel/stacktrace.c

@@ -38,9 +38,6 @@ void start_backtrace(struct stackframe *frame, unsigned long fp,
 {
 	frame->fp = fp;
 	frame->pc = pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame->graph = 0;
-#endif
 #ifdef CONFIG_KRETPROBES
 	frame->kr_cur = NULL;
 #endif
@@ -116,20 +113,23 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	frame->prev_fp = fp;
 	frame->prev_type = info.type;
 
+	frame->pc = ptrauth_strip_insn_pac(frame->pc);
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (tsk->ret_stack &&
-		(ptrauth_strip_insn_pac(frame->pc) == (unsigned long)return_to_handler)) {
+		(frame->pc == (unsigned long)return_to_handler)) {
-		struct ftrace_ret_stack *ret_stack;
+		unsigned long orig_pc;
 		/*
 		 * This is a case where function graph tracer has
 		 * modified a return address (LR) in a stack frame
 		 * to hook a function return.
 		 * So replace it to an original value.
 		 */
-		ret_stack = ftrace_graph_get_ret_stack(tsk, frame->graph++);
+		orig_pc = ftrace_graph_ret_addr(tsk, NULL, frame->pc,
-		if (WARN_ON_ONCE(!ret_stack))
+						(void *)frame->fp);
+		if (WARN_ON_ONCE(frame->pc == orig_pc))
 			return -EINVAL;
-		frame->pc = ret_stack->ret;
+		frame->pc = orig_pc;
 	}
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 #ifdef CONFIG_KRETPROBES
@@ -137,8 +137,6 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 		frame->pc = kretprobe_find_ret_addr(tsk, (void *)frame->fp, &frame->kr_cur);
 #endif
 
-	frame->pc = ptrauth_strip_insn_pac(frame->pc);
-
 	return 0;
 }
 NOKPROBE_SYMBOL(unwind_frame);

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -403,6 +403,8 @@ typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *);
 
 static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu);
 
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code);
+
 /*
  * Allow the hypervisor to handle the exit with an exit handler if it has one.
  *
@@ -429,6 +431,18 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
  */
 static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
+	/*
+	 * Save PSTATE early so that we can evaluate the vcpu mode
+	 * early on.
+	 */
+	vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR);
+
+	/*
+	 * Check whether we want to repaint the state one way or
+	 * another.
+	 */
+	early_exit_filter(vcpu, exit_code);
+
 	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
 

arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h

@@ -70,7 +70,12 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->regs.pc			= read_sysreg_el2(SYS_ELR);
-	ctxt->regs.pstate		= read_sysreg_el2(SYS_SPSR);
+	/*
+	 * Guest PSTATE gets saved at guest fixup time in all
+	 * cases. We still need to handle the nVHE host side here.
+	 */
+	if (!has_vhe() && ctxt->__hyp_running_vcpu)
+		ctxt->regs.pstate	= read_sysreg_el2(SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
 		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -233,7 +233,7 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
  * Returns false if the guest ran in AArch32 when it shouldn't have, and
  * thus should exit to the host, or true if a the guest run loop can continue.
  */
-static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code)
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 
@@ -248,10 +248,7 @@ static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code)
 		vcpu->arch.target = -1;
 		*exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT);
 		*exit_code |= ARM_EXCEPTION_IL;
-		return false;
 	}
-
-	return true;
 }
 
 /* Switch to the guest for legacy non-VHE systems */
@@ -316,9 +313,6 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu);
 
-		if (unlikely(!handle_aarch32_guest(vcpu, &exit_code)))
-			break;
-
 		/* And we're baaack! */
 	} while (fixup_guest_exit(vcpu, &exit_code));
 

arch/arm64/kvm/hyp/vhe/switch.c

@@ -112,6 +112,10 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
 	return hyp_exit_handlers;
 }
 
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+}
+
 /* Switch to the guest for VHE systems running in EL2 */
 static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 {

arch/ia64/kernel/syscalls/syscall.tbl

@@ -369,3 +369,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv

arch/m68k/include/asm/cacheflush_mm.h

@@ -250,7 +250,6 @@ static inline void __flush_page_to_ram(void *vaddr)
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 #define flush_dcache_page(page)		__flush_page_to_ram(page_address(page))
-void flush_dcache_folio(struct folio *folio);
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 #define flush_icache_page(vma, page)	__flush_page_to_ram(page_address(page))

arch/m68k/kernel/syscalls/syscall.tbl

@@ -448,3 +448,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv

arch/microblaze/kernel/syscalls/syscall.tbl

@@ -454,3 +454,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv

arch/mips/Kconfig

@@ -3097,7 +3097,7 @@ config STACKTRACE_SUPPORT
 config PGTABLE_LEVELS
 	int
 	default 4 if PAGE_SIZE_4KB && MIPS_VA_BITS_48
-	default 3 if 64BIT && !PAGE_SIZE_64KB
+	default 3 if 64BIT && (!PAGE_SIZE_64KB || MIPS_VA_BITS_48)
 	default 2
 
 config MIPS_AUTO_PFN_OFFSET

arch/mips/boot/compressed/Makefile

@@ -52,7 +52,7 @@ endif
 
 vmlinuzobjs-$(CONFIG_KERNEL_XZ) += $(obj)/ashldi3.o
 
-vmlinuzobjs-$(CONFIG_KERNEL_ZSTD) += $(obj)/bswapdi.o
+vmlinuzobjs-$(CONFIG_KERNEL_ZSTD) += $(obj)/bswapdi.o $(obj)/ashldi3.o
 
 targets := $(notdir $(vmlinuzobjs-y))
 

arch/mips/include/asm/cacheflush.h

@@ -61,8 +61,6 @@ static inline void flush_dcache_page(struct page *page)
 		SetPageDcacheDirty(page);
 }
 
-void flush_dcache_folio(struct folio *folio);
-
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 

arch/mips/kernel/cpu-probe.c

@@ -1734,8 +1734,6 @@ static inline void decode_cpucfg(struct cpuinfo_mips *c)
 
 static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 {
-	decode_configs(c);
-
 	/* All Loongson processors covered here define ExcCode 16 as GSExc. */
 	c->options |= MIPS_CPU_GSEXCEX;
 
@@ -1796,6 +1794,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 		panic("Unknown Loongson Processor ID!");
 		break;
 	}
+
+	decode_configs(c);
 }
 #else
 static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { }

arch/mips/kernel/proc.c

@@ -185,7 +185,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_puts(m, " tx39_cache");
 	if (cpu_has_octeon_cache)
 		seq_puts(m, " octeon_cache");
-	if (cpu_has_fpu)
+	if (raw_cpu_has_fpu)
 		seq_puts(m, " fpu");
 	if (cpu_has_32fpr)
 		seq_puts(m, " 32fpr");

arch/nds32/include/asm/cacheflush.h

@@ -27,7 +27,6 @@ void flush_cache_vunmap(unsigned long start, unsigned long end);
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 void flush_dcache_page(struct page *page);
-void flush_dcache_folio(struct folio *folio);
 void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 		       unsigned long vaddr, void *dst, void *src, int len);
 void copy_from_user_page(struct vm_area_struct *vma, struct page *page,

arch/nios2/include/asm/cacheflush.h

@@ -29,7 +29,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 	unsigned long pfn);
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 void flush_dcache_page(struct page *page);
-void flush_dcache_folio(struct folio *folio);
 
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void flush_icache_page(struct vm_area_struct *vma, struct page *page);

arch/parisc/Makefile

@@ -15,7 +15,12 @@
 # Mike Shaver, Helge Deller and Martin K. Petersen
 #
 
+ifdef CONFIG_PARISC_SELF_EXTRACT
+boot := arch/parisc/boot
+KBUILD_IMAGE := $(boot)/bzImage
+else
 KBUILD_IMAGE := vmlinuz
+endif
 
 NM		= sh $(srctree)/arch/parisc/nm
 CHECKFLAGS	+= -D__hppa__=1

arch/parisc/configs/generic-64bit_defconfig

@@ -1,7 +1,9 @@
 CONFIG_LOCALVERSION="-64bit"
 # CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_KERNEL_LZ4=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_AUDIT=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_TASKSTATS=y
@@ -35,6 +37,7 @@ CONFIG_MODVERSIONS=y
 CONFIG_BLK_DEV_INTEGRITY=y
 CONFIG_BINFMT_MISC=m
 # CONFIG_COMPACTION is not set
+CONFIG_MEMORY_FAILURE=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -65,12 +68,15 @@ CONFIG_SCSI_ISCSI_ATTRS=y
 CONFIG_SCSI_SRP_ATTRS=y
 CONFIG_ISCSI_BOOT_SYSFS=y
 CONFIG_SCSI_MPT2SAS=y
-CONFIG_SCSI_LASI700=m
+CONFIG_SCSI_LASI700=y
 CONFIG_SCSI_SYM53C8XX_2=y
 CONFIG_SCSI_ZALON=y
 CONFIG_SCSI_QLA_ISCSI=m
 CONFIG_SCSI_DH=y
 CONFIG_ATA=y
+CONFIG_SATA_SIL=y
+CONFIG_SATA_SIS=y
+CONFIG_SATA_VIA=y
 CONFIG_PATA_NS87415=y
 CONFIG_PATA_SIL680=y
 CONFIG_ATA_GENERIC=y
@@ -79,6 +85,7 @@ CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_RAID=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_AUDIT=y
 CONFIG_FUSION=y
 CONFIG_FUSION_SPI=y
 CONFIG_FUSION_SAS=y
@@ -196,10 +203,15 @@ CONFIG_FB_MATROX_G=y
 CONFIG_FB_MATROX_I2C=y
 CONFIG_FB_MATROX_MAVEN=y
 CONFIG_FB_RADEON=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_CLUT224 is not set
 CONFIG_HIDRAW=y
 CONFIG_HID_PID=y
 CONFIG_USB_HIDDEV=y
 CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
 CONFIG_UIO=y
 CONFIG_UIO_PDRV_GENIRQ=m
 CONFIG_UIO_AEC=m

arch/parisc/include/asm/assembly.h

@@ -147,6 +147,17 @@
 	extrd,u \r, 63-(\sa), 64-(\sa), \t
 	.endm
 
+	/* Extract unsigned for 32- and 64-bit
+	 * The extru instruction leaves the most significant 32 bits of the
+	 * target register in an undefined state on PA 2.0 systems. */
+	.macro extru_safe r, p, len, t
+#ifdef CONFIG_64BIT
+	extrd,u	\r, 32+(\p), \len, \t
+#else
+	extru	\r, \p, \len, \t
+#endif
+	.endm
+
 	/* load 32-bit 'value' into 'reg' compensating for the ldil
 	 * sign-extension when running in wide mode.
 	 * WARNING!! neither 'value' nor 'reg' can be expressions

arch/parisc/include/asm/cacheflush.h

@@ -50,7 +50,6 @@ void invalidate_kernel_vmap_range(void *vaddr, int size);
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 void flush_dcache_page(struct page *page);
-void flush_dcache_folio(struct folio *folio);
 
 #define flush_dcache_mmap_lock(mapping)		xa_lock_irq(&mapping->i_pages)
 #define flush_dcache_mmap_unlock(mapping)	xa_unlock_irq(&mapping->i_pages)

arch/parisc/install.sh

@@ -39,6 +39,7 @@ verify "$3"
 if [ -n "${INSTALLKERNEL}" ]; then
   if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
   if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
+  if [ -x /usr/sbin/${INSTALLKERNEL} ]; then exec /usr/sbin/${INSTALLKERNEL} "$@"; fi
 fi
 
 # Default install

arch/parisc/kernel/entry.S

@@ -366,17 +366,9 @@
 	 */
 	.macro		L2_ptep	pmd,pte,index,va,fault
 #if CONFIG_PGTABLE_LEVELS == 3
-	extru		\va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index
+	extru_safe	\va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index
 #else
-# if defined(CONFIG_64BIT)
+	extru_safe	\va,31-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index
-	extrd,u		\va,63-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index
-  #else
-  # if PAGE_SIZE > 4096
-	extru		\va,31-ASM_PGDIR_SHIFT,32-ASM_PGDIR_SHIFT,\index
-  # else
-	extru		\va,31-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index
-  # endif
-# endif
 #endif
 	dep             %r0,31,PAGE_SHIFT,\pmd  /* clear offset */
 #if CONFIG_PGTABLE_LEVELS < 3
@@ -386,7 +378,7 @@
 	bb,>=,n		\pmd,_PxD_PRESENT_BIT,\fault
 	dep		%r0,31,PxD_FLAG_SHIFT,\pmd /* clear flags */
 	SHLREG		\pmd,PxD_VALUE_SHIFT,\pmd
-	extru		\va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index
+	extru_safe	\va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index
 	dep		%r0,31,PAGE_SHIFT,\pmd  /* clear offset */
 	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */
 	.endm

arch/parisc/kernel/syscall.S

@@ -566,7 +566,7 @@ lws_compare_and_swap:
 	ldo	R%lws_lock_start(%r20), %r28
 
 	/* Extract eight bits from r26 and hash lock (Bits 3-11) */
-	extru  %r26, 28, 8, %r20
+	extru_safe  %r26, 28, 8, %r20
 
 	/* Find lock to use, the hash is either one of 0 to
 	   15, multiplied by 16 (keep it 16-byte aligned)
@@ -751,7 +751,7 @@ cas2_lock_start:
 	ldo	R%lws_lock_start(%r20), %r28
 
 	/* Extract eight bits from r26 and hash lock (Bits 3-11) */
-	extru  %r26, 28, 8, %r20
+	extru_safe  %r26, 28, 8, %r20
 
 	/* Find lock to use, the hash is either one of 0 to
 	   15, multiplied by 16 (keep it 16-byte aligned)

arch/parisc/kernel/time.c

@@ -249,30 +249,16 @@ void __init time_init(void)
 static int __init init_cr16_clocksource(void)
 {
 	/*
-	 * The cr16 interval timers are not syncronized across CPUs on
+	 * The cr16 interval timers are not syncronized across CPUs, even if
-	 * different sockets, so mark them unstable and lower rating on
+	 * they share the same socket.
-	 * multi-socket SMP systems.
 	 */
 	if (num_online_cpus() > 1 && !running_on_qemu) {
-		int cpu;
+		/* mark sched_clock unstable */
-		unsigned long cpu0_loc;
+		clear_sched_clock_stable();
-		cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;
 
-		for_each_online_cpu(cpu) {
+		clocksource_cr16.name = "cr16_unstable";
-			if (cpu == 0)
+		clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
-				continue;
+		clocksource_cr16.rating = 0;
-			if ((cpu0_loc != 0) &&
-			    (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc))
-				continue;
-
-			/* mark sched_clock unstable */
-			clear_sched_clock_stable();
-
-			clocksource_cr16.name = "cr16_unstable";
-			clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
-			clocksource_cr16.rating = 0;
-			break;
-		}
 	}
 
 	/* register at clocksource framework */

arch/parisc/kernel/vmlinux.lds.S

@@ -57,8 +57,6 @@ SECTIONS
 {
 	. = KERNEL_BINARY_TEXT_START;
 
-	_stext = .;	/* start of kernel text, includes init code & data */
-
 	__init_begin = .;
 	HEAD_TEXT_SECTION
 	MLONGCALL_DISCARD(INIT_TEXT_SECTION(8))
@@ -82,6 +80,7 @@ SECTIONS
 	/* freed after init ends here */
 
 	_text = .;		/* Text and read-only data */
+	_stext = .;
 	MLONGCALL_KEEP(INIT_TEXT_SECTION(8))
 	.text ALIGN(PAGE_SIZE) : {
 		TEXT_TEXT

arch/powerpc/kernel/head_32.h

@@ -202,11 +202,11 @@ vmap_stack_overflow:
 	mfspr	r1, SPRN_SPRG_THREAD
 	lwz	r1, TASK_CPU - THREAD(r1)
 	slwi	r1, r1, 3
-	addis	r1, r1, emergency_ctx@ha
+	addis	r1, r1, emergency_ctx-PAGE_OFFSET@ha
 #else
-	lis	r1, emergency_ctx@ha
+	lis	r1, emergency_ctx-PAGE_OFFSET@ha
 #endif
-	lwz	r1, emergency_ctx@l(r1)
+	lwz	r1, emergency_ctx-PAGE_OFFSET@l(r1)
 	addi	r1, r1, THREAD_SIZE - INT_FRAME_SIZE
 	EXCEPTION_PROLOG_2 0 vmap_stack_overflow
 	prepare_transfer_to_handler

arch/powerpc/kernel/syscalls/syscall.tbl

@@ -528,3 +528,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -695,6 +695,7 @@ static void flush_guest_tlb(struct kvm *kvm)
 				       "r" (0) : "memory");
 		}
 		asm volatile("ptesync": : :"memory");
+		// POWER9 congruence-class TLBIEL leaves ERAT. Flush it now.
 		asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory");
 	} else {
 		for (set = 0; set < kvm->arch.tlb_sets; ++set) {
@@ -705,7 +706,9 @@ static void flush_guest_tlb(struct kvm *kvm)
 			rb += PPC_BIT(51);	/* increment set number */
 		}
 		asm volatile("ptesync": : :"memory");
-		asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
+		// POWER9 congruence-class TLBIEL leaves ERAT. Flush it now.
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
 	}
 }
 

arch/riscv/include/asm/kvm_host.h

@@ -12,14 +12,12 @@
 #include <linux/types.h>
 #include <linux/kvm.h>
 #include <linux/kvm_types.h>
+#include <asm/csr.h>
 #include <asm/kvm_vcpu_fp.h>
 #include <asm/kvm_vcpu_timer.h>
 
-#ifdef CONFIG_64BIT
+#define KVM_MAX_VCPUS			\
-#define KVM_MAX_VCPUS			(1U << 16)
+	((HGATP_VMID_MASK >> HGATP_VMID_SHIFT) + 1)
-#else
-#define KVM_MAX_VCPUS			(1U << 9)
-#endif
 
 #define KVM_HALT_POLL_NS_DEFAULT	500000
 

arch/riscv/kvm/mmu.c

@@ -453,6 +453,12 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
+	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = slot->npages << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	stage2_unmap_range(kvm, gpa, size, false);
+	spin_unlock(&kvm->mmu_lock);
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,

arch/s390/configs/debug_defconfig

@@ -403,7 +403,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_CONNECTOR=y
 CONFIG_ZRAM=y
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
@@ -476,6 +475,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_VXLAN=m
 CONFIG_BAREUDP=m
+CONFIG_AMT=m
 CONFIG_TUN=m
 CONFIG_VETH=m
 CONFIG_VIRTIO_NET=m
@@ -489,6 +489,7 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_ASIX is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_BROCADE is not set
@@ -571,6 +572,7 @@ CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
 CONFIG_DIAG288_WATCHDOG=m
+# CONFIG_DRM_DEBUG_MODESET_LOCK is not set
 CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
@@ -775,12 +777,14 @@ CONFIG_CRC4=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
 CONFIG_RANDOM32_SELFTEST=y
+CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=0
 CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_DEBUG_INFO_BTF=y
 CONFIG_GDB_SCRIPTS=y
 CONFIG_HEADERS_INSTALL=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
@@ -807,6 +811,7 @@ CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
 CONFIG_DEBUG_PER_CPU_MAPS=y
 CONFIG_KFENCE=y
+CONFIG_KFENCE_STATIC_KEYS=y
 CONFIG_DEBUG_SHIRQ=y
 CONFIG_PANIC_ON_OOPS=y
 CONFIG_DETECT_HUNG_TASK=y
@@ -842,6 +847,7 @@ CONFIG_FTRACE_STARTUP_TEST=y
 CONFIG_SAMPLES=y
 CONFIG_SAMPLE_TRACE_PRINTK=m
 CONFIG_SAMPLE_FTRACE_DIRECT=m
+CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m
 CONFIG_DEBUG_ENTRY=y
 CONFIG_CIO_INJECT=y
 CONFIG_KUNIT=m
@@ -860,7 +866,7 @@ CONFIG_FAIL_FUNCTION=y
 CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
 CONFIG_LKDTM=m
 CONFIG_TEST_MIN_HEAP=y
-CONFIG_KPROBES_SANITY_TEST=y
+CONFIG_KPROBES_SANITY_TEST=m
 CONFIG_RBTREE_TEST=y
 CONFIG_INTERVAL_TREE_TEST=m
 CONFIG_PERCPU_TEST=m

arch/s390/configs/defconfig

@@ -394,7 +394,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_CONNECTOR=y
 CONFIG_ZRAM=y
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
@@ -467,6 +466,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_VXLAN=m
 CONFIG_BAREUDP=m
+CONFIG_AMT=m
 CONFIG_TUN=m
 CONFIG_VETH=m
 CONFIG_VIRTIO_NET=m
@@ -480,6 +480,7 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_ASIX is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_BROCADE is not set
@@ -762,12 +763,14 @@ CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC4=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
+CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=0
 CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_DEBUG_INFO_BTF=y
 CONFIG_GDB_SCRIPTS=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_MAGIC_SYSRQ=y
@@ -792,9 +795,11 @@ CONFIG_HIST_TRIGGERS=y
 CONFIG_SAMPLES=y
 CONFIG_SAMPLE_TRACE_PRINTK=m
 CONFIG_SAMPLE_FTRACE_DIRECT=m
+CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m
 CONFIG_KUNIT=m
 CONFIG_KUNIT_DEBUGFS=y
 CONFIG_LKDTM=m
+CONFIG_KPROBES_SANITY_TEST=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_TEST_BPF=m

arch/s390/configs/zfcpdump_defconfig

@@ -65,9 +65,11 @@ CONFIG_ZFCP=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_LSM="yama,loadpin,safesetid,integrity"
 # CONFIG_ZLIB_DFLTCC is not set
+CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_PRINTK_TIME=y
 # CONFIG_SYMBOLIC_ERRNAME is not set
 CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_BTF=y
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_PANIC_ON_OOPS=y

arch/s390/include/asm/pci_io.h

@@ -14,12 +14,13 @@
 
 /* I/O Map */
 #define ZPCI_IOMAP_SHIFT		48
-#define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000UL
+#define ZPCI_IOMAP_ADDR_SHIFT		62
+#define ZPCI_IOMAP_ADDR_BASE		(1UL << ZPCI_IOMAP_ADDR_SHIFT)
 #define ZPCI_IOMAP_ADDR_OFF_MASK	((1UL << ZPCI_IOMAP_SHIFT) - 1)
 #define ZPCI_IOMAP_MAX_ENTRIES							\
-	((ULONG_MAX - ZPCI_IOMAP_ADDR_BASE + 1) / (1UL << ZPCI_IOMAP_SHIFT))
+	(1UL << (ZPCI_IOMAP_ADDR_SHIFT - ZPCI_IOMAP_SHIFT))
 #define ZPCI_IOMAP_ADDR_IDX_MASK						\
-	(~ZPCI_IOMAP_ADDR_OFF_MASK - ZPCI_IOMAP_ADDR_BASE)
+	((ZPCI_IOMAP_ADDR_BASE - 1) & ~ZPCI_IOMAP_ADDR_OFF_MASK)
 
 struct zpci_iomap_entry {
 	u32 fh;

arch/s390/lib/test_unwind.c

@@ -173,10 +173,11 @@ static noinline int unwindme_func4(struct unwindme *u)
 		}
 
 		/*
-		 * trigger specification exception
+		 * Trigger operation exception; use insn notation to bypass
+		 * llvm's integrated assembler sanity checks.
 		 */
 		asm volatile(
-			"	mvcl	%%r1,%%r1\n"
+			"	.insn	e,0x0000\n"	/* illegal opcode */
 			"0:	nopr	%%r7\n"
 			EX_TABLE(0b, 0b)
 			:);

arch/sh/include/asm/cacheflush.h

@@ -43,7 +43,6 @@ extern void flush_cache_range(struct vm_area_struct *vma,
 				 unsigned long start, unsigned long end);
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 void flush_dcache_page(struct page *page);
-void flush_dcache_folio(struct folio *folio);
 extern void flush_icache_range(unsigned long start, unsigned long end);
 #define flush_icache_user_range flush_icache_range
 extern void flush_icache_page(struct vm_area_struct *vma,

arch/sh/kernel/syscalls/syscall.tbl

@@ -451,3 +451,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv

arch/sparc/kernel/syscalls/syscall.tbl

@@ -494,3 +494,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv

arch/x86/entry/entry_64.S

@@ -574,6 +574,10 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 	ud2
 1:
 #endif
+#ifdef CONFIG_XEN_PV
+	ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
+#endif
+
 	POP_REGS pop_rdi=0
 
 	/*
@@ -890,6 +894,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 .Lparanoid_entry_checkgs:
 	/* EBX = 1 -> kernel GSBASE active, no restore required */
 	movl	$1, %ebx
+
 	/*
 	 * The kernel-enforced convention is a negative GSBASE indicates
 	 * a kernel value. No SWAPGS needed on entry and exit.
@@ -897,21 +902,14 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 	movl	$MSR_GS_BASE, %ecx
 	rdmsr
 	testl	%edx, %edx
-	jns	.Lparanoid_entry_swapgs
+	js	.Lparanoid_kernel_gsbase
-	ret
-
-.Lparanoid_entry_swapgs:
-	swapgs
-
-	/*
-	 * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an
-	 * unconditional CR3 write, even in the PTI case.  So do an lfence
-	 * to prevent GS speculation, regardless of whether PTI is enabled.
-	 */
-	FENCE_SWAPGS_KERNEL_ENTRY
 
 	/* EBX = 0 -> SWAPGS required on exit */
 	xorl	%ebx, %ebx
+	swapgs
+.Lparanoid_kernel_gsbase:
+
+	FENCE_SWAPGS_KERNEL_ENTRY
 	ret
 SYM_CODE_END(paranoid_entry)
 
@@ -993,11 +991,6 @@ SYM_CODE_START_LOCAL(error_entry)
 	pushq	%r12
 	ret
 
-.Lerror_entry_done_lfence:
-	FENCE_SWAPGS_KERNEL_ENTRY
-.Lerror_entry_done:
-	ret
-
 	/*
 	 * There are two places in the kernel that can potentially fault with
 	 * usergs. Handle them here.  B stepping K8s sometimes report a
@@ -1020,8 +1013,14 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * .Lgs_change's error handler with kernel gsbase.
 	 */
 	SWAPGS
-	FENCE_SWAPGS_USER_ENTRY
+
-	jmp .Lerror_entry_done
+	/*
+	 * Issue an LFENCE to prevent GS speculation, regardless of whether it is a
+	 * kernel or user gsbase.
+	 */
+.Lerror_entry_done_lfence:
+	FENCE_SWAPGS_KERNEL_ENTRY
+	ret
 
 .Lbstep_iret:
 	/* Fix truncated RIP */

arch/x86/include/asm/fpu/api.h

@@ -102,12 +102,6 @@ extern void switch_fpu_return(void);
  */
 extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
 
-/*
- * Tasks that are not using SVA have mm->pasid set to zero to note that they
- * will not have the valid bit set in MSR_IA32_PASID while they are running.
- */
-#define PASID_DISABLED	0
-
 /* Trap handling */
 extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
 extern void fpu_sync_fpstate(struct fpu *fpu);

arch/x86/include/asm/intel-family.h

@@ -108,7 +108,7 @@
 #define INTEL_FAM6_ALDERLAKE		0x97	/* Golden Cove / Gracemont */
 #define INTEL_FAM6_ALDERLAKE_L		0x9A	/* Golden Cove / Gracemont */
 
-#define INTEL_FAM6_RAPTOR_LAKE		0xB7
+#define INTEL_FAM6_RAPTORLAKE		0xB7
 
 /* "Small Core" Processors (Atom) */
 

arch/x86/include/asm/kvm_host.h

@@ -1036,6 +1036,7 @@ struct kvm_x86_msr_filter {
 #define APICV_INHIBIT_REASON_PIT_REINJ  4
 #define APICV_INHIBIT_REASON_X2APIC	5
 #define APICV_INHIBIT_REASON_BLOCKIRQ	6
+#define APICV_INHIBIT_REASON_ABSENT	7
 
 struct kvm_arch {
 	unsigned long n_used_mmu_pages;

arch/x86/include/asm/sev-common.h

@@ -73,4 +73,15 @@
 
 #define GHCB_RESP_CODE(v)		((v) & GHCB_MSR_INFO_MASK)
 
+/*
+ * Error codes related to GHCB input that can be communicated back to the guest
+ * by setting the lower 32-bits of the GHCB SW_EXITINFO1 field to 2.
+ */
+#define GHCB_ERR_NOT_REGISTERED		1
+#define GHCB_ERR_INVALID_USAGE		2
+#define GHCB_ERR_INVALID_SCRATCH_AREA	3
+#define GHCB_ERR_MISSING_INPUT		4
+#define GHCB_ERR_INVALID_INPUT		5
+#define GHCB_ERR_INVALID_EVENT		6
+
 #endif

arch/x86/include/asm/xen/hypercall.h

@@ -281,13 +281,13 @@ HYPERVISOR_callback_op(int cmd, void *arg)
 	return _hypercall2(int, callback_op, cmd, arg);
 }
 
-static inline int
+static __always_inline int
 HYPERVISOR_set_debugreg(int reg, unsigned long value)
 {
 	return _hypercall2(int, set_debugreg, reg, value);
 }
 
-static inline unsigned long
+static __always_inline unsigned long
 HYPERVISOR_get_debugreg(int reg)
 {
 	return _hypercall1(unsigned long, get_debugreg, reg);

arch/x86/include/asm/xen/hypervisor.h

@@ -64,6 +64,7 @@ void xen_arch_unregister_cpu(int num);
 
 #ifdef CONFIG_PVH
 void __init xen_pvh_init(struct boot_params *boot_params);
+void __init mem_map_via_hcall(struct boot_params *boot_params_p);
 #endif
 
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */

arch/x86/kernel/fpu/signal.c

@@ -118,7 +118,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 				      struct fpstate *fpstate)
 {
 	struct xregs_state __user *x = buf;
-	struct _fpx_sw_bytes sw_bytes;
+	struct _fpx_sw_bytes sw_bytes = {};
 	u32 xfeatures;
 	int err;
 

arch/x86/kernel/setup.c

@@ -742,7 +742,7 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
 	return 0;
 }
 
-static char *prepare_command_line(void)
+static char * __init prepare_command_line(void)
 {
 #ifdef CONFIG_CMDLINE_BOOL
 #ifdef CONFIG_CMDLINE_OVERRIDE

arch/x86/kernel/sev.c

@@ -294,11 +294,6 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
 				   char *dst, char *buf, size_t size)
 {
 	unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;
-	char __user *target = (char __user *)dst;
-	u64 d8;
-	u32 d4;
-	u16 d2;
-	u8  d1;
 
 	/*
 	 * This function uses __put_user() independent of whether kernel or user
@@ -320,26 +315,42 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
 	 * instructions here would cause infinite nesting.
 	 */
 	switch (size) {
-	case 1:
+	case 1: {
+		u8 d1;
+		u8 __user *target = (u8 __user *)dst;
+
 		memcpy(&d1, buf, 1);
 		if (__put_user(d1, target))
 			goto fault;
 		break;
-	case 2:
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *target = (u16 __user *)dst;
+
 		memcpy(&d2, buf, 2);
 		if (__put_user(d2, target))
 			goto fault;
 		break;
-	case 4:
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *target = (u32 __user *)dst;
+
 		memcpy(&d4, buf, 4);
 		if (__put_user(d4, target))
 			goto fault;
 		break;
-	case 8:
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *target = (u64 __user *)dst;
+
 		memcpy(&d8, buf, 8);
 		if (__put_user(d8, target))
 			goto fault;
 		break;
+	}
 	default:
 		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
 		return ES_UNSUPPORTED;
@@ -362,11 +373,6 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 				  char *src, char *buf, size_t size)
 {
 	unsigned long error_code = X86_PF_PROT;
-	char __user *s = (char __user *)src;
-	u64 d8;
-	u32 d4;
-	u16 d2;
-	u8  d1;
 
 	/*
 	 * This function uses __get_user() independent of whether kernel or user
@@ -388,26 +394,41 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 	 * instructions here would cause infinite nesting.
 	 */
 	switch (size) {
-	case 1:
+	case 1: {
+		u8 d1;
+		u8 __user *s = (u8 __user *)src;
+
 		if (__get_user(d1, s))
 			goto fault;
 		memcpy(buf, &d1, 1);
 		break;
-	case 2:
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *s = (u16 __user *)src;
+
 		if (__get_user(d2, s))
 			goto fault;
 		memcpy(buf, &d2, 2);
 		break;
-	case 4:
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *s = (u32 __user *)src;
+
 		if (__get_user(d4, s))
 			goto fault;
 		memcpy(buf, &d4, 4);
 		break;
-	case 8:
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *s = (u64 __user *)src;
 		if (__get_user(d8, s))
 			goto fault;
 		memcpy(buf, &d8, 8);
 		break;
+	}
 	default:
 		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
 		return ES_UNSUPPORTED;

arch/x86/kernel/tsc.c

@@ -1180,6 +1180,12 @@ void mark_tsc_unstable(char *reason)
 
 EXPORT_SYMBOL_GPL(mark_tsc_unstable);
 
+static void __init tsc_disable_clocksource_watchdog(void)
+{
+	clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+	clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+}
+
 static void __init check_system_tsc_reliable(void)
 {
 #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC)
@@ -1196,6 +1202,23 @@ static void __init check_system_tsc_reliable(void)
 #endif
 	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
 		tsc_clocksource_reliable = 1;
+
+	/*
+	 * Disable the clocksource watchdog when the system has:
+	 *  - TSC running at constant frequency
+	 *  - TSC which does not stop in C-States
+	 *  - the TSC_ADJUST register which allows to detect even minimal
+	 *    modifications
+	 *  - not more than two sockets. As the number of sockets cannot be
+	 *    evaluated at the early boot stage where this has to be
+	 *    invoked, check the number of online memory nodes as a
+	 *    fallback solution which is an reasonable estimate.
+	 */
+	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
+	    boot_cpu_has(X86_FEATURE_NONSTOP_TSC) &&
+	    boot_cpu_has(X86_FEATURE_TSC_ADJUST) &&
+	    nr_online_nodes <= 2)
+		tsc_disable_clocksource_watchdog();
 }
 
 /*
@@ -1387,9 +1410,6 @@ static int __init init_tsc_clocksource(void)
 	if (tsc_unstable)
 		goto unreg;
 
-	if (tsc_clocksource_reliable || no_tsc_watchdog)
-		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
-
 	if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
 		clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
 
@@ -1527,7 +1547,7 @@ void __init tsc_init(void)
 	}
 
 	if (tsc_clocksource_reliable || no_tsc_watchdog)
-		clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+		tsc_disable_clocksource_watchdog();
 
 	clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
 	detect_art();

arch/x86/kernel/tsc_sync.c

@@ -30,6 +30,7 @@ struct tsc_adjust {
 };
 
 static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust);
+static struct timer_list tsc_sync_check_timer;
 
 /*
  * TSC's on different sockets may be reset asynchronously.
@@ -77,6 +78,46 @@ void tsc_verify_tsc_adjust(bool resume)
 	}
 }
 
+/*
+ * Normally the tsc_sync will be checked every time system enters idle
+ * state, but there is still caveat that a system won't enter idle,
+ * either because it's too busy or configured purposely to not enter
+ * idle.
+ *
+ * So setup a periodic timer (every 10 minutes) to make sure the check
+ * is always on.
+ */
+
+#define SYNC_CHECK_INTERVAL		(HZ * 600)
+
+static void tsc_sync_check_timer_fn(struct timer_list *unused)
+{
+	int next_cpu;
+
+	tsc_verify_tsc_adjust(false);
+
+	/* Run the check for all onlined CPUs in turn */
+	next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
+	if (next_cpu >= nr_cpu_ids)
+		next_cpu = cpumask_first(cpu_online_mask);
+
+	tsc_sync_check_timer.expires += SYNC_CHECK_INTERVAL;
+	add_timer_on(&tsc_sync_check_timer, next_cpu);
+}
+
+static int __init start_sync_check_timer(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_TSC_ADJUST) || tsc_clocksource_reliable)
+		return 0;
+
+	timer_setup(&tsc_sync_check_timer, tsc_sync_check_timer_fn, 0);
+	tsc_sync_check_timer.expires = jiffies + SYNC_CHECK_INTERVAL;
+	add_timer(&tsc_sync_check_timer);
+
+	return 0;
+}
+late_initcall(start_sync_check_timer);
+
 static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval,
 				   unsigned int cpu, bool bootcpu)
 {

arch/x86/kvm/ioapic.h

@@ -81,7 +81,6 @@ struct kvm_ioapic {
 	unsigned long irq_states[IOAPIC_NUM_PINS];
 	struct kvm_io_device dev;
 	struct kvm *kvm;
-	void (*ack_notifier)(void *opaque, int irq);
 	spinlock_t lock;
 	struct rtc_status rtc_status;
 	struct delayed_work eoi_inject;

arch/x86/kvm/irq.h

@@ -56,7 +56,6 @@ struct kvm_pic {
 	struct kvm_io_device dev_master;
 	struct kvm_io_device dev_slave;
 	struct kvm_io_device dev_elcr;
-	void (*ack_notifier)(void *opaque, int irq);
 	unsigned long irq_states[PIC_NUM_PINS];
 };
 

arch/x86/kvm/lapic.c

@@ -707,7 +707,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr)
 {
 	int highest_irr;
-	if (apic->vcpu->arch.apicv_active)
+	if (kvm_x86_ops.sync_pir_to_irr)
 		highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu);
 	else
 		highest_irr = apic_find_highest_irr(apic);

arch/x86/kvm/mmu/mmu.c

@@ -1582,7 +1582,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 		flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp);
 
 	if (is_tdp_mmu_enabled(kvm))
-		flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
+		flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
 
 	return flush;
 }
@@ -1936,7 +1936,11 @@ static void mmu_audit_disable(void) { }
 
 static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	return sp->role.invalid ||
+	if (sp->role.invalid)
+		return true;
+
+	/* TDP MMU pages due not use the MMU generation. */
+	return !sp->tdp_mmu_page &&
 	       unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
 }
 
@@ -2173,10 +2177,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
 	iterator->shadow_addr = root;
 	iterator->level = vcpu->arch.mmu->shadow_root_level;
 
-	if (iterator->level == PT64_ROOT_4LEVEL &&
+	if (iterator->level >= PT64_ROOT_4LEVEL &&
 	    vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
 	    !vcpu->arch.mmu->direct_map)
-		--iterator->level;
+		iterator->level = PT32E_ROOT_LEVEL;
 
 	if (iterator->level == PT32E_ROOT_LEVEL) {
 		/*
@@ -3976,6 +3980,20 @@ out_retry:
 	return true;
 }
 
+/*
+ * Returns true if the page fault is stale and needs to be retried, i.e. if the
+ * root was invalidated by a memslot update or a relevant mmu_notifier fired.
+ */
+static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
+				struct kvm_page_fault *fault, int mmu_seq)
+{
+	if (is_obsolete_sp(vcpu->kvm, to_shadow_page(vcpu->arch.mmu->root_hpa)))
+		return true;
+
+	return fault->slot &&
+	       mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
+}
+
 static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu);
@@ -4013,8 +4031,9 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	else
 		write_lock(&vcpu->kvm->mmu_lock);
 
-	if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva))
+	if (is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
+
 	r = make_mmu_pages_available(vcpu);
 	if (r)
 		goto out_unlock;
@@ -4855,7 +4874,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0,
 	struct kvm_mmu *context = &vcpu->arch.guest_mmu;
 	struct kvm_mmu_role_regs regs = {
 		.cr0 = cr0,
-		.cr4 = cr4,
+		.cr4 = cr4 & ~X86_CR4_PKE,
 		.efer = efer,
 	};
 	union kvm_mmu_role new_role;
@@ -4919,7 +4938,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 	context->direct_map = false;
 
 	update_permission_bitmask(context, true);
-	update_pkru_bitmask(context);
+	context->pkru_mask = 0;
 	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
 	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
 }
@@ -5025,6 +5044,14 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	/*
 	 * Invalidate all MMU roles to force them to reinitialize as CPUID
 	 * information is factored into reserved bit calculations.
+	 *
+	 * Correctly handling multiple vCPU models with respect to paging and
+	 * physical address properties) in a single VM would require tracking
+	 * all relevant CPUID information in kvm_mmu_page_role. That is very
+	 * undesirable as it would increase the memory requirements for
+	 * gfn_track (see struct kvm_mmu_page_role comments).  For now that
+	 * problem is swept under the rug; KVM's CPUID API is horrific and
+	 * it's all but impossible to solve it without introducing a new API.
 	 */
 	vcpu->arch.root_mmu.mmu_role.ext.valid = 0;
 	vcpu->arch.guest_mmu.mmu_role.ext.valid = 0;
@@ -5032,24 +5059,10 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	kvm_mmu_reset_context(vcpu);
 
 	/*
-	 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
+	 * Changing guest CPUID after KVM_RUN is forbidden, see the comment in
-	 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
+	 * kvm_arch_vcpu_ioctl().
-	 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
-	 * faults due to reusing SPs/SPTEs.  Alert userspace, but otherwise
-	 * sweep the problem under the rug.
-	 *
-	 * KVM's horrific CPUID ABI makes the problem all but impossible to
-	 * solve, as correctly handling multiple vCPU models (with respect to
-	 * paging and physical address properties) in a single VM would require
-	 * tracking all relevant CPUID information in kvm_mmu_page_role.  That
-	 * is very undesirable as it would double the memory requirements for
-	 * gfn_track (see struct kvm_mmu_page_role comments), and in practice
-	 * no sane VMM mucks with the core vCPU model on the fly.
 	 */
-	if (vcpu->arch.last_vmentry_cpu != -1) {
+	KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm);
-		pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} after KVM_RUN may cause guest instability\n");
-		pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} will fail after KVM_RUN starting with Linux 5.16\n");
-	}
 }
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
@@ -5369,7 +5382,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	kvm_mmu_invalidate_gva(vcpu, vcpu->arch.mmu, gva, INVALID_PAGE);
+	kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE);
 	++vcpu->stat.invlpg;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
@@ -5854,8 +5867,6 @@ restart:
 void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 				   const struct kvm_memory_slot *slot)
 {
-	bool flush = false;
-
 	if (kvm_memslots_have_rmaps(kvm)) {
 		write_lock(&kvm->mmu_lock);
 		/*
@@ -5863,17 +5874,14 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 		 * logging at a 4k granularity and never creates collapsible
 		 * 2m SPTEs during dirty logging.
 		 */
-		flush = slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true);
+		if (slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true))
-		if (flush)
 			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
 		write_unlock(&kvm->mmu_lock);
 	}
 
 	if (is_tdp_mmu_enabled(kvm)) {
 		read_lock(&kvm->mmu_lock);
-		flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush);
+		kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot);
-		if (flush)
-			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
 		read_unlock(&kvm->mmu_lock);
 	}
 }
@@ -6182,23 +6190,46 @@ void kvm_mmu_module_exit(void)
 	mmu_audit_disable();
 }
 
+/*
+ * Calculate the effective recovery period, accounting for '0' meaning "let KVM
+ * select a halving time of 1 hour".  Returns true if recovery is enabled.
+ */
+static bool calc_nx_huge_pages_recovery_period(uint *period)
+{
+	/*
+	 * Use READ_ONCE to get the params, this may be called outside of the
+	 * param setters, e.g. by the kthread to compute its next timeout.
+	 */
+	bool enabled = READ_ONCE(nx_huge_pages);
+	uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
+
+	if (!enabled || !ratio)
+		return false;
+
+	*period = READ_ONCE(nx_huge_pages_recovery_period_ms);
+	if (!*period) {
+		/* Make sure the period is not less than one second.  */
+		ratio = min(ratio, 3600u);
+		*period = 60 * 60 * 1000 / ratio;
+	}
+	return true;
+}
+
 static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp)
 {
 	bool was_recovery_enabled, is_recovery_enabled;
 	uint old_period, new_period;
 	int err;
 
-	was_recovery_enabled = nx_huge_pages_recovery_ratio;
+	was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period);
-	old_period = nx_huge_pages_recovery_period_ms;
 
 	err = param_set_uint(val, kp);
 	if (err)
 		return err;
 
-	is_recovery_enabled = nx_huge_pages_recovery_ratio;
+	is_recovery_enabled = calc_nx_huge_pages_recovery_period(&new_period);
-	new_period = nx_huge_pages_recovery_period_ms;
 
-	if (READ_ONCE(nx_huge_pages) && is_recovery_enabled &&
+	if (is_recovery_enabled &&
 	    (!was_recovery_enabled || old_period > new_period)) {
 		struct kvm *kvm;
 
@@ -6262,18 +6293,13 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 
 static long get_nx_lpage_recovery_timeout(u64 start_time)
 {
-	uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
+	bool enabled;
-	uint period = READ_ONCE(nx_huge_pages_recovery_period_ms);
+	uint period;
 
-	if (!period && ratio) {
+	enabled = calc_nx_huge_pages_recovery_period(&period);
-		/* Make sure the period is not less than one second.  */
-		ratio = min(ratio, 3600u);
-		period = 60 * 60 * 1000 / ratio;
-	}
 
-	return READ_ONCE(nx_huge_pages) && ratio
+	return enabled ? start_time + msecs_to_jiffies(period) - get_jiffies_64()
-		? start_time + msecs_to_jiffies(period) - get_jiffies_64()
+		       : MAX_SCHEDULE_TIMEOUT;
-		: MAX_SCHEDULE_TIMEOUT;
 }
 
 static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)

arch/x86/kvm/mmu/paging_tmpl.h

@@ -911,7 +911,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 
 	r = RET_PF_RETRY;
 	write_lock(&vcpu->kvm->mmu_lock);
-	if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva))
+
+	if (is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
 
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);

arch/x86/kvm/mmu/tdp_mmu.c

@@ -317,9 +317,6 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 	struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
 	int level = sp->role.level;
 	gfn_t base_gfn = sp->gfn;
-	u64 old_child_spte;
-	u64 *sptep;
-	gfn_t gfn;
 	int i;
 
 	trace_kvm_mmu_prepare_zap_page(sp);
@@ -327,8 +324,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 	tdp_mmu_unlink_page(kvm, sp, shared);
 
 	for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
-		sptep = rcu_dereference(pt) + i;
+		u64 *sptep = rcu_dereference(pt) + i;
-		gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
+		gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
+		u64 old_child_spte;
 
 		if (shared) {
 			/*
@@ -374,7 +372,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 				    shared);
 	}
 
-	kvm_flush_remote_tlbs_with_address(kvm, gfn,
+	kvm_flush_remote_tlbs_with_address(kvm, base_gfn,
 					   KVM_PAGES_PER_HPAGE(level + 1));
 
 	call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
@@ -1033,9 +1031,9 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 {
 	struct kvm_mmu_page *root;
 
-	for_each_tdp_mmu_root(kvm, root, range->slot->as_id)
+	for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false)
-		flush |= zap_gfn_range(kvm, root, range->start, range->end,
+		flush = zap_gfn_range(kvm, root, range->start, range->end,
-				       range->may_block, flush, false);
+				      range->may_block, flush, false);
 
 	return flush;
 }
@@ -1364,10 +1362,9 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
  * Clear leaf entries which could be replaced by large mappings, for
  * GFNs within the slot.
  */
-static bool zap_collapsible_spte_range(struct kvm *kvm,
+static void zap_collapsible_spte_range(struct kvm *kvm,
 				       struct kvm_mmu_page *root,
-				       const struct kvm_memory_slot *slot,
+				       const struct kvm_memory_slot *slot)
-				       bool flush)
 {
 	gfn_t start = slot->base_gfn;
 	gfn_t end = start + slot->npages;
@@ -1378,10 +1375,8 @@ static bool zap_collapsible_spte_range(struct kvm *kvm,
 
 	tdp_root_for_each_pte(iter, root, start, end) {
 retry:
-		if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) {
+		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
-			flush = false;
 			continue;
-		}
 
 		if (!is_shadow_present_pte(iter.old_spte) ||
 		    !is_last_spte(iter.old_spte, iter.level))
@@ -1393,6 +1388,7 @@ retry:
 							    pfn, PG_LEVEL_NUM))
 			continue;
 
+		/* Note, a successful atomic zap also does a remote TLB flush. */
 		if (!tdp_mmu_zap_spte_atomic(kvm, &iter)) {
 			/*
 			 * The iter must explicitly re-read the SPTE because
@@ -1401,30 +1397,24 @@ retry:
 			iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
 			goto retry;
 		}
-		flush = true;
 	}
 
 	rcu_read_unlock();
-
-	return flush;
 }
 
 /*
  * Clear non-leaf entries (and free associated page tables) which could
  * be replaced by large mappings, for GFNs within the slot.
  */
-bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot,
+				       const struct kvm_memory_slot *slot)
-				       bool flush)
 {
 	struct kvm_mmu_page *root;
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
-		flush = zap_collapsible_spte_range(kvm, root, slot, flush);
+		zap_collapsible_spte_range(kvm, root, slot);
-
-	return flush;
 }
 
 /*

arch/x86/kvm/mmu/tdp_mmu.h

@@ -64,9 +64,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 				       struct kvm_memory_slot *slot,
 				       gfn_t gfn, unsigned long mask,
 				       bool wrprot);
-bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot,
+				       const struct kvm_memory_slot *slot);
-				       bool flush);
 
 bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn,

arch/x86/kvm/svm/avic.c

@@ -900,6 +900,7 @@ out:
 bool svm_check_apicv_inhibit_reasons(ulong bit)
 {
 	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
+			  BIT(APICV_INHIBIT_REASON_ABSENT) |
 			  BIT(APICV_INHIBIT_REASON_HYPERV) |
 			  BIT(APICV_INHIBIT_REASON_NESTED) |
 			  BIT(APICV_INHIBIT_REASON_IRQWIN) |
@@ -989,16 +990,18 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	int cpu = get_cpu();
 
+	WARN_ON(cpu != vcpu->cpu);
 	svm->avic_is_running = is_run;
 
-	if (!kvm_vcpu_apicv_active(vcpu))
+	if (kvm_vcpu_apicv_active(vcpu)) {
-		return;
+		if (is_run)
-
+			avic_vcpu_load(vcpu, cpu);
-	if (is_run)
+		else
-		avic_vcpu_load(vcpu, vcpu->cpu);
+			avic_vcpu_put(vcpu);
-	else
+	}
-		avic_vcpu_put(vcpu);
+	put_cpu();
 }
 
 void svm_vcpu_blocking(struct kvm_vcpu *vcpu)

arch/x86/kvm/svm/pmu.c

@@ -281,7 +281,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 		pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS;
 
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
-	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->reserved_bits = 0xfffffff000280000ull;
 	pmu->version = 1;
 	/* not applicable to AMD; but clean them to prevent any fall out */
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;

arch/x86/kvm/svm/sev.c

@@ -1543,28 +1543,50 @@ static bool is_cmd_allowed_from_mirror(u32 cmd_id)
 	return false;
 }
 
-static int sev_lock_for_migration(struct kvm *kvm)
+static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info;
+	struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info;
+	int r = -EBUSY;
+
+	if (dst_kvm == src_kvm)
+		return -EINVAL;
 
 	/*
-	 * Bail if this VM is already involved in a migration to avoid deadlock
+	 * Bail if these VMs are already involved in a migration to avoid
-	 * between two VMs trying to migrate to/from each other.
+	 * deadlock between two VMs trying to migrate to/from each other.
 	 */
-	if (atomic_cmpxchg_acquire(&sev->migration_in_progress, 0, 1))
+	if (atomic_cmpxchg_acquire(&dst_sev->migration_in_progress, 0, 1))
 		return -EBUSY;
 
-	mutex_lock(&kvm->lock);
+	if (atomic_cmpxchg_acquire(&src_sev->migration_in_progress, 0, 1))
+		goto release_dst;
 
+	r = -EINTR;
+	if (mutex_lock_killable(&dst_kvm->lock))
+		goto release_src;
+	if (mutex_lock_killable(&src_kvm->lock))
+		goto unlock_dst;
 	return 0;
+
+unlock_dst:
+	mutex_unlock(&dst_kvm->lock);
+release_src:
+	atomic_set_release(&src_sev->migration_in_progress, 0);
+release_dst:
+	atomic_set_release(&dst_sev->migration_in_progress, 0);
+	return r;
 }
 
-static void sev_unlock_after_migration(struct kvm *kvm)
+static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info;
+	struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info;
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&dst_kvm->lock);
-	atomic_set_release(&sev->migration_in_progress, 0);
+	mutex_unlock(&src_kvm->lock);
+	atomic_set_release(&dst_sev->migration_in_progress, 0);
+	atomic_set_release(&src_sev->migration_in_progress, 0);
 }
 
 
@@ -1607,14 +1629,15 @@ static void sev_migrate_from(struct kvm_sev_info *dst,
 	dst->asid = src->asid;
 	dst->handle = src->handle;
 	dst->pages_locked = src->pages_locked;
+	dst->enc_context_owner = src->enc_context_owner;
 
 	src->asid = 0;
 	src->active = false;
 	src->handle = 0;
 	src->pages_locked = 0;
+	src->enc_context_owner = NULL;
 
-	INIT_LIST_HEAD(&dst->regions_list);
+	list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list);
-	list_replace_init(&src->regions_list, &dst->regions_list);
 }
 
 static int sev_es_migrate_from(struct kvm *dst, struct kvm *src)
@@ -1666,15 +1689,6 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd)
 	bool charged = false;
 	int ret;
 
-	ret = sev_lock_for_migration(kvm);
-	if (ret)
-		return ret;
-
-	if (sev_guest(kvm)) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
 	source_kvm_file = fget(source_fd);
 	if (!file_is_kvm(source_kvm_file)) {
 		ret = -EBADF;
@@ -1682,16 +1696,26 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd)
 	}
 
 	source_kvm = source_kvm_file->private_data;
-	ret = sev_lock_for_migration(source_kvm);
+	ret = sev_lock_two_vms(kvm, source_kvm);
 	if (ret)
 		goto out_fput;
 
-	if (!sev_guest(source_kvm)) {
+	if (sev_guest(kvm) || !sev_guest(source_kvm)) {
 		ret = -EINVAL;
-		goto out_source;
+		goto out_unlock;
 	}
 
 	src_sev = &to_kvm_svm(source_kvm)->sev_info;
+
+	/*
+	 * VMs mirroring src's encryption context rely on it to keep the
+	 * ASID allocated, but below we are clearing src_sev->asid.
+	 */
+	if (src_sev->num_mirrored_vms) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
 	dst_sev->misc_cg = get_current_misc_cg();
 	cg_cleanup_sev = dst_sev;
 	if (dst_sev->misc_cg != src_sev->misc_cg) {
@@ -1728,13 +1752,11 @@ out_dst_cgroup:
 		sev_misc_cg_uncharge(cg_cleanup_sev);
 	put_misc_cg(cg_cleanup_sev->misc_cg);
 	cg_cleanup_sev->misc_cg = NULL;
-out_source:
+out_unlock:
-	sev_unlock_after_migration(source_kvm);
+	sev_unlock_two_vms(kvm, source_kvm);
 out_fput:
 	if (source_kvm_file)
 		fput(source_kvm_file);
-out_unlock:
-	sev_unlock_after_migration(kvm);
 	return ret;
 }
 
@@ -1953,76 +1975,60 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 {
 	struct file *source_kvm_file;
 	struct kvm *source_kvm;
-	struct kvm_sev_info source_sev, *mirror_sev;
+	struct kvm_sev_info *source_sev, *mirror_sev;
 	int ret;
 
 	source_kvm_file = fget(source_fd);
 	if (!file_is_kvm(source_kvm_file)) {
 		ret = -EBADF;
-		goto e_source_put;
+		goto e_source_fput;
 	}
 
 	source_kvm = source_kvm_file->private_data;
-	mutex_lock(&source_kvm->lock);
+	ret = sev_lock_two_vms(kvm, source_kvm);
+	if (ret)
+		goto e_source_fput;
 
-	if (!sev_guest(source_kvm)) {
+	/*
+	 * Mirrors of mirrors should work, but let's not get silly.  Also
+	 * disallow out-of-band SEV/SEV-ES init if the target is already an
+	 * SEV guest, or if vCPUs have been created.  KVM relies on vCPUs being
+	 * created after SEV/SEV-ES initialization, e.g. to init intercepts.
+	 */
+	if (sev_guest(kvm) || !sev_guest(source_kvm) ||
+	    is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) {
 		ret = -EINVAL;
-		goto e_source_unlock;
+		goto e_unlock;
 	}
 
-	/* Mirrors of mirrors should work, but let's not get silly */
-	if (is_mirroring_enc_context(source_kvm) || source_kvm == kvm) {
-		ret = -EINVAL;
-		goto e_source_unlock;
-	}
-
-	memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info,
-	       sizeof(source_sev));
-
 	/*
 	 * The mirror kvm holds an enc_context_owner ref so its asid can't
 	 * disappear until we're done with it
 	 */
+	source_sev = &to_kvm_svm(source_kvm)->sev_info;
 	kvm_get_kvm(source_kvm);
-
+	source_sev->num_mirrored_vms++;
-	fput(source_kvm_file);
-	mutex_unlock(&source_kvm->lock);
-	mutex_lock(&kvm->lock);
-
-	/*
-	 * Disallow out-of-band SEV/SEV-ES init if the target is already an
-	 * SEV guest, or if vCPUs have been created.  KVM relies on vCPUs being
-	 * created after SEV/SEV-ES initialization, e.g. to init intercepts.
-	 */
-	if (sev_guest(kvm) || kvm->created_vcpus) {
-		ret = -EINVAL;
-		goto e_mirror_unlock;
-	}
 
 	/* Set enc_context_owner and copy its encryption context over */
 	mirror_sev = &to_kvm_svm(kvm)->sev_info;
 	mirror_sev->enc_context_owner = source_kvm;
 	mirror_sev->active = true;
-	mirror_sev->asid = source_sev.asid;
+	mirror_sev->asid = source_sev->asid;
-	mirror_sev->fd = source_sev.fd;
+	mirror_sev->fd = source_sev->fd;
-	mirror_sev->es_active = source_sev.es_active;
+	mirror_sev->es_active = source_sev->es_active;
-	mirror_sev->handle = source_sev.handle;
+	mirror_sev->handle = source_sev->handle;
+	INIT_LIST_HEAD(&mirror_sev->regions_list);
+	ret = 0;
+
 	/*
 	 * Do not copy ap_jump_table. Since the mirror does not share the same
 	 * KVM contexts as the original, and they may have different
 	 * memory-views.
 	 */
 
-	mutex_unlock(&kvm->lock);
+e_unlock:
-	return 0;
+	sev_unlock_two_vms(kvm, source_kvm);
-
+e_source_fput:
-e_mirror_unlock:
-	mutex_unlock(&kvm->lock);
-	kvm_put_kvm(source_kvm);
-	return ret;
-e_source_unlock:
-	mutex_unlock(&source_kvm->lock);
-e_source_put:
 	if (source_kvm_file)
 		fput(source_kvm_file);
 	return ret;
@@ -2034,17 +2040,24 @@ void sev_vm_destroy(struct kvm *kvm)
 	struct list_head *head = &sev->regions_list;
 	struct list_head *pos, *q;
 
+	WARN_ON(sev->num_mirrored_vms);
+
 	if (!sev_guest(kvm))
 		return;
 
 	/* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */
 	if (is_mirroring_enc_context(kvm)) {
-		kvm_put_kvm(sev->enc_context_owner);
+		struct kvm *owner_kvm = sev->enc_context_owner;
+		struct kvm_sev_info *owner_sev = &to_kvm_svm(owner_kvm)->sev_info;
+
+		mutex_lock(&owner_kvm->lock);
+		if (!WARN_ON(!owner_sev->num_mirrored_vms))
+			owner_sev->num_mirrored_vms--;
+		mutex_unlock(&owner_kvm->lock);
+		kvm_put_kvm(owner_kvm);
 		return;
 	}
 
-	mutex_lock(&kvm->lock);
-
 	/*
 	 * Ensure that all guest tagged cache entries are flushed before
 	 * releasing the pages back to the system for use. CLFLUSH will
@@ -2064,8 +2077,6 @@ void sev_vm_destroy(struct kvm *kvm)
 		}
 	}
 
-	mutex_unlock(&kvm->lock);
-
 	sev_unbind_asid(kvm, sev->handle);
 	sev_asid_free(sev);
 }
@@ -2249,7 +2260,7 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_page(virt_to_page(svm->sev_es.vmsa));
 
 	if (svm->sev_es.ghcb_sa_free)
-		kfree(svm->sev_es.ghcb_sa);
+		kvfree(svm->sev_es.ghcb_sa);
 }
 
 static void dump_ghcb(struct vcpu_svm *svm)
@@ -2341,24 +2352,29 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
 }
 
-static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
+static bool sev_es_validate_vmgexit(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu;
 	struct ghcb *ghcb;
-	u64 exit_code = 0;
+	u64 exit_code;
+	u64 reason;
 
 	ghcb = svm->sev_es.ghcb;
 
-	/* Only GHCB Usage code 0 is supported */
-	if (ghcb->ghcb_usage)
-		goto vmgexit_err;
-
 	/*
-	 * Retrieve the exit code now even though is may not be marked valid
+	 * Retrieve the exit code now even though it may not be marked valid
 	 * as it could help with debugging.
 	 */
 	exit_code = ghcb_get_sw_exit_code(ghcb);
 
+	/* Only GHCB Usage code 0 is supported */
+	if (ghcb->ghcb_usage) {
+		reason = GHCB_ERR_INVALID_USAGE;
+		goto vmgexit_err;
+	}
+
+	reason = GHCB_ERR_MISSING_INPUT;
+
 	if (!ghcb_sw_exit_code_is_valid(ghcb) ||
 	    !ghcb_sw_exit_info_1_is_valid(ghcb) ||
 	    !ghcb_sw_exit_info_2_is_valid(ghcb))
@@ -2437,30 +2453,34 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		break;
 	default:
+		reason = GHCB_ERR_INVALID_EVENT;
 		goto vmgexit_err;
 	}
 
-	return 0;
+	return true;
 
 vmgexit_err:
 	vcpu = &svm->vcpu;
 
-	if (ghcb->ghcb_usage) {
+	if (reason == GHCB_ERR_INVALID_USAGE) {
 		vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n",
 			    ghcb->ghcb_usage);
+	} else if (reason == GHCB_ERR_INVALID_EVENT) {
+		vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n",
+			    exit_code);
 	} else {
-		vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n",
+		vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n",
 			    exit_code);
 		dump_ghcb(svm);
 	}
 
-	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	/* Clear the valid entries fields */
-	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
+	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
-	vcpu->run->internal.ndata = 2;
-	vcpu->run->internal.data[0] = exit_code;
-	vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
 
-	return -EINVAL;
+	ghcb_set_sw_exit_info_1(ghcb, 2);
+	ghcb_set_sw_exit_info_2(ghcb, reason);
+
+	return false;
 }
 
 void sev_es_unmap_ghcb(struct vcpu_svm *svm)
@@ -2482,7 +2502,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm)
 			svm->sev_es.ghcb_sa_sync = false;
 		}
 
-		kfree(svm->sev_es.ghcb_sa);
+		kvfree(svm->sev_es.ghcb_sa);
 		svm->sev_es.ghcb_sa = NULL;
 		svm->sev_es.ghcb_sa_free = false;
 	}
@@ -2530,14 +2550,14 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 	scratch_gpa_beg = ghcb_get_sw_scratch(ghcb);
 	if (!scratch_gpa_beg) {
 		pr_err("vmgexit: scratch gpa not provided\n");
-		return false;
+		goto e_scratch;
 	}
 
 	scratch_gpa_end = scratch_gpa_beg + len;
 	if (scratch_gpa_end < scratch_gpa_beg) {
 		pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n",
 		       len, scratch_gpa_beg);
-		return false;
+		goto e_scratch;
 	}
 
 	if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) {
@@ -2555,7 +2575,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		    scratch_gpa_end > ghcb_scratch_end) {
 			pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n",
 			       scratch_gpa_beg, scratch_gpa_end);
-			return false;
+			goto e_scratch;
 		}
 
 		scratch_va = (void *)svm->sev_es.ghcb;
@@ -2568,18 +2588,18 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		if (len > GHCB_SCRATCH_AREA_LIMIT) {
 			pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n",
 			       len, GHCB_SCRATCH_AREA_LIMIT);
-			return false;
+			goto e_scratch;
 		}
-		scratch_va = kzalloc(len, GFP_KERNEL_ACCOUNT);
+		scratch_va = kvzalloc(len, GFP_KERNEL_ACCOUNT);
 		if (!scratch_va)
-			return false;
+			goto e_scratch;
 
 		if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) {
 			/* Unable to copy scratch area from guest */
 			pr_err("vmgexit: kvm_read_guest for scratch area failed\n");
 
-			kfree(scratch_va);
+			kvfree(scratch_va);
-			return false;
+			goto e_scratch;
 		}
 
 		/*
@@ -2596,6 +2616,12 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 	svm->sev_es.ghcb_sa_len = len;
 
 	return true;
+
+e_scratch:
+	ghcb_set_sw_exit_info_1(ghcb, 2);
+	ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA);
+
+	return false;
 }
 
 static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask,
@@ -2646,7 +2672,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 
 		ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_CPUID);
 		if (!ret) {
-			ret = -EINVAL;
+			/* Error, keep GHCB MSR value as-is */
 			break;
 		}
 
@@ -2682,10 +2708,13 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 						GHCB_MSR_TERM_REASON_POS);
 		pr_info("SEV-ES guest requested termination: %#llx:%#llx\n",
 			reason_set, reason_code);
-		fallthrough;
+
+		ret = -EINVAL;
+		break;
 	}
 	default:
-		ret = -EINVAL;
+		/* Error, keep GHCB MSR value as-is */
+		break;
 	}
 
 	trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id,
@@ -2709,14 +2738,18 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 
 	if (!ghcb_gpa) {
 		vcpu_unimpl(vcpu, "vmgexit: GHCB gpa is not set\n");
-		return -EINVAL;
+
+		/* Without a GHCB, just return right back to the guest */
+		return 1;
 	}
 
 	if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) {
 		/* Unable to map GHCB from guest */
 		vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n",
 			    ghcb_gpa);
-		return -EINVAL;
+
+		/* Without a GHCB, just return right back to the guest */
+		return 1;
 	}
 
 	svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva;
@@ -2726,15 +2759,14 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 
 	exit_code = ghcb_get_sw_exit_code(ghcb);
 
-	ret = sev_es_validate_vmgexit(svm);
+	if (!sev_es_validate_vmgexit(svm))
-	if (ret)
+		return 1;
-		return ret;
 
 	sev_es_sync_from_ghcb(svm);
 	ghcb_set_sw_exit_info_1(ghcb, 0);
 	ghcb_set_sw_exit_info_2(ghcb, 0);
 
-	ret = -EINVAL;
+	ret = 1;
 	switch (exit_code) {
 	case SVM_VMGEXIT_MMIO_READ:
 		if (!setup_vmgexit_scratch(svm, true, control->exit_info_2))
@@ -2775,20 +2807,17 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		default:
 			pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n",
 			       control->exit_info_1);
-			ghcb_set_sw_exit_info_1(ghcb, 1);
+			ghcb_set_sw_exit_info_1(ghcb, 2);
-			ghcb_set_sw_exit_info_2(ghcb,
+			ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT);
-						X86_TRAP_UD |
-						SVM_EVTINJ_TYPE_EXEPT |
-						SVM_EVTINJ_VALID);
 		}
 
-		ret = 1;
 		break;
 	}
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		vcpu_unimpl(vcpu,
 			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
 			    control->exit_info_1, control->exit_info_2);
+		ret = -EINVAL;
 		break;
 	default:
 		ret = svm_invoke_exit_handler(vcpu, exit_code);
@@ -2810,7 +2839,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 		return -EINVAL;
 
 	if (!setup_vmgexit_scratch(svm, in, bytes))
-		return -EINVAL;
+		return 1;
 
 	return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa,
 				    count, in);

arch/x86/kvm/svm/svm.c

@@ -4651,7 +4651,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
 	.hwapic_irr_update = svm_hwapic_irr_update,
 	.hwapic_isr_update = svm_hwapic_isr_update,
-	.sync_pir_to_irr = kvm_lapic_find_highest_irr,
 	.apicv_post_state_restore = avic_post_state_restore,
 
 	.set_tss_addr = svm_set_tss_addr,

arch/x86/kvm/svm/svm.h

@@ -79,6 +79,7 @@ struct kvm_sev_info {
 	struct list_head regions_list;  /* List of registered regions */
 	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */
 	struct kvm *enc_context_owner; /* Owner of copied encryption context */
+	unsigned long num_mirrored_vms; /* Number of VMs sharing this ASID */
 	struct misc_cg *misc_cg; /* For misc cgroup accounting */
 	atomic_t migration_in_progress;
 };

arch/x86/kvm/vmx/nested.c

@@ -1162,29 +1162,26 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 	WARN_ON(!enable_vpid);
 
 	/*
-	 * If VPID is enabled and used by vmc12, but L2 does not have a unique
+	 * VPID is enabled and in use by vmcs12.  If vpid12 is changing, then
-	 * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate
+	 * emulate a guest TLB flush as KVM does not track vpid12 history nor
-	 * a VPID for L2, flush the current context as the effective ASID is
+	 * is the VPID incorporated into the MMU context.  I.e. KVM must assume
-	 * common to both L1 and L2.
+	 * that the new vpid12 has never been used and thus represents a new
-	 *
+	 * guest ASID that cannot have entries in the TLB.
-	 * Defer the flush so that it runs after vmcs02.EPTP has been set by
-	 * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid
-	 * redundant flushes further down the nested pipeline.
-	 *
-	 * If a TLB flush isn't required due to any of the above, and vpid12 is
-	 * changing then the new "virtual" VPID (vpid12) will reuse the same
-	 * "real" VPID (vpid02), and so needs to be flushed.  There's no direct
-	 * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for
-	 * all nested vCPUs.  Remember, a flush on VM-Enter does not invalidate
-	 * guest-physical mappings, so there is no need to sync the nEPT MMU.
 	 */
-	if (!nested_has_guest_tlb_tag(vcpu)) {
+	if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
-		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
-	} else if (is_vmenter &&
-		   vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
 		vmx->nested.last_vpid = vmcs12->virtual_processor_id;
-		vpid_sync_context(nested_get_vpid02(vcpu));
+		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
+		return;
 	}
+
+	/*
+	 * If VPID is enabled, used by vmc12, and vpid12 is not changing but
+	 * does not have a unique TLB tag (ASID), i.e. EPT is disabled and
+	 * KVM was unable to allocate a VPID for L2, flush the current context
+	 * as the effective ASID is common to both L1 and L2.
+	 */
+	if (!nested_has_guest_tlb_tag(vcpu))
+		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 }
 
 static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
@@ -2594,8 +2591,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
 	    WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
-				     vmcs12->guest_ia32_perf_global_ctrl)))
+				     vmcs12->guest_ia32_perf_global_ctrl))) {
+		*entry_failure_code = ENTRY_FAIL_DEFAULT;
 		return -EINVAL;
+	}
 
 	kvm_rsp_write(vcpu, vmcs12->guest_rsp);
 	kvm_rip_write(vcpu, vmcs12->guest_rip);
@@ -3344,8 +3343,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	};
 	u32 failed_index;
 
-	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+	kvm_service_local_tlb_flush_requests(vcpu);
-		kvm_vcpu_flush_tlb_current(vcpu);
 
 	evaluate_pending_interrupts = exec_controls_get(vmx) &
 		(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING);
@@ -4502,9 +4500,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		(void)nested_get_evmcs_page(vcpu);
 	}
 
-	/* Service the TLB flush request for L2 before switching to L1. */
+	/* Service pending TLB flush requests for L2 before switching to L1. */
-	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+	kvm_service_local_tlb_flush_requests(vcpu);
-		kvm_vcpu_flush_tlb_current(vcpu);
 
 	/*
 	 * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between
@@ -4857,6 +4854,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 	if (!vmx->nested.cached_vmcs12)
 		goto out_cached_vmcs12;
 
+	vmx->nested.shadow_vmcs12_cache.gpa = INVALID_GPA;
 	vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT);
 	if (!vmx->nested.cached_shadow_vmcs12)
 		goto out_cached_shadow_vmcs12;
@@ -5289,8 +5287,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache;
 		struct vmcs_hdr hdr;
 
-		if (ghc->gpa != vmptr &&
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) {
-		    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) {
 			/*
 			 * Reads from an unbacked page return all 1s,
 			 * which means that the 32 bits located at the

arch/x86/kvm/vmx/posted_intr.c

@@ -5,6 +5,7 @@
 #include <asm/cpu.h>
 
 #include "lapic.h"
+#include "irq.h"
 #include "posted_intr.h"
 #include "trace.h"
 #include "vmx.h"
@@ -77,13 +78,18 @@ after_clear_sn:
 		pi_set_on(pi_desc);
 }
 
+static bool vmx_can_use_vtd_pi(struct kvm *kvm)
+{
+	return irqchip_in_kernel(kvm) && enable_apicv &&
+		kvm_arch_has_assigned_device(kvm) &&
+		irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
 void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
 		return;
 
 	/* Set SN when the vCPU is preempted */
@@ -141,9 +147,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu)
 	struct pi_desc old, new;
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
 		return 0;
 
 	WARN_ON(irqs_disabled());
@@ -270,9 +274,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq,
 	struct vcpu_data vcpu_info;
 	int idx, ret = 0;
 
-	if (!kvm_arch_has_assigned_device(kvm) ||
+	if (!vmx_can_use_vtd_pi(kvm))
-	    !irq_remapping_cap(IRQ_POSTING_CAP) ||
-	    !kvm_vcpu_apicv_active(kvm->vcpus[0]))
 		return 0;
 
 	idx = srcu_read_lock(&kvm->irq_srcu);

arch/x86/kvm/vmx/vmx.c

@@ -2918,6 +2918,13 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu)
 	}
 }
 
+static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu)
+{
+	if (is_guest_mode(vcpu))
+		return nested_get_vpid02(vcpu);
+	return to_vmx(vcpu)->vpid;
+}
+
 static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
@@ -2930,31 +2937,29 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 	if (enable_ept)
 		ept_sync_context(construct_eptp(vcpu, root_hpa,
 						mmu->shadow_root_level));
-	else if (!is_guest_mode(vcpu))
-		vpid_sync_context(to_vmx(vcpu)->vpid);
 	else
-		vpid_sync_context(nested_get_vpid02(vcpu));
+		vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
 
 static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
 {
 	/*
-	 * vpid_sync_vcpu_addr() is a nop if vmx->vpid==0, see the comment in
+	 * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in
 	 * vmx_flush_tlb_guest() for an explanation of why this is ok.
 	 */
-	vpid_sync_vcpu_addr(to_vmx(vcpu)->vpid, addr);
+	vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr);
 }
 
 static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu)
 {
 	/*
-	 * vpid_sync_context() is a nop if vmx->vpid==0, e.g. if enable_vpid==0
+	 * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a
-	 * or a vpid couldn't be allocated for this vCPU.  VM-Enter and VM-Exit
+	 * vpid couldn't be allocated for this vCPU.  VM-Enter and VM-Exit are
-	 * are required to flush GVA->{G,H}PA mappings from the TLB if vpid is
+	 * required to flush GVA->{G,H}PA mappings from the TLB if vpid is
 	 * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed),
 	 * i.e. no explicit INVVPID is necessary.
 	 */
-	vpid_sync_context(to_vmx(vcpu)->vpid);
+	vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
 
 void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu)
@@ -6262,9 +6267,9 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int max_irr;
-	bool max_irr_updated;
+	bool got_posted_interrupt;
 
-	if (KVM_BUG_ON(!vcpu->arch.apicv_active, vcpu->kvm))
+	if (KVM_BUG_ON(!enable_apicv, vcpu->kvm))
 		return -EIO;
 
 	if (pi_test_on(&vmx->pi_desc)) {
@@ -6274,22 +6279,33 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 		 * But on x86 this is just a compiler barrier anyway.
 		 */
 		smp_mb__after_atomic();
-		max_irr_updated =
+		got_posted_interrupt =
 			kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);
-
-		/*
-		 * If we are running L2 and L1 has a new pending interrupt
-		 * which can be injected, this may cause a vmexit or it may
-		 * be injected into L2.  Either way, this interrupt will be
-		 * processed via KVM_REQ_EVENT, not RVI, because we do not use
-		 * virtual interrupt delivery to inject L1 interrupts into L2.
-		 */
-		if (is_guest_mode(vcpu) && max_irr_updated)
-			kvm_make_request(KVM_REQ_EVENT, vcpu);
 	} else {
 		max_irr = kvm_lapic_find_highest_irr(vcpu);
+		got_posted_interrupt = false;
 	}
-	vmx_hwapic_irr_update(vcpu, max_irr);
+
+	/*
+	 * Newly recognized interrupts are injected via either virtual interrupt
+	 * delivery (RVI) or KVM_REQ_EVENT.  Virtual interrupt delivery is
+	 * disabled in two cases:
+	 *
+	 * 1) If L2 is running and the vCPU has a new pending interrupt.  If L1
+	 * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a
+	 * VM-Exit to L1.  If L1 doesn't want to exit, the interrupt is injected
+	 * into L2, but KVM doesn't use virtual interrupt delivery to inject
+	 * interrupts into L2, and so KVM_REQ_EVENT is again needed.
+	 *
+	 * 2) If APICv is disabled for this vCPU, assigned devices may still
+	 * attempt to post interrupts.  The posted interrupt vector will cause
+	 * a VM-Exit and the subsequent entry will call sync_pir_to_irr.
+	 */
+	if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu))
+		vmx_set_rvi(max_irr);
+	else if (got_posted_interrupt)
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
 	return max_irr;
 }
 
@@ -7509,6 +7525,7 @@ static void hardware_unsetup(void)
 static bool vmx_check_apicv_inhibit_reasons(ulong bit)
 {
 	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
+			  BIT(APICV_INHIBIT_REASON_ABSENT) |
 			  BIT(APICV_INHIBIT_REASON_HYPERV) |
 			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
 
@@ -7761,10 +7778,10 @@ static __init int hardware_setup(void)
 		ple_window_shrink = 0;
 	}
 
-	if (!cpu_has_vmx_apicv()) {
+	if (!cpu_has_vmx_apicv())
 		enable_apicv = 0;
+	if (!enable_apicv)
 		vmx_x86_ops.sync_pir_to_irr = NULL;
-	}
 
 	if (cpu_has_vmx_tsc_scaling()) {
 		kvm_has_tsc_control = true;

arch/x86/kvm/x86.c

@@ -3258,6 +3258,29 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
 	static_call(kvm_x86_tlb_flush_guest)(vcpu);
 }
 
+
+static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+	++vcpu->stat.tlb_flush;
+	static_call(kvm_x86_tlb_flush_current)(vcpu);
+}
+
+/*
+ * Service "local" TLB flush requests, which are specific to the current MMU
+ * context.  In addition to the generic event handling in vcpu_enter_guest(),
+ * TLB flushes that are targeted at an MMU context also need to be serviced
+ * prior before nested VM-Enter/VM-Exit.
+ */
+void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu)
+{
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+		kvm_vcpu_flush_tlb_current(vcpu);
+
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
+		kvm_vcpu_flush_tlb_guest(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests);
+
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
 	struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache;
@@ -4133,6 +4156,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SGX_ATTRIBUTE:
 #endif
 	case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM:
+	case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM:
 	case KVM_CAP_SREGS2:
 	case KVM_CAP_EXIT_ON_EMULATION_FAILURE:
 	case KVM_CAP_VCPU_ATTRIBUTES:
@@ -4448,8 +4472,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
 				    struct kvm_lapic_state *s)
 {
-	if (vcpu->arch.apicv_active)
+	static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
-		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
 
 	return kvm_apic_get_state(vcpu, s);
 }
@@ -5124,6 +5147,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid __user *cpuid_arg = argp;
 		struct kvm_cpuid cpuid;
 
+		/*
+		 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
+		 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
+		 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
+		 * faults due to reusing SPs/SPTEs.  In practice no sane VMM mucks with
+		 * the core vCPU model on the fly, so fail.
+		 */
+		r = -EINVAL;
+		if (vcpu->arch.last_vmentry_cpu != -1)
+			goto out;
+
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
@@ -5134,6 +5168,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid2 __user *cpuid_arg = argp;
 		struct kvm_cpuid2 cpuid;
 
+		/*
+		 * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in
+		 * KVM_SET_CPUID case above.
+		 */
+		r = -EINVAL;
+		if (vcpu->arch.last_vmentry_cpu != -1)
+			goto out;
+
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
@@ -5698,6 +5740,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		smp_wmb();
 		kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT;
 		kvm->arch.nr_reserved_ioapic_pins = cap->args[0];
+		kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT);
 		r = 0;
 split_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
@@ -6078,6 +6121,7 @@ set_identity_unlock:
 		/* Write kvm->irq_routing before enabling irqchip_in_kernel. */
 		smp_wmb();
 		kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL;
+		kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT);
 	create_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
 		break;
@@ -8776,10 +8820,9 @@ static void kvm_apicv_init(struct kvm *kvm)
 {
 	init_rwsem(&kvm->arch.apicv_update_lock);
 
-	if (enable_apicv)
+	set_bit(APICV_INHIBIT_REASON_ABSENT,
-		clear_bit(APICV_INHIBIT_REASON_DISABLE,
+		&kvm->arch.apicv_inhibit_reasons);
-			  &kvm->arch.apicv_inhibit_reasons);
+	if (!enable_apicv)
-	else
 		set_bit(APICV_INHIBIT_REASON_DISABLE,
 			&kvm->arch.apicv_inhibit_reasons);
 }
@@ -9528,8 +9571,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	if (irqchip_split(vcpu->kvm))
 		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
 	else {
-		if (vcpu->arch.apicv_active)
+		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
-			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
 		if (ioapic_in_kernel(vcpu->kvm))
 			kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
 	}
@@ -9648,10 +9690,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			/* Flushing all ASIDs flushes the current ASID... */
 			kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 		}
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+		kvm_service_local_tlb_flush_requests(vcpu);
-			kvm_vcpu_flush_tlb_current(vcpu);
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
-			kvm_vcpu_flush_tlb_guest(vcpu);
 
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
@@ -9802,10 +9841,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	/*
 	 * This handles the case where a posted interrupt was
-	 * notified with kvm_vcpu_kick.
+	 * notified with kvm_vcpu_kick.  Assigned devices can
+	 * use the POSTED_INTR_VECTOR even if APICv is disabled,
+	 * so do it even if APICv is disabled on this vCPU.
 	 */
-	if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active)
+	if (kvm_lapic_enabled(vcpu))
-		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 	if (kvm_vcpu_exit_request(vcpu)) {
 		vcpu->mode = OUTSIDE_GUEST_MODE;
@@ -9849,8 +9890,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
 			break;
 
-		if (vcpu->arch.apicv_active)
+		if (kvm_lapic_enabled(vcpu))
-			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+			static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 		if (unlikely(kvm_vcpu_exit_request(vcpu))) {
 			exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;

arch/x86/kvm/x86.h

@@ -103,6 +103,7 @@ static inline unsigned int __shrink_ple_window(unsigned int val,
 
 #define MSR_IA32_CR_PAT_DEFAULT  0x0007040600070406ULL
 
+void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu);
 int kvm_check_nested_events(struct kvm_vcpu *vcpu);
 
 static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
@@ -185,12 +186,6 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
 	return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
 }
 
-static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
-{
-	++vcpu->stat.tlb_flush;
-	static_call(kvm_x86_tlb_flush_current)(vcpu);
-}
-
 static inline int is_pae(struct kvm_vcpu *vcpu)
 {
 	return kvm_read_cr4_bits(vcpu, X86_CR4_PAE);

arch/x86/realmode/init.c

@@ -72,6 +72,7 @@ static void __init setup_real_mode(void)
 #ifdef CONFIG_X86_64
 	u64 *trampoline_pgd;
 	u64 efer;
+	int i;
 #endif
 
 	base = (unsigned char *)real_mode_header;
@@ -128,8 +129,17 @@ static void __init setup_real_mode(void)
 	trampoline_header->flags = 0;
 
 	trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
+
+	/* Map the real mode stub as virtual == physical */
 	trampoline_pgd[0] = trampoline_pgd_entry.pgd;
-	trampoline_pgd[511] = init_top_pgt[511].pgd;
+
+	/*
+	 * Include the entirety of the kernel mapping into the trampoline
+	 * PGD.  This way, all mappings present in the normal kernel page
+	 * tables are usable while running on trampoline_pgd.
+	 */
+	for (i = pgd_index(__PAGE_OFFSET); i < PTRS_PER_PGD; i++)
+		trampoline_pgd[i] = init_top_pgt[i].pgd;
 #endif
 
 	sme_sev_setup_real_mode(trampoline_header);

arch/x86/xen/xen-asm.S

@@ -20,6 +20,7 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <../entry/calling.h>
 
 .pushsection .noinstr.text, "ax"
 /*
@@ -192,6 +193,25 @@ SYM_CODE_START(xen_iret)
 	jmp hypercall_iret
 SYM_CODE_END(xen_iret)
 
+/*
+ * XEN pv doesn't use trampoline stack, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is
+ * also the kernel stack.  Reusing swapgs_restore_regs_and_return_to_usermode()
+ * in XEN pv would cause %rsp to move up to the top of the kernel stack and
+ * leave the IRET frame below %rsp, which is dangerous to be corrupted if #NMI
+ * interrupts. And swapgs_restore_regs_and_return_to_usermode() pushing the IRET
+ * frame at the same address is useless.
+ */
+SYM_CODE_START(xenpv_restore_regs_and_return_to_usermode)
+	UNWIND_HINT_REGS
+	POP_REGS
+
+	/* stackleak_erase() can work safely on the kernel stack. */
+	STACKLEAK_ERASE_NOCLOBBER
+
+	addq	$8, %rsp	/* skip regs->orig_ax */
+	jmp xen_iret
+SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode)
+
 /*
  * Xen handles syscall callbacks much like ordinary exceptions, which
  * means we have:

arch/xtensa/include/asm/cacheflush.h

@@ -121,7 +121,6 @@ void flush_cache_page(struct vm_area_struct*,
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 void flush_dcache_page(struct page *);
-void flush_dcache_folio(struct folio *);
 
 void local_flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end);
@@ -138,9 +137,7 @@ void local_flush_cache_page(struct vm_area_struct *vma,
 #define flush_cache_vunmap(start,end)			do { } while (0)
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
 #define flush_dcache_page(page)				do { } while (0)
-static inline void flush_dcache_folio(struct folio *folio) { }
 
 #define flush_icache_range local_flush_icache_range
 #define flush_cache_page(vma, addr, pfn)		do { } while (0)

arch/xtensa/kernel/syscalls/syscall.tbl

@@ -419,3 +419,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv

block/bdev.c

@@ -753,8 +753,7 @@ struct block_device *blkdev_get_no_open(dev_t dev)
 
 	if (!bdev)
 		return NULL;
-	if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN) ||
+	if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN)) {
-	    !try_module_get(bdev->bd_disk->fops->owner)) {
 		put_device(&bdev->bd_device);
 		return NULL;
 	}
@@ -764,7 +763,6 @@ struct block_device *blkdev_get_no_open(dev_t dev)
 
 void blkdev_put_no_open(struct block_device *bdev)
 {
-	module_put(bdev->bd_disk->fops->owner);
 	put_device(&bdev->bd_device);
 }
 
@@ -820,12 +818,14 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 	ret = -ENXIO;
 	if (!disk_live(disk))
 		goto abort_claiming;
+	if (!try_module_get(disk->fops->owner))
+		goto abort_claiming;
 	if (bdev_is_partition(bdev))
 		ret = blkdev_get_part(bdev, mode);
 	else
 		ret = blkdev_get_whole(bdev, mode);
 	if (ret)
-		goto abort_claiming;
+		goto put_module;
 	if (mode & FMODE_EXCL) {
 		bd_finish_claiming(bdev, holder);
 
@@ -847,7 +847,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 	if (unblock_events)
 		disk_unblock_events(disk);
 	return bdev;
-
+put_module:
+	module_put(disk->fops->owner);
 abort_claiming:
 	if (mode & FMODE_EXCL)
 		bd_abort_claiming(bdev, holder);
@@ -956,6 +957,7 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 		blkdev_put_whole(bdev, mode);
 	mutex_unlock(&disk->open_mutex);
 
+	module_put(disk->fops->owner);
 	blkdev_put_no_open(bdev);
 }
 EXPORT_SYMBOL(blkdev_put);

block/blk-core.c

@@ -1017,6 +1017,7 @@ EXPORT_SYMBOL(submit_bio);
 /**
  * bio_poll - poll for BIO completions
  * @bio: bio to poll for
+ * @iob: batches of IO
  * @flags: BLK_POLL_* flags that control the behavior
  *
  * Poll for completions on queue associated with the bio. Returns number of