diff options
474 files changed, 13334 insertions, 5743 deletions
@@ -160,6 +160,7 @@ Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com> Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com> Jens Axboe <axboe@suse.de> Jens Osterkamp <Jens.Osterkamp@de.ibm.com> +Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net> Jiri Slaby <jirislaby@kernel.org> <jirislaby@gmail.com> Jiri Slaby <jirislaby@kernel.org> <jslaby@novell.com> Jiri Slaby <jirislaby@kernel.org> <jslaby@suse.com> diff --git a/Documentation/ABI/obsolete/sysfs-class-dax b/Documentation/ABI/obsolete/sysfs-class-dax index 0faf1354cd05..5bcce27458e3 100644 --- a/Documentation/ABI/obsolete/sysfs-class-dax +++ b/Documentation/ABI/obsolete/sysfs-class-dax @@ -1,7 +1,7 @@ What: /sys/class/dax/ Date: May, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: Device DAX is the device-centric analogue of Filesystem DAX (CONFIG_FS_DAX). It allows memory ranges to be allocated and mapped without need of an intervening file diff --git a/Documentation/ABI/obsolete/sysfs-kernel-fadump_registered b/Documentation/ABI/obsolete/sysfs-kernel-fadump_registered index 0360be39c98e..dae880b1a5d5 100644 --- a/Documentation/ABI/obsolete/sysfs-kernel-fadump_registered +++ b/Documentation/ABI/obsolete/sysfs-kernel-fadump_registered @@ -1,4 +1,4 @@ -This ABI is renamed and moved to a new location /sys/kernel/fadump/registered.¬ +This ABI is renamed and moved to a new location /sys/kernel/fadump/registered. What: /sys/kernel/fadump_registered Date: Feb 2012 diff --git a/Documentation/ABI/obsolete/sysfs-kernel-fadump_release_mem b/Documentation/ABI/obsolete/sysfs-kernel-fadump_release_mem index 6ce0b129ab12..ca2396edb5f1 100644 --- a/Documentation/ABI/obsolete/sysfs-kernel-fadump_release_mem +++ b/Documentation/ABI/obsolete/sysfs-kernel-fadump_release_mem @@ -1,4 +1,4 @@ -This ABI is renamed and moved to a new location /sys/kernel/fadump/release_mem.¬ +This ABI is renamed and moved to a new location /sys/kernel/fadump/release_mem. What: /sys/kernel/fadump_release_mem Date: Feb 2012 diff --git a/Documentation/ABI/removed/sysfs-bus-nfit b/Documentation/ABI/removed/sysfs-bus-nfit index ae8c1ca53828..277437005def 100644 --- a/Documentation/ABI/removed/sysfs-bus-nfit +++ b/Documentation/ABI/removed/sysfs-bus-nfit @@ -1,7 +1,7 @@ What: /sys/bus/nd/devices/regionX/nfit/ecc_unit_size Date: Aug, 2017 KernelVersion: v4.14 (Removed v4.18) -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Size of a write request to a DIMM that will not incur a read-modify-write cycle at the memory controller. diff --git a/Documentation/ABI/testing/sysfs-bus-nfit b/Documentation/ABI/testing/sysfs-bus-nfit index 63ef0b9ecce7..e7282d184a74 100644 --- a/Documentation/ABI/testing/sysfs-bus-nfit +++ b/Documentation/ABI/testing/sysfs-bus-nfit @@ -5,7 +5,7 @@ Interface Table (NFIT)' section in the ACPI specification What: /sys/bus/nd/devices/nmemX/nfit/serial Date: Jun, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Serial number of the NVDIMM (non-volatile dual in-line memory module), assigned by the module vendor. @@ -14,7 +14,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/handle Date: Apr, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) The address (given by the _ADR object) of the device on its parent bus of the NVDIMM device containing the NVDIMM region. @@ -23,7 +23,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/device Date: Apr, 2015 KernelVersion: v4.1 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Device id for the NVDIMM, assigned by the module vendor. @@ -31,7 +31,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/rev_id Date: Jun, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Revision of the NVDIMM, assigned by the module vendor. @@ -39,7 +39,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/phys_id Date: Apr, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Handle (i.e., instance number) for the SMBIOS (system management BIOS) Memory Device structure describing the NVDIMM @@ -49,7 +49,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/flags Date: Jun, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) The flags in the NFIT memory device sub-structure indicate the state of the data on the nvdimm relative to its energy @@ -68,7 +68,7 @@ What: /sys/bus/nd/devices/nmemX/nfit/format1 What: /sys/bus/nd/devices/nmemX/nfit/formats Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) The interface codes indicate support for persistent memory mapped directly into system physical address space and / or a @@ -84,7 +84,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/vendor Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Vendor id of the NVDIMM. @@ -92,7 +92,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/dsm_mask Date: May, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) The bitmask indicates the supported device specific control functions relative to the NVDIMM command family supported by the @@ -102,7 +102,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/family Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Displays the NVDIMM family command sets. Values 0, 1, 2 and 3 correspond to NVDIMM_FAMILY_INTEL, @@ -118,7 +118,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/id Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) ACPI specification 6.2 section 5.2.25.9, defines an identifier for an NVDIMM, which refelects the id attribute. @@ -127,7 +127,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/subsystem_vendor Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Sub-system vendor id of the NVDIMM non-volatile memory subsystem controller. @@ -136,7 +136,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/subsystem_rev_id Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Sub-system revision id of the NVDIMM non-volatile memory subsystem controller, assigned by the non-volatile memory subsystem @@ -146,7 +146,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/subsystem_device Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Sub-system device id for the NVDIMM non-volatile memory subsystem controller, assigned by the non-volatile memory @@ -156,7 +156,7 @@ Description: What: /sys/bus/nd/devices/ndbusX/nfit/revision Date: Jun, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) ACPI NFIT table revision number. @@ -164,7 +164,7 @@ Description: What: /sys/bus/nd/devices/ndbusX/nfit/scrub Date: Sep, 2016 KernelVersion: v4.9 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RW) This shows the number of full Address Range Scrubs (ARS) that have been completed since driver load time. Userspace can @@ -177,7 +177,7 @@ Description: What: /sys/bus/nd/devices/ndbusX/nfit/hw_error_scrub Date: Sep, 2016 KernelVersion: v4.9 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RW) Provides a way to toggle the behavior between just adding the address (cache line) where the MCE happened to the poison @@ -196,7 +196,7 @@ Description: What: /sys/bus/nd/devices/ndbusX/nfit/dsm_mask Date: Jun, 2017 KernelVersion: v4.13 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) The bitmask indicates the supported bus specific control functions. See the section named 'NVDIMM Root Device _DSMs' in @@ -205,7 +205,7 @@ Description: What: /sys/bus/nd/devices/ndbusX/nfit/firmware_activate_noidle Date: Apr, 2020 KernelVersion: v5.8 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RW) The Intel platform implementation of firmware activate support exposes an option let the platform force idle devices in @@ -225,7 +225,7 @@ Description: What: /sys/bus/nd/devices/regionX/nfit/range_index Date: Jun, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) A unique number provided by the BIOS to identify an address range. Used by NVDIMM Region Mapping Structure to uniquely refer diff --git a/Documentation/ABI/testing/sysfs-bus-papr-pmem b/Documentation/ABI/testing/sysfs-bus-papr-pmem index 8316c33862a0..92e2db0e2d3d 100644 --- a/Documentation/ABI/testing/sysfs-bus-papr-pmem +++ b/Documentation/ABI/testing/sysfs-bus-papr-pmem @@ -1,7 +1,7 @@ What: /sys/bus/nd/devices/nmemX/papr/flags Date: Apr, 2020 KernelVersion: v5.8 -Contact: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>, linux-nvdimm@lists.01.org, +Contact: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>, nvdimm@lists.linux.dev, Description: (RO) Report flags indicating various states of a papr-pmem NVDIMM device. Each flag maps to a one or @@ -36,7 +36,7 @@ Description: What: /sys/bus/nd/devices/nmemX/papr/perf_stats Date: May, 2020 KernelVersion: v5.9 -Contact: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>, linux-nvdimm@lists.01.org, +Contact: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>, nvdimm@lists.linux.dev, Description: (RO) Report various performance stats related to papr-scm NVDIMM device. Each stat is reported on a new line with each line diff --git a/Documentation/ABI/testing/sysfs-module b/Documentation/ABI/testing/sysfs-module index a485434d2a0f..88bddf192ceb 100644 --- a/Documentation/ABI/testing/sysfs-module +++ b/Documentation/ABI/testing/sysfs-module @@ -37,13 +37,13 @@ Description: Maximum time allowed for periodic transfers per microframe (μs) What: /sys/module/*/{coresize,initsize} Date: Jan 2012 -KernelVersion:»·3.3 +KernelVersion: 3.3 Contact: Kay Sievers <kay.sievers@vrfy.org> Description: Module size in bytes. What: /sys/module/*/taint Date: Jan 2012 -KernelVersion:»·3.3 +KernelVersion: 3.3 Contact: Kay Sievers <kay.sievers@vrfy.org> Description: Module taint flags: == ===================== diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 1d56a6b73a4e..7ca8df5451d4 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -483,10 +483,11 @@ modprobe ======== The full path to the usermode helper for autoloading kernel modules, -by default "/sbin/modprobe". This binary is executed when the kernel -requests a module. For example, if userspace passes an unknown -filesystem type to mount(), then the kernel will automatically request -the corresponding filesystem module by executing this usermode helper. +by default ``CONFIG_MODPROBE_PATH``, which in turn defaults to +"/sbin/modprobe". This binary is executed when the kernel requests a +module. For example, if userspace passes an unknown filesystem type +to mount(), then the kernel will automatically request the +corresponding filesystem module by executing this usermode helper. This usermode helper should insert the needed module into the kernel. This sysctl only affects module autoloading. It has no effect on the diff --git a/Documentation/block/data-integrity.rst b/Documentation/block/data-integrity.rst index 4f2452a95c43..07a97aa26668 100644 --- a/Documentation/block/data-integrity.rst +++ b/Documentation/block/data-integrity.rst @@ -1,4 +1,4 @@ -============== +============== Data Integrity ============== diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst index 70500b189cc8..5845960ca382 100644 --- a/Documentation/cdrom/cdrom-standard.rst +++ b/Documentation/cdrom/cdrom-standard.rst @@ -146,18 +146,18 @@ with the kernel as a block device by registering the following general *struct file_operations*:: struct file_operations cdrom_fops = { - NULL, /∗ lseek ∗/ - block _read , /∗ read—general block-dev read ∗/ - block _write, /∗ write—general block-dev write ∗/ - NULL, /∗ readdir ∗/ - NULL, /∗ select ∗/ - cdrom_ioctl, /∗ ioctl ∗/ - NULL, /∗ mmap ∗/ - cdrom_open, /∗ open ∗/ - cdrom_release, /∗ release ∗/ - NULL, /∗ fsync ∗/ - NULL, /∗ fasync ∗/ - NULL /∗ revalidate ∗/ + NULL, /* lseek */ + block _read , /* read--general block-dev read */ + block _write, /* write--general block-dev write */ + NULL, /* readdir */ + NULL, /* select */ + cdrom_ioctl, /* ioctl */ + NULL, /* mmap */ + cdrom_open, /* open */ + cdrom_release, /* release */ + NULL, /* fsync */ + NULL, /* fasync */ + NULL /* revalidate */ }; Every active CD-ROM device shares this *struct*. The routines @@ -250,12 +250,12 @@ The drive-specific, minor-like information that is registered with `cdrom.c`, currently contains the following fields:: struct cdrom_device_info { - const struct cdrom_device_ops * ops; /* device operations for this major */ + const struct cdrom_device_ops * ops; /* device operations for this major */ struct list_head list; /* linked list of all device_info */ struct gendisk * disk; /* matching block layer disk */ void * handle; /* driver-dependent data */ - int mask; /* mask of capability: disables them */ + int mask; /* mask of capability: disables them */ int speed; /* maximum speed for reading data */ int capacity; /* number of discs in a jukebox */ @@ -569,7 +569,7 @@ the *CDC_CLOSE_TRAY* bit in *mask*. In the file `cdrom.c` you will encounter many constructions of the type:: - if (cdo->capability & ∼cdi->mask & CDC _⟨capability⟩) ... + if (cdo->capability & ~cdi->mask & CDC _<capability>) ... There is no *ioctl* to set the mask... The reason is that I think it is better to control the **behavior** rather than the diff --git a/Documentation/driver-api/nvdimm/nvdimm.rst b/Documentation/driver-api/nvdimm/nvdimm.rst index ef6d59e0978e..1d8302b89bd4 100644 --- a/Documentation/driver-api/nvdimm/nvdimm.rst +++ b/Documentation/driver-api/nvdimm/nvdimm.rst @@ -4,7 +4,7 @@ LIBNVDIMM: Non-Volatile Devices libnvdimm - kernel / libndctl - userspace helper library -linux-nvdimm@lists.01.org +nvdimm@lists.linux.dev Version 13 diff --git a/Documentation/driver-api/serial/index.rst b/Documentation/driver-api/serial/index.rst index 21351b8c95a4..8f7d7af3b90b 100644 --- a/Documentation/driver-api/serial/index.rst +++ b/Documentation/driver-api/serial/index.rst @@ -19,7 +19,6 @@ Serial drivers moxa-smartio n_gsm - rocket serial-iso7816 serial-rs485 diff --git a/Documentation/driver-api/usb/usb.rst b/Documentation/driver-api/usb/usb.rst index 543e70434da2..820e867af45a 100644 --- a/Documentation/driver-api/usb/usb.rst +++ b/Documentation/driver-api/usb/usb.rst @@ -109,16 +109,19 @@ well as to make sure they aren't relying on some HCD-specific behavior. USB-Standard Types ================== -In ``drivers/usb/common/common.c`` and ``drivers/usb/common/debug.c`` you -will find the USB data types defined in chapter 9 of the USB specification. -These data types are used throughout USB, and in APIs including this host -side API, gadget APIs, usb character devices and debugfs interfaces. +In ``include/uapi/linux/usb/ch9.h`` you will find the USB data types defined +in chapter 9 of the USB specification. These data types are used throughout +USB, and in APIs including this host side API, gadget APIs, usb character +devices and debugfs interfaces. That file is itself included by +``include/linux/usb/ch9.h``, which also contains declarations of a few +utility routines for manipulating these data types; the implementations +are in ``drivers/usb/common/common.c``. .. kernel-doc:: drivers/usb/common/common.c :export: -.. kernel-doc:: drivers/usb/common/debug.c - :export: +In addition, some functions useful for creating debugging output are +defined in ``drivers/usb/common/debug.c``. Host-Side Data Types and Macros =============================== diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst index bf145171c2bf..832839fcf4c3 100644 --- a/Documentation/filesystems/erofs.rst +++ b/Documentation/filesystems/erofs.rst @@ -50,8 +50,8 @@ Here is the main features of EROFS: - Support POSIX.1e ACLs by using xattrs; - - Support transparent file compression as an option: - LZ4 algorithm with 4 KB fixed-sized output compression for high performance. + - Support transparent data compression as an option: + LZ4 algorithm with the fixed-sized output compression for high performance. The following git tree provides the file system user-space tools under development (ex, formatting tool mkfs.erofs): @@ -113,31 +113,31 @@ may not. All metadatas can be now observed in two different spaces (views): :: - |-> aligned with 8B - |-> followed closely - + meta_blkaddr blocks |-> another slot - _____________________________________________________________________ - | ... | inode | xattrs | extents | data inline | ... | inode ... - |________|_______|(optional)|(optional)|__(optional)_|_____|__________ - |-> aligned with the inode slot size - . . - . . - . . - . . - . . - . . - .____________________________________________________|-> aligned with 4B - | xattr_ibody_header | shared xattrs | inline xattrs | - |____________________|_______________|_______________| - |-> 12 bytes <-|->x * 4 bytes<-| . - . . . - . . . - . . . - ._______________________________.______________________. - | id | id | id | id | ... | id | ent | ... | ent| ... | - |____|____|____|____|______|____|_____|_____|____|_____| - |-> aligned with 4B - |-> aligned with 4B + |-> aligned with 8B + |-> followed closely + + meta_blkaddr blocks |-> another slot + _____________________________________________________________________ + | ... | inode | xattrs | extents | data inline | ... | inode ... + |________|_______|(optional)|(optional)|__(optional)_|_____|__________ + |-> aligned with the inode slot size + . . + . . + . . + . . + . . + . . + .____________________________________________________|-> aligned with 4B + | xattr_ibody_header | shared xattrs | inline xattrs | + |____________________|_______________|_______________| + |-> 12 bytes <-|->x * 4 bytes<-| . + . . . + . . . + . . . + ._______________________________.______________________. + | id | id | id | id | ... | id | ent | ... | ent| ... | + |____|____|____|____|______|____|_____|_____|____|_____| + |-> aligned with 4B + |-> aligned with 4B Inode could be 32 or 64 bytes, which can be distinguished from a common field which all inode versions have -- i_format:: @@ -175,13 +175,13 @@ may not. All metadatas can be now observed in two different spaces (views): Each share xattr can also be directly found by the following formula: xattr offset = xattr_blkaddr * block_size + 4 * xattr_id - :: +:: - |-> aligned by 4 bytes - + xattr_blkaddr blocks |-> aligned with 4 bytes - _________________________________________________________________________ - | ... | xattr_entry | xattr data | ... | xattr_entry | xattr data ... - |________|_____________|_____________|_____|______________|_______________ + |-> aligned by 4 bytes + + xattr_blkaddr blocks |-> aligned with 4 bytes + _________________________________________________________________________ + | ... | xattr_entry | xattr data | ... | xattr_entry | xattr data ... + |________|_____________|_____________|_____|______________|_______________ Directories ----------- @@ -193,48 +193,77 @@ algorithm (could refer to the related source code). :: - ___________________________ - / | - / ______________|________________ - / / | nameoff1 | nameoffN-1 - ____________.______________._______________v________________v__________ - | dirent | dirent | ... | dirent | filename | filename | ... | filename | - |___.0___|____1___|_____|___N-1__|____0_____|____1_____|_____|___N-1____| - \ ^ - \ | * could have - \ | trailing '\0' - \________________________| nameoff0 - - Directory block + ___________________________ + / | + / ______________|________________ + / / | nameoff1 | nameoffN-1 + ____________.______________._______________v________________v__________ + | dirent | dirent | ... | dirent | filename | filename | ... | filename | + |___.0___|____1___|_____|___N-1__|____0_____|____1_____|_____|___N-1____| + \ ^ + \ | * could have + \ | trailing '\0' + \________________________| nameoff0 + Directory block Note that apart from the offset of the first filename, nameoff0 also indicates the total number of directory entries in this block since it is no need to introduce another on-disk field at all. -Compression ------------ -Currently, EROFS supports 4KB fixed-sized output transparent file compression, -as illustrated below:: - - |---- Variant-Length Extent ----|-------- VLE --------|----- VLE ----- - clusterofs clusterofs clusterofs - | | | logical data - _________v_______________________________v_____________________v_______________ - ... | . | | . | | . | ... - ____|____.________|_____________|________.____|_____________|__.__________|____ - |-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-| - size size size size size - . . . . - . . . . - . . . . - _______._____________._____________._____________._____________________ - ... | | | | ... physical data - _______|_____________|_____________|_____________|_____________________ - |-> cluster <-|-> cluster <-|-> cluster <-| - size size size - -Currently each on-disk physical cluster can contain 4KB (un)compressed data -at most. For each logical cluster, there is a corresponding on-disk index to -describe its cluster type, physical cluster address, etc. - -See "struct z_erofs_vle_decompressed_index" in erofs_fs.h for more details. +Data compression +---------------- +EROFS implements LZ4 fixed-sized output compression which generates fixed-sized +compressed data blocks from variable-sized input in contrast to other existing +fixed-sized input solutions. Relatively higher compression ratios can be gotten +by using fixed-sized output compression since nowadays popular data compression +algorithms are mostly LZ77-based and such fixed-sized output approach can be +benefited from the historical dictionary (aka. sliding window). + +In details, original (uncompressed) data is turned into several variable-sized +extents and in the meanwhile, compressed into physical clusters (pclusters). +In order to record each variable-sized extent, logical clusters (lclusters) are +introduced as the basic unit of compress indexes to indicate whether a new +extent is generated within the range (HEAD) or not (NONHEAD). Lclusters are now +fixed in block size, as illustrated below:: + + |<- variable-sized extent ->|<- VLE ->| + clusterofs clusterofs clusterofs + | | | + _________v_________________________________v_______________________v________ + ... | . | | . | | . ... + ____|____._________|______________|________.___ _|______________|__.________ + |-> lcluster <-|-> lcluster <-|-> lcluster <-|-> lcluster <-| + (HEAD) (NONHEAD) (HEAD) (NONHEAD) . + . CBLKCNT . . + . . . + . . . + _______._____________________________.______________._________________ + ... | | | | ... + _______|______________|______________|______________|_________________ + |-> big pcluster <-|-> pcluster <-| + +A physical cluster can be seen as a container of physical compressed blocks +which contains compressed data. Previously, only lcluster-sized (4KB) pclusters +were supported. After big pcluster feature is introduced (available since +Linux v5.13), pcluster can be a multiple of lcluster size. + +For each HEAD lcluster, clusterofs is recorded to indicate where a new extent +starts and blkaddr is used to seek the compressed data. For each NONHEAD +lcluster, delta0 and delta1 are available instead of blkaddr to indicate the +distance to its HEAD lcluster and the next HEAD lcluster. A PLAIN lcluster is +also a HEAD lcluster except that its data is uncompressed. See the comments +around "struct z_erofs_vle_decompressed_index" in erofs_fs.h for more details. + +If big pcluster is enabled, pcluster size in lclusters needs to be recorded as +well. Let the delta0 of the first NONHEAD lcluster store the compressed block +count with a special flag as a new called CBLKCNT NONHEAD lcluster. It's easy +to understand its delta0 is constantly 1, as illustrated below:: + + __________________________________________________________ + | HEAD | NONHEAD | NONHEAD | ... | NONHEAD | HEAD | HEAD | + |__:___|_(CBLKCNT)_|_________|_____|_________|__:___|____:_| + |<----- a big pcluster (with CBLKCNT) ------>|<-- -->| + a lcluster-sized pcluster (without CBLKCNT) ^ + +If another HEAD follows a HEAD lcluster, there is no room to record CBLKCNT, +but it's easy to know the size of such pcluster is 1 lcluster as well. diff --git a/Documentation/hwmon/tmp103.rst b/Documentation/hwmon/tmp103.rst index e195a7d14309..b3ef81475cf8 100644 --- a/Documentation/hwmon/tmp103.rst +++ b/Documentation/hwmon/tmp103.rst @@ -21,10 +21,10 @@ Description The TMP103 is a digital output temperature sensor in a four-ball wafer chip-scale package (WCSP). The TMP103 is capable of reading temperatures to a resolution of 1°C. The TMP103 is specified for -operation over a temperature range of –40°C to +125°C. +operation over a temperature range of -40°C to +125°C. Resolution: 8 Bits -Accuracy: ±1°C Typ (–10°C to +100°C) +Accuracy: ±1°C Typ (-10°C to +100°C) The driver provides the common sysfs-interface for temperatures (see Documentation/hwmon/sysfs-interface.rst under Temperatures). diff --git a/Documentation/networking/device_drivers/ethernet/intel/i40e.rst b/Documentation/networking/device_drivers/ethernet/intel/i40e.rst index 8a9b18573688..2d3f6bd969a2 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/i40e.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/i40e.rst @@ -173,7 +173,7 @@ Director rule is added from ethtool (Sideband filter), ATR is turned off by the driver. To re-enable ATR, the sideband can be disabled with the ethtool -K option. For example:: - ethtool –K [adapter] ntuple [off|on] + ethtool -K [adapter] ntuple [off|on] If sideband is re-enabled after ATR is re-enabled, ATR remains enabled until a TCP-IP flow is added. When all TCP-IP sideband rules are deleted, ATR is @@ -688,7 +688,7 @@ shaper bw_rlimit: for each tc, sets minimum and maximum bandwidth rates. Totals must be equal or less than port speed. For example: min_rate 1Gbit 3Gbit: Verify bandwidth limit using network -monitoring tools such as ifstat or sar –n DEV [interval] [number of samples] +monitoring tools such as `ifstat` or `sar -n DEV [interval] [number of samples]` 2. Enable HW TC offload on interface:: diff --git a/Documentation/networking/device_drivers/ethernet/intel/iavf.rst b/Documentation/networking/device_drivers/ethernet/intel/iavf.rst index 52e037b11c97..25330b7b5168 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/iavf.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/iavf.rst @@ -179,7 +179,7 @@ shaper bw_rlimit: for each tc, sets minimum and maximum bandwidth rates. Totals must be equal or less than port speed. For example: min_rate 1Gbit 3Gbit: Verify bandwidth limit using network -monitoring tools such as ifstat or sar –n DEV [interval] [number of samples] +monitoring tools such as ``ifstat`` or ``sar -n DEV [interval] [number of samples]`` NOTE: Setting up channels via ethtool (ethtool -L) is not supported when the diff --git a/Documentation/process/kernel-enforcement-statement.rst b/Documentation/process/kernel-enforcement-statement.rst index e5a1be476047..dc2d813b2e79 100644 --- a/Documentation/process/kernel-enforcement-statement.rst +++ b/Documentation/process/kernel-enforcement-statement.rst @@ -1,4 +1,4 @@ -.. _process_statement_kernel: +.. _process_statement_kernel: Linux Kernel Enforcement Statement ---------------------------------- diff --git a/Documentation/security/tpm/xen-tpmfront.rst b/Documentation/security/tpm/xen-tpmfront.rst index 00d5b1db227d..31c67522f2ad 100644 --- a/Documentation/security/tpm/xen-tpmfront.rst +++ b/Documentation/security/tpm/xen-tpmfront.rst @@ -1,4 +1,4 @@ -============================= +============================= Virtual TPM interface for Xen ============================= diff --git a/Documentation/timers/no_hz.rst b/Documentation/timers/no_hz.rst index c4c70e1aada3..6cadad7c3aad 100644 --- a/Documentation/timers/no_hz.rst +++ b/Documentation/timers/no_hz.rst @@ -1,4 +1,4 @@ -====================================== +====================================== NO_HZ: Reducing Scheduling-Clock Ticks ====================================== diff --git a/Documentation/translations/zh_CN/SecurityBugs b/Documentation/translations/zh_CN/SecurityBugs deleted file mode 100644 index 2d0fffd122ce..000000000000 --- a/Documentation/translations/zh_CN/SecurityBugs +++ /dev/null @@ -1,50 +0,0 @@ -Chinese translated version of Documentation/admin-guide/security-bugs.rst - -If you have any comment or update to the content, please contact the -original document maintainer directly. However, if you have a problem -communicating in English you can also ask the Chinese maintainer for -help. Contact the Chinese maintainer if this translation is outdated -or if there is a problem with the translation. - -Chinese maintainer: Harry Wei <harryxiyou@gmail.com> ---------------------------------------------------------------------- -Documentation/admin-guide/security-bugs.rst 的中文翻译 - -如果想评论或更新本文的内容,请直接联系原文档的维护者。如果你使用英文 -交流有困难的话,也可以向中文版维护者求助。如果本翻译更新不及时或者翻 -译存在问题,请联系中文版维护者。 - -中文版维护者: 贾威威 Harry Wei <harryxiyou@gmail.com> -中文版翻译者: 贾威威 Harry Wei <harryxiyou@gmail.com> -中文版校译者: 贾威威 Harry Wei <harryxiyou@gmail.com> - - -以下为正文 ---------------------------------------------------------------------- -Linux内核开发者认为安全非常重要。因此,我们想要知道当一个有关于 -安全的漏洞被发现的时候,并且它可能会被尽快的修复或者公开。请把这个安全 -漏洞报告给Linux内核安全团队。 - -1) 联系 - -linux内核安全团队可以通过email<security@kernel.org>来联系。这是 -一组独立的安全工作人员,可以帮助改善漏洞报告并且公布和取消一个修复。安 -全团队有可能会从部分的维护者那里引进额外的帮助来了解并且修复安全漏洞。 -当遇到任何漏洞,所能提供的信息越多就越能诊断和修复。如果你不清楚什么 -是有帮助的信息,那就请重温一下admin-guide/reporting-bugs.rst文件中的概述过程。任 -何攻击性的代码都是非常有用的,未经报告者的同意不会被取消,除非它已经 -被公布于众。 - -2) 公开 - -Linux内核安全团队的宗旨就是和漏洞提交者一起处理漏洞的解决方案直 -到公开。我们喜欢尽快地完全公开漏洞。当一个漏洞或者修复还没有被完全地理 -解,解决方案没有通过测试或者供应商协调,可以合理地延迟公开。然而,我们 -期望这些延迟尽可能的短些,是可数的几天,而不是几个星期或者几个月。公开 -日期是通过安全团队和漏洞提供者以及供应商洽谈后的结果。公开时间表是从很 -短(特殊的,它已经被公众所知道)到几个星期。作为一个基本的默认政策,我 -们所期望通知公众的日期是7天的安排。 - -3) 保密协议 - -Linux内核安全团队不是一个正式的团体,因此不能加入任何的保密协议。 diff --git a/Documentation/usb/gadget_configfs.rst b/Documentation/usb/gadget_configfs.rst index 158e48dab586..e4566ffb223f 100644 --- a/Documentation/usb/gadget_configfs.rst +++ b/Documentation/usb/gadget_configfs.rst @@ -140,7 +140,7 @@ is an arbitrary string allowed in a filesystem, e.g.:: Each function provides its specific set of attributes, with either read-only or read-write access. Where applicable they need to be written to as appropriate. -Please refer to Documentation/ABI/*/configfs-usb-gadget* for more information. +Please refer to Documentation/ABI/testing/configfs-usb-gadget for more information. 4. Associating the functions with their configurations ------------------------------------------------------ diff --git a/Documentation/usb/mtouchusb.rst b/Documentation/usb/mtouchusb.rst index d1111b74bf75..5ae1f74fe74b 100644 --- a/Documentation/usb/mtouchusb.rst +++ b/Documentation/usb/mtouchusb.rst @@ -1,4 +1,4 @@ -================ +================ mtouchusb driver ================ diff --git a/Documentation/usb/usb-serial.rst b/Documentation/usb/usb-serial.rst index 8fa7dbd3da9a..69586aeb60bb 100644 --- a/Documentation/usb/usb-serial.rst +++ b/Documentation/usb/usb-serial.rst @@ -1,4 +1,4 @@ -========== +========== USB serial ========== diff --git a/Documentation/virt/kvm/amd-memory-encryption.rst b/Documentation/virt/kvm/amd-memory-encryption.rst index 5ec8a1902e15..5c081c8c7164 100644 --- a/Documentation/virt/kvm/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/amd-memory-encryption.rst @@ -22,7 +22,7 @@ to SEV:: [ecx]: Bits[31:0] Number of encrypted guests supported simultaneously -If support for SEV is present, MSR 0xc001_0010 (MSR_K8_SYSCFG) and MSR 0xc001_0015 +If support for SEV is present, MSR 0xc001_0010 (MSR_AMD64_SYSCFG) and MSR 0xc001_0015 (MSR_K7_HWCR) can be used to determine if it can be enabled:: 0xc001_0010: diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 22d077562149..3b6e3b1628b4 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -688,9 +688,14 @@ MSRs that have been set successfully. Defines the vcpu responses to the cpuid instruction. Applications should use the KVM_SET_CPUID2 ioctl if available. -Note, when this IOCTL fails, KVM gives no guarantees that previous valid CPUID -configuration (if there is) is not corrupted. Userspace can get a copy of the -resulting CPUID configuration through KVM_GET_CPUID2 in case. +Caveat emptor: + - If this IOCTL fails, KVM gives no guarantees that previous valid CPUID + configuration (if there is) is not corrupted. Userspace can get a copy + of the resulting CPUID configuration through KVM_GET_CPUID2 in case. + - Using KVM_SET_CPUID{,2} after KVM_RUN, i.e. changing the guest vCPU model + after running the guest, may cause guest instability. + - Using heterogeneous CPUID configurations, modulo APIC IDs, topology, etc... + may cause guest instability. :: @@ -4803,7 +4808,7 @@ KVM_PV_VM_VERIFY 4.126 KVM_X86_SET_MSR_FILTER ---------------------------- -:Capability: KVM_X86_SET_MSR_FILTER +:Capability: KVM_CAP_X86_MSR_FILTER :Architectures: x86 :Type: vm ioctl :Parameters: struct kvm_msr_filter @@ -5034,6 +5039,224 @@ see KVM_XEN_VCPU_SET_ATTR above. The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used with the KVM_XEN_VCPU_GET_ATTR ioctl. + +4.131 KVM_GET_SREGS2 +------------------ + +:Capability: KVM_CAP_SREGS2 +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_sregs2 (out) +:Returns: 0 on success, -1 on error + +Reads special registers from the vcpu. +This ioctl (when supported) replaces the KVM_GET_SREGS. + +:: + +struct kvm_sregs2 { + /* out (KVM_GET_SREGS2) / in (KVM_SET_SREGS2) */ + struct kvm_segment cs, ds, es, fs, gs, ss; + struct kvm_segment tr, ldt; + struct kvm_dtable gdt, idt; + __u64 cr0, cr2, cr3, cr4, cr8; + __u64 efer; + __u64 apic_base; + __u64 flags; + __u64 pdptrs[4]; +}; + +flags values for ``kvm_sregs2``: + +``KVM_SREGS2_FLAGS_PDPTRS_VALID`` + + Indicates thats the struct contain valid PDPTR values. + + +4.132 KVM_SET_SREGS2 +------------------ + +:Capability: KVM_CAP_SREGS2 +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_sregs2 (in) +:Returns: 0 on success, -1 on error + +Writes special registers into the vcpu. +See KVM_GET_SREGS2 for the data structures. +This ioctl (when supported) replaces the KVM_SET_SREGS. + +4.133 KVM_GET_STATS_FD +---------------------- + +:Capability: KVM_CAP_STATS_BINARY_FD +:Architectures: all +:Type: vm ioctl, vcpu ioctl +:Parameters: none +:Returns: statistics file descriptor on success, < 0 on error + +Errors: + + ====== ====================================================== + ENOMEM if the fd could not be created due to lack of memory + EMFILE if the number of opened files exceeds the limit + ====== ====================================================== + +The returned file descriptor can be used to read VM/vCPU statistics data in +binary format. The data in the file descriptor consists of four blocks +organized as follows: + ++-------------+ +| Header | ++-------------+ +| id string | ++-------------+ +| Descriptors | ++-------------+ +| Stats Data | ++-------------+ + +Apart from the header starting at offset 0, please be aware that it is +not guaranteed that the four blocks are adjacent or in the above order; +the offsets of the id, descriptors and data blocks are found in the +header. However, all four blocks are aligned to 64 bit offsets in the +file and they do not overlap. + +All blocks except the data block are immutable. Userspace can read them +only one time after retrieving the file descriptor, and then use ``pread`` or +``lseek`` to read the statistics repeatedly. + +All data is in system endianness. + +The format of the header is as follows:: + + struct kvm_stats_header { + __u32 flags; + __u32 name_size; + __u32 num_desc; + __u32 id_offset; + __u32 desc_offset; + __u32 data_offset; + }; + +The ``flags`` field is not used at the moment. It is always read as 0. + +The ``name_size`` field is the size (in byte) of the statistics name string +(including trailing '\0') which is contained in the "id string" block and +appended at the end of every descriptor. + +The ``num_desc`` field is the number of descriptors that are included in the +descriptor block. (The actual number of values in the data block may be +larger, since each descriptor may comprise more than one value). + +The ``id_offset`` field is the offset of the id string from the start of the +file indicated by the file descriptor. It is a multiple of 8. + +The ``desc_offset`` field is the offset of the Descriptors block from the start +of the file indicated by the file descriptor. It is a multiple of 8. + +The ``data_offset`` field is the offset of the Stats Data block from the start +of the file indicated by the file descriptor. It is a multiple of 8. + +The id string block contains a string which identifies the file descriptor on +which KVM_GET_STATS_FD was invoked. The size of the block, including the +trailing ``'\0'``, is indicated by the ``name_size`` field in the header. + +The descriptors block is only needed to be read once for the lifetime of the +file descriptor contains a sequence of ``struct kvm_stats_desc``, each followed +by a string of size ``name_size``. + + #define KVM_STATS_TYPE_SHIFT 0 + #define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT) + #define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) + #define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) + #define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT) + + #define KVM_STATS_UNIT_SHIFT 4 + #define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) + #define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT) + #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) + #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) + #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) + + #define KVM_STATS_BASE_SHIFT 8 + #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) + #define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT) + #define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT) + + struct kvm_stats_desc { + __u32 flags; + __s16 exponent; + __u16 size; + __u32 offset; + __u32 unused; + char name[]; + }; + +The ``flags`` field contains the type and unit of the statistics data described +by this descriptor. Its endianness is CPU native. +The following flags are supported: + +Bits 0-3 of ``flags`` encode the type: + * ``KVM_STATS_TYPE_CUMULATIVE`` + The statistics data is cumulative. The value of data can only be increased. + Most of the counters used in KVM are of this type. + The corresponding ``size`` field for this type is always 1. + All cumulative statistics data are read/write. + * ``KVM_STATS_TYPE_INSTANT`` + The statistics data is instantaneous. Its value can be increased or + decreased. This type is usually used as a measurement of some resources, + like the number of dirty pages, the number of large pages, etc. + All instant statistics are read only. + The corresponding ``size`` field for this type is always 1. + * ``KVM_STATS_TYPE_PEAK`` + The statistics data is peak. The value of data can only be increased, and + represents a peak value for a measurement, for example the maximum number + of items in a hash table bucket, the longest time waited and so on. + The corresponding ``size`` field for this type is always 1. + +Bits 4-7 of ``flags`` encode the unit: + * ``KVM_STATS_UNIT_NONE`` + There is no unit for the value of statistics data. This usually means that + the value is a simple counter of an event. + * ``KVM_STATS_UNIT_BYTES`` + It indicates that the statistics data is used to measure memory size, in the + unit of Byte, KiByte, MiByte, GiByte, etc. The unit of the data is + determined by the ``exponent`` field in the descriptor. + * ``KVM_STATS_UNIT_SECONDS`` + It indicates that the statistics data is used to measure time or latency. + * ``KVM_STATS_UNIT_CYCLES`` + It indicates that the statistics data is used to measure CPU clock cycles. + +Bits 8-11 of ``flags``, together with ``exponent``, encode the scale of the +unit: + * ``KVM_STATS_BASE_POW10`` + The scale is based on power of 10. It is used for measurement of time and + CPU clock cycles. For example, an exponent of -9 can be used with + ``KVM_STATS_UNIT_SECONDS`` to express that the unit is nanoseconds. + * ``KVM_STATS_BASE_POW2`` + The scale is based on power of 2. It is used for measurement of memory size. + For example, an exponent of 20 can be used with ``KVM_STATS_UNIT_BYTES`` to + express that the unit is MiB. + +The ``size`` field is the number of values of this statistics data. Its +value is usually 1 for most of simple statistics. 1 means it contains an +unsigned 64bit data. + +The ``offset`` field is the offset from the start of Data Block to the start of +the corresponding statistics data. + +The ``unused`` field is reserved for future support for other types of +statistics data, like log/linear histogram. Its value is always 0 for the types +defined above. + +The ``name`` field is the name string of the statistics data. The name string +starts at the end of ``struct kvm_stats_desc``. The maximum length including +the trailing ``'\0'``, is indicated by ``name_size`` in the header. + +The Stats Data block contains an array of 64-bit values in the same order +as the descriptors in Descriptors block. + 5. The kvm_run structure ======================== @@ -6323,6 +6546,7 @@ KVM_RUN_BUS_LOCK flag is used to distinguish between them. This capability can be used to check / enable 2nd DAWR feature provided by POWER10 processor. + 7.24 KVM_CAP_VM_COPY_ENC_CONTEXT_FROM ------------------------------------- @@ -6362,6 +6586,43 @@ default. See Documentation/x86/sgx/2.Kernel-internals.rst for more details. +7.26 KVM_CAP_PPC_RPT_INVALIDATE +------------------------------- + +:Capability: KVM_CAP_PPC_RPT_INVALIDATE +:Architectures: ppc +:Type: vm + +This capability indicates that the kernel is capable of handling +H_RPT_INVALIDATE hcall. + +In order to enable the use of H_RPT_INVALIDATE in the guest, +user space might have to advertise it for the guest. For example, +IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is +present in the "ibm,hypertas-functions" device-tree property. + +This capability is enabled for hypervisors on platforms like POWER9 +that support radix MMU. + +7.27 KVM_CAP_EXIT_ON_EMULATION_FAILURE +-------------------------------------- + +:Architectures: x86 +:Parameters: args[0] whether the feature should be enabled or not + +When this capability is enabled, an emulation failure will result in an exit +to userspace with KVM_INTERNAL_ERROR (except when the emulator was invoked +to handle a VMware backdoor instruction). Furthermore, KVM will now provide up +to 15 instruction bytes for any exit to userspace resulting from an emulation +failure. When these exits to userspace occur use the emulation_failure struct +instead of the internal struct. They both have the same layout, but the +emulation_failure struct matches the content better. It also explicitly +defines the 'flags' field which is used to describe the fields in the struct +that are valid (ie: if KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES is +set in the 'flags' field then both 'insn_size' and 'insn_bytes' have valid data +in them.) + + 8. Other capabilities. ====================== @@ -6715,7 +6976,7 @@ accesses that would usually trigger a #GP by KVM into the guest will instead get bounced to user space through the KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications. -8.27 KVM_X86_SET_MSR_FILTER +8.27 KVM_CAP_X86_MSR_FILTER --------------------------- :Architectures: x86 @@ -6891,3 +7152,33 @@ This capability is always enabled. This capability indicates that the KVM virtual PTP service is supported in the host. A VMM can check whether the service is available to the guest on migration. + +8.33 KVM_CAP_HYPERV_ENFORCE_CPUID +----------------------------- + +Architectures: x86 + +When enabled, KVM will disable emulated Hyper-V features provided to the +guest according to the bits Hyper-V CPUID feature leaves. Otherwise, all +currently implmented Hyper-V features are provided unconditionally when +Hyper-V identification is set in the HYPERV_CPUID_INTERFACE (0x40000001) +leaf. + +8.34 KVM_CAP_EXIT_HYPERCALL +--------------------------- + +:Capability: KVM_CAP_EXIT_HYPERCALL +:Architectures: x86 +:Type: vm + +This capability, if enabled, will cause KVM to exit to userspace +with KVM_EXIT_HYPERCALL exit reason to process some hypercalls. + +Calling KVM_CHECK_EXTENSION for this capability will return a bitmask +of hypercalls that can be configured to exit to userspace. +Right now, the only such hypercall is KVM_HC_MAP_GPA_RANGE. + +The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset +of the result of KVM_CHECK_EXTENSION. KVM will forward to userspace +the hypercalls whose corresponding bit is in the argument, and return +ENOSYS for the others. diff --git a/Documentation/virt/kvm/cpuid.rst b/Documentation/virt/kvm/cpuid.rst index cf62162d4be2..bda3e3e737d7 100644 --- a/Documentation/virt/kvm/cpuid.rst +++ b/Documentation/virt/kvm/cpuid.rst @@ -96,6 +96,13 @@ KVM_FEATURE_MSI_EXT_DEST_ID 15 guest checks this feature bit before using extended destination ID bits in MSI address bits 11-5. +KVM_FEATURE_HC_MAP_GPA_RANGE 16 guest checks this feature bit before + using the map gpa range hypercall + to notify the page state change + +KVM_FEATURE_MIGRATION_CONTROL 17 guest checks this feature bit before + using MSR_KVM_MIGRATION_CONTROL + KVM_FEATURE_CLOCKSOURCE_STABLE_BIT 24 host will warn if no guest-side per-cpu warps are expected in kvmclock diff --git a/Documentation/virt/kvm/hypercalls.rst b/Documentation/virt/kvm/hypercalls.rst index ed4fddd364ea..e56fa8b9cfca 100644 --- a/Documentation/virt/kvm/hypercalls.rst +++ b/Documentation/virt/kvm/hypercalls.rst @@ -169,3 +169,24 @@ a0: destination APIC ID :Usage example: When sending a call-function IPI-many to vCPUs, yield if any of the IPI target vCPUs was preempted. + +8. KVM_HC_MAP_GPA_RANGE +------------------------- +:Architecture: x86 +:Status: active +:Purpose: Request KVM to map a GPA range with the specified attributes. + +a0: the guest physical address of the start page +a1: the number of (4kb) pages (must be contiguous in GPA space) +a2: attributes + + Where 'attributes' : + * bits 3:0 - preferred page size encoding 0 = 4kb, 1 = 2mb, 2 = 1gb, etc... + * bit 4 - plaintext = 0, encrypted = 1 + * bits 63:5 - reserved (must be zero) + +**Implementation note**: this hypercall is implemented in userspace via +the KVM_CAP_EXIT_HYPERCALL capability. Userspace must enable that capability +before advertising KVM_FEATURE_HC_MAP_GPA_RANGE in the guest CPUID. In +addition, if the guest supports KVM_FEATURE_MIGRATION_CONTROL, userspace +must also set up an MSR filter to process writes to MSR_KVM_MIGRATION_CONTROL. diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 1fc860c007a3..35eca377543d 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -16,6 +16,11 @@ The acquisition orders for mutexes are as follows: - kvm->slots_lock is taken outside kvm->irq_lock, though acquiring them together is quite rare. +- Unlike kvm->slots_lock, kvm->slots_arch_lock is released before + synchronize_srcu(&kvm->srcu). Therefore kvm->slots_arch_lock + can be taken inside a kvm->srcu read-side critical section, + while kvm->slots_lock cannot. + On x86: - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock diff --git a/Documentation/virt/kvm/mmu.rst b/Documentation/virt/kvm/mmu.rst index 5bfe28b0728e..f60f5488e121 100644 --- a/Documentation/virt/kvm/mmu.rst +++ b/Documentation/virt/kvm/mmu.rst @@ -171,8 +171,8 @@ Shadow pages contain the following information: shadow pages) so role.quadrant takes values in the range 0..3. Each quadrant maps 1GB virtual address space. role.access: - Inherited guest access permissions in the form uwx. Note execute - permission is positive, not negative. + Inherited guest access permissions from the parent ptes in the form uwx. + Note execute permission is positive, not negative. role.invalid: The page is invalid and should not be used. It is a root page that is currently pinned (by a cpu hardware register pointing to it); once it is @@ -180,8 +180,8 @@ Shadow pages contain the following information: role.gpte_is_8_bytes: Reflects the size of the guest PTE for which the page is valid, i.e. '1' if 64-bit gptes are in use, '0' if 32-bit gptes are in use. - role.nxe: - Contains the value of efer.nxe for which the page is valid. + role.efer_nx: + Contains the value of efer.nx for which the page is valid. role.cr0_wp: Contains the value of cr0.wp for which the page is valid. role.smep_andnot_wp: @@ -192,9 +192,6 @@ Shadow pages contain the following information: Contains the value of cr4.smap && !cr0.wp for which the page is valid (pages for which this is true are different from other pages; see the treatment of cr0.wp=0 below). - role.ept_sp: - This is a virtual flag to denote a shadowed nested EPT page. ept_sp - is true if "cr0_wp && smap_andnot_wp", an otherwise invalid combination. role.smm: Is 1 if the page is valid in system management mode. This field determines which of the kvm_memslots array was used to build this diff --git a/Documentation/virt/kvm/msr.rst b/Documentation/virt/kvm/msr.rst index e37a14c323d2..9315fc385fb0 100644 --- a/Documentation/virt/kvm/msr.rst +++ b/Documentation/virt/kvm/msr.rst @@ -376,3 +376,16 @@ data: write '1' to bit 0 of the MSR, this causes the host to re-scan its queue and check if there are more notifications pending. The MSR is available if KVM_FEATURE_ASYNC_PF_INT is present in CPUID. + +MSR_KVM_MIGRATION_CONTROL: + 0x4b564d08 + +data: + This MSR is available if KVM_FEATURE_MIGRATION_CONTROL is present in + CPUID. Bit 0 represents whether live migration of the guest is allowed. + + When a guest is started, bit 0 will be 0 if the guest has encrypted + memory and 1 if the guest does not have encrypted memory. If the + guest is communicating page encryption status to the host using the + ``KVM_HC_MAP_GPA_RANGE`` hypercall, it can set bit 0 in this MSR to + allow live migration of the guest. diff --git a/Documentation/virt/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst index 5feb3706a7ae..af1b37441e0a 100644 --- a/Documentation/virt/kvm/vcpu-requests.rst +++ b/Documentation/virt/kvm/vcpu-requests.rst @@ -118,10 +118,12 @@ KVM_REQ_MMU_RELOAD necessary to inform each VCPU to completely refresh the tables. This request is used for that. -KVM_REQ_PENDING_TIMER +KVM_REQ_UNBLOCK - This request may be made from a timer handler run on the host on behalf - of a VCPU. It informs the VCPU thread to inject a timer interrupt. + This request informs the vCPU to exit kvm_vcpu_block. It is used for + example from timer handlers that run on the host on behalf of a vCPU, + or in order to update the interrupt routing and ensure that assigned + devices will wake up the vCPU. KVM_REQ_UNHALT diff --git a/Documentation/x86/amd-memory-encryption.rst b/Documentation/x86/amd-memory-encryption.rst index c48d452d0718..a1940ebe7be5 100644 --- a/Documentation/x86/amd-memory-encryption.rst +++ b/Documentation/x86/amd-memory-encryption.rst @@ -53,7 +53,7 @@ CPUID function 0x8000001f reports information related to SME:: system physical addresses, not guest physical addresses) -If support for SME is present, MSR 0xc00100010 (MSR_K8_SYSCFG) can be used to +If support for SME is present, MSR 0xc00100010 (MSR_AMD64_SYSCFG) can be used to determine if SME is enabled and/or to enable memory encryption:: 0xc0010010: @@ -79,7 +79,7 @@ The state of SME in the Linux kernel can be documented as follows: The CPU supports SME (determined through CPUID instruction). - Enabled: - Supported and bit 23 of MSR_K8_SYSCFG is set. + Supported and bit 23 of MSR_AMD64_SYSCFG is set. - Active: Supported, Enabled and the Linux kernel is actively applying @@ -89,7 +89,7 @@ The state of SME in the Linux kernel can be documented as follows: SME can also be enabled and activated in the BIOS. If SME is enabled and activated in the BIOS, then all memory accesses will be encrypted and it will not be necessary to activate the Linux memory encryption support. If the BIOS -merely enables SME (sets bit 23 of the MSR_K8_SYSCFG), then Linux can activate +merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG), then Linux can activate memory encryption by default (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) or by supplying mem_encrypt=on on the kernel command line. However, if BIOS does not enable SME, then Linux will not be able to activate memory encryption, even diff --git a/MAINTAINERS b/MAINTAINERS index bd7aff0c120f..008fcad7ac00 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1578,7 +1578,7 @@ F: drivers/clk/sunxi/ ARM/Allwinner sunXi SoC support M: Maxime Ripard <mripard@kernel.org> M: Chen-Yu Tsai <wens@csie.org> -R: Jernej Skrabec <jernej.skrabec@siol.net> +R: Jernej Skrabec <jernej.skrabec@gmail.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git @@ -5089,7 +5089,7 @@ S: Maintained F: drivers/net/fddi/defza.* DEINTERLACE DRIVERS FOR ALLWINNER H3 -M: Jernej Skrabec <jernej.skrabec@siol.net> +M: Jernej Skrabec <jernej.skrabec@gmail.com> L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media_tree.git @@ -5237,7 +5237,7 @@ DEVICE DIRECT ACCESS (DAX) M: Dan Williams <dan.j.williams@intel.com> M: Vishal Verma <vishal.l.verma@intel.com> M: Dave Jiang <dave.jiang@intel.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported F: drivers/dax/ @@ -5632,14 +5632,14 @@ F: include/linux/power/smartreflex.h DRM DRIVER FOR ALLWINNER DE2 AND DE3 ENGINE M: Maxime Ripard <mripard@kernel.org> M: Chen-Yu Tsai <wens@csie.org> -R: Jernej Skrabec <jernej.skrabec@siol.net> +R: Jernej Skrabec <jernej.skrabec@gmail.com> L: dri-devel@lists.freedesktop.org S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/sun4i/sun8i* DRM DRIVER FOR ARM PL111 CLCD -M: Eric Anholt <eric@anholt.net> +M: Emma Anholt <emma@anholt.net> S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/pl111/ @@ -5719,7 +5719,7 @@ T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/tiny/gm12u320.c DRM DRIVER FOR HX8357D PANELS -M: Eric Anholt <eric@anholt.net> +M: Emma Anholt <emma@anholt.net> S: Maintained T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/himax,hx8357d.txt @@ -6023,7 +6023,7 @@ M: Neil Armstrong <narmstrong@baylibre.com> M: Robert Foss <robert.foss@linaro.org> R: Laurent Pinchart <Laurent.pinchart@ideasonboard.com> R: Jonas Karlman <jonas@kwiboo.se> -R: Jernej Skrabec <jernej.skrabec@siol.net> +R: Jernej Skrabec <jernej.skrabec@gmail.com> S: Maintained T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/bridge/ @@ -6177,7 +6177,7 @@ F: Documentation/devicetree/bindings/display/ti/ F: drivers/gpu/drm/omapdrm/ DRM DRIVERS FOR V3D -M: Eric Anholt <eric@anholt.net> +M: Emma Anholt <emma@anholt.net> S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/gpu/brcm,bcm-v3d.yaml @@ -6185,7 +6185,7 @@ F: drivers/gpu/drm/v3d/ F: include/uapi/drm/v3d_drm.h DRM DRIVERS FOR VC4 -M: Eric Anholt <eric@anholt.net> +M: Emma Anholt <emma@anholt.net> M: Maxime Ripard <mripard@kernel.org> S: Supported T: git git://github.com/anholt/linux @@ -7006,7 +7006,7 @@ M: Dan Williams <dan.j.williams@intel.com> R: Matthew Wilcox <willy@infradead.org> R: Jan Kara <jack@suse.cz> L: linux-fsdevel@vger.kernel.org -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported F: fs/dax.c F: include/linux/dax.h @@ -10378,7 +10378,7 @@ LIBNVDIMM BLK: MMIO-APERTURE DRIVER M: Dan Williams <dan.j.williams@intel.com> M: Vishal Verma <vishal.l.verma@intel.com> M: Dave Jiang <dave.jiang@intel.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ P: Documentation/nvdimm/maintainer-entry-profile.rst @@ -10389,7 +10389,7 @@ LIBNVDIMM BTT: BLOCK TRANSLATION TABLE M: Vishal Verma <vishal.l.verma@intel.com> M: Dan Williams <dan.j.williams@intel.com> M: Dave Jiang <dave.jiang@intel.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ P: Documentation/nvdimm/maintainer-entry-profile.rst @@ -10399,7 +10399,7 @@ LIBNVDIMM PMEM: PERSISTENT MEMORY DRIVER M: Dan Williams <dan.j.williams@intel.com> M: Vishal Verma <vishal.l.verma@intel.com> M: Dave Jiang <dave.jiang@intel.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ P: Documentation/nvdimm/maintainer-entry-profile.rst @@ -10407,7 +10407,7 @@ F: drivers/nvdimm/pmem* LIBNVDIMM: DEVICETREE BINDINGS M: Oliver O'Halloran <oohall@gmail.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ F: Documentation/devicetree/bindings/pmem/pmem-region.txt @@ -10418,7 +10418,7 @@ M: Dan Williams <dan.j.williams@intel.com> M: Vishal Verma <vishal.l.verma@intel.com> M: Dave Jiang <dave.jiang@intel.com> M: Ira Weiny <ira.weiny@intel.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ P: Documentation/nvdimm/maintainer-entry-profile.rst @@ -15815,7 +15815,7 @@ F: include/uapi/linux/rose.h F: net/rose/ ROTATION DRIVER FOR ALLWINNER A83T -M: Jernej Skrabec <jernej.skrabec@siol.net> +M: Jernej Skrabec <jernej.skrabec@gmail.com> L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media_tree.git @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Frozen Wasteland # *DOCUMENTATION* diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 4392c9c189c4..e47adc97a89b 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -31,7 +31,7 @@ endif ifdef CONFIG_ARC_CURR_IN_REG -# For a global register defintion, make sure it gets passed to every file +# For a global register definition, make sure it gets passed to every file # We had a customer reported bug where some code built in kernel was NOT using # any kernel headers, and missing the r25 global register # Can't do unconditionally because of recursive include issues diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h index 9b87e162e539..dfeffa25499b 100644 --- a/arch/arc/include/asm/cmpxchg.h +++ b/arch/arc/include/asm/cmpxchg.h @@ -116,7 +116,7 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr, * * Technically the lock is also needed for UP (boils down to irq save/restore) * but we can cheat a bit since cmpxchg() atomic_ops_lock() would cause irqs to - * be disabled thus can't possibly be interrpted/preempted/clobbered by xchg() + * be disabled thus can't possibly be interrupted/preempted/clobbered by xchg() * Other way around, xchg is one instruction anyways, so can't be interrupted * as such */ @@ -143,7 +143,7 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr, /* * "atomic" variant of xchg() * REQ: It needs to follow the same serialization rules as other atomic_xxx() - * Since xchg() doesn't always do that, it would seem that following defintion + * Since xchg() doesn't always do that, it would seem that following definition * is incorrect. But here's the rationale: * SMP : Even xchg() takes the atomic_ops_lock, so OK. * LLSC: atomic_ops_lock are not relevant at all (even if SMP, since LLSC diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index ad9b7fe4dba3..4a9d33372fe2 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -7,6 +7,18 @@ #include <uapi/asm/page.h> +#ifdef CONFIG_ARC_HAS_PAE40 + +#define MAX_POSSIBLE_PHYSMEM_BITS 40 +#define PAGE_MASK_PHYS (0xff00000000ull | PAGE_MASK) + +#else /* CONFIG_ARC_HAS_PAE40 */ + +#define MAX_POSSIBLE_PHYSMEM_BITS 32 +#define PAGE_MASK_PHYS PAGE_MASK + +#endif /* CONFIG_ARC_HAS_PAE40 */ + #ifndef __ASSEMBLY__ #define clear_page(paddr) memset((paddr), 0, PAGE_SIZE) diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 163641726a2b..5878846f00cf 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -107,8 +107,8 @@ #define ___DEF (_PAGE_PRESENT | _PAGE_CACHEABLE) /* Set of bits not changed in pte_modify */ -#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL) - +#define _PAGE_CHG_MASK (PAGE_MASK_PHYS | _PAGE_ACCESSED | _PAGE_DIRTY | \ + _PAGE_SPECIAL) /* More Abbrevaited helpers */ #define PAGE_U_NONE __pgprot(___DEF) #define PAGE_U_R __pgprot(___DEF | _PAGE_READ) @@ -132,13 +132,7 @@ #define PTE_BITS_IN_PD0 (_PAGE_GLOBAL | _PAGE_PRESENT | _PAGE_HW_SZ) #define PTE_BITS_RWX (_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ) -#ifdef CONFIG_ARC_HAS_PAE40 -#define PTE_BITS_NON_RWX_IN_PD1 (0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE) -#define MAX_POSSIBLE_PHYSMEM_BITS 40 -#else -#define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE) -#define MAX_POSSIBLE_PHYSMEM_BITS 32 -#endif +#define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK_PHYS | _PAGE_CACHEABLE) /************************************************************************** * Mapping of vm_flags (Generic VM) to PTE flags (arch specific) diff --git a/arch/arc/include/uapi/asm/page.h b/arch/arc/include/uapi/asm/page.h index 2a97e2718a21..2a4ad619abfb 100644 --- a/arch/arc/include/uapi/asm/page.h +++ b/arch/arc/include/uapi/asm/page.h @@ -33,5 +33,4 @@ #define PAGE_MASK (~(PAGE_SIZE-1)) - #endif /* _UAPI__ASM_ARC_PAGE_H */ diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 1743506081da..2cb8dfe866b6 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -177,7 +177,7 @@ tracesys: ; Do the Sys Call as we normally would. ; Validate the Sys Call number - cmp r8, NR_syscalls + cmp r8, NR_syscalls - 1 mov.hi r0, -ENOSYS bhi tracesys_exit @@ -255,7 +255,7 @@ ENTRY(EV_Trap) ;============ Normal syscall case ; syscall num shd not exceed the total system calls avail - cmp r8, NR_syscalls + cmp r8, NR_syscalls - 1 mov.hi r0, -ENOSYS bhi .Lret_from_system_call diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c index ecfbc42d3a40..345a0000554c 100644 --- a/arch/arc/kernel/kgdb.c +++ b/arch/arc/kernel/kgdb.c @@ -140,6 +140,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, ptr = &remcomInBuffer[1]; if (kgdb_hex2long(&ptr, &addr)) regs->ret = addr; + fallthrough; case 'D': case 'k': diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index d838d0d57696..3793876f42d9 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -50,14 +50,14 @@ SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new) int ret; /* - * This is only for old cores lacking LLOCK/SCOND, which by defintion + * This is only for old cores lacking LLOCK/SCOND, which by definition * can't possibly be SMP. Thus doesn't need to be SMP safe. * And this also helps reduce the overhead for serializing in * the UP case */ WARN_ON_ONCE(IS_ENABLED(CONFIG_SMP)); - /* Z indicates to userspace if operation succeded */ + /* Z indicates to userspace if operation succeeded */ regs->status32 &= ~STATUS_Z_MASK; ret = access_ok(uaddr, sizeof(*uaddr)); @@ -107,7 +107,7 @@ fail: void arch_cpu_idle(void) { - /* Re-enable interrupts <= default irq priority before commiting SLEEP */ + /* Re-enable interrupts <= default irq priority before committing SLEEP */ const unsigned int arg = 0x10 | ARCV2_IRQ_DEF_PRIO; __asm__ __volatile__( @@ -120,7 +120,7 @@ void arch_cpu_idle(void) void arch_cpu_idle(void) { - /* sleep, but enable both set E1/E2 (levels of interrutps) before committing */ + /* sleep, but enable both set E1/E2 (levels of interrupts) before committing */ __asm__ __volatile__("sleep 0x3 \n"); } diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index fdbe06c98895..b3ccb9e5ffe4 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -259,7 +259,7 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) regs->r2 = (unsigned long)&sf->uc; /* - * small optim to avoid unconditonally calling do_sigaltstack + * small optim to avoid unconditionally calling do_sigaltstack * in sigreturn path, now that we only have rt_sigreturn */ magic = MAGIC_SIGALTSTK; @@ -391,7 +391,7 @@ void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs) { /* - * ASM glue gaurantees that this is only called when returning to + * ASM glue guarantees that this is only called when returning to * user mode */ if (test_thread_flag(TIF_NOTIFY_RESUME)) diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 33832e36bdb7..e2ed355438c9 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -157,7 +157,16 @@ void __init setup_arch_memory(void) min_high_pfn = PFN_DOWN(high_mem_start); max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz); - max_zone_pfn[ZONE_HIGHMEM] = min_low_pfn; + /* + * max_high_pfn should be ok here for both HIGHMEM and HIGHMEM+PAE. + * For HIGHMEM without PAE max_high_pfn should be less than + * min_low_pfn to guarantee that these two regions don't overlap. + * For PAE case highmem is greater than lowmem, so it is natural + * to use max_high_pfn. + * + * In both cases, holes should be handled by pfn_valid(). + */ + max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn; high_memory = (void *)(min_high_pfn << PAGE_SHIFT); diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c index fac4adc90204..95c649fbc95a 100644 --- a/arch/arc/mm/ioremap.c +++ b/arch/arc/mm/ioremap.c @@ -53,9 +53,10 @@ EXPORT_SYMBOL(ioremap); void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size, unsigned long flags) { + unsigned int off; unsigned long vaddr; struct vm_struct *area; - phys_addr_t off, end; + phys_addr_t end; pgprot_t prot = __pgprot(flags); /* Don't allow wraparound, zero size */ @@ -72,7 +73,7 @@ void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size, /* Mappings have to be page-aligned */ off = paddr & ~PAGE_MASK; - paddr &= PAGE_MASK; + paddr &= PAGE_MASK_PHYS; size = PAGE_ALIGN(end + 1) - paddr; /* diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index 9bb3c24f3677..9c7c68247289 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -576,7 +576,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, pte_t *ptep) { unsigned long vaddr = vaddr_unaligned & PAGE_MASK; - phys_addr_t paddr = pte_val(*ptep) & PAGE_MASK; + phys_addr_t paddr = pte_val(*ptep) & PAGE_MASK_PHYS; struct page *page = pfn_to_page(pte_pfn(*ptep)); create_tlb(vma, vaddr, ptep); diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index f8f07469d259..a7e54a087b80 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -135,24 +135,18 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) return; } -int xen_swiotlb_detect(void) -{ - if (!xen_domain()) - return 0; - if (xen_feature(XENFEAT_direct_mapped)) - return 1; - /* legacy case */ - if (!xen_feature(XENFEAT_not_direct_mapped) && xen_initial_domain()) - return 1; - return 0; -} - static int __init xen_mm_init(void) { struct gnttab_cache_flush cflush; + int rc; + if (!xen_swiotlb_detect()) return 0; - xen_swiotlb_init(); + + rc = xen_swiotlb_init(); + /* we can work with the default swiotlb */ + if (rc < 0 && rc != -EEXIST) + return rc; cflush.op = 0; cflush.a.dev_bus_addr = 0; diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 7ef44478560d..b52481f0605d 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -175,6 +175,9 @@ vdso_install: $(if $(CONFIG_COMPAT_VDSO), \ $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@) +archprepare: + $(Q)$(MAKE) $(build)=arch/arm64/tools kapi + # We use MRPROPER_FILES and CLEAN_FILES now archclean: $(Q)$(MAKE) $(clean)=$(boot) diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 07ac208edc89..26889dbfe904 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -5,3 +5,5 @@ generic-y += qrwlock.h generic-y += qspinlock.h generic-y += set_memory.h generic-y += user.h + +generated-y += cpucaps.h diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h deleted file mode 100644 index b0c5eda0498f..000000000000 --- a/arch/arm64/include/asm/cpucaps.h +++ /dev/null @@ -1,74 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm64/include/asm/cpucaps.h - * - * Copyright (C) 2016 ARM Ltd. - */ -#ifndef __ASM_CPUCAPS_H -#define __ASM_CPUCAPS_H - -#define ARM64_WORKAROUND_CLEAN_CACHE 0 -#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE 1 -#define ARM64_WORKAROUND_845719 2 -#define ARM64_HAS_SYSREG_GIC_CPUIF 3 -#define ARM64_HAS_PAN 4 -#define ARM64_HAS_LSE_ATOMICS 5 -#define ARM64_WORKAROUND_CAVIUM_23154 6 -#define ARM64_WORKAROUND_834220 7 -#define ARM64_HAS_NO_HW_PREFETCH 8 -#define ARM64_HAS_VIRT_HOST_EXTN 11 -#define ARM64_WORKAROUND_CAVIUM_27456 12 -#define ARM64_HAS_32BIT_EL0 13 -#define ARM64_SPECTRE_V3A 14 -#define ARM64_HAS_CNP 15 -#define ARM64_HAS_NO_FPSIMD 16 -#define ARM64_WORKAROUND_REPEAT_TLBI 17 -#define ARM64_WORKAROUND_QCOM_FALKOR_E1003 18 -#define ARM64_WORKAROUND_858921 19 -#define ARM64_WORKAROUND_CAVIUM_30115 20 -#define ARM64_HAS_DCPOP 21 -#define ARM64_SVE 22 -#define ARM64_UNMAP_KERNEL_AT_EL0 23 -#define ARM64_SPECTRE_V2 24 -#define ARM64_HAS_RAS_EXTN 25 -#define ARM64_WORKAROUND_843419 26 -#define ARM64_HAS_CACHE_IDC 27 -#define ARM64_HAS_CACHE_DIC 28 -#define ARM64_HW_DBM 29 -#define ARM64_SPECTRE_V4 30 -#define ARM64_MISMATCHED_CACHE_TYPE 31 -#define ARM64_HAS_STAGE2_FWB 32 -#define ARM64_HAS_CRC32 33 -#define ARM64_SSBS 34 -#define ARM64_WORKAROUND_1418040 35 -#define ARM64_HAS_SB 36 -#define ARM64_WORKAROUND_SPECULATIVE_AT 37 -#define ARM64_HAS_ADDRESS_AUTH_ARCH 38 -#define ARM64_HAS_ADDRESS_AUTH_IMP_DEF 39 -#define ARM64_HAS_GENERIC_AUTH_ARCH 40 -#define ARM64_HAS_GENERIC_AUTH_IMP_DEF 41 -#define ARM64_HAS_IRQ_PRIO_MASKING 42 -#define ARM64_HAS_DCPODP 43 -#define ARM64_WORKAROUND_1463225 44 -#define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM 45 -#define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM 46 -#define ARM64_WORKAROUND_1542419 47 -#define ARM64_HAS_E0PD 48 -#define ARM64_HAS_RNG 49 -#define ARM64_HAS_AMU_EXTN 50 -#define ARM64_HAS_ADDRESS_AUTH 51 -#define ARM64_HAS_GENERIC_AUTH 52 -#define ARM64_HAS_32BIT_EL1 53 -#define ARM64_BTI 54 -#define ARM64_HAS_ARMv8_4_TTL 55 -#define ARM64_HAS_TLB_RANGE 56 -#define ARM64_MTE 57 -#define ARM64_WORKAROUND_1508412 58 -#define ARM64_HAS_LDAPR 59 -#define ARM64_KVM_PROTECTED_MODE 60 -#define ARM64_WORKAROUND_NVIDIA_CARMEL_CNP 61 -#define ARM64_HAS_EPAN 62 - -#define ARM64_NCAPS 63 - -#endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index cf8df032b9c3..5e9b33cbac51 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -63,6 +63,7 @@ #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19 #define __KVM_HOST_SMCCC_FUNC___pkvm_mark_hyp 20 +#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 21 #ifndef __ASSEMBLY__ @@ -201,6 +202,8 @@ extern void __kvm_timer_set_cntvoff(u64 cntvoff); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); +extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu); + extern u64 __vgic_v3_get_gic_config(void); extern u64 __vgic_v3_read_vmcr(void); extern void __vgic_v3_write_vmcr(u32 vmcr); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index f612c090f2e4..01b9857757f2 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -463,4 +463,9 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) vcpu->arch.flags |= KVM_ARM64_INCREMENT_PC; } +static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature) +{ + return test_bit(feature, vcpu->arch.features); +} + #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7cd7d5c8c4bc..5a2c82f63baa 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -556,16 +556,11 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg) } struct kvm_vm_stat { - ulong remote_tlb_flush; + struct kvm_vm_stat_generic generic; }; struct kvm_vcpu_stat { - u64 halt_successful_poll; - u64 halt_attempted_poll; - u64 halt_poll_success_ns; - u64 halt_poll_fail_ns; - u64 halt_poll_invalid; - u64 halt_wakeup; + struct kvm_vcpu_stat_generic generic; u64 hvc_exit_stat; u64 wfe_exit_stat; u64 wfi_exit_stat; diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 589921392cb1..989bb5dad2c8 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM) += hyp/ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ - $(KVM)/vfio.o $(KVM)/irqchip.o \ + $(KVM)/vfio.o $(KVM)/irqchip.o $(KVM)/binary_stats.o \ arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o \ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 1cb39c0803a4..e720148232a0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -720,11 +720,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) return ret; } - if (run->immediate_exit) - return -EINTR; - vcpu_load(vcpu); + if (run->immediate_exit) { + ret = -EINTR; + goto out; + } + kvm_sigset_activate(vcpu); ret = 1; @@ -897,6 +899,18 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_sigset_deactivate(vcpu); +out: + /* + * In the unlikely event that we are returning to userspace + * with pending exceptions or PC adjustment, commit these + * adjustments in order to give userspace a consistent view of + * the vcpu state. Note that this relies on __kvm_adjust_pc() + * being preempt-safe on VHE. + */ + if (unlikely(vcpu->arch.flags & (KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_INCREMENT_PC))) + kvm_call_hyp(__kvm_adjust_pc, vcpu); + vcpu_put(vcpu); return ret; } diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 5cb4a1cd5603..1512a8007a78 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -28,20 +28,40 @@ #include "trace.h" -struct kvm_stats_debugfs_item debugfs_entries[] = { - VCPU_STAT("halt_successful_poll", halt_successful_poll), - VCPU_STAT("halt_attempted_poll", halt_attempted_poll), - VCPU_STAT("halt_poll_invalid", halt_poll_invalid), - VCPU_STAT("halt_wakeup", halt_wakeup), - VCPU_STAT("hvc_exit_stat", hvc_exit_stat), - VCPU_STAT("wfe_exit_stat", wfe_exit_stat), - VCPU_STAT("wfi_exit_stat", wfi_exit_stat), - VCPU_STAT("mmio_exit_user", mmio_exit_user), - VCPU_STAT("mmio_exit_kernel", mmio_exit_kernel), - VCPU_STAT("exits", exits), - VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), - VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), - { NULL } +const struct _kvm_stats_desc kvm_vm_stats_desc[] = { + KVM_GENERIC_VM_STATS() +}; +static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == + sizeof(struct kvm_vm_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vm_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vm_stats_desc), +}; + +const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { + KVM_GENERIC_VCPU_STATS(), + STATS_DESC_COUNTER(VCPU, hvc_exit_stat), + STATS_DESC_COUNTER(VCPU, wfe_exit_stat), + STATS_DESC_COUNTER(VCPU, wfi_exit_stat), + STATS_DESC_COUNTER(VCPU, mmio_exit_user), + STATS_DESC_COUNTER(VCPU, mmio_exit_kernel), + STATS_DESC_COUNTER(VCPU, exits) +}; +static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == + sizeof(struct kvm_vcpu_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vcpu_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vcpu_stats_desc), }; static bool core_reg_offset_is_vreg(u64 off) diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index 73629094f903..11541b94b328 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -296,7 +296,7 @@ static void enter_exception32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) *vcpu_pc(vcpu) = vect_offset; } -void kvm_inject_exception(struct kvm_vcpu *vcpu) +static void kvm_inject_exception(struct kvm_vcpu *vcpu) { if (vcpu_el1_is_32bit(vcpu)) { switch (vcpu->arch.flags & KVM_ARM64_EXCEPT_MASK) { @@ -329,3 +329,19 @@ void kvm_inject_exception(struct kvm_vcpu *vcpu) } } } + +/* + * Adjust the guest PC (and potentially exception state) depending on + * flags provided by the emulation code. + */ +void __kvm_adjust_pc(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) { + kvm_inject_exception(vcpu); + vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_EXCEPT_MASK); + } else if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) { + kvm_skip_instr(vcpu); + vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC; + } +} diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h index 61716359035d..4fdfeabefeb4 100644 --- a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h +++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h @@ -13,8 +13,6 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> -void kvm_inject_exception(struct kvm_vcpu *vcpu); - static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { @@ -44,22 +42,6 @@ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) } /* - * Adjust the guest PC on entry, depending on flags provided by EL1 - * for the purpose of emulation (MMIO, sysreg) or exception injection. - */ -static inline void __adjust_pc(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) { - kvm_inject_exception(vcpu); - vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION | - KVM_ARM64_EXCEPT_MASK); - } else if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) { - kvm_skip_instr(vcpu); - vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC; - } -} - -/* * Skip an instruction while host sysregs are live. * Assumes host is always 64-bit. */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index f36420a80474..1632f001f4ed 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -28,6 +28,13 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) cpu_reg(host_ctxt, 1) = __kvm_vcpu_run(kern_hyp_va(vcpu)); } +static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1); + + __kvm_adjust_pc(kern_hyp_va(vcpu)); +} + static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt) { __kvm_flush_vm_context(); @@ -170,6 +177,7 @@ typedef void (*hcall_t)(struct kvm_cpu_context *); static const hcall_t host_hcall[] = { HANDLE_FUNC(__kvm_vcpu_run), + HANDLE_FUNC(__kvm_adjust_pc), HANDLE_FUNC(__kvm_flush_vm_context), HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa), HANDLE_FUNC(__kvm_tlb_flush_vmid), diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index e342f7f4f4fb..4b60c0056c04 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -23,8 +23,8 @@ extern unsigned long hyp_nr_cpus; struct host_kvm host_kvm; -struct hyp_pool host_s2_mem; -struct hyp_pool host_s2_dev; +static struct hyp_pool host_s2_mem; +static struct hyp_pool host_s2_dev; /* * Copies of the host's CPU features registers holding sanitized values. diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 7488f53b0aa2..a3d3a275344e 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -17,7 +17,6 @@ #include <nvhe/trap_handler.h> struct hyp_pool hpool; -struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; unsigned long hyp_nr_cpus; #define hyp_percpu_size ((unsigned long)__per_cpu_end - \ @@ -27,6 +26,7 @@ static void *vmemmap_base; static void *hyp_pgt_base; static void *host_s2_mem_pgt_base; static void *host_s2_dev_pgt_base; +static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; static int divide_memory_pool(void *virt, unsigned long size) { diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index e9f6ea704d07..f7af9688c1f7 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -4,7 +4,6 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ -#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <hyp/sysreg-sr.h> @@ -201,7 +200,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) */ __debug_save_host_buffers_nvhe(vcpu); - __adjust_pc(vcpu); + __kvm_adjust_pc(vcpu); /* * We must restore the 32-bit state before the sysregs, thanks diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 7b8f7db5c1ed..b3229924d243 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -4,7 +4,6 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ -#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <linux/arm-smccc.h> @@ -132,7 +131,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) __load_guest_stage2(vcpu->arch.hw_mmu); __activate_traps(vcpu); - __adjust_pc(vcpu); + __kvm_adjust_pc(vcpu); sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index c5d1f3c87dbd..c10207fed2f3 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1156,13 +1156,13 @@ out_unlock: bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) - return 0; + return false; __unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); - return 0; + return false; } bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1170,7 +1170,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) kvm_pfn_t pfn = pte_pfn(range->pte); if (!kvm->arch.mmu.pgt) - return 0; + return false; WARN_ON(range->end - range->start != 1); @@ -1190,7 +1190,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) PAGE_SIZE, __pfn_to_phys(pfn), KVM_PGTABLE_PROT_R, NULL); - return 0; + return false; } bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1200,7 +1200,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) pte_t pte; if (!kvm->arch.mmu.pgt) - return 0; + return false; WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); @@ -1213,7 +1213,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) - return 0; + return false; return kvm_pgtable_stage2_is_young(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT); diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 956cdc240148..d37ebee085cf 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -166,6 +166,25 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) return 0; } +static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu *tmp; + bool is32bit; + int i; + + is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); + if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) + return false; + + /* Check that the vcpus are either all 32bit or all 64bit */ + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit) + return false; + } + + return true; +} + /** * kvm_reset_vcpu - sets core registers and sys_regs to reset value * @vcpu: The VCPU pointer @@ -217,13 +236,14 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) } } + if (!vcpu_allowed_register_width(vcpu)) { + ret = -EINVAL; + goto out; + } + switch (vcpu->arch.target) { default: if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { - if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) { - ret = -EINVAL; - goto out; - } pstate = VCPU_RESET_PSTATE_SVC; } else { pstate = VCPU_RESET_PSTATE_EL1; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 76ea2800c33e..1a7968ad078c 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -399,14 +399,14 @@ static bool trap_bvr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -414,7 +414,7 @@ static bool trap_bvr(struct kvm_vcpu *vcpu, static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -424,7 +424,7 @@ static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -434,21 +434,21 @@ static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = rd->val; } static bool trap_bcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -456,7 +456,7 @@ static bool trap_bcr(struct kvm_vcpu *vcpu, static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -467,7 +467,7 @@ static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -477,22 +477,22 @@ static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = rd->val; } static bool trap_wvr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]); + trace_trap_reg(__func__, rd->CRm, p->is_write, + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]); return true; } @@ -500,7 +500,7 @@ static bool trap_wvr(struct kvm_vcpu *vcpu, static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -510,7 +510,7 @@ static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -520,21 +520,21 @@ static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = rd->val; } static bool trap_wcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -542,7 +542,7 @@ static bool trap_wcr(struct kvm_vcpu *vcpu, static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -552,7 +552,7 @@ static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -562,7 +562,7 @@ static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = rd->val; } static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index ac485163a4a7..6d44c028d1c9 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -55,8 +55,10 @@ void __sync_icache_dcache(pte_t pte) { struct page *page = pte_page(pte); - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) + if (!test_bit(PG_dcache_clean, &page->flags)) { sync_icache_aliases(page_address(page), page_size(page)); + set_bit(PG_dcache_clean, &page->flags); + } } EXPORT_SYMBOL_GPL(__sync_icache_dcache); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 16a2b2b1c54d..e55409caaee3 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -43,6 +43,7 @@ #include <linux/sizes.h> #include <asm/tlb.h> #include <asm/alternative.h> +#include <asm/xen/swiotlb-xen.h> /* * We need to be able to catch inadvertent references to memstart_addr @@ -482,7 +483,7 @@ void __init mem_init(void) if (swiotlb_force == SWIOTLB_FORCE || max_pfn > PFN_DOWN(arm64_dma_phys_limit)) swiotlb_init(1); - else + else if (!xen_swiotlb_detect()) swiotlb_force = SWIOTLB_NO_FORCE; set_max_mapnr(max_pfn - PHYS_PFN_OFFSET); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 0a48191534ff..97d7bcd8d4f2 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -447,6 +447,18 @@ SYM_FUNC_START(__cpu_setup) mov x10, #(SYS_GCR_EL1_RRND | SYS_GCR_EL1_EXCL_MASK) msr_s SYS_GCR_EL1, x10 + /* + * If GCR_EL1.RRND=1 is implemented the same way as RRND=0, then + * RGSR_EL1.SEED must be non-zero for IRG to produce + * pseudorandom numbers. As RGSR_EL1 is UNKNOWN out of reset, we + * must initialize it. + */ + mrs x10, CNTVCT_EL0 + ands x10, x10, #SYS_RGSR_EL1_SEED_MASK + csinc x10, x10, xzr, ne + lsl x10, x10, #SYS_RGSR_EL1_SEED_SHIFT + msr_s SYS_RGSR_EL1, x10 + /* clear any pending tag check faults in TFSR*_EL1 */ msr_s SYS_TFSR_EL1, xzr msr_s SYS_TFSRE0_EL1, xzr diff --git a/arch/arm64/tools/Makefile b/arch/arm64/tools/Makefile new file mode 100644 index 000000000000..932b4fe5c768 --- /dev/null +++ b/arch/arm64/tools/Makefile @@ -0,0 +1,22 @@ +# SPDX-License-Identifier: GPL-2.0 + +gen := arch/$(ARCH)/include/generated +kapi := $(gen)/asm + +kapi-hdrs-y := $(kapi)/cpucaps.h + +targets += $(addprefix ../../../,$(gen-y) $(kapi-hdrs-y)) + +PHONY += kapi + +kapi: $(kapi-hdrs-y) $(gen-y) + +# Create output directory if not already present +_dummy := $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') + +quiet_cmd_gen_cpucaps = GEN $@ + cmd_gen_cpucaps = mkdir -p $(dir $@) && \ + $(AWK) -f $(filter-out $(PHONY),$^) > $@ + +$(kapi)/cpucaps.h: $(src)/gen-cpucaps.awk $(src)/cpucaps FORCE + $(call if_changed,gen_cpucaps) diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps new file mode 100644 index 000000000000..21fbdda7086e --- /dev/null +++ b/arch/arm64/tools/cpucaps @@ -0,0 +1,65 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Internal CPU capabilities constants, keep this list sorted + +BTI +HAS_32BIT_EL0 +HAS_32BIT_EL1 +HAS_ADDRESS_AUTH +HAS_ADDRESS_AUTH_ARCH +HAS_ADDRESS_AUTH_IMP_DEF +HAS_AMU_EXTN +HAS_ARMv8_4_TTL +HAS_CACHE_DIC +HAS_CACHE_IDC +HAS_CNP +HAS_CRC32 +HAS_DCPODP +HAS_DCPOP +HAS_E0PD +HAS_EPAN +HAS_GENERIC_AUTH +HAS_GENERIC_AUTH_ARCH +HAS_GENERIC_AUTH_IMP_DEF +HAS_IRQ_PRIO_MASKING +HAS_LDAPR +HAS_LSE_ATOMICS +HAS_NO_FPSIMD +HAS_NO_HW_PREFETCH +HAS_PAN +HAS_RAS_EXTN +HAS_RNG +HAS_SB +HAS_STAGE2_FWB +HAS_SYSREG_GIC_CPUIF +HAS_TLB_RANGE +HAS_VIRT_HOST_EXTN +HW_DBM +KVM_PROTECTED_MODE +MISMATCHED_CACHE_TYPE +MTE +SPECTRE_V2 +SPECTRE_V3A +SPECTRE_V4 +SSBS +SVE +UNMAP_KERNEL_AT_EL0 +WORKAROUND_834220 +WORKAROUND_843419 +WORKAROUND_845719 +WORKAROUND_858921 +WORKAROUND_1418040 +WORKAROUND_1463225 +WORKAROUND_1508412 +WORKAROUND_1542419 +WORKAROUND_CAVIUM_23154 +WORKAROUND_CAVIUM_27456 +WORKAROUND_CAVIUM_30115 +WORKAROUND_CAVIUM_TX2_219_PRFM +WORKAROUND_CAVIUM_TX2_219_TVM +WORKAROUND_CLEAN_CACHE +WORKAROUND_DEVICE_LOAD_ACQUIRE +WORKAROUND_NVIDIA_CARMEL_CNP +WORKAROUND_QCOM_FALKOR_E1003 +WORKAROUND_REPEAT_TLBI +WORKAROUND_SPECULATIVE_AT diff --git a/arch/arm64/tools/gen-cpucaps.awk b/arch/arm64/tools/gen-cpucaps.awk new file mode 100755 index 000000000000..00c9e72a200a --- /dev/null +++ b/arch/arm64/tools/gen-cpucaps.awk @@ -0,0 +1,40 @@ +#!/bin/awk -f +# SPDX-License-Identifier: GPL-2.0 +# gen-cpucaps.awk: arm64 cpucaps header generator +# +# Usage: awk -f gen-cpucaps.awk cpucaps.txt + +# Log an error and terminate +function fatal(msg) { + print "Error at line " NR ": " msg > "/dev/stderr" + exit 1 +} + +# skip blank lines and comment lines +/^$/ { next } +/^#/ { next } + +BEGIN { + print "#ifndef __ASM_CPUCAPS_H" + print "#define __ASM_CPUCAPS_H" + print "" + print "/* Generated file - do not edit */" + cap_num = 0 + print "" +} + +/^[vA-Z0-9_]+$/ { + printf("#define ARM64_%-30s\t%d\n", $0, cap_num++) + next +} + +END { + printf("#define ARM64_NCAPS\t\t\t\t%d\n", cap_num) + print "" + print "#endif /* __ASM_CPUCAPS_H */" +} + +# Any lines not handled by previous rules are unexpected +{ + fatal("unhandled statement") +} diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index fca4547d580f..696f6b009377 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -109,10 +109,11 @@ static inline bool kvm_is_error_hva(unsigned long addr) } struct kvm_vm_stat { - ulong remote_tlb_flush; + struct kvm_vm_stat_generic generic; }; struct kvm_vcpu_stat { + struct kvm_vcpu_stat_generic generic; u64 wait_exits; u64 cache_exits; u64 signal_exits; @@ -142,12 +143,6 @@ struct kvm_vcpu_stat { #ifdef CONFIG_CPU_LOONGSON64 u64 vz_cpucfg_exits; #endif - u64 halt_successful_poll; - u64 halt_attempted_poll; - u64 halt_poll_success_ns; - u64 halt_poll_fail_ns; - u64 halt_poll_invalid; - u64 halt_wakeup; }; struct kvm_arch_memory_slot { diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile index 30cc060857c7..c67250a956b8 100644 --- a/arch/mips/kvm/Makefile +++ b/arch/mips/kvm/Makefile @@ -2,7 +2,7 @@ # Makefile for KVM support for MIPS # -common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o eventfd.o) +common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o eventfd.o binary_stats.o) EXTRA_CFLAGS += -Ivirt/kvm -Iarch/mips/kvm diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 4d4af97dcc88..af9dd029a4e1 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -38,43 +38,63 @@ #define VECTORSPACING 0x100 /* for EI/VI mode */ #endif -struct kvm_stats_debugfs_item debugfs_entries[] = { - VCPU_STAT("wait", wait_exits), - VCPU_STAT("cache", cache_exits), - VCPU_STAT("signal", signal_exits), - VCPU_STAT("interrupt", int_exits), - VCPU_STAT("cop_unusable", cop_unusable_exits), - VCPU_STAT("tlbmod", tlbmod_exits), - VCPU_STAT("tlbmiss_ld", tlbmiss_ld_exits), - VCPU_STAT("tlbmiss_st", tlbmiss_st_exits), - VCPU_STAT("addrerr_st", addrerr_st_exits), - VCPU_STAT("addrerr_ld", addrerr_ld_exits), - VCPU_STAT("syscall", syscall_exits), - VCPU_STAT("resvd_inst", resvd_inst_exits), - VCPU_STAT("break_inst", break_inst_exits), - VCPU_STAT("trap_inst", trap_inst_exits), - VCPU_STAT("msa_fpe", msa_fpe_exits), - VCPU_STAT("fpe", fpe_exits), - VCPU_STAT("msa_disabled", msa_disabled_exits), - VCPU_STAT("flush_dcache", flush_dcache_exits), - VCPU_STAT("vz_gpsi", vz_gpsi_exits), - VCPU_STAT("vz_gsfc", vz_gsfc_exits), - VCPU_STAT("vz_hc", vz_hc_exits), - VCPU_STAT("vz_grr", vz_grr_exits), - VCPU_STAT("vz_gva", vz_gva_exits), - VCPU_STAT("vz_ghfc", vz_ghfc_exits), - VCPU_STAT("vz_gpa", vz_gpa_exits), - VCPU_STAT("vz_resvd", vz_resvd_exits), +const struct _kvm_stats_desc kvm_vm_stats_desc[] = { + KVM_GENERIC_VM_STATS() +}; +static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == + sizeof(struct kvm_vm_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vm_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vm_stats_desc), +}; + +const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { + KVM_GENERIC_VCPU_STATS(), + STATS_DESC_COUNTER(VCPU, wait_exits), + STATS_DESC_COUNTER(VCPU, cache_exits), + STATS_DESC_COUNTER(VCPU, signal_exits), + STATS_DESC_COUNTER(VCPU, int_exits), + STATS_DESC_COUNTER(VCPU, cop_unusable_exits), + STATS_DESC_COUNTER(VCPU, tlbmod_exits), + STATS_DESC_COUNTER(VCPU, tlbmiss_ld_exits), + STATS_DESC_COUNTER(VCPU, tlbmiss_st_exits), + STATS_DESC_COUNTER(VCPU, addrerr_st_exits), + STATS_DESC_COUNTER(VCPU, addrerr_ld_exits), + STATS_DESC_COUNTER(VCPU, syscall_exits), + STATS_DESC_COUNTER(VCPU, resvd_inst_exits), + STATS_DESC_COUNTER(VCPU, break_inst_exits), + STATS_DESC_COUNTER(VCPU, trap_inst_exits), + STATS_DESC_COUNTER(VCPU, msa_fpe_exits), + STATS_DESC_COUNTER(VCPU, fpe_exits), + STATS_DESC_COUNTER(VCPU, msa_disabled_exits), + STATS_DESC_COUNTER(VCPU, flush_dcache_exits), + STATS_DESC_COUNTER(VCPU, vz_gpsi_exits), + STATS_DESC_COUNTER(VCPU, vz_gsfc_exits), + STATS_DESC_COUNTER(VCPU, vz_hc_exits), + STATS_DESC_COUNTER(VCPU, vz_grr_exits), + STATS_DESC_COUNTER(VCPU, vz_gva_exits), + STATS_DESC_COUNTER(VCPU, vz_ghfc_exits), + STATS_DESC_COUNTER(VCPU, vz_gpa_exits), + STATS_DESC_COUNTER(VCPU, vz_resvd_exits), #ifdef CONFIG_CPU_LOONGSON64 - VCPU_STAT("vz_cpucfg", vz_cpucfg_exits), + STATS_DESC_COUNTER(VCPU, vz_cpucfg_exits), #endif - VCPU_STAT("halt_successful_poll", halt_successful_poll), - VCPU_STAT("halt_attempted_poll", halt_attempted_poll), - VCPU_STAT("halt_poll_invalid", halt_poll_invalid), - VCPU_STAT("halt_wakeup", halt_wakeup), - VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), - VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), - {NULL} +}; +static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == + sizeof(struct kvm_vcpu_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vcpu_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vcpu_stats_desc), }; bool kvm_trace_guest_mode_change; diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 1c7b75834e04..02ee6f5ac9fe 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -120,6 +120,7 @@ extern s32 patch__call_flush_branch_caches3; extern s32 patch__flush_count_cache_return; extern s32 patch__flush_link_stack_return; extern s32 patch__call_kvm_flush_link_stack; +extern s32 patch__call_kvm_flush_link_stack_p9; extern s32 patch__memset_nocache, patch__memcpy_nocache; extern long flush_branch_caches; @@ -140,7 +141,7 @@ void kvmhv_load_host_pmu(void); void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use); void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu); -int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu); +void kvmppc_p9_enter_guest(struct kvm_vcpu *vcpu); long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr); long kvmppc_h_set_xdabr(struct kvm_vcpu *vcpu, unsigned long dabr, diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index eace8c3f7b0a..c02f42d1031e 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -19,6 +19,7 @@ struct mmu_psize_def { int penc[MMU_PAGE_COUNT]; /* HPTE encoding */ unsigned int tlbiel; /* tlbiel supported for that page size */ unsigned long avpnm; /* bits to mask out in AVPN in the HPTE */ + unsigned long h_rpt_pgsize; /* H_RPT_INVALIDATE page size encoding */ union { unsigned long sllp; /* SLB L||LP (exact mask to use in slbmte) */ unsigned long ap; /* Ap encoding used by PowerISA 3.0 */ diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 8b33601cdb9d..a46fd37ad552 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -4,6 +4,10 @@ #include <asm/hvcall.h> +#define RIC_FLUSH_TLB 0 +#define RIC_FLUSH_PWC 1 +#define RIC_FLUSH_ALL 2 + struct vm_area_struct; struct mm_struct; struct mmu_gather; diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index 98c8bd155bf9..b167186aaee4 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -98,6 +98,36 @@ static inline int cpu_last_thread_sibling(int cpu) return cpu | (threads_per_core - 1); } +/* + * tlb_thread_siblings are siblings which share a TLB. This is not + * architected, is not something a hypervisor could emulate and a future + * CPU may change behaviour even in compat mode, so this should only be + * used on PowerNV, and only with care. + */ +static inline int cpu_first_tlb_thread_sibling(int cpu) +{ + if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8)) + return cpu & ~0x6; /* Big Core */ + else + return cpu_first_thread_sibling(cpu); +} + +static inline int cpu_last_tlb_thread_sibling(int cpu) +{ + if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8)) + return cpu | 0x6; /* Big Core */ + else + return cpu_last_thread_sibling(cpu); +} + +static inline int cpu_tlb_thread_sibling_step(void) +{ + if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8)) + return 2; /* Big Core */ + else + return 1; +} + static inline u32 get_tensr(void) { #ifdef CONFIG_BOOKE diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index c1a8aac01cf9..bb6f78fcf981 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -35,6 +35,19 @@ /* PACA save area size in u64 units (exgen, exmc, etc) */ #define EX_SIZE 10 +/* PACA save area offsets */ +#define EX_R9 0 +#define EX_R10 8 +#define EX_R11 16 +#define EX_R12 24 +#define EX_R13 32 +#define EX_DAR 40 +#define EX_DSISR 48 +#define EX_CCR 52 +#define EX_CFAR 56 +#define EX_PPR 64 +#define EX_CTR 72 + /* * maximum recursive depth of MCE exceptions */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 443050906018..7e4b2cef40c2 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -413,9 +413,9 @@ #define H_RPTI_TYPE_NESTED 0x0001 /* Invalidate nested guest partition-scope */ #define H_RPTI_TYPE_TLB 0x0002 /* Invalidate TLB */ #define H_RPTI_TYPE_PWC 0x0004 /* Invalidate Page Walk Cache */ -/* Invalidate Process Table Entries if H_RPTI_TYPE_NESTED is clear */ +/* Invalidate caching of Process Table Entries if H_RPTI_TYPE_NESTED is clear */ #define H_RPTI_TYPE_PRT 0x0008 -/* Invalidate Partition Table Entries if H_RPTI_TYPE_NESTED is set */ +/* Invalidate caching of Partition Table Entries if H_RPTI_TYPE_NESTED is set */ #define H_RPTI_TYPE_PAT 0x0008 #define H_RPTI_TYPE_ALL (H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | \ H_RPTI_TYPE_PRT) @@ -448,6 +448,9 @@ */ long plpar_hcall_norets(unsigned long opcode, ...); +/* Variant which does not do hcall tracing */ +long plpar_hcall_norets_notrace(unsigned long opcode, ...); + /** * plpar_hcall: - Make a pseries hypervisor call * @opcode: The hypervisor call to make. diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index 44cde2e129b8..59f704408d65 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -153,8 +153,6 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup */ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state) { - if (user_mode(regs)) - kuep_unlock(); } static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state) @@ -222,6 +220,13 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte local_paca->irq_soft_mask = IRQS_ALL_DISABLED; local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !(regs->msr & MSR_PR) && + regs->nip < (unsigned long)__end_interrupts) { + // Kernel code running below __end_interrupts is + // implicitly soft-masked. + regs->softe = IRQS_ALL_DISABLED; + } + /* Don't do any per-CPU operations until interrupt state is fixed */ if (nmi_disables_ftrace(regs)) { diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index a3633560493b..fbbf3cec92e9 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -147,6 +147,7 @@ #define KVM_GUEST_MODE_SKIP 2 #define KVM_GUEST_MODE_GUEST_HV 3 #define KVM_GUEST_MODE_HOST_HV 4 +#define KVM_GUEST_MODE_HV_P9 5 /* ISA >= v3.0 path */ #define KVM_INST_FETCH_FAILED -1 diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index e6b53c6e21e3..caaa0f592d8e 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -307,6 +307,9 @@ void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1); void kvmhv_release_all_nested(struct kvm *kvm); long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu); long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu); +long do_h_rpt_invalidate_pat(struct kvm_vcpu *vcpu, unsigned long lpid, + unsigned long type, unsigned long pg_sizes, + unsigned long start, unsigned long end); int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr); void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr); diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 9bb9bb370b53..eaf3a562bf1e 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -153,10 +153,18 @@ static inline bool kvmhv_vcpu_is_radix(struct kvm_vcpu *vcpu) return radix; } +int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr); + #define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ #endif /* + * Invalid HDSISR value which is used to indicate when HW has not set the reg. + * Used to work around an errata. + */ +#define HDSISR_CANARY 0x7fff + +/* * We use a lock bit in HPTE dword 0 to synchronize updates and * accesses to each HPTE, and another bit to indicate non-present * HPTEs. diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 1e83359f286b..9f52f282b1aa 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -51,6 +51,7 @@ /* PPC-specific vcpu->requests bit members */ #define KVM_REQ_WATCHDOG KVM_ARCH_REQ(0) #define KVM_REQ_EPR_EXIT KVM_ARCH_REQ(1) +#define KVM_REQ_PENDING_TIMER KVM_ARCH_REQ(2) #include <linux/mmu_notifier.h> @@ -80,12 +81,13 @@ struct kvmppc_book3s_shadow_vcpu; struct kvm_nested_guest; struct kvm_vm_stat { - ulong remote_tlb_flush; - ulong num_2M_pages; - ulong num_1G_pages; + struct kvm_vm_stat_generic generic; + u64 num_2M_pages; + u64 num_1G_pages; }; struct kvm_vcpu_stat { + struct kvm_vcpu_stat_generic generic; u64 sum_exits; u64 mmio_exits; u64 signal_exits; @@ -101,14 +103,8 @@ struct kvm_vcpu_stat { u64 emulated_inst_exits; u64 dec_exits; u64 ext_intr_exits; - u64 halt_poll_success_ns; - u64 halt_poll_fail_ns; u64 halt_wait_ns; - u64 halt_successful_poll; - u64 halt_attempted_poll; u64 halt_successful_wait; - u64 halt_poll_invalid; - u64 halt_wakeup; u64 dbell_exits; u64 gdbell_exits; u64 ld; @@ -297,7 +293,6 @@ struct kvm_arch { u8 fwnmi_enabled; u8 secure_guest; u8 svm_enabled; - bool threads_indep; bool nested_enable; bool dawr1_enabled; pgd_t *pgtable; @@ -683,7 +678,12 @@ struct kvm_vcpu_arch { ulong fault_dar; u32 fault_dsisr; unsigned long intr_msr; - ulong fault_gpa; /* guest real address of page fault (POWER9) */ + /* + * POWER9 and later: fault_gpa contains the guest real address of page + * fault for a radix guest, or segment descriptor (equivalent to result + * from slbmfev of SLB entry that translated the EA) for hash guests. + */ + ulong fault_gpa; #endif #ifdef CONFIG_BOOKE diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 5bf8ae9bb2cc..2d88944f9f34 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -129,6 +129,7 @@ extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu); extern int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu); extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags); +extern void kvmppc_core_queue_syscall(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags); extern void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu); @@ -606,6 +607,7 @@ extern void kvmppc_free_pimap(struct kvm *kvm); extern int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall); extern void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu); extern int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd); +extern int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req); extern u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu); extern int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval); extern int kvmppc_xics_connect_vcpu(struct kvm_device *dev, @@ -638,6 +640,8 @@ static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) static inline void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu) { } static inline int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd) { return 0; } +static inline int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req) + { return 0; } #endif #ifdef CONFIG_KVM_XIVE @@ -655,8 +659,6 @@ extern int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority); extern int kvmppc_xive_int_on(struct kvm *kvm, u32 irq); extern int kvmppc_xive_int_off(struct kvm *kvm, u32 irq); -extern void kvmppc_xive_init_module(void); -extern void kvmppc_xive_exit_module(void); extern int kvmppc_xive_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu); @@ -671,6 +673,8 @@ extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval); extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu); +extern void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu); +extern void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu); static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu) { @@ -680,8 +684,6 @@ static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu) extern int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu); extern void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu); -extern void kvmppc_xive_native_init_module(void); -extern void kvmppc_xive_native_exit_module(void); extern int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val); extern int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu, @@ -695,8 +697,6 @@ static inline int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority) { return -1; } static inline int kvmppc_xive_int_on(struct kvm *kvm, u32 irq) { return -1; } static inline int kvmppc_xive_int_off(struct kvm *kvm, u32 irq) { return -1; } -static inline void kvmppc_xive_init_module(void) { } -static inline void kvmppc_xive_exit_module(void) { } static inline int kvmppc_xive_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; } @@ -711,14 +711,14 @@ static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { retur static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status) { return -ENODEV; } static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { } +static inline void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu) { } +static inline void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu) { } static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu) { return 0; } static inline int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; } static inline void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { } -static inline void kvmppc_xive_native_init_module(void) { } -static inline void kvmppc_xive_native_exit_module(void) { } static inline int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val) { return 0; } @@ -754,7 +754,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, unsigned long tce_value, unsigned long npages); long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target, unsigned int yield_count); -long kvmppc_h_random(struct kvm_vcpu *vcpu); +long kvmppc_rm_h_random(struct kvm_vcpu *vcpu); void kvmhv_commence_exit(int trap); void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu); void kvmppc_subcore_enter_guest(void); diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 4bc45d3ed8b0..db186c539d37 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -122,12 +122,6 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea) } #endif -#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU) -extern void radix_kvm_prefetch_workaround(struct mm_struct *mm); -#else -static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { } -#endif - extern void switch_cop(struct mm_struct *next); extern int use_cop(unsigned long acop, struct mm_struct *mm); extern void drop_cop(unsigned long acop, struct mm_struct *mm); @@ -222,6 +216,18 @@ static inline void mm_context_add_copro(struct mm_struct *mm) { } static inline void mm_context_remove_copro(struct mm_struct *mm) { } #endif +#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU) +void do_h_rpt_invalidate_prt(unsigned long pid, unsigned long lpid, + unsigned long type, unsigned long pg_sizes, + unsigned long start, unsigned long end); +#else +static inline void do_h_rpt_invalidate_prt(unsigned long pid, + unsigned long lpid, + unsigned long type, + unsigned long pg_sizes, + unsigned long start, + unsigned long end) { } +#endif extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h index 5d1726bb28e7..bcb7b5f917be 100644 --- a/arch/powerpc/include/asm/paravirt.h +++ b/arch/powerpc/include/asm/paravirt.h @@ -28,19 +28,35 @@ static inline u32 yield_count_of(int cpu) return be32_to_cpu(yield_count); } +/* + * Spinlock code confers and prods, so don't trace the hcalls because the + * tracing code takes spinlocks which can cause recursion deadlocks. + * + * These calls are made while the lock is not held: the lock slowpath yields if + * it can not acquire the lock, and unlock slow path might prod if a waiter has + * yielded). So this may not be a problem for simple spin locks because the + * tracing does not technically recurse on the lock, but we avoid it anyway. + * + * However the queued spin lock contended path is more strictly ordered: the + * H_CONFER hcall is made after the task has queued itself on the lock, so then + * recursing on that lock will cause the task to then queue up again behind the + * first instance (or worse: queued spinlocks use tricks that assume a context + * never waits on more than one spinlock, so such recursion may cause random + * corruption in the lock code). + */ static inline void yield_to_preempted(int cpu, u32 yield_count) { - plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(cpu), yield_count); + plpar_hcall_norets_notrace(H_CONFER, get_hard_smp_processor_id(cpu), yield_count); } static inline void prod_cpu(int cpu) { - plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu)); + plpar_hcall_norets_notrace(H_PROD, get_hard_smp_processor_id(cpu)); } static inline void yield_to_any(void) { - plpar_hcall_norets(H_CONFER, -1, 0); + plpar_hcall_norets_notrace(H_CONFER, -1, 0); } #else static inline bool is_shared_processor(void) diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index ece84a430701..83e0f701ebc6 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -28,7 +28,11 @@ static inline void set_cede_latency_hint(u8 latency_hint) static inline long cede_processor(void) { - return plpar_hcall_norets(H_CEDE); + /* + * We cannot call tracepoints inside RCU idle regions which + * means we must not trace H_CEDE. + */ + return plpar_hcall_norets_notrace(H_CEDE); } static inline long extended_cede_processor(unsigned long latency_hint) diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 8dd3cdb25338..8c2c3dd4ddba 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -97,6 +97,18 @@ extern void div128_by_32(u64 dividend_high, u64 dividend_low, extern void secondary_cpu_time_init(void); extern void __init time_init(void); +#ifdef CONFIG_PPC64 +static inline unsigned long test_irq_work_pending(void) +{ + unsigned long x; + + asm volatile("lbz %0,%1(13)" + : "=r" (x) + : "i" (offsetof(struct paca_struct, irq_work_pending))); + return x; +} +#endif + DECLARE_PER_CPU(u64, decrementers_next_tb); /* Convert timebase ticks to nanoseconds */ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index a09e4240c5b1..22c79ab40006 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -157,7 +157,7 @@ do { \ "2: lwz%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ EX_TABLE(2b, %l2) \ - : "=r" (x) \ + : "=&r" (x) \ : "m" (*addr) \ : \ : label) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 28af4efb4587..aa267d173ded 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -534,7 +534,6 @@ int main(void) OFFSET(VCPU_SLB_NR, kvm_vcpu, arch.slb_nr); OFFSET(VCPU_FAULT_DSISR, kvm_vcpu, arch.fault_dsisr); OFFSET(VCPU_FAULT_DAR, kvm_vcpu, arch.fault_dar); - OFFSET(VCPU_FAULT_GPA, kvm_vcpu, arch.fault_gpa); OFFSET(VCPU_INTR_MSR, kvm_vcpu, arch.intr_msr); OFFSET(VCPU_LAST_INST, kvm_vcpu, arch.last_inst); OFFSET(VCPU_TRAP, kvm_vcpu, arch.trap); diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 7c3654b0d0f4..f1ae710274bc 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -340,6 +340,12 @@ ret_from_mc_except: andi. r10,r10,IRQS_DISABLED; /* yes -> go out of line */ \ bne masked_interrupt_book3e_##n +/* + * Additional regs must be re-loaded from paca before EXCEPTION_COMMON* is + * called, because that does SAVE_NVGPRS which must see the original register + * values, otherwise the scratch values might be restored when exiting the + * interrupt. + */ #define PROLOG_ADDITION_2REGS_GEN(n) \ std r14,PACA_EXGEN+EX_R14(r13); \ std r15,PACA_EXGEN+EX_R15(r13) @@ -535,6 +541,10 @@ __end_interrupts: PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR + std r14,_DAR(r1) + std r15,_DSISR(r1) + ld r14,PACA_EXGEN+EX_R14(r13) + ld r15,PACA_EXGEN+EX_R15(r13) EXCEPTION_COMMON(0x300) b storage_fault_common @@ -544,6 +554,10 @@ __end_interrupts: PROLOG_ADDITION_2REGS) li r15,0 mr r14,r10 + std r14,_DAR(r1) + std r15,_DSISR(r1) + ld r14,PACA_EXGEN+EX_R14(r13) + ld r15,PACA_EXGEN+EX_R15(r13) EXCEPTION_COMMON(0x400) b storage_fault_common @@ -557,6 +571,10 @@ __end_interrupts: PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR + std r14,_DAR(r1) + std r15,_DSISR(r1) + ld r14,PACA_EXGEN+EX_R14(r13) + ld r15,PACA_EXGEN+EX_R15(r13) EXCEPTION_COMMON(0x600) b alignment_more /* no room, go out of line */ @@ -565,10 +583,10 @@ __end_interrupts: NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM, PROLOG_ADDITION_1REG) mfspr r14,SPRN_ESR - EXCEPTION_COMMON(0x700) std r14,_DSISR(r1) - addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXGEN+EX_R14(r13) + EXCEPTION_COMMON(0x700) + addi r3,r1,STACK_FRAME_OVERHEAD bl program_check_exception REST_NVGPRS(r1) b interrupt_return @@ -725,11 +743,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) * normal exception */ mfspr r14,SPRN_DBSR - EXCEPTION_COMMON_CRIT(0xd00) std r14,_DSISR(r1) - addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXCRIT+EX_R14(r13) ld r15,PACA_EXCRIT+EX_R15(r13) + EXCEPTION_COMMON_CRIT(0xd00) + addi r3,r1,STACK_FRAME_OVERHEAD bl DebugException REST_NVGPRS(r1) b interrupt_return @@ -796,11 +814,11 @@ kernel_dbg_exc: * normal exception */ mfspr r14,SPRN_DBSR - EXCEPTION_COMMON_DBG(0xd08) std r14,_DSISR(r1) - addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXDBG+EX_R14(r13) ld r15,PACA_EXDBG+EX_R15(r13) + EXCEPTION_COMMON_DBG(0xd08) + addi r3,r1,STACK_FRAME_OVERHEAD bl DebugException REST_NVGPRS(r1) b interrupt_return @@ -931,11 +949,7 @@ masked_interrupt_book3e_0x2c0: * original values stashed away in the PACA */ storage_fault_common: - std r14,_DAR(r1) - std r15,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD - ld r14,PACA_EXGEN+EX_R14(r13) - ld r15,PACA_EXGEN+EX_R15(r13) bl do_page_fault b interrupt_return @@ -944,11 +958,7 @@ storage_fault_common: * continues here. */ alignment_more: - std r14,_DAR(r1) - std r15,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD - ld r14,PACA_EXGEN+EX_R14(r13) - ld r15,PACA_EXGEN+EX_R15(r13) bl alignment_exception REST_NVGPRS(r1) b interrupt_return diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index fa8e52a0239e..f7fc6e078d4e 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -21,22 +21,6 @@ #include <asm/feature-fixups.h> #include <asm/kup.h> -/* PACA save area offsets (exgen, exmc, etc) */ -#define EX_R9 0 -#define EX_R10 8 -#define EX_R11 16 -#define EX_R12 24 -#define EX_R13 32 -#define EX_DAR 40 -#define EX_DSISR 48 -#define EX_CCR 52 -#define EX_CFAR 56 -#define EX_PPR 64 -#define EX_CTR 72 -.if EX_SIZE != 10 - .error "EX_SIZE is wrong" -.endif - /* * Following are fixed section helper macros. * @@ -133,7 +117,6 @@ name: #define IBRANCH_TO_COMMON .L_IBRANCH_TO_COMMON_\name\() /* ENTRY branch to common */ #define IREALMODE_COMMON .L_IREALMODE_COMMON_\name\() /* Common runs in realmode */ #define IMASK .L_IMASK_\name\() /* IRQ soft-mask bit */ -#define IKVM_SKIP .L_IKVM_SKIP_\name\() /* Generate KVM skip handler */ #define IKVM_REAL .L_IKVM_REAL_\name\() /* Real entry tests KVM */ #define __IKVM_REAL(name) .L_IKVM_REAL_ ## name #define IKVM_VIRT .L_IKVM_VIRT_\name\() /* Virt entry tests KVM */ @@ -190,9 +173,6 @@ do_define_int n .ifndef IMASK IMASK=0 .endif - .ifndef IKVM_SKIP - IKVM_SKIP=0 - .endif .ifndef IKVM_REAL IKVM_REAL=0 .endif @@ -207,8 +187,6 @@ do_define_int n .endif .endm -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE /* * All interrupts which set HSRR registers, as well as SRESET and MCE and * syscall when invoked with "sc 1" switch to MSR[HV]=1 (HVMODE) to be taken, @@ -238,88 +216,28 @@ do_define_int n /* * If an interrupt is taken while a guest is running, it is immediately routed - * to KVM to handle. If both HV and PR KVM arepossible, KVM interrupts go first - * to kvmppc_interrupt_hv, which handles the PR guest case. + * to KVM to handle. */ -#define kvmppc_interrupt kvmppc_interrupt_hv -#else -#define kvmppc_interrupt kvmppc_interrupt_pr -#endif -.macro KVMTEST name +.macro KVMTEST name handler +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER lbz r10,HSTATE_IN_GUEST(r13) cmpwi r10,0 - bne \name\()_kvm -.endm - -.macro GEN_KVM name - .balign IFETCH_ALIGN_BYTES -\name\()_kvm: - - .if IKVM_SKIP - cmpwi r10,KVM_GUEST_MODE_SKIP - beq 89f - .else -BEGIN_FTR_SECTION - ld r10,IAREA+EX_CFAR(r13) - std r10,HSTATE_CFAR(r13) -END_FTR_SECTION_IFSET(CPU_FTR_CFAR) - .endif - - ld r10,IAREA+EX_CTR(r13) - mtctr r10 -BEGIN_FTR_SECTION - ld r10,IAREA+EX_PPR(r13) - std r10,HSTATE_PPR(r13) -END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) - ld r11,IAREA+EX_R11(r13) - ld r12,IAREA+EX_R12(r13) - std r12,HSTATE_SCRATCH0(r13) - sldi r12,r9,32 - ld r9,IAREA+EX_R9(r13) - ld r10,IAREA+EX_R10(r13) /* HSRR variants have the 0x2 bit added to their trap number */ .if IHSRR_IF_HVMODE BEGIN_FTR_SECTION - ori r12,r12,(IVEC + 0x2) - FTR_SECTION_ELSE - ori r12,r12,(IVEC) - ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) - .elseif IHSRR - ori r12,r12,(IVEC+ 0x2) - .else - ori r12,r12,(IVEC) - .endif - b kvmppc_interrupt - - .if IKVM_SKIP -89: mtocrf 0x80,r9 - ld r10,IAREA+EX_CTR(r13) - mtctr r10 - ld r9,IAREA+EX_R9(r13) - ld r10,IAREA+EX_R10(r13) - ld r11,IAREA+EX_R11(r13) - ld r12,IAREA+EX_R12(r13) - .if IHSRR_IF_HVMODE - BEGIN_FTR_SECTION - b kvmppc_skip_Hinterrupt + li r10,(IVEC + 0x2) FTR_SECTION_ELSE - b kvmppc_skip_interrupt + li r10,(IVEC) ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) .elseif IHSRR - b kvmppc_skip_Hinterrupt + li r10,(IVEC + 0x2) .else - b kvmppc_skip_interrupt + li r10,(IVEC) .endif - .endif -.endm - -#else -.macro KVMTEST name -.endm -.macro GEN_KVM name -.endm + bne \handler #endif +.endm /* * This is the BOOK3S interrupt entry code macro. @@ -461,7 +379,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) DEFINE_FIXED_SYMBOL(\name\()_common_real) \name\()_common_real: .if IKVM_REAL - KVMTEST \name + KVMTEST \name kvm_interrupt .endif ld r10,PACAKMSR(r13) /* get MSR value for kernel */ @@ -484,7 +402,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real) DEFINE_FIXED_SYMBOL(\name\()_common_virt) \name\()_common_virt: .if IKVM_VIRT - KVMTEST \name + KVMTEST \name kvm_interrupt 1: .endif .endif /* IVIRT */ @@ -498,7 +416,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_virt) DEFINE_FIXED_SYMBOL(\name\()_common_real) \name\()_common_real: .if IKVM_REAL - KVMTEST \name + KVMTEST \name kvm_interrupt .endif .endm @@ -1000,8 +918,6 @@ EXC_COMMON_BEGIN(system_reset_common) EXCEPTION_RESTORE_REGS RFI_TO_USER_OR_KERNEL - GEN_KVM system_reset - /** * Interrupt 0x200 - Machine Check Interrupt (MCE). @@ -1070,7 +986,6 @@ INT_DEFINE_BEGIN(machine_check) ISET_RI=0 IDAR=1 IDSISR=1 - IKVM_SKIP=1 IKVM_REAL=1 INT_DEFINE_END(machine_check) @@ -1166,7 +1081,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) /* * Check if we are coming from guest. If yes, then run the normal * exception handler which will take the - * machine_check_kvm->kvmppc_interrupt branch to deliver the MC event + * machine_check_kvm->kvm_interrupt branch to deliver the MC event * to guest. */ lbz r11,HSTATE_IN_GUEST(r13) @@ -1236,8 +1151,6 @@ EXC_COMMON_BEGIN(machine_check_common) bl machine_check_exception b interrupt_return - GEN_KVM machine_check - #ifdef CONFIG_PPC_P7_NAP /* @@ -1342,7 +1255,6 @@ INT_DEFINE_BEGIN(data_access) IVEC=0x300 IDAR=1 IDSISR=1 - IKVM_SKIP=1 IKVM_REAL=1 INT_DEFINE_END(data_access) @@ -1373,8 +1285,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) REST_NVGPRS(r1) b interrupt_return - GEN_KVM data_access - /** * Interrupt 0x380 - Data Segment Interrupt (DSLB). @@ -1396,7 +1306,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) INT_DEFINE_BEGIN(data_access_slb) IVEC=0x380 IDAR=1 - IKVM_SKIP=1 IKVM_REAL=1 INT_DEFINE_END(data_access_slb) @@ -1425,8 +1334,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) bl do_bad_slb_fault b interrupt_return - GEN_KVM data_access_slb - /** * Interrupt 0x400 - Instruction Storage Interrupt (ISI). @@ -1463,8 +1370,6 @@ MMU_FTR_SECTION_ELSE ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) b interrupt_return - GEN_KVM instruction_access - /** * Interrupt 0x480 - Instruction Segment Interrupt (ISLB). @@ -1509,8 +1414,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) bl do_bad_slb_fault b interrupt_return - GEN_KVM instruction_access_slb - /** * Interrupt 0x500 - External Interrupt. @@ -1555,8 +1458,6 @@ EXC_COMMON_BEGIN(hardware_interrupt_common) bl do_IRQ b interrupt_return - GEN_KVM hardware_interrupt - /** * Interrupt 0x600 - Alignment Interrupt @@ -1584,8 +1485,6 @@ EXC_COMMON_BEGIN(alignment_common) REST_NVGPRS(r1) /* instruction emulation may change GPRs */ b interrupt_return - GEN_KVM alignment - /** * Interrupt 0x700 - Program Interrupt (program check). @@ -1693,8 +1592,6 @@ EXC_COMMON_BEGIN(program_check_common) REST_NVGPRS(r1) /* instruction emulation may change GPRs */ b interrupt_return - GEN_KVM program_check - /* * Interrupt 0x800 - Floating-Point Unavailable Interrupt. @@ -1744,8 +1641,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) b interrupt_return #endif - GEN_KVM fp_unavailable - /** * Interrupt 0x900 - Decrementer Interrupt. @@ -1784,8 +1679,6 @@ EXC_COMMON_BEGIN(decrementer_common) bl timer_interrupt b interrupt_return - GEN_KVM decrementer - /** * Interrupt 0x980 - Hypervisor Decrementer Interrupt. @@ -1831,8 +1724,6 @@ EXC_COMMON_BEGIN(hdecrementer_common) ld r13,PACA_EXGEN+EX_R13(r13) HRFI_TO_KERNEL - GEN_KVM hdecrementer - /** * Interrupt 0xa00 - Directed Privileged Doorbell Interrupt. @@ -1872,8 +1763,6 @@ EXC_COMMON_BEGIN(doorbell_super_common) #endif b interrupt_return - GEN_KVM doorbell_super - EXC_REAL_NONE(0xb00, 0x100) EXC_VIRT_NONE(0x4b00, 0x100) @@ -1923,7 +1812,7 @@ INT_DEFINE_END(system_call) GET_PACA(r13) std r10,PACA_EXGEN+EX_R10(r13) INTERRUPT_TO_KERNEL - KVMTEST system_call /* uses r10, branch to system_call_kvm */ + KVMTEST system_call kvm_hcall /* uses r10, branch to kvm_hcall */ mfctr r9 #else mr r9,r13 @@ -1979,14 +1868,16 @@ EXC_VIRT_BEGIN(system_call, 0x4c00, 0x100) EXC_VIRT_END(system_call, 0x4c00, 0x100) #ifdef CONFIG_KVM_BOOK3S_64_HANDLER -TRAMP_REAL_BEGIN(system_call_kvm) - /* - * This is a hcall, so register convention is as above, with these - * differences: - * r13 = PACA - * ctr = orig r13 - * orig r10 saved in PACA - */ +TRAMP_REAL_BEGIN(kvm_hcall) + std r9,PACA_EXGEN+EX_R9(r13) + std r11,PACA_EXGEN+EX_R11(r13) + std r12,PACA_EXGEN+EX_R12(r13) + mfcr r9 + mfctr r10 + std r10,PACA_EXGEN+EX_R13(r13) + li r10,0 + std r10,PACA_EXGEN+EX_CFAR(r13) + std r10,PACA_EXGEN+EX_CTR(r13) /* * Save the PPR (on systems that support it) before changing to * HMT_MEDIUM. That allows the KVM code to save that value into the @@ -1994,31 +1885,24 @@ TRAMP_REAL_BEGIN(system_call_kvm) */ BEGIN_FTR_SECTION mfspr r10,SPRN_PPR - std r10,HSTATE_PPR(r13) + std r10,PACA_EXGEN+EX_PPR(r13) END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + HMT_MEDIUM - mfctr r10 - SET_SCRATCH0(r10) - mfcr r10 - std r12,HSTATE_SCRATCH0(r13) - sldi r12,r10,32 - ori r12,r12,0xc00 + #ifdef CONFIG_RELOCATABLE /* - * Requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives + * Requires __LOAD_FAR_HANDLER beause kvmppc_hcall lives * outside the head section. */ - __LOAD_FAR_HANDLER(r10, kvmppc_interrupt) + __LOAD_FAR_HANDLER(r10, kvmppc_hcall) mtctr r10 - ld r10,PACA_EXGEN+EX_R10(r13) bctr #else - ld r10,PACA_EXGEN+EX_R10(r13) - b kvmppc_interrupt + b kvmppc_hcall #endif #endif - /** * Interrupt 0xd00 - Trace Interrupt. * This is a synchronous interrupt in response to instruction step or @@ -2043,8 +1927,6 @@ EXC_COMMON_BEGIN(single_step_common) bl single_step_exception b interrupt_return - GEN_KVM single_step - /** * Interrupt 0xe00 - Hypervisor Data Storage Interrupt (HDSI). @@ -2063,7 +1945,6 @@ INT_DEFINE_BEGIN(h_data_storage) IHSRR=1 IDAR=1 IDSISR=1 - IKVM_SKIP=1 IKVM_REAL=1 IKVM_VIRT=1 INT_DEFINE_END(h_data_storage) @@ -2084,8 +1965,6 @@ MMU_FTR_SECTION_ELSE ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX) b interrupt_return - GEN_KVM h_data_storage - /** * Interrupt 0xe20 - Hypervisor Instruction Storage Interrupt (HISI). @@ -2111,8 +1990,6 @@ EXC_COMMON_BEGIN(h_instr_storage_common) bl unknown_exception b interrupt_return - GEN_KVM h_instr_storage - /** * Interrupt 0xe40 - Hypervisor Emulation Assistance Interrupt. @@ -2137,8 +2014,6 @@ EXC_COMMON_BEGIN(emulation_assist_common) REST_NVGPRS(r1) /* instruction emulation may change GPRs */ b interrupt_return - GEN_KVM emulation_assist - /** * Interrupt 0xe60 - Hypervisor Maintenance Interrupt (HMI). @@ -2210,16 +2085,12 @@ EXC_COMMON_BEGIN(hmi_exception_early_common) EXCEPTION_RESTORE_REGS hsrr=1 GEN_INT_ENTRY hmi_exception, virt=0 - GEN_KVM hmi_exception_early - EXC_COMMON_BEGIN(hmi_exception_common) GEN_COMMON hmi_exception addi r3,r1,STACK_FRAME_OVERHEAD bl handle_hmi_exception b interrupt_return - GEN_KVM hmi_exception - /** * Interrupt 0xe80 - Directed Hypervisor Doorbell Interrupt. @@ -2250,8 +2121,6 @@ EXC_COMMON_BEGIN(h_doorbell_common) #endif b interrupt_return - GEN_KVM h_doorbell - /** * Interrupt 0xea0 - Hypervisor Virtualization Interrupt. @@ -2278,8 +2147,6 @@ EXC_COMMON_BEGIN(h_virt_irq_common) bl do_IRQ b interrupt_return - GEN_KVM h_virt_irq - EXC_REAL_NONE(0xec0, 0x20) EXC_VIRT_NONE(0x4ec0, 0x20) @@ -2323,8 +2190,6 @@ EXC_COMMON_BEGIN(performance_monitor_common) bl performance_monitor_exception b interrupt_return - GEN_KVM performance_monitor - /** * Interrupt 0xf20 - Vector Unavailable Interrupt. @@ -2374,8 +2239,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) bl altivec_unavailable_exception b interrupt_return - GEN_KVM altivec_unavailable - /** * Interrupt 0xf40 - VSX Unavailable Interrupt. @@ -2424,8 +2287,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) bl vsx_unavailable_exception b interrupt_return - GEN_KVM vsx_unavailable - /** * Interrupt 0xf60 - Facility Unavailable Interrupt. @@ -2454,8 +2315,6 @@ EXC_COMMON_BEGIN(facility_unavailable_common) REST_NVGPRS(r1) /* instruction emulation may change GPRs */ b interrupt_return - GEN_KVM facility_unavailable - /** * Interrupt 0xf60 - Hypervisor Facility Unavailable Interrupt. @@ -2484,8 +2343,6 @@ EXC_COMMON_BEGIN(h_facility_unavailable_common) REST_NVGPRS(r1) /* XXX Shouldn't be necessary in practice */ b interrupt_return - GEN_KVM h_facility_unavailable - EXC_REAL_NONE(0xfa0, 0x20) EXC_VIRT_NONE(0x4fa0, 0x20) @@ -2515,8 +2372,6 @@ EXC_COMMON_BEGIN(cbe_system_error_common) bl cbe_system_error_exception b interrupt_return - GEN_KVM cbe_system_error - #else /* CONFIG_CBE_RAS */ EXC_REAL_NONE(0x1200, 0x100) EXC_VIRT_NONE(0x5200, 0x100) @@ -2548,8 +2403,6 @@ EXC_COMMON_BEGIN(instruction_breakpoint_common) bl instruction_breakpoint_exception b interrupt_return - GEN_KVM instruction_breakpoint - EXC_REAL_NONE(0x1400, 0x100) EXC_VIRT_NONE(0x5400, 0x100) @@ -2670,8 +2523,6 @@ EXC_COMMON_BEGIN(denorm_exception_common) bl unknown_exception b interrupt_return - GEN_KVM denorm_exception - #ifdef CONFIG_CBE_RAS INT_DEFINE_BEGIN(cbe_maintenance) @@ -2689,8 +2540,6 @@ EXC_COMMON_BEGIN(cbe_maintenance_common) bl cbe_maintenance_exception b interrupt_return - GEN_KVM cbe_maintenance - #else /* CONFIG_CBE_RAS */ EXC_REAL_NONE(0x1600, 0x100) EXC_VIRT_NONE(0x5600, 0x100) @@ -2721,8 +2570,6 @@ EXC_COMMON_BEGIN(altivec_assist_common) #endif b interrupt_return - GEN_KVM altivec_assist - #ifdef CONFIG_CBE_RAS INT_DEFINE_BEGIN(cbe_thermal) @@ -2740,8 +2587,6 @@ EXC_COMMON_BEGIN(cbe_thermal_common) bl cbe_thermal_exception b interrupt_return - GEN_KVM cbe_thermal - #else /* CONFIG_CBE_RAS */ EXC_REAL_NONE(0x1800, 0x100) EXC_VIRT_NONE(0x5800, 0x100) @@ -2994,6 +2839,15 @@ TRAMP_REAL_BEGIN(rfscv_flush_fallback) USE_TEXT_SECTION() +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +kvm_interrupt: + /* + * The conditional branch in KVMTEST can't reach all the way, + * make a stub. + */ + b kvmppc_interrupt +#endif + _GLOBAL(do_uaccess_flush) UACCESS_FLUSH_FIXUP_SECTION nop @@ -3009,32 +2863,6 @@ EXPORT_SYMBOL(do_uaccess_flush) MASKED_INTERRUPT MASKED_INTERRUPT hsrr=1 -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER -kvmppc_skip_interrupt: - /* - * Here all GPRs are unchanged from when the interrupt happened - * except for r13, which is saved in SPRG_SCRATCH0. - */ - mfspr r13, SPRN_SRR0 - addi r13, r13, 4 - mtspr SPRN_SRR0, r13 - GET_SCRATCH0(r13) - RFI_TO_KERNEL - b . - -kvmppc_skip_Hinterrupt: - /* - * Here all GPRs are unchanged from when the interrupt happened - * except for r13, which is saved in SPRG_SCRATCH0. - */ - mfspr r13, SPRN_HSRR0 - addi r13, r13, 4 - mtspr SPRN_HSRR0, r13 - GET_SCRATCH0(r13) - HRFI_TO_KERNEL - b . -#endif - /* * Relocation-on interrupts: A subset of the interrupts can be delivered * with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index e4559f8914eb..e0938ba298f2 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -34,9 +34,6 @@ notrace long system_call_exception(long r3, long r4, long r5, syscall_fn f; kuep_lock(); -#ifdef CONFIG_PPC32 - kuap_save_and_lock(regs); -#endif regs->orig_gpr3 = r3; @@ -427,6 +424,7 @@ again: /* Restore user access locks last */ kuap_user_restore(regs); + kuep_unlock(); return ret; } diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 8b2c1a8553a0..cfc03e016ff2 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -356,13 +356,16 @@ static void __init setup_legacy_serial_console(int console) static int __init ioremap_legacy_serial_console(void) { - struct legacy_serial_info *info = &legacy_serial_infos[legacy_serial_console]; - struct plat_serial8250_port *port = &legacy_serial_ports[legacy_serial_console]; + struct plat_serial8250_port *port; + struct legacy_serial_info *info; void __iomem *vaddr; if (legacy_serial_console < 0) return 0; + info = &legacy_serial_infos[legacy_serial_console]; + port = &legacy_serial_ports[legacy_serial_console]; + if (!info->early_addr) return 0; diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 0fdfcdd9d880..c17d1c9362b5 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -432,16 +432,19 @@ device_initcall(stf_barrier_debugfs_init); static void update_branch_cache_flush(void) { - u32 *site; + u32 *site, __maybe_unused *site2; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE site = &patch__call_kvm_flush_link_stack; + site2 = &patch__call_kvm_flush_link_stack_p9; // This controls the branch from guest_exit_cont to kvm_flush_link_stack if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) { patch_instruction_site(site, ppc_inst(PPC_INST_NOP)); + patch_instruction_site(site2, ppc_inst(PPC_INST_NOP)); } else { // Could use HW flush, but that could also flush count cache patch_branch_site(site, (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); + patch_branch_site(site2, (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); } #endif diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index f4aafa337c2e..1f07317964e4 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -166,9 +166,9 @@ copy_ckfpr_from_user(struct task_struct *task, void __user *from) } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ #else -#define unsafe_copy_fpr_to_user(to, task, label) do { } while (0) +#define unsafe_copy_fpr_to_user(to, task, label) do { if (0) goto label;} while (0) -#define unsafe_copy_fpr_from_user(task, from, label) do { } while (0) +#define unsafe_copy_fpr_from_user(task, from, label) do { if (0) goto label;} while (0) static inline unsigned long copy_fpr_to_user(void __user *to, struct task_struct *task) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index b67d93a609a2..da995c5fb97d 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -508,16 +508,6 @@ EXPORT_SYMBOL(profile_pc); * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable... */ #ifdef CONFIG_PPC64 -static inline unsigned long test_irq_work_pending(void) -{ - unsigned long x; - - asm volatile("lbz %0,%1(13)" - : "=r" (x) - : "i" (offsetof(struct paca_struct, irq_work_pending))); - return x; -} - static inline void set_irq_work_pending_flag(void) { asm volatile("stb %0,%1(13)" : : diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 2bfeaa13befb..583c14ef596e 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -6,7 +6,7 @@ ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm KVM := ../../../virt/kvm -common-objs-y = $(KVM)/kvm_main.o $(KVM)/eventfd.o +common-objs-y = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/binary_stats.o common-objs-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o common-objs-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o @@ -57,6 +57,7 @@ kvm-pr-y := \ book3s_32_mmu.o kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ + book3s_64_entry.o \ tm.o ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE @@ -86,6 +87,7 @@ kvm-book3s_64-builtin-tm-objs-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \ ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ book3s_hv_hmi.o \ + book3s_hv_p9_entry.o \ book3s_hv_rmhandlers.o \ book3s_hv_rm_mmu.o \ book3s_hv_ras.o \ diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 2b691f4d1f26..79833f78d1da 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -38,37 +38,66 @@ /* #define EXIT_DEBUG */ -struct kvm_stats_debugfs_item debugfs_entries[] = { - VCPU_STAT("exits", sum_exits), - VCPU_STAT("mmio", mmio_exits), - VCPU_STAT("sig", signal_exits), - VCPU_STAT("sysc", syscall_exits), - VCPU_STAT("inst_emu", emulated_inst_exits), - VCPU_STAT("dec", dec_exits), - VCPU_STAT("ext_intr", ext_intr_exits), - VCPU_STAT("queue_intr", queue_intr), - VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), - VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), - VCPU_STAT("halt_wait_ns", halt_wait_ns), - VCPU_STAT("halt_successful_poll", halt_successful_poll), - VCPU_STAT("halt_attempted_poll", halt_attempted_poll), - VCPU_STAT("halt_successful_wait", halt_successful_wait), - VCPU_STAT("halt_poll_invalid", halt_poll_invalid), - VCPU_STAT("halt_wakeup", halt_wakeup), - VCPU_STAT("pf_storage", pf_storage), - VCPU_STAT("sp_storage", sp_storage), - VCPU_STAT("pf_instruc", pf_instruc), - VCPU_STAT("sp_instruc", sp_instruc), - VCPU_STAT("ld", ld), - VCPU_STAT("ld_slow", ld_slow), - VCPU_STAT("st", st), - VCPU_STAT("st_slow", st_slow), - VCPU_STAT("pthru_all", pthru_all), - VCPU_STAT("pthru_host", pthru_host), - VCPU_STAT("pthru_bad_aff", pthru_bad_aff), - VM_STAT("largepages_2M", num_2M_pages, .mode = 0444), - VM_STAT("largepages_1G", num_1G_pages, .mode = 0444), - { NULL } +const struct _kvm_stats_desc kvm_vm_stats_desc[] = { + KVM_GENERIC_VM_STATS(), + STATS_DESC_ICOUNTER(VM, num_2M_pages), + STATS_DESC_ICOUNTER(VM, num_1G_pages) +}; +static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == + sizeof(struct kvm_vm_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vm_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vm_stats_desc), +}; + +const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { + KVM_GENERIC_VCPU_STATS(), + STATS_DESC_COUNTER(VCPU, sum_exits), + STATS_DESC_COUNTER(VCPU, mmio_exits), + STATS_DESC_COUNTER(VCPU, signal_exits), + STATS_DESC_COUNTER(VCPU, light_exits), + STATS_DESC_COUNTER(VCPU, itlb_real_miss_exits), + STATS_DESC_COUNTER(VCPU, itlb_virt_miss_exits), + STATS_DESC_COUNTER(VCPU, dtlb_real_miss_exits), + STATS_DESC_COUNTER(VCPU, dtlb_virt_miss_exits), + STATS_DESC_COUNTER(VCPU, syscall_exits), + STATS_DESC_COUNTER(VCPU, isi_exits), + STATS_DESC_COUNTER(VCPU, dsi_exits), + STATS_DESC_COUNTER(VCPU, emulated_inst_exits), + STATS_DESC_COUNTER(VCPU, dec_exits), + STATS_DESC_COUNTER(VCPU, ext_intr_exits), + STATS_DESC_TIME_NSEC(VCPU, halt_wait_ns), + STATS_DESC_COUNTER(VCPU, halt_successful_wait), + STATS_DESC_COUNTER(VCPU, dbell_exits), + STATS_DESC_COUNTER(VCPU, gdbell_exits), + STATS_DESC_COUNTER(VCPU, ld), + STATS_DESC_COUNTER(VCPU, st), + STATS_DESC_COUNTER(VCPU, pf_storage), + STATS_DESC_COUNTER(VCPU, pf_instruc), + STATS_DESC_COUNTER(VCPU, sp_storage), + STATS_DESC_COUNTER(VCPU, sp_instruc), + STATS_DESC_COUNTER(VCPU, queue_intr), + STATS_DESC_COUNTER(VCPU, ld_slow), + STATS_DESC_COUNTER(VCPU, st_slow), + STATS_DESC_COUNTER(VCPU, pthru_all), + STATS_DESC_COUNTER(VCPU, pthru_host), + STATS_DESC_COUNTER(VCPU, pthru_bad_aff) +}; +static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == + sizeof(struct kvm_vcpu_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vcpu_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vcpu_stats_desc), }; static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu, @@ -171,6 +200,12 @@ void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags) } EXPORT_SYMBOL_GPL(kvmppc_core_queue_machine_check); +void kvmppc_core_queue_syscall(struct kvm_vcpu *vcpu) +{ + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_SYSCALL, 0); +} +EXPORT_SYMBOL(kvmppc_core_queue_syscall); + void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags) { /* might as well deliver this straight away */ @@ -1044,13 +1079,10 @@ static int kvmppc_book3s_init(void) #ifdef CONFIG_KVM_XICS #ifdef CONFIG_KVM_XIVE if (xics_on_xive()) { - kvmppc_xive_init_module(); kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS); - if (kvmppc_xive_native_supported()) { - kvmppc_xive_native_init_module(); + if (kvmppc_xive_native_supported()) kvm_register_device_ops(&kvm_xive_native_ops, KVM_DEV_TYPE_XIVE); - } } else #endif kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS); @@ -1060,12 +1092,6 @@ static int kvmppc_book3s_init(void) static void kvmppc_book3s_exit(void) { -#ifdef CONFIG_KVM_XICS - if (xics_on_xive()) { - kvmppc_xive_exit_module(); - kvmppc_xive_native_exit_module(); - } -#endif #ifdef CONFIG_KVM_BOOK3S_32_HANDLER kvmppc_book3s_exit_pr(); #endif diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S new file mode 100644 index 000000000000..983b8c18bc31 --- /dev/null +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -0,0 +1,416 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#include <asm/asm-offsets.h> +#include <asm/cache.h> +#include <asm/code-patching-asm.h> +#include <asm/exception-64s.h> +#include <asm/export.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_book3s_asm.h> +#include <asm/mmu.h> +#include <asm/ppc_asm.h> +#include <asm/ptrace.h> +#include <asm/reg.h> +#include <asm/ultravisor-api.h> + +/* + * These are branched to from interrupt handlers in exception-64s.S which set + * IKVM_REAL or IKVM_VIRT, if HSTATE_IN_GUEST was found to be non-zero. + */ + +/* + * This is a hcall, so register convention is as + * Documentation/powerpc/papr_hcalls.rst. + * + * This may also be a syscall from PR-KVM userspace that is to be + * reflected to the PR guest kernel, so registers may be set up for + * a system call rather than hcall. We don't currently clobber + * anything here, but the 0xc00 handler has already clobbered CTR + * and CR0, so PR-KVM can not support a guest kernel that preserves + * those registers across its system calls. + * + * The state of registers is as kvmppc_interrupt, except CFAR is not + * saved, R13 is not in SCRATCH0, and R10 does not contain the trap. + */ +.global kvmppc_hcall +.balign IFETCH_ALIGN_BYTES +kvmppc_hcall: +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + lbz r10,HSTATE_IN_GUEST(r13) + cmpwi r10,KVM_GUEST_MODE_HV_P9 + beq kvmppc_p9_exit_hcall +#endif + ld r10,PACA_EXGEN+EX_R13(r13) + SET_SCRATCH0(r10) + li r10,0xc00 + /* Now we look like kvmppc_interrupt */ + li r11,PACA_EXGEN + b .Lgot_save_area + +/* + * KVM interrupt entry occurs after GEN_INT_ENTRY runs, and follows that + * call convention: + * + * guest R9-R13, CTR, CFAR, PPR saved in PACA EX_xxx save area + * guest (H)DAR, (H)DSISR are also in the save area for relevant interrupts + * guest R13 also saved in SCRATCH0 + * R13 = PACA + * R11 = (H)SRR0 + * R12 = (H)SRR1 + * R9 = guest CR + * PPR is set to medium + * + * With the addition for KVM: + * R10 = trap vector + */ +.global kvmppc_interrupt +.balign IFETCH_ALIGN_BYTES +kvmppc_interrupt: +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + std r10,HSTATE_SCRATCH0(r13) + lbz r10,HSTATE_IN_GUEST(r13) + cmpwi r10,KVM_GUEST_MODE_HV_P9 + beq kvmppc_p9_exit_interrupt + ld r10,HSTATE_SCRATCH0(r13) +#endif + li r11,PACA_EXGEN + cmpdi r10,0x200 + bgt+ .Lgot_save_area + li r11,PACA_EXMC + beq .Lgot_save_area + li r11,PACA_EXNMI +.Lgot_save_area: + add r11,r11,r13 +BEGIN_FTR_SECTION + ld r12,EX_CFAR(r11) + std r12,HSTATE_CFAR(r13) +END_FTR_SECTION_IFSET(CPU_FTR_CFAR) + ld r12,EX_CTR(r11) + mtctr r12 +BEGIN_FTR_SECTION + ld r12,EX_PPR(r11) + std r12,HSTATE_PPR(r13) +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + ld r12,EX_R12(r11) + std r12,HSTATE_SCRATCH0(r13) + sldi r12,r9,32 + or r12,r12,r10 + ld r9,EX_R9(r11) + ld r10,EX_R10(r11) + ld r11,EX_R11(r11) + + /* + * Hcalls and other interrupts come here after normalising register + * contents and save locations: + * + * R12 = (guest CR << 32) | interrupt vector + * R13 = PACA + * guest R12 saved in shadow HSTATE_SCRATCH0 + * guest R13 saved in SPRN_SCRATCH0 + */ + std r9,HSTATE_SCRATCH2(r13) + lbz r9,HSTATE_IN_GUEST(r13) + cmpwi r9,KVM_GUEST_MODE_SKIP + beq- .Lmaybe_skip +.Lno_skip: +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE + cmpwi r9,KVM_GUEST_MODE_GUEST + beq kvmppc_interrupt_pr +#endif + b kvmppc_interrupt_hv +#else + b kvmppc_interrupt_pr +#endif + +/* + * "Skip" interrupts are part of a trick KVM uses a with hash guests to load + * the faulting instruction in guest memory from the the hypervisor without + * walking page tables. + * + * When the guest takes a fault that requires the hypervisor to load the + * instruction (e.g., MMIO emulation), KVM is running in real-mode with HV=1 + * and the guest MMU context loaded. It sets KVM_GUEST_MODE_SKIP, and sets + * MSR[DR]=1 while leaving MSR[IR]=0, so it continues to fetch HV instructions + * but loads and stores will access the guest context. This is used to load + * the faulting instruction using the faulting guest effective address. + * + * However the guest context may not be able to translate, or it may cause a + * machine check or other issue, which results in a fault in the host + * (even with KVM-HV). + * + * These faults come here because KVM_GUEST_MODE_SKIP was set, so if they + * are (or are likely) caused by that load, the instruction is skipped by + * just returning with the PC advanced +4, where it is noticed the load did + * not execute and it goes to the slow path which walks the page tables to + * read guest memory. + */ +.Lmaybe_skip: + cmpwi r12,BOOK3S_INTERRUPT_MACHINE_CHECK + beq 1f + cmpwi r12,BOOK3S_INTERRUPT_DATA_STORAGE + beq 1f + cmpwi r12,BOOK3S_INTERRUPT_DATA_SEGMENT + beq 1f +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* HSRR interrupts get 2 added to interrupt number */ + cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE | 0x2 + beq 2f +#endif + b .Lno_skip +1: mfspr r9,SPRN_SRR0 + addi r9,r9,4 + mtspr SPRN_SRR0,r9 + ld r12,HSTATE_SCRATCH0(r13) + ld r9,HSTATE_SCRATCH2(r13) + GET_SCRATCH0(r13) + RFI_TO_KERNEL +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +2: mfspr r9,SPRN_HSRR0 + addi r9,r9,4 + mtspr SPRN_HSRR0,r9 + ld r12,HSTATE_SCRATCH0(r13) + ld r9,HSTATE_SCRATCH2(r13) + GET_SCRATCH0(r13) + HRFI_TO_KERNEL +#endif + +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + +/* Stack frame offsets for kvmppc_p9_enter_guest */ +#define SFS (144 + STACK_FRAME_MIN_SIZE) +#define STACK_SLOT_NVGPRS (SFS - 144) /* 18 gprs */ + +/* + * void kvmppc_p9_enter_guest(struct vcpu *vcpu); + * + * Enter the guest on a ISAv3.0 or later system. + */ +.balign IFETCH_ALIGN_BYTES +_GLOBAL(kvmppc_p9_enter_guest) +EXPORT_SYMBOL_GPL(kvmppc_p9_enter_guest) + mflr r0 + std r0,PPC_LR_STKOFF(r1) + stdu r1,-SFS(r1) + + std r1,HSTATE_HOST_R1(r13) + + mfcr r4 + stw r4,SFS+8(r1) + + reg = 14 + .rept 18 + std reg,STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1) + reg = reg + 1 + .endr + + ld r4,VCPU_LR(r3) + mtlr r4 + ld r4,VCPU_CTR(r3) + mtctr r4 + ld r4,VCPU_XER(r3) + mtspr SPRN_XER,r4 + + ld r1,VCPU_CR(r3) + +BEGIN_FTR_SECTION + ld r4,VCPU_CFAR(r3) + mtspr SPRN_CFAR,r4 +END_FTR_SECTION_IFSET(CPU_FTR_CFAR) +BEGIN_FTR_SECTION + ld r4,VCPU_PPR(r3) + mtspr SPRN_PPR,r4 +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + + reg = 4 + .rept 28 + ld reg,__VCPU_GPR(reg)(r3) + reg = reg + 1 + .endr + + ld r4,VCPU_KVM(r3) + lbz r4,KVM_SECURE_GUEST(r4) + cmpdi r4,0 + ld r4,VCPU_GPR(R4)(r3) + bne .Lret_to_ultra + + mtcr r1 + + ld r0,VCPU_GPR(R0)(r3) + ld r1,VCPU_GPR(R1)(r3) + ld r2,VCPU_GPR(R2)(r3) + ld r3,VCPU_GPR(R3)(r3) + + HRFI_TO_GUEST + b . + + /* + * Use UV_RETURN ultracall to return control back to the Ultravisor + * after processing an hypercall or interrupt that was forwarded + * (a.k.a. reflected) to the Hypervisor. + * + * All registers have already been reloaded except the ucall requires: + * R0 = hcall result + * R2 = SRR1, so UV can detect a synthesized interrupt (if any) + * R3 = UV_RETURN + */ +.Lret_to_ultra: + mtcr r1 + ld r1,VCPU_GPR(R1)(r3) + + ld r0,VCPU_GPR(R3)(r3) + mfspr r2,SPRN_SRR1 + LOAD_REG_IMMEDIATE(r3, UV_RETURN) + sc 2 + +/* + * kvmppc_p9_exit_hcall and kvmppc_p9_exit_interrupt are branched to from + * above if the interrupt was taken for a guest that was entered via + * kvmppc_p9_enter_guest(). + * + * The exit code recovers the host stack and vcpu pointer, saves all guest GPRs + * and CR, LR, XER as well as guest MSR and NIA into the VCPU, then re- + * establishes the host stack and registers to return from the + * kvmppc_p9_enter_guest() function, which saves CTR and other guest registers + * (SPRs and FP, VEC, etc). + */ +.balign IFETCH_ALIGN_BYTES +kvmppc_p9_exit_hcall: + mfspr r11,SPRN_SRR0 + mfspr r12,SPRN_SRR1 + li r10,0xc00 + std r10,HSTATE_SCRATCH0(r13) + +.balign IFETCH_ALIGN_BYTES +kvmppc_p9_exit_interrupt: + /* + * If set to KVM_GUEST_MODE_HV_P9 but we're still in the + * hypervisor, that means we can't return from the entry stack. + */ + rldicl. r10,r12,64-MSR_HV_LG,63 + bne- kvmppc_p9_bad_interrupt + + std r1,HSTATE_SCRATCH1(r13) + std r3,HSTATE_SCRATCH2(r13) + ld r1,HSTATE_HOST_R1(r13) + ld r3,HSTATE_KVM_VCPU(r13) + + std r9,VCPU_CR(r3) + +1: + std r11,VCPU_PC(r3) + std r12,VCPU_MSR(r3) + + reg = 14 + .rept 18 + std reg,__VCPU_GPR(reg)(r3) + reg = reg + 1 + .endr + + /* r1, r3, r9-r13 are saved to vcpu by C code */ + std r0,VCPU_GPR(R0)(r3) + std r2,VCPU_GPR(R2)(r3) + reg = 4 + .rept 5 + std reg,__VCPU_GPR(reg)(r3) + reg = reg + 1 + .endr + + ld r2,PACATOC(r13) + + mflr r4 + std r4,VCPU_LR(r3) + mfspr r4,SPRN_XER + std r4,VCPU_XER(r3) + + reg = 14 + .rept 18 + ld reg,STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1) + reg = reg + 1 + .endr + + lwz r4,SFS+8(r1) + mtcr r4 + + /* + * Flush the link stack here, before executing the first blr on the + * way out of the guest. + * + * The link stack won't match coming out of the guest anyway so the + * only cost is the flush itself. The call clobbers r0. + */ +1: nop + patch_site 1b patch__call_kvm_flush_link_stack_p9 + + addi r1,r1,SFS + ld r0,PPC_LR_STKOFF(r1) + mtlr r0 + blr + +/* + * Took an interrupt somewhere right before HRFID to guest, so registers are + * in a bad way. Return things hopefully enough to run host virtual code and + * run the Linux interrupt handler (SRESET or MCE) to print something useful. + * + * We could be really clever and save all host registers in known locations + * before setting HSTATE_IN_GUEST, then restoring them all here, and setting + * return address to a fixup that sets them up again. But that's a lot of + * effort for a small bit of code. Lots of other things to do first. + */ +kvmppc_p9_bad_interrupt: +BEGIN_MMU_FTR_SECTION + /* + * Hash host doesn't try to recover MMU (requires host SLB reload) + */ + b . +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) + /* + * Clean up guest registers to give host a chance to run. + */ + li r10,0 + mtspr SPRN_AMR,r10 + mtspr SPRN_IAMR,r10 + mtspr SPRN_CIABR,r10 + mtspr SPRN_DAWRX0,r10 +BEGIN_FTR_SECTION + mtspr SPRN_DAWRX1,r10 +END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) + mtspr SPRN_PID,r10 + + /* + * Switch to host MMU mode + */ + ld r10, HSTATE_KVM_VCPU(r13) + ld r10, VCPU_KVM(r10) + lwz r10, KVM_HOST_LPID(r10) + mtspr SPRN_LPID,r10 + + ld r10, HSTATE_KVM_VCPU(r13) + ld r10, VCPU_KVM(r10) + ld r10, KVM_HOST_LPCR(r10) + mtspr SPRN_LPCR,r10 + + /* + * Set GUEST_MODE_NONE so the handler won't branch to KVM, and clear + * MSR_RI in r12 ([H]SRR1) so the handler won't try to return. + */ + li r10,KVM_GUEST_MODE_NONE + stb r10,HSTATE_IN_GUEST(r13) + li r10,MSR_RI + andc r12,r12,r10 + + /* + * Go back to interrupt handler. MCE and SRESET have their specific + * PACA save area so they should be used directly. They set up their + * own stack. The other handlers all use EXGEN. They will use the + * guest r1 if it looks like a kernel stack, so just load the + * emergency stack and go to program check for all other interrupts. + */ + ld r10,HSTATE_SCRATCH0(r13) + cmpwi r10,BOOK3S_INTERRUPT_MACHINE_CHECK + beq machine_check_common + + cmpwi r10,BOOK3S_INTERRUPT_SYSTEM_RESET + beq system_reset_common + + b . +#endif diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 2d9193cd73be..c63e263312a4 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -840,7 +840,7 @@ bool kvm_unmap_gfn_range_hv(struct kvm *kvm, struct kvm_gfn_range *range) kvm_unmap_radix(kvm, range->slot, gfn); } else { for (gfn = range->start; gfn < range->end; gfn++) - kvm_unmap_rmapp(kvm, range->slot, range->start); + kvm_unmap_rmapp(kvm, range->slot, gfn); } return false; diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index d909c069363e..b5905ae4377c 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -21,6 +21,7 @@ #include <asm/pte-walk.h> #include <asm/ultravisor.h> #include <asm/kvm_book3s_uvmem.h> +#include <asm/plpar_wrappers.h> /* * Supported radix tree geometry. @@ -318,9 +319,19 @@ void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr, } psi = shift_to_mmu_psize(pshift); - rb = addr | (mmu_get_ap(psi) << PPC_BITLSHIFT(58)); - rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(0, 0, 1), - lpid, rb); + + if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE)) { + rb = addr | (mmu_get_ap(psi) << PPC_BITLSHIFT(58)); + rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(0, 0, 1), + lpid, rb); + } else { + rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU, + H_RPTI_TYPE_NESTED | + H_RPTI_TYPE_TLB, + psize_to_rpti_pgsize(psi), + addr, addr + psize); + } + if (rc) pr_err("KVM: TLB page invalidation hcall failed, rc=%ld\n", rc); } @@ -334,8 +345,14 @@ static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid) return; } - rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(1, 0, 1), - lpid, TLBIEL_INVAL_SET_LPID); + if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE)) + rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(1, 0, 1), + lpid, TLBIEL_INVAL_SET_LPID); + else + rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU, + H_RPTI_TYPE_NESTED | + H_RPTI_TYPE_PWC, H_RPTI_PAGE_ALL, + 0, -1UL); if (rc) pr_err("KVM: TLB PWC invalidation hcall failed, rc=%ld\n", rc); } diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 083a4e037718..dc6591548f0c 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -391,10 +391,6 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, /* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */ /* liobn, ioba, tce); */ - /* For radix, we might be in virtual mode, so punt */ - if (kvm_is_radix(vcpu->kvm)) - return H_TOO_HARD; - stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -489,10 +485,6 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, bool prereg = false; struct kvmppc_spapr_tce_iommu_table *stit; - /* For radix, we might be in virtual mode, so punt */ - if (kvm_is_radix(vcpu->kvm)) - return H_TOO_HARD; - /* * used to check for invalidations in progress */ @@ -602,10 +594,6 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, long i, ret; struct kvmppc_spapr_tce_iommu_table *stit; - /* For radix, we might be in virtual mode, so punt */ - if (kvm_is_radix(vcpu->kvm)) - return H_TOO_HARD; - stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 28a80d240b76..cd544a46183e 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -76,6 +76,7 @@ #include <asm/kvm_book3s_uvmem.h> #include <asm/ultravisor.h> #include <asm/dtl.h> +#include <asm/plpar_wrappers.h> #include "book3s.h" @@ -103,13 +104,9 @@ static int target_smt_mode; module_param(target_smt_mode, int, 0644); MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)"); -static bool indep_threads_mode = true; -module_param(indep_threads_mode, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(indep_threads_mode, "Independent-threads mode (only on POWER9)"); - static bool one_vm_per_core; module_param(one_vm_per_core, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(one_vm_per_core, "Only run vCPUs from the same VM on a core (requires indep_threads_mode=N)"); +MODULE_PARM_DESC(one_vm_per_core, "Only run vCPUs from the same VM on a core (requires POWER8 or older)"); #ifdef CONFIG_KVM_XICS static const struct kernel_param_ops module_param_ops = { @@ -134,9 +131,6 @@ static inline bool nesting_enabled(struct kvm *kvm) return kvm->arch.nested_enable && kvm_is_radix(kvm); } -/* If set, the threads on each CPU core have to be in the same MMU mode */ -static bool no_mixing_hpt_and_radix __read_mostly; - static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); /* @@ -236,7 +230,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) waitp = kvm_arch_vcpu_get_wait(vcpu); if (rcuwait_wake_up(waitp)) - ++vcpu->stat.halt_wakeup; + ++vcpu->stat.generic.halt_wakeup; cpu = READ_ONCE(vcpu->arch.thread_cpu); if (cpu >= 0 && kvmppc_ipi_thread(cpu)) @@ -807,7 +801,8 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, * KVM does not support mflags=2 (AIL=2) and AIL=1 is reserved. * Keep this in synch with kvmppc_filter_guest_lpcr_hv. */ - if (mflags != 0 && mflags != 3) + if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG) && + kvmhv_vcpu_is_radix(vcpu) && mflags == 3) return H_UNSUPPORTED_FLAG_START; return H_TOO_HARD; default: @@ -899,6 +894,10 @@ static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target) * H_SUCCESS if the source vcore wasn't idle (e.g. if it may * have useful work to do and should not confer) so we don't * recheck that here. + * + * In the case of the P9 single vcpu per vcore case, the real + * mode handler is not called but no other threads are in the + * source vcore. */ spin_lock(&vcore->lock); @@ -924,8 +923,71 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu) return yield_count; } +/* + * H_RPT_INVALIDATE hcall handler for nested guests. + * + * Handles only nested process-scoped invalidation requests in L0. + */ +static int kvmppc_nested_h_rpt_invalidate(struct kvm_vcpu *vcpu) +{ + unsigned long type = kvmppc_get_gpr(vcpu, 6); + unsigned long pid, pg_sizes, start, end; + + /* + * The partition-scoped invalidations aren't handled here in L0. + */ + if (type & H_RPTI_TYPE_NESTED) + return RESUME_HOST; + + pid = kvmppc_get_gpr(vcpu, 4); + pg_sizes = kvmppc_get_gpr(vcpu, 7); + start = kvmppc_get_gpr(vcpu, 8); + end = kvmppc_get_gpr(vcpu, 9); + + do_h_rpt_invalidate_prt(pid, vcpu->arch.nested->shadow_lpid, + type, pg_sizes, start, end); + + kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + return RESUME_GUEST; +} + +static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu, + unsigned long id, unsigned long target, + unsigned long type, unsigned long pg_sizes, + unsigned long start, unsigned long end) +{ + if (!kvm_is_radix(vcpu->kvm)) + return H_UNSUPPORTED; + + if (end < start) + return H_P5; + + /* + * Partition-scoped invalidation for nested guests. + */ + if (type & H_RPTI_TYPE_NESTED) { + if (!nesting_enabled(vcpu->kvm)) + return H_FUNCTION; + + /* Support only cores as target */ + if (target != H_RPTI_TARGET_CMMU) + return H_P2; + + return do_h_rpt_invalidate_pat(vcpu, id, type, pg_sizes, + start, end); + } + + /* + * Process-scoped invalidation for L1 guests. + */ + do_h_rpt_invalidate_prt(id, vcpu->kvm->arch.lpid, + type, pg_sizes, start, end); + return H_SUCCESS; +} + int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) { + struct kvm *kvm = vcpu->kvm; unsigned long req = kvmppc_get_gpr(vcpu, 3); unsigned long target, ret = H_SUCCESS; int yield_count; @@ -937,11 +999,57 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) return RESUME_HOST; switch (req) { + case H_REMOVE: + ret = kvmppc_h_remove(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_ENTER: + ret = kvmppc_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6), + kvmppc_get_gpr(vcpu, 7)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_READ: + ret = kvmppc_h_read(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_CLEAR_MOD: + ret = kvmppc_h_clear_mod(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_CLEAR_REF: + ret = kvmppc_h_clear_ref(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_PROTECT: + ret = kvmppc_h_protect(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_BULK_REMOVE: + ret = kvmppc_h_bulk_remove(vcpu); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_CEDE: break; case H_PROD: target = kvmppc_get_gpr(vcpu, 4); - tvcpu = kvmppc_find_vcpu(vcpu->kvm, target); + tvcpu = kvmppc_find_vcpu(kvm, target); if (!tvcpu) { ret = H_PARAMETER; break; @@ -955,7 +1063,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) target = kvmppc_get_gpr(vcpu, 4); if (target == -1) break; - tvcpu = kvmppc_find_vcpu(vcpu->kvm, target); + tvcpu = kvmppc_find_vcpu(kvm, target); if (!tvcpu) { ret = H_PARAMETER; break; @@ -971,12 +1079,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) kvmppc_get_gpr(vcpu, 6)); break; case H_RTAS: - if (list_empty(&vcpu->kvm->arch.rtas_tokens)) + if (list_empty(&kvm->arch.rtas_tokens)) return RESUME_HOST; - idx = srcu_read_lock(&vcpu->kvm->srcu); + idx = srcu_read_lock(&kvm->srcu); rc = kvmppc_rtas_hcall(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); + srcu_read_unlock(&kvm->srcu, idx); if (rc == -ENOENT) return RESUME_HOST; @@ -1060,15 +1168,23 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) if (!powernv_get_random_long(&vcpu->arch.regs.gpr[4])) ret = H_HARDWARE; break; + case H_RPT_INVALIDATE: + ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6), + kvmppc_get_gpr(vcpu, 7), + kvmppc_get_gpr(vcpu, 8), + kvmppc_get_gpr(vcpu, 9)); + break; case H_SET_PARTITION_TABLE: ret = H_FUNCTION; - if (nesting_enabled(vcpu->kvm)) + if (nesting_enabled(kvm)) ret = kvmhv_set_partition_table(vcpu); break; case H_ENTER_NESTED: ret = H_FUNCTION; - if (!nesting_enabled(vcpu->kvm)) + if (!nesting_enabled(kvm)) break; ret = kvmhv_enter_nested_guest(vcpu); if (ret == H_INTERRUPT) { @@ -1083,12 +1199,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) break; case H_TLB_INVALIDATE: ret = H_FUNCTION; - if (nesting_enabled(vcpu->kvm)) + if (nesting_enabled(kvm)) ret = kvmhv_do_nested_tlbie(vcpu); break; case H_COPY_TOFROM_GUEST: ret = H_FUNCTION; - if (nesting_enabled(vcpu->kvm)) + if (nesting_enabled(kvm)) ret = kvmhv_copy_tofrom_guest_nested(vcpu); break; case H_PAGE_INIT: @@ -1099,7 +1215,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) case H_SVM_PAGE_IN: ret = H_UNSUPPORTED; if (kvmppc_get_srr1(vcpu) & MSR_S) - ret = kvmppc_h_svm_page_in(vcpu->kvm, + ret = kvmppc_h_svm_page_in(kvm, kvmppc_get_gpr(vcpu, 4), kvmppc_get_gpr(vcpu, 5), kvmppc_get_gpr(vcpu, 6)); @@ -1107,7 +1223,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) case H_SVM_PAGE_OUT: ret = H_UNSUPPORTED; if (kvmppc_get_srr1(vcpu) & MSR_S) - ret = kvmppc_h_svm_page_out(vcpu->kvm, + ret = kvmppc_h_svm_page_out(kvm, kvmppc_get_gpr(vcpu, 4), kvmppc_get_gpr(vcpu, 5), kvmppc_get_gpr(vcpu, 6)); @@ -1115,12 +1231,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) case H_SVM_INIT_START: ret = H_UNSUPPORTED; if (kvmppc_get_srr1(vcpu) & MSR_S) - ret = kvmppc_h_svm_init_start(vcpu->kvm); + ret = kvmppc_h_svm_init_start(kvm); break; case H_SVM_INIT_DONE: ret = H_UNSUPPORTED; if (kvmppc_get_srr1(vcpu) & MSR_S) - ret = kvmppc_h_svm_init_done(vcpu->kvm); + ret = kvmppc_h_svm_init_done(kvm); break; case H_SVM_INIT_ABORT: /* @@ -1130,24 +1246,26 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) * Instead the kvm->arch.secure_guest flag is checked inside * kvmppc_h_svm_init_abort(). */ - ret = kvmppc_h_svm_init_abort(vcpu->kvm); + ret = kvmppc_h_svm_init_abort(kvm); break; default: return RESUME_HOST; } + WARN_ON_ONCE(ret == H_TOO_HARD); kvmppc_set_gpr(vcpu, 3, ret); vcpu->arch.hcall_needed = 0; return RESUME_GUEST; } /* - * Handle H_CEDE in the nested virtualization case where we haven't - * called the real-mode hcall handlers in book3s_hv_rmhandlers.S. + * Handle H_CEDE in the P9 path where we don't call the real-mode hcall + * handlers in book3s_hv_rmhandlers.S. + * * This has to be done early, not in kvmppc_pseries_do_hcall(), so * that the cede logic in kvmppc_run_single_vcpu() works properly. */ -static void kvmppc_nested_cede(struct kvm_vcpu *vcpu) +static void kvmppc_cede(struct kvm_vcpu *vcpu) { vcpu->arch.shregs.msr |= MSR_EE; vcpu->arch.ceded = 1; @@ -1178,6 +1296,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd) case H_XIRR_X: #endif case H_PAGE_INIT: + case H_RPT_INVALIDATE: return 1; } @@ -1400,13 +1519,39 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, } case BOOK3S_INTERRUPT_SYSCALL: { - /* hcall - punt to userspace */ int i; - /* hypercall with MSR_PR has already been handled in rmode, - * and never reaches here. - */ + if (unlikely(vcpu->arch.shregs.msr & MSR_PR)) { + /* + * Guest userspace executed sc 1. This can only be + * reached by the P9 path because the old path + * handles this case in realmode hcall handlers. + */ + if (!kvmhv_vcpu_is_radix(vcpu)) { + /* + * A guest could be running PR KVM, so this + * may be a PR KVM hcall. It must be reflected + * to the guest kernel as a sc interrupt. + */ + kvmppc_core_queue_syscall(vcpu); + } else { + /* + * Radix guests can not run PR KVM or nested HV + * hash guests which might run PR KVM, so this + * is always a privilege fault. Send a program + * check to guest kernel. + */ + kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV); + } + r = RESUME_GUEST; + break; + } + /* + * hcall - gather args and set exit_reason. This will next be + * handled by kvmppc_pseries_do_hcall which may be able to deal + * with it and resume guest, or may punt to userspace. + */ run->papr_hcall.nr = kvmppc_get_gpr(vcpu, 3); for (i = 0; i < 9; ++i) run->papr_hcall.args[i] = kvmppc_get_gpr(vcpu, 4 + i); @@ -1419,20 +1564,102 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * We get these next two if the guest accesses a page which it thinks * it has mapped but which is not actually present, either because * it is for an emulated I/O device or because the corresonding - * host page has been paged out. Any other HDSI/HISI interrupts - * have been handled already. + * host page has been paged out. + * + * Any other HDSI/HISI interrupts have been handled already for P7/8 + * guests. For POWER9 hash guests not using rmhandlers, basic hash + * fault handling is done here. */ - case BOOK3S_INTERRUPT_H_DATA_STORAGE: - r = RESUME_PAGE_FAULT; + case BOOK3S_INTERRUPT_H_DATA_STORAGE: { + unsigned long vsid; + long err; + + if (vcpu->arch.fault_dsisr == HDSISR_CANARY) { + r = RESUME_GUEST; /* Just retry if it's the canary */ + break; + } + + if (kvm_is_radix(vcpu->kvm) || !cpu_has_feature(CPU_FTR_ARCH_300)) { + /* + * Radix doesn't require anything, and pre-ISAv3.0 hash + * already attempted to handle this in rmhandlers. The + * hash fault handling below is v3 only (it uses ASDR + * via fault_gpa). + */ + r = RESUME_PAGE_FAULT; + break; + } + + if (!(vcpu->arch.fault_dsisr & (DSISR_NOHPTE | DSISR_PROTFAULT))) { + kvmppc_core_queue_data_storage(vcpu, + vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); + r = RESUME_GUEST; + break; + } + + if (!(vcpu->arch.shregs.msr & MSR_DR)) + vsid = vcpu->kvm->arch.vrma_slb_v; + else + vsid = vcpu->arch.fault_gpa; + + err = kvmppc_hpte_hv_fault(vcpu, vcpu->arch.fault_dar, + vsid, vcpu->arch.fault_dsisr, true); + if (err == 0) { + r = RESUME_GUEST; + } else if (err == -1 || err == -2) { + r = RESUME_PAGE_FAULT; + } else { + kvmppc_core_queue_data_storage(vcpu, + vcpu->arch.fault_dar, err); + r = RESUME_GUEST; + } break; - case BOOK3S_INTERRUPT_H_INST_STORAGE: + } + case BOOK3S_INTERRUPT_H_INST_STORAGE: { + unsigned long vsid; + long err; + vcpu->arch.fault_dar = kvmppc_get_pc(vcpu); vcpu->arch.fault_dsisr = vcpu->arch.shregs.msr & DSISR_SRR1_MATCH_64S; - if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE) - vcpu->arch.fault_dsisr |= DSISR_ISSTORE; - r = RESUME_PAGE_FAULT; + if (kvm_is_radix(vcpu->kvm) || !cpu_has_feature(CPU_FTR_ARCH_300)) { + /* + * Radix doesn't require anything, and pre-ISAv3.0 hash + * already attempted to handle this in rmhandlers. The + * hash fault handling below is v3 only (it uses ASDR + * via fault_gpa). + */ + if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE) + vcpu->arch.fault_dsisr |= DSISR_ISSTORE; + r = RESUME_PAGE_FAULT; + break; + } + + if (!(vcpu->arch.fault_dsisr & SRR1_ISI_NOPT)) { + kvmppc_core_queue_inst_storage(vcpu, + vcpu->arch.fault_dsisr); + r = RESUME_GUEST; + break; + } + + if (!(vcpu->arch.shregs.msr & MSR_IR)) + vsid = vcpu->kvm->arch.vrma_slb_v; + else + vsid = vcpu->arch.fault_gpa; + + err = kvmppc_hpte_hv_fault(vcpu, vcpu->arch.fault_dar, + vsid, vcpu->arch.fault_dsisr, false); + if (err == 0) { + r = RESUME_GUEST; + } else if (err == -1) { + r = RESUME_PAGE_FAULT; + } else { + kvmppc_core_queue_inst_storage(vcpu, err); + r = RESUME_GUEST; + } break; + } + /* * This occurs if the guest executes an illegal instruction. * If the guest debug is disabled, generate a program interrupt @@ -1593,6 +1820,23 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) if (!xics_on_xive()) kvmppc_xics_rm_complete(vcpu, 0); break; + case BOOK3S_INTERRUPT_SYSCALL: + { + unsigned long req = kvmppc_get_gpr(vcpu, 3); + + /* + * The H_RPT_INVALIDATE hcalls issued by nested + * guests for process-scoped invalidations when + * GTSE=0, are handled here in L0. + */ + if (req == H_RPT_INVALIDATE) { + r = kvmppc_nested_h_rpt_invalidate(vcpu); + break; + } + + r = RESUME_HOST; + break; + } default: r = RESUME_HOST; break; @@ -1654,6 +1898,14 @@ unsigned long kvmppc_filter_lpcr_hv(struct kvm *kvm, unsigned long lpcr) lpcr &= ~LPCR_AIL; if ((lpcr & LPCR_AIL) != LPCR_AIL_3) lpcr &= ~LPCR_AIL; /* LPCR[AIL]=1/2 is disallowed */ + /* + * On some POWER9s we force AIL off for radix guests to prevent + * executing in MSR[HV]=1 mode with the MMU enabled and PIDR set to + * guest, which can result in Q0 translations with LPID=0 PID=PIDR to + * be cached, which the host TLB management does not expect. + */ + if (kvm_is_radix(kvm) && cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) + lpcr &= ~LPCR_AIL; /* * On POWER9, allow userspace to enable large decrementer for the @@ -2233,7 +2485,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, */ static int threads_per_vcore(struct kvm *kvm) { - if (kvm->arch.threads_indep) + if (cpu_has_feature(CPU_FTR_ARCH_300)) return 1; return threads_per_subcore; } @@ -2657,7 +2909,7 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) cpumask_t *cpu_in_guest; int i; - cpu = cpu_first_thread_sibling(cpu); + cpu = cpu_first_tlb_thread_sibling(cpu); if (nested) { cpumask_set_cpu(cpu, &nested->need_tlb_flush); cpu_in_guest = &nested->cpu_in_guest; @@ -2671,9 +2923,10 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) * the other side is the first smp_mb() in kvmppc_run_core(). */ smp_mb(); - for (i = 0; i < threads_per_core; ++i) - if (cpumask_test_cpu(cpu + i, cpu_in_guest)) - smp_call_function_single(cpu + i, do_nothing, NULL, 1); + for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu); + i += cpu_tlb_thread_sibling_step()) + if (cpumask_test_cpu(i, cpu_in_guest)) + smp_call_function_single(i, do_nothing, NULL, 1); } static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) @@ -2704,8 +2957,8 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) */ if (prev_cpu != pcpu) { if (prev_cpu >= 0 && - cpu_first_thread_sibling(prev_cpu) != - cpu_first_thread_sibling(pcpu)) + cpu_first_tlb_thread_sibling(prev_cpu) != + cpu_first_tlb_thread_sibling(pcpu)) radix_flush_cpu(kvm, prev_cpu, vcpu); if (nested) nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu; @@ -2967,9 +3220,6 @@ static void prepare_threads(struct kvmppc_vcore *vc) for_each_runnable_thread(i, vcpu, vc) { if (signal_pending(vcpu->arch.run_task)) vcpu->arch.ret = -EINTR; - else if (no_mixing_hpt_and_radix && - kvm_is_radix(vc->kvm) != radix_enabled()) - vcpu->arch.ret = -EINVAL; else if (vcpu->arch.vpa.update_pending || vcpu->arch.slb_shadow.update_pending || vcpu->arch.dtl.update_pending) @@ -3176,6 +3426,9 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) int trap; bool is_power8; + if (WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300))) + return; + /* * Remove from the list any threads that have a signal pending * or need a VPA update done @@ -3203,9 +3456,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) * Make sure we are running on primary threads, and that secondary * threads are offline. Also check if the number of threads in this * guest are greater than the current system threads per guest. - * On POWER9, we need to be not in independent-threads mode if - * this is a HPT guest on a radix host machine where the - * CPU threads may not be in different MMU modes. */ if ((controlled_threads > 1) && ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) { @@ -3230,18 +3480,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) collect_piggybacks(&core_info, target_threads); /* - * On radix, arrange for TLB flushing if necessary. - * This has to be done before disabling interrupts since - * it uses smp_call_function(). - */ - pcpu = smp_processor_id(); - if (kvm_is_radix(vc->kvm)) { - for (sub = 0; sub < core_info.n_subcores; ++sub) - for_each_runnable_thread(i, vcpu, core_info.vc[sub]) - kvmppc_prepare_radix_vcpu(vcpu, pcpu); - } - - /* * Hard-disable interrupts, and check resched flag and signals. * If we need to reschedule or deliver a signal, clean up * and return without going into the guest(s). @@ -3273,8 +3511,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) cmd_bit = stat_bit = 0; split = core_info.n_subcores; sip = NULL; - is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S) - && !cpu_has_feature(CPU_FTR_ARCH_300); + is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S); if (split > 1) { sip = &split_info; @@ -3478,184 +3715,113 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) trace_kvmppc_run_core(vc, 1); } -/* - * Load up hypervisor-mode registers on P9. - */ -static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit, - unsigned long lpcr) +static void load_spr_state(struct kvm_vcpu *vcpu) { - struct kvmppc_vcore *vc = vcpu->arch.vcore; - s64 hdec; - u64 tb, purr, spurr; - int trap; - unsigned long host_hfscr = mfspr(SPRN_HFSCR); - unsigned long host_ciabr = mfspr(SPRN_CIABR); - unsigned long host_dawr0 = mfspr(SPRN_DAWR0); - unsigned long host_dawrx0 = mfspr(SPRN_DAWRX0); - unsigned long host_psscr = mfspr(SPRN_PSSCR); - unsigned long host_pidr = mfspr(SPRN_PID); - unsigned long host_dawr1 = 0; - unsigned long host_dawrx1 = 0; - - if (cpu_has_feature(CPU_FTR_DAWR1)) { - host_dawr1 = mfspr(SPRN_DAWR1); - host_dawrx1 = mfspr(SPRN_DAWRX1); - } + mtspr(SPRN_DSCR, vcpu->arch.dscr); + mtspr(SPRN_IAMR, vcpu->arch.iamr); + mtspr(SPRN_PSPB, vcpu->arch.pspb); + mtspr(SPRN_FSCR, vcpu->arch.fscr); + mtspr(SPRN_TAR, vcpu->arch.tar); + mtspr(SPRN_EBBHR, vcpu->arch.ebbhr); + mtspr(SPRN_EBBRR, vcpu->arch.ebbrr); + mtspr(SPRN_BESCR, vcpu->arch.bescr); + mtspr(SPRN_WORT, vcpu->arch.wort); + mtspr(SPRN_TIDR, vcpu->arch.tid); + mtspr(SPRN_AMR, vcpu->arch.amr); + mtspr(SPRN_UAMOR, vcpu->arch.uamor); /* - * P8 and P9 suppress the HDEC exception when LPCR[HDICE] = 0, - * so set HDICE before writing HDEC. + * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI] + * clear (or hstate set appropriately to catch those registers + * being clobbered if we take a MCE or SRESET), so those are done + * later. */ - mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr | LPCR_HDICE); - isync(); - - hdec = time_limit - mftb(); - if (hdec < 0) { - mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr); - isync(); - return BOOK3S_INTERRUPT_HV_DECREMENTER; - } - mtspr(SPRN_HDEC, hdec); - - if (vc->tb_offset) { - u64 new_tb = mftb() + vc->tb_offset; - mtspr(SPRN_TBU40, new_tb); - tb = mftb(); - if ((tb & 0xffffff) < (new_tb & 0xffffff)) - mtspr(SPRN_TBU40, new_tb + 0x1000000); - vc->tb_offset_applied = vc->tb_offset; - } - - if (vc->pcr) - mtspr(SPRN_PCR, vc->pcr | PCR_MASK); - mtspr(SPRN_DPDES, vc->dpdes); - mtspr(SPRN_VTB, vc->vtb); - - local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR); - local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR); - mtspr(SPRN_PURR, vcpu->arch.purr); - mtspr(SPRN_SPURR, vcpu->arch.spurr); - - if (dawr_enabled()) { - mtspr(SPRN_DAWR0, vcpu->arch.dawr0); - mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0); - if (cpu_has_feature(CPU_FTR_DAWR1)) { - mtspr(SPRN_DAWR1, vcpu->arch.dawr1); - mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1); - } - } - mtspr(SPRN_CIABR, vcpu->arch.ciabr); - mtspr(SPRN_IC, vcpu->arch.ic); - mtspr(SPRN_PID, vcpu->arch.pid); - mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC | - (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); - - mtspr(SPRN_HFSCR, vcpu->arch.hfscr); - - mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0); - mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1); - mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2); - mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3); - - mtspr(SPRN_AMOR, ~0UL); - - mtspr(SPRN_LPCR, lpcr); - isync(); - - kvmppc_xive_push_vcpu(vcpu); - - mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0); - mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1); - - trap = __kvmhv_vcpu_entry_p9(vcpu); - - /* Advance host PURR/SPURR by the amount used by guest */ - purr = mfspr(SPRN_PURR); - spurr = mfspr(SPRN_SPURR); - mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr + - purr - vcpu->arch.purr); - mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr + - spurr - vcpu->arch.spurr); - vcpu->arch.purr = purr; - vcpu->arch.spurr = spurr; + if (!(vcpu->arch.ctrl & 1)) + mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1); +} - vcpu->arch.ic = mfspr(SPRN_IC); - vcpu->arch.pid = mfspr(SPRN_PID); - vcpu->arch.psscr = mfspr(SPRN_PSSCR) & PSSCR_GUEST_VIS; +static void store_spr_state(struct kvm_vcpu *vcpu) +{ + vcpu->arch.ctrl = mfspr(SPRN_CTRLF); - vcpu->arch.shregs.sprg0 = mfspr(SPRN_SPRG0); - vcpu->arch.shregs.sprg1 = mfspr(SPRN_SPRG1); - vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2); - vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3); + vcpu->arch.iamr = mfspr(SPRN_IAMR); + vcpu->arch.pspb = mfspr(SPRN_PSPB); + vcpu->arch.fscr = mfspr(SPRN_FSCR); + vcpu->arch.tar = mfspr(SPRN_TAR); + vcpu->arch.ebbhr = mfspr(SPRN_EBBHR); + vcpu->arch.ebbrr = mfspr(SPRN_EBBRR); + vcpu->arch.bescr = mfspr(SPRN_BESCR); + vcpu->arch.wort = mfspr(SPRN_WORT); + vcpu->arch.tid = mfspr(SPRN_TIDR); + vcpu->arch.amr = mfspr(SPRN_AMR); + vcpu->arch.uamor = mfspr(SPRN_UAMOR); + vcpu->arch.dscr = mfspr(SPRN_DSCR); +} - /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ - mtspr(SPRN_PSSCR, host_psscr | - (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); - mtspr(SPRN_HFSCR, host_hfscr); - mtspr(SPRN_CIABR, host_ciabr); - mtspr(SPRN_DAWR0, host_dawr0); - mtspr(SPRN_DAWRX0, host_dawrx0); - if (cpu_has_feature(CPU_FTR_DAWR1)) { - mtspr(SPRN_DAWR1, host_dawr1); - mtspr(SPRN_DAWRX1, host_dawrx1); - } - mtspr(SPRN_PID, host_pidr); +/* + * Privileged (non-hypervisor) host registers to save. + */ +struct p9_host_os_sprs { + unsigned long dscr; + unsigned long tidr; + unsigned long iamr; + unsigned long amr; + unsigned long fscr; +}; - /* - * Since this is radix, do a eieio; tlbsync; ptesync sequence in - * case we interrupted the guest between a tlbie and a ptesync. - */ - asm volatile("eieio; tlbsync; ptesync"); +static void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs) +{ + host_os_sprs->dscr = mfspr(SPRN_DSCR); + host_os_sprs->tidr = mfspr(SPRN_TIDR); + host_os_sprs->iamr = mfspr(SPRN_IAMR); + host_os_sprs->amr = mfspr(SPRN_AMR); + host_os_sprs->fscr = mfspr(SPRN_FSCR); +} - /* - * cp_abort is required if the processor supports local copy-paste - * to clear the copy buffer that was under control of the guest. - */ - if (cpu_has_feature(CPU_FTR_ARCH_31)) - asm volatile(PPC_CP_ABORT); +/* vcpu guest regs must already be saved */ +static void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + mtspr(SPRN_PSPB, 0); + mtspr(SPRN_WORT, 0); + mtspr(SPRN_UAMOR, 0); - mtspr(SPRN_LPID, vcpu->kvm->arch.host_lpid); /* restore host LPID */ - isync(); + mtspr(SPRN_DSCR, host_os_sprs->dscr); + mtspr(SPRN_TIDR, host_os_sprs->tidr); + mtspr(SPRN_IAMR, host_os_sprs->iamr); - vc->dpdes = mfspr(SPRN_DPDES); - vc->vtb = mfspr(SPRN_VTB); - mtspr(SPRN_DPDES, 0); - if (vc->pcr) - mtspr(SPRN_PCR, PCR_MASK); + if (host_os_sprs->amr != vcpu->arch.amr) + mtspr(SPRN_AMR, host_os_sprs->amr); - if (vc->tb_offset_applied) { - u64 new_tb = mftb() - vc->tb_offset_applied; - mtspr(SPRN_TBU40, new_tb); - tb = mftb(); - if ((tb & 0xffffff) < (new_tb & 0xffffff)) - mtspr(SPRN_TBU40, new_tb + 0x1000000); - vc->tb_offset_applied = 0; - } + if (host_os_sprs->fscr != vcpu->arch.fscr) + mtspr(SPRN_FSCR, host_os_sprs->fscr); - mtspr(SPRN_HDEC, 0x7fffffff); - mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr); + /* Save guest CTRL register, set runlatch to 1 */ + if (!(vcpu->arch.ctrl & 1)) + mtspr(SPRN_CTRLT, 1); +} - return trap; +static inline bool hcall_is_xics(unsigned long req) +{ + return req == H_EOI || req == H_CPPR || req == H_IPI || + req == H_IPOLL || req == H_XIRR || req == H_XIRR_X; } /* - * Virtual-mode guest entry for POWER9 and later when the host and - * guest are both using the radix MMU. The LPIDR has already been set. + * Guest entry for POWER9 and later CPUs. */ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr) { struct kvmppc_vcore *vc = vcpu->arch.vcore; - unsigned long host_dscr = mfspr(SPRN_DSCR); - unsigned long host_tidr = mfspr(SPRN_TIDR); - unsigned long host_iamr = mfspr(SPRN_IAMR); - unsigned long host_amr = mfspr(SPRN_AMR); - unsigned long host_fscr = mfspr(SPRN_FSCR); + struct p9_host_os_sprs host_os_sprs; s64 dec; u64 tb; int trap, save_pmu; + WARN_ON_ONCE(vcpu->arch.ceded); + dec = mfspr(SPRN_DEC); tb = mftb(); if (dec < 0) @@ -3664,7 +3830,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, if (local_paca->kvm_hstate.dec_expires < time_limit) time_limit = local_paca->kvm_hstate.dec_expires; - vcpu->arch.ceded = 0; + save_p9_host_os_sprs(&host_os_sprs); kvmhv_save_host_pmu(); /* saves it to PACA kvm_hstate */ @@ -3693,24 +3859,20 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, #endif mtspr(SPRN_VRSAVE, vcpu->arch.vrsave); - mtspr(SPRN_DSCR, vcpu->arch.dscr); - mtspr(SPRN_IAMR, vcpu->arch.iamr); - mtspr(SPRN_PSPB, vcpu->arch.pspb); - mtspr(SPRN_FSCR, vcpu->arch.fscr); - mtspr(SPRN_TAR, vcpu->arch.tar); - mtspr(SPRN_EBBHR, vcpu->arch.ebbhr); - mtspr(SPRN_EBBRR, vcpu->arch.ebbrr); - mtspr(SPRN_BESCR, vcpu->arch.bescr); - mtspr(SPRN_WORT, vcpu->arch.wort); - mtspr(SPRN_TIDR, vcpu->arch.tid); - mtspr(SPRN_DAR, vcpu->arch.shregs.dar); - mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); - mtspr(SPRN_AMR, vcpu->arch.amr); - mtspr(SPRN_UAMOR, vcpu->arch.uamor); - - if (!(vcpu->arch.ctrl & 1)) - mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1); + load_spr_state(vcpu); + /* + * When setting DEC, we must always deal with irq_work_raise via NMI vs + * setting DEC. The problem occurs right as we switch into guest mode + * if a NMI hits and sets pending work and sets DEC, then that will + * apply to the guest and not bring us back to the host. + * + * irq_work_raise could check a flag (or possibly LPCR[HDICE] for + * example) and set HDEC to 1? That wouldn't solve the nested hv + * case which needs to abort the hcall or zero the time limit. + * + * XXX: Another day's problem. + */ mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb()); if (kvmhv_on_pseries()) { @@ -3718,7 +3880,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, * We need to save and restore the guest visible part of the * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor * doesn't do this for us. Note only required if pseries since - * this is done in kvmhv_load_hv_regs_and_go() below otherwise. + * this is done in kvmhv_vcpu_entry_p9() below otherwise. */ unsigned long host_psscr; /* call our hypervisor to load up HV regs and go */ @@ -3738,6 +3900,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, hvregs.vcpu_token = vcpu->vcpu_id; } hvregs.hdec_expiry = time_limit; + mtspr(SPRN_DAR, vcpu->arch.shregs.dar); + mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), __pa(&vcpu->arch.regs)); kvmhv_restore_hv_return_state(vcpu, &hvregs); @@ -3750,15 +3914,41 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, /* H_CEDE has to be handled now, not later */ if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && kvmppc_get_gpr(vcpu, 3) == H_CEDE) { - kvmppc_nested_cede(vcpu); + kvmppc_cede(vcpu); kvmppc_set_gpr(vcpu, 3, 0); trap = 0; } } else { - trap = kvmhv_load_hv_regs_and_go(vcpu, time_limit, lpcr); + kvmppc_xive_push_vcpu(vcpu); + trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr); + if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && + !(vcpu->arch.shregs.msr & MSR_PR)) { + unsigned long req = kvmppc_get_gpr(vcpu, 3); + + /* H_CEDE has to be handled now, not later */ + if (req == H_CEDE) { + kvmppc_cede(vcpu); + kvmppc_xive_rearm_escalation(vcpu); /* may un-cede */ + kvmppc_set_gpr(vcpu, 3, 0); + trap = 0; + + /* XICS hcalls must be handled before xive is pulled */ + } else if (hcall_is_xics(req)) { + int ret; + + ret = kvmppc_xive_xics_hcall(vcpu, req); + if (ret != H_TOO_HARD) { + kvmppc_set_gpr(vcpu, 3, ret); + trap = 0; + } + } + } + kvmppc_xive_pull_vcpu(vcpu); + + if (kvm_is_radix(vcpu->kvm)) + vcpu->arch.slb_max = 0; } - vcpu->arch.slb_max = 0; dec = mfspr(SPRN_DEC); if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ dec = (s32) dec; @@ -3766,36 +3956,10 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.dec_expires = dec + tb; vcpu->cpu = -1; vcpu->arch.thread_cpu = -1; - /* Save guest CTRL register, set runlatch to 1 */ - vcpu->arch.ctrl = mfspr(SPRN_CTRLF); - if (!(vcpu->arch.ctrl & 1)) - mtspr(SPRN_CTRLT, vcpu->arch.ctrl | 1); - - vcpu->arch.iamr = mfspr(SPRN_IAMR); - vcpu->arch.pspb = mfspr(SPRN_PSPB); - vcpu->arch.fscr = mfspr(SPRN_FSCR); - vcpu->arch.tar = mfspr(SPRN_TAR); - vcpu->arch.ebbhr = mfspr(SPRN_EBBHR); - vcpu->arch.ebbrr = mfspr(SPRN_EBBRR); - vcpu->arch.bescr = mfspr(SPRN_BESCR); - vcpu->arch.wort = mfspr(SPRN_WORT); - vcpu->arch.tid = mfspr(SPRN_TIDR); - vcpu->arch.amr = mfspr(SPRN_AMR); - vcpu->arch.uamor = mfspr(SPRN_UAMOR); - vcpu->arch.dscr = mfspr(SPRN_DSCR); - mtspr(SPRN_PSPB, 0); - mtspr(SPRN_WORT, 0); - mtspr(SPRN_UAMOR, 0); - mtspr(SPRN_DSCR, host_dscr); - mtspr(SPRN_TIDR, host_tidr); - mtspr(SPRN_IAMR, host_iamr); + store_spr_state(vcpu); - if (host_amr != vcpu->arch.amr) - mtspr(SPRN_AMR, host_amr); - - if (host_fscr != vcpu->arch.fscr) - mtspr(SPRN_FSCR, host_fscr); + restore_p9_host_os_sprs(vcpu, &host_os_sprs); msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX); store_fp_state(&vcpu->arch.fp); @@ -3825,6 +3989,9 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vc->in_guest = 0; mtspr(SPRN_DEC, local_paca->kvm_hstate.dec_expires - mftb()); + /* We may have raced with new irq work */ + if (test_irq_work_pending()) + set_dec(1); mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso); kvmhv_load_host_pmu(); @@ -3925,7 +4092,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) cur = start_poll = ktime_get(); if (vc->halt_poll_ns) { ktime_t stop = ktime_add_ns(start_poll, vc->halt_poll_ns); - ++vc->runner->stat.halt_attempted_poll; + ++vc->runner->stat.generic.halt_attempted_poll; vc->vcore_state = VCORE_POLLING; spin_unlock(&vc->lock); @@ -3936,13 +4103,13 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) break; } cur = ktime_get(); - } while (single_task_running() && ktime_before(cur, stop)); + } while (kvm_vcpu_can_poll(cur, stop)); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; if (!do_sleep) { - ++vc->runner->stat.halt_successful_poll; + ++vc->runner->stat.generic.halt_successful_poll; goto out; } } @@ -3954,7 +4121,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) do_sleep = 0; /* If we polled, count this as a successful poll */ if (vc->halt_poll_ns) - ++vc->runner->stat.halt_successful_poll; + ++vc->runner->stat.generic.halt_successful_poll; goto out; } @@ -3981,13 +4148,13 @@ out: ktime_to_ns(cur) - ktime_to_ns(start_wait); /* Attribute failed poll time */ if (vc->halt_poll_ns) - vc->runner->stat.halt_poll_fail_ns += + vc->runner->stat.generic.halt_poll_fail_ns += ktime_to_ns(start_wait) - ktime_to_ns(start_poll); } else { /* Attribute successful poll time */ if (vc->halt_poll_ns) - vc->runner->stat.halt_poll_success_ns += + vc->runner->stat.generic.halt_poll_success_ns += ktime_to_ns(cur) - ktime_to_ns(start_poll); } @@ -4014,7 +4181,6 @@ out: /* * This never fails for a radix guest, as none of the operations it does * for a radix guest can fail or have a way to report failure. - * kvmhv_run_single_vcpu() relies on this fact. */ static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu) { @@ -4170,7 +4336,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, { struct kvm_run *run = vcpu->run; int trap, r, pcpu; - int srcu_idx, lpid; + int srcu_idx; struct kvmppc_vcore *vc; struct kvm *kvm = vcpu->kvm; struct kvm_nested_guest *nested = vcpu->arch.nested; @@ -4193,8 +4359,15 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, vc->runner = vcpu; /* See if the MMU is ready to go */ - if (!kvm->arch.mmu_ready) - kvmhv_setup_mmu(vcpu); + if (!kvm->arch.mmu_ready) { + r = kvmhv_setup_mmu(vcpu); + if (r) { + run->exit_reason = KVM_EXIT_FAIL_ENTRY; + run->fail_entry.hardware_entry_failure_reason = 0; + vcpu->arch.ret = r; + return r; + } + } if (need_resched()) cond_resched(); @@ -4207,7 +4380,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, preempt_disable(); pcpu = smp_processor_id(); vc->pcpu = pcpu; - kvmppc_prepare_radix_vcpu(vcpu, pcpu); + if (kvm_is_radix(kvm)) + kvmppc_prepare_radix_vcpu(vcpu, pcpu); local_irq_disable(); hard_irq_disable(); @@ -4244,13 +4418,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, vc->vcore_state = VCORE_RUNNING; trace_kvmppc_run_core(vc, 0); - if (cpu_has_feature(CPU_FTR_HVMODE)) { - lpid = nested ? nested->shadow_lpid : kvm->arch.lpid; - mtspr(SPRN_LPID, lpid); - isync(); - kvmppc_check_need_tlb_flush(kvm, pcpu, nested); - } - guest_enter_irqoff(); srcu_idx = srcu_read_lock(&kvm->srcu); @@ -4269,11 +4436,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, srcu_read_unlock(&kvm->srcu, srcu_idx); - if (cpu_has_feature(CPU_FTR_HVMODE)) { - mtspr(SPRN_LPID, kvm->arch.host_lpid); - isync(); - } - set_irq_happened(trap); kvmppc_set_host_core(pcpu); @@ -4419,19 +4581,23 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; do { - /* - * The TLB prefetch bug fixup is only in the kvmppc_run_vcpu - * path, which also handles hash and dependent threads mode. - */ - if (kvm->arch.threads_indep && kvm_is_radix(kvm) && - !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) + if (cpu_has_feature(CPU_FTR_ARCH_300)) r = kvmhv_run_single_vcpu(vcpu, ~(u64)0, vcpu->arch.vcore->lpcr); else r = kvmppc_run_vcpu(vcpu); - if (run->exit_reason == KVM_EXIT_PAPR_HCALL && - !(vcpu->arch.shregs.msr & MSR_PR)) { + if (run->exit_reason == KVM_EXIT_PAPR_HCALL) { + if (WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_PR)) { + /* + * These should have been caught reflected + * into the guest by now. Final sanity check: + * don't allow userspace to execute hcalls in + * the hypervisor. + */ + r = RESUME_GUEST; + continue; + } trace_kvm_hcall_enter(vcpu); r = kvmppc_pseries_do_hcall(vcpu); trace_kvm_hcall_exit(vcpu, r); @@ -4455,7 +4621,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) mtspr(SPRN_EBBRR, ebb_regs[1]); mtspr(SPRN_BESCR, ebb_regs[2]); mtspr(SPRN_TAR, user_tar); - mtspr(SPRN_FSCR, current->thread.fscr); } mtspr(SPRN_VRSAVE, user_vrsave); @@ -5039,18 +5204,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) /* * Track that we now have a HV mode VM active. This blocks secondary * CPU threads from coming online. - * On POWER9, we only need to do this if the "indep_threads_mode" - * module parameter has been set to N. */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) { - if (!indep_threads_mode && !cpu_has_feature(CPU_FTR_HVMODE)) { - pr_warn("KVM: Ignoring indep_threads_mode=N in nested hypervisor\n"); - kvm->arch.threads_indep = true; - } else { - kvm->arch.threads_indep = indep_threads_mode; - } - } - if (!kvm->arch.threads_indep) + if (!cpu_has_feature(CPU_FTR_ARCH_300)) kvm_hv_vm_activated(); /* @@ -5091,7 +5246,7 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) { debugfs_remove_recursive(kvm->arch.debugfs_dir); - if (!kvm->arch.threads_indep) + if (!cpu_has_feature(CPU_FTR_ARCH_300)) kvm_hv_vm_deactivated(); kvmppc_free_vcores(kvm); @@ -5512,7 +5667,9 @@ static int kvmhv_enable_nested(struct kvm *kvm) { if (!nested) return -EPERM; - if (!cpu_has_feature(CPU_FTR_ARCH_300) || no_mixing_hpt_and_radix) + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return -ENODEV; + if (!radix_enabled()) return -ENODEV; /* kvm == NULL means the caller is testing if the capability exists */ @@ -5675,11 +5832,25 @@ static int kvmhv_enable_dawr1(struct kvm *kvm) static bool kvmppc_hash_v3_possible(void) { - if (radix_enabled() && no_mixing_hpt_and_radix) + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return false; + + if (!cpu_has_feature(CPU_FTR_HVMODE)) return false; - return cpu_has_feature(CPU_FTR_ARCH_300) && - cpu_has_feature(CPU_FTR_HVMODE); + /* + * POWER9 chips before version 2.02 can't have some threads in + * HPT mode and some in radix mode on the same core. + */ + if (radix_enabled()) { + unsigned int pvr = mfspr(SPRN_PVR); + if ((pvr >> 16) == PVR_POWER9 && + (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) || + ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101))) + return false; + } + + return true; } static struct kvmppc_ops kvm_ops_hv = { @@ -5823,18 +5994,6 @@ static int kvmppc_book3s_init_hv(void) if (kvmppc_radix_possible()) r = kvmppc_radix_init(); - /* - * POWER9 chips before version 2.02 can't have some threads in - * HPT mode and some in radix mode on the same core. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) { - unsigned int pvr = mfspr(SPRN_PVR); - if ((pvr >> 16) == PVR_POWER9 && - (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) || - ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101))) - no_mixing_hpt_and_radix = true; - } - r = kvmppc_uvmem_init(); if (r < 0) pr_err("KVM-HV: kvmppc_uvmem_init failed %d\n", r); diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 7a0e33a9c980..be8ef1c5b1bf 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -35,21 +35,6 @@ #include "book3s_xive.h" /* - * The XIVE module will populate these when it loads - */ -unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu); -unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server); -int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server, - unsigned long mfrr); -int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr); -int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr); -EXPORT_SYMBOL_GPL(__xive_vm_h_xirr); -EXPORT_SYMBOL_GPL(__xive_vm_h_ipoll); -EXPORT_SYMBOL_GPL(__xive_vm_h_ipi); -EXPORT_SYMBOL_GPL(__xive_vm_h_cppr); -EXPORT_SYMBOL_GPL(__xive_vm_h_eoi); - -/* * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206) * should be power of 2. */ @@ -196,16 +181,9 @@ int kvmppc_hwrng_present(void) } EXPORT_SYMBOL_GPL(kvmppc_hwrng_present); -long kvmppc_h_random(struct kvm_vcpu *vcpu) +long kvmppc_rm_h_random(struct kvm_vcpu *vcpu) { - int r; - - /* Only need to do the expensive mfmsr() on radix */ - if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR)) - r = powernv_get_random_long(&vcpu->arch.regs.gpr[4]); - else - r = powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4]); - if (r) + if (powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4])) return H_SUCCESS; return H_HARDWARE; @@ -221,15 +199,6 @@ void kvmhv_rm_send_ipi(int cpu) void __iomem *xics_phys; unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); - /* For a nested hypervisor, use the XICS via hcall */ - if (kvmhv_on_pseries()) { - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - plpar_hcall_raw(H_IPI, retbuf, get_hard_smp_processor_id(cpu), - IPI_PRIORITY); - return; - } - /* On POWER9 we can use msgsnd for any destination cpu. */ if (cpu_has_feature(CPU_FTR_ARCH_300)) { msg |= get_hard_smp_processor_id(cpu); @@ -442,19 +411,12 @@ static long kvmppc_read_one_intr(bool *again) return 1; /* Now read the interrupt from the ICP */ - if (kvmhv_on_pseries()) { - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall_raw(H_XIRR, retbuf, 0xFF); - xirr = cpu_to_be32(retbuf[0]); - } else { - xics_phys = local_paca->kvm_hstate.xics_phys; - rc = 0; - if (!xics_phys) - rc = opal_int_get_xirr(&xirr, false); - else - xirr = __raw_rm_readl(xics_phys + XICS_XIRR); - } + xics_phys = local_paca->kvm_hstate.xics_phys; + rc = 0; + if (!xics_phys) + rc = opal_int_get_xirr(&xirr, false); + else + xirr = __raw_rm_readl(xics_phys + XICS_XIRR); if (rc < 0) return 1; @@ -483,13 +445,7 @@ static long kvmppc_read_one_intr(bool *again) */ if (xisr == XICS_IPI) { rc = 0; - if (kvmhv_on_pseries()) { - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - plpar_hcall_raw(H_IPI, retbuf, - hard_smp_processor_id(), 0xff); - plpar_hcall_raw(H_EOI, retbuf, h_xirr); - } else if (xics_phys) { + if (xics_phys) { __raw_rm_writeb(0xff, xics_phys + XICS_MFRR); __raw_rm_writel(xirr, xics_phys + XICS_XIRR); } else { @@ -515,13 +471,7 @@ static long kvmppc_read_one_intr(bool *again) /* We raced with the host, * we need to resend that IPI, bummer */ - if (kvmhv_on_pseries()) { - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - plpar_hcall_raw(H_IPI, retbuf, - hard_smp_processor_id(), - IPI_PRIORITY); - } else if (xics_phys) + if (xics_phys) __raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR); else @@ -541,22 +491,13 @@ static long kvmppc_read_one_intr(bool *again) } #ifdef CONFIG_KVM_XICS -static inline bool is_rm(void) -{ - return !(mfmsr() & MSR_DR); -} - unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xics_on_xive()) { - if (is_rm()) - return xive_rm_h_xirr(vcpu); - if (unlikely(!__xive_vm_h_xirr)) - return H_NOT_AVAILABLE; - return __xive_vm_h_xirr(vcpu); - } else + if (xics_on_xive()) + return xive_rm_h_xirr(vcpu); + else return xics_rm_h_xirr(vcpu); } @@ -565,13 +506,9 @@ unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu) if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; vcpu->arch.regs.gpr[5] = get_tb(); - if (xics_on_xive()) { - if (is_rm()) - return xive_rm_h_xirr(vcpu); - if (unlikely(!__xive_vm_h_xirr)) - return H_NOT_AVAILABLE; - return __xive_vm_h_xirr(vcpu); - } else + if (xics_on_xive()) + return xive_rm_h_xirr(vcpu); + else return xics_rm_h_xirr(vcpu); } @@ -579,13 +516,9 @@ unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xics_on_xive()) { - if (is_rm()) - return xive_rm_h_ipoll(vcpu, server); - if (unlikely(!__xive_vm_h_ipoll)) - return H_NOT_AVAILABLE; - return __xive_vm_h_ipoll(vcpu, server); - } else + if (xics_on_xive()) + return xive_rm_h_ipoll(vcpu, server); + else return H_TOO_HARD; } @@ -594,13 +527,9 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xics_on_xive()) { - if (is_rm()) - return xive_rm_h_ipi(vcpu, server, mfrr); - if (unlikely(!__xive_vm_h_ipi)) - return H_NOT_AVAILABLE; - return __xive_vm_h_ipi(vcpu, server, mfrr); - } else + if (xics_on_xive()) + return xive_rm_h_ipi(vcpu, server, mfrr); + else return xics_rm_h_ipi(vcpu, server, mfrr); } @@ -608,13 +537,9 @@ int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xics_on_xive()) { - if (is_rm()) - return xive_rm_h_cppr(vcpu, cppr); - if (unlikely(!__xive_vm_h_cppr)) - return H_NOT_AVAILABLE; - return __xive_vm_h_cppr(vcpu, cppr); - } else + if (xics_on_xive()) + return xive_rm_h_cppr(vcpu, cppr); + else return xics_rm_h_cppr(vcpu, cppr); } @@ -622,13 +547,9 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xics_on_xive()) { - if (is_rm()) - return xive_rm_h_eoi(vcpu, xirr); - if (unlikely(!__xive_vm_h_eoi)) - return H_NOT_AVAILABLE; - return __xive_vm_h_eoi(vcpu, xirr); - } else + if (xics_on_xive()) + return xive_rm_h_eoi(vcpu, xirr); + else return xics_rm_h_eoi(vcpu, xirr); } #endif /* CONFIG_KVM_XICS */ @@ -800,7 +721,7 @@ void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu, * Thus we make all 4 threads use the same bit. */ if (cpu_has_feature(CPU_FTR_ARCH_300)) - pcpu = cpu_first_thread_sibling(pcpu); + pcpu = cpu_first_tlb_thread_sibling(pcpu); if (nested) need_tlb_flush = &nested->need_tlb_flush; diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 327417d79eac..4444f83cb133 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -58,7 +58,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) /* * Put whatever is in the decrementer into the * hypervisor decrementer. - * Because of a hardware deviation in P8 and P9, + * Because of a hardware deviation in P8, * we need to set LPCR[HDICE] before writing HDEC. */ ld r5, HSTATE_KVM_VCORE(r13) @@ -67,15 +67,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) ori r8, r9, LPCR_HDICE mtspr SPRN_LPCR, r8 isync - andis. r0, r9, LPCR_LD@h mfspr r8,SPRN_DEC mftb r7 -BEGIN_FTR_SECTION - /* On POWER9, don't sign-extend if host LPCR[LD] bit is set */ - bne 32f -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) extsw r8,r8 -32: mtspr SPRN_HDEC,r8 + mtspr SPRN_HDEC,r8 add r8,r8,r7 std r8,HSTATE_DECEXP(r13) diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 60724f674421..8543ad538b0c 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -19,6 +19,7 @@ #include <asm/pgalloc.h> #include <asm/pte-walk.h> #include <asm/reg.h> +#include <asm/plpar_wrappers.h> static struct patb_entry *pseries_partition_tb; @@ -53,7 +54,8 @@ void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr) hr->dawrx1 = vcpu->arch.dawrx1; } -static void byteswap_pt_regs(struct pt_regs *regs) +/* Use noinline_for_stack due to https://bugs.llvm.org/show_bug.cgi?id=49610 */ +static noinline_for_stack void byteswap_pt_regs(struct pt_regs *regs) { unsigned long *addr = (unsigned long *) regs; @@ -467,8 +469,15 @@ static void kvmhv_flush_lpid(unsigned int lpid) return; } - rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1), - lpid, TLBIEL_INVAL_SET_LPID); + if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE)) + rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1), + lpid, TLBIEL_INVAL_SET_LPID); + else + rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU, + H_RPTI_TYPE_NESTED | + H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | + H_RPTI_TYPE_PAT, + H_RPTI_PAGE_ALL, 0, -1UL); if (rc) pr_err("KVM: TLB LPID invalidation hcall failed, rc=%ld\n", rc); } @@ -1214,6 +1223,113 @@ long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu) return H_SUCCESS; } +static long do_tlb_invalidate_nested_all(struct kvm_vcpu *vcpu, + unsigned long lpid, unsigned long ric) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_nested_guest *gp; + + gp = kvmhv_get_nested(kvm, lpid, false); + if (gp) { + kvmhv_emulate_tlbie_lpid(vcpu, gp, ric); + kvmhv_put_nested(gp); + } + return H_SUCCESS; +} + +/* + * Number of pages above which we invalidate the entire LPID rather than + * flush individual pages. + */ +static unsigned long tlb_range_flush_page_ceiling __read_mostly = 33; + +static long do_tlb_invalidate_nested_tlb(struct kvm_vcpu *vcpu, + unsigned long lpid, + unsigned long pg_sizes, + unsigned long start, + unsigned long end) +{ + int ret = H_P4; + unsigned long addr, nr_pages; + struct mmu_psize_def *def; + unsigned long psize, ap, page_size; + bool flush_lpid; + + for (psize = 0; psize < MMU_PAGE_COUNT; psize++) { + def = &mmu_psize_defs[psize]; + if (!(pg_sizes & def->h_rpt_pgsize)) + continue; + + nr_pages = (end - start) >> def->shift; + flush_lpid = nr_pages > tlb_range_flush_page_ceiling; + if (flush_lpid) + return do_tlb_invalidate_nested_all(vcpu, lpid, + RIC_FLUSH_TLB); + addr = start; + ap = mmu_get_ap(psize); + page_size = 1UL << def->shift; + do { + ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap, + get_epn(addr)); + if (ret) + return H_P4; + addr += page_size; + } while (addr < end); + } + return ret; +} + +/* + * Performs partition-scoped invalidations for nested guests + * as part of H_RPT_INVALIDATE hcall. + */ +long do_h_rpt_invalidate_pat(struct kvm_vcpu *vcpu, unsigned long lpid, + unsigned long type, unsigned long pg_sizes, + unsigned long start, unsigned long end) +{ + /* + * If L2 lpid isn't valid, we need to return H_PARAMETER. + * + * However, nested KVM issues a L2 lpid flush call when creating + * partition table entries for L2. This happens even before the + * corresponding shadow lpid is created in HV which happens in + * H_ENTER_NESTED call. Since we can't differentiate this case from + * the invalid case, we ignore such flush requests and return success. + */ + if (!kvmhv_find_nested(vcpu->kvm, lpid)) + return H_SUCCESS; + + /* + * A flush all request can be handled by a full lpid flush only. + */ + if ((type & H_RPTI_TYPE_NESTED_ALL) == H_RPTI_TYPE_NESTED_ALL) + return do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_ALL); + + /* + * We don't need to handle a PWC flush like process table here, + * because intermediate partition scoped table in nested guest doesn't + * really have PWC. Only level we have PWC is in L0 and for nested + * invalidate at L0 we always do kvm_flush_lpid() which does + * radix__flush_all_lpid(). For range invalidate at any level, we + * are not removing the higher level page tables and hence there is + * no PWC invalidate needed. + * + * if (type & H_RPTI_TYPE_PWC) { + * ret = do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_PWC); + * if (ret) + * return H_P4; + * } + */ + + if (start == 0 && end == -1) + return do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_TLB); + + if (type & H_RPTI_TYPE_TLB) + return do_tlb_invalidate_nested_tlb(vcpu, lpid, pg_sizes, + start, end); + return H_SUCCESS; +} + /* Used to convert a nested guest real address to a L1 guest real address */ static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu, struct kvm_nested_guest *gp, diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c new file mode 100644 index 000000000000..83f592eadcd2 --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c @@ -0,0 +1,508 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/kernel.h> +#include <linux/kvm_host.h> +#include <asm/asm-prototypes.h> +#include <asm/dbell.h> +#include <asm/kvm_ppc.h> +#include <asm/ppc-opcode.h> + +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +static void __start_timing(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + u64 tb = mftb() - vc->tb_offset_applied; + + vcpu->arch.cur_activity = next; + vcpu->arch.cur_tb_start = tb; +} + +static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + struct kvmhv_tb_accumulator *curr; + u64 tb = mftb() - vc->tb_offset_applied; + u64 prev_tb; + u64 delta; + u64 seq; + + curr = vcpu->arch.cur_activity; + vcpu->arch.cur_activity = next; + prev_tb = vcpu->arch.cur_tb_start; + vcpu->arch.cur_tb_start = tb; + + if (!curr) + return; + + delta = tb - prev_tb; + + seq = curr->seqcount; + curr->seqcount = seq + 1; + smp_wmb(); + curr->tb_total += delta; + if (seq == 0 || delta < curr->tb_min) + curr->tb_min = delta; + if (delta > curr->tb_max) + curr->tb_max = delta; + smp_wmb(); + curr->seqcount = seq + 2; +} + +#define start_timing(vcpu, next) __start_timing(vcpu, next) +#define end_timing(vcpu) __start_timing(vcpu, NULL) +#define accumulate_time(vcpu, next) __accumulate_time(vcpu, next) +#else +#define start_timing(vcpu, next) do {} while (0) +#define end_timing(vcpu) do {} while (0) +#define accumulate_time(vcpu, next) do {} while (0) +#endif + +static inline void mfslb(unsigned int idx, u64 *slbee, u64 *slbev) +{ + asm volatile("slbmfev %0,%1" : "=r" (*slbev) : "r" (idx)); + asm volatile("slbmfee %0,%1" : "=r" (*slbee) : "r" (idx)); +} + +static inline void mtslb(u64 slbee, u64 slbev) +{ + asm volatile("slbmte %0,%1" :: "r" (slbev), "r" (slbee)); +} + +static inline void clear_slb_entry(unsigned int idx) +{ + mtslb(idx, 0); +} + +static inline void slb_clear_invalidate_partition(void) +{ + clear_slb_entry(0); + asm volatile(PPC_SLBIA(6)); +} + +/* + * Malicious or buggy radix guests may have inserted SLB entries + * (only 0..3 because radix always runs with UPRT=1), so these must + * be cleared here to avoid side-channels. slbmte is used rather + * than slbia, as it won't clear cached translations. + */ +static void radix_clear_slb(void) +{ + int i; + + for (i = 0; i < 4; i++) + clear_slb_entry(i); +} + +static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr) +{ + struct kvm_nested_guest *nested = vcpu->arch.nested; + u32 lpid; + + lpid = nested ? nested->shadow_lpid : kvm->arch.lpid; + + /* + * All the isync()s are overkill but trivially follow the ISA + * requirements. Some can likely be replaced with justification + * comment for why they are not needed. + */ + isync(); + mtspr(SPRN_LPID, lpid); + isync(); + mtspr(SPRN_LPCR, lpcr); + isync(); + mtspr(SPRN_PID, vcpu->arch.pid); + isync(); +} + +static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr) +{ + u32 lpid; + int i; + + lpid = kvm->arch.lpid; + + mtspr(SPRN_LPID, lpid); + mtspr(SPRN_LPCR, lpcr); + mtspr(SPRN_PID, vcpu->arch.pid); + + for (i = 0; i < vcpu->arch.slb_max; i++) + mtslb(vcpu->arch.slb[i].orige, vcpu->arch.slb[i].origv); + + isync(); +} + +static void switch_mmu_to_host(struct kvm *kvm, u32 pid) +{ + isync(); + mtspr(SPRN_PID, pid); + isync(); + mtspr(SPRN_LPID, kvm->arch.host_lpid); + isync(); + mtspr(SPRN_LPCR, kvm->arch.host_lpcr); + isync(); + + if (!radix_enabled()) + slb_restore_bolted_realmode(); +} + +static void save_clear_host_mmu(struct kvm *kvm) +{ + if (!radix_enabled()) { + /* + * Hash host could save and restore host SLB entries to + * reduce SLB fault overheads of VM exits, but for now the + * existing code clears all entries and restores just the + * bolted ones when switching back to host. + */ + slb_clear_invalidate_partition(); + } +} + +static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu) +{ + if (kvm_is_radix(kvm)) { + radix_clear_slb(); + } else { + int i; + int nr = 0; + + /* + * This must run before switching to host (radix host can't + * access all SLBs). + */ + for (i = 0; i < vcpu->arch.slb_nr; i++) { + u64 slbee, slbev; + mfslb(i, &slbee, &slbev); + if (slbee & SLB_ESID_V) { + vcpu->arch.slb[nr].orige = slbee | i; + vcpu->arch.slb[nr].origv = slbev; + nr++; + } + } + vcpu->arch.slb_max = nr; + slb_clear_invalidate_partition(); + } +} + +int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_nested_guest *nested = vcpu->arch.nested; + struct kvmppc_vcore *vc = vcpu->arch.vcore; + s64 hdec; + u64 tb, purr, spurr; + u64 *exsave; + bool ri_set; + int trap; + unsigned long msr; + unsigned long host_hfscr; + unsigned long host_ciabr; + unsigned long host_dawr0; + unsigned long host_dawrx0; + unsigned long host_psscr; + unsigned long host_pidr; + unsigned long host_dawr1; + unsigned long host_dawrx1; + + hdec = time_limit - mftb(); + if (hdec < 0) + return BOOK3S_INTERRUPT_HV_DECREMENTER; + + WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_HV); + WARN_ON_ONCE(!(vcpu->arch.shregs.msr & MSR_ME)); + + start_timing(vcpu, &vcpu->arch.rm_entry); + + vcpu->arch.ceded = 0; + + if (vc->tb_offset) { + u64 new_tb = mftb() + vc->tb_offset; + mtspr(SPRN_TBU40, new_tb); + tb = mftb(); + if ((tb & 0xffffff) < (new_tb & 0xffffff)) + mtspr(SPRN_TBU40, new_tb + 0x1000000); + vc->tb_offset_applied = vc->tb_offset; + } + + msr = mfmsr(); + + host_hfscr = mfspr(SPRN_HFSCR); + host_ciabr = mfspr(SPRN_CIABR); + host_dawr0 = mfspr(SPRN_DAWR0); + host_dawrx0 = mfspr(SPRN_DAWRX0); + host_psscr = mfspr(SPRN_PSSCR); + host_pidr = mfspr(SPRN_PID); + if (cpu_has_feature(CPU_FTR_DAWR1)) { + host_dawr1 = mfspr(SPRN_DAWR1); + host_dawrx1 = mfspr(SPRN_DAWRX1); + } + + if (vc->pcr) + mtspr(SPRN_PCR, vc->pcr | PCR_MASK); + mtspr(SPRN_DPDES, vc->dpdes); + mtspr(SPRN_VTB, vc->vtb); + + local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR); + local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR); + mtspr(SPRN_PURR, vcpu->arch.purr); + mtspr(SPRN_SPURR, vcpu->arch.spurr); + + if (dawr_enabled()) { + mtspr(SPRN_DAWR0, vcpu->arch.dawr0); + mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0); + if (cpu_has_feature(CPU_FTR_DAWR1)) { + mtspr(SPRN_DAWR1, vcpu->arch.dawr1); + mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1); + } + } + mtspr(SPRN_CIABR, vcpu->arch.ciabr); + mtspr(SPRN_IC, vcpu->arch.ic); + + mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC | + (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + + mtspr(SPRN_HFSCR, vcpu->arch.hfscr); + + mtspr(SPRN_HSRR0, vcpu->arch.regs.nip); + mtspr(SPRN_HSRR1, (vcpu->arch.shregs.msr & ~MSR_HV) | MSR_ME); + + /* + * On POWER9 DD2.1 and below, sometimes on a Hypervisor Data Storage + * Interrupt (HDSI) the HDSISR is not be updated at all. + * + * To work around this we put a canary value into the HDSISR before + * returning to a guest and then check for this canary when we take a + * HDSI. If we find the canary on a HDSI, we know the hardware didn't + * update the HDSISR. In this case we return to the guest to retake the + * HDSI which should correctly update the HDSISR the second time HDSI + * entry. + * + * Just do this on all p9 processors for now. + */ + mtspr(SPRN_HDSISR, HDSISR_CANARY); + + mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0); + mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1); + mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2); + mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3); + + mtspr(SPRN_AMOR, ~0UL); + + local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_HV_P9; + + /* + * Hash host, hash guest, or radix guest with prefetch bug, all have + * to disable the MMU before switching to guest MMU state. + */ + if (!radix_enabled() || !kvm_is_radix(kvm) || + cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) + __mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0); + + save_clear_host_mmu(kvm); + + if (kvm_is_radix(kvm)) { + switch_mmu_to_guest_radix(kvm, vcpu, lpcr); + if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) + __mtmsrd(0, 1); /* clear RI */ + + } else { + switch_mmu_to_guest_hpt(kvm, vcpu, lpcr); + } + + /* TLBIEL uses LPID=LPIDR, so run this after setting guest LPID */ + kvmppc_check_need_tlb_flush(kvm, vc->pcpu, nested); + + /* + * P9 suppresses the HDEC exception when LPCR[HDICE] = 0, + * so set guest LPCR (with HDICE) before writing HDEC. + */ + mtspr(SPRN_HDEC, hdec); + + mtspr(SPRN_DAR, vcpu->arch.shregs.dar); + mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); + mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0); + mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1); + + accumulate_time(vcpu, &vcpu->arch.guest_time); + + kvmppc_p9_enter_guest(vcpu); + + accumulate_time(vcpu, &vcpu->arch.rm_intr); + + /* XXX: Could get these from r11/12 and paca exsave instead */ + vcpu->arch.shregs.srr0 = mfspr(SPRN_SRR0); + vcpu->arch.shregs.srr1 = mfspr(SPRN_SRR1); + vcpu->arch.shregs.dar = mfspr(SPRN_DAR); + vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); + + /* 0x2 bit for HSRR is only used by PR and P7/8 HV paths, clear it */ + trap = local_paca->kvm_hstate.scratch0 & ~0x2; + + /* HSRR interrupts leave MSR[RI] unchanged, SRR interrupts clear it. */ + ri_set = false; + if (likely(trap > BOOK3S_INTERRUPT_MACHINE_CHECK)) { + if (trap != BOOK3S_INTERRUPT_SYSCALL && + (vcpu->arch.shregs.msr & MSR_RI)) + ri_set = true; + exsave = local_paca->exgen; + } else if (trap == BOOK3S_INTERRUPT_SYSTEM_RESET) { + exsave = local_paca->exnmi; + } else { /* trap == 0x200 */ + exsave = local_paca->exmc; + } + + vcpu->arch.regs.gpr[1] = local_paca->kvm_hstate.scratch1; + vcpu->arch.regs.gpr[3] = local_paca->kvm_hstate.scratch2; + + /* + * Only set RI after reading machine check regs (DAR, DSISR, SRR0/1) + * and hstate scratch (which we need to move into exsave to make + * re-entrant vs SRESET/MCE) + */ + if (ri_set) { + if (unlikely(!(mfmsr() & MSR_RI))) { + __mtmsrd(MSR_RI, 1); + WARN_ON_ONCE(1); + } + } else { + WARN_ON_ONCE(mfmsr() & MSR_RI); + __mtmsrd(MSR_RI, 1); + } + + vcpu->arch.regs.gpr[9] = exsave[EX_R9/sizeof(u64)]; + vcpu->arch.regs.gpr[10] = exsave[EX_R10/sizeof(u64)]; + vcpu->arch.regs.gpr[11] = exsave[EX_R11/sizeof(u64)]; + vcpu->arch.regs.gpr[12] = exsave[EX_R12/sizeof(u64)]; + vcpu->arch.regs.gpr[13] = exsave[EX_R13/sizeof(u64)]; + vcpu->arch.ppr = exsave[EX_PPR/sizeof(u64)]; + vcpu->arch.cfar = exsave[EX_CFAR/sizeof(u64)]; + vcpu->arch.regs.ctr = exsave[EX_CTR/sizeof(u64)]; + + vcpu->arch.last_inst = KVM_INST_FETCH_FAILED; + + if (unlikely(trap == BOOK3S_INTERRUPT_MACHINE_CHECK)) { + vcpu->arch.fault_dar = exsave[EX_DAR/sizeof(u64)]; + vcpu->arch.fault_dsisr = exsave[EX_DSISR/sizeof(u64)]; + kvmppc_realmode_machine_check(vcpu); + + } else if (unlikely(trap == BOOK3S_INTERRUPT_HMI)) { + kvmppc_realmode_hmi_handler(); + + } else if (trap == BOOK3S_INTERRUPT_H_EMUL_ASSIST) { + vcpu->arch.emul_inst = mfspr(SPRN_HEIR); + + } else if (trap == BOOK3S_INTERRUPT_H_DATA_STORAGE) { + vcpu->arch.fault_dar = exsave[EX_DAR/sizeof(u64)]; + vcpu->arch.fault_dsisr = exsave[EX_DSISR/sizeof(u64)]; + vcpu->arch.fault_gpa = mfspr(SPRN_ASDR); + + } else if (trap == BOOK3S_INTERRUPT_H_INST_STORAGE) { + vcpu->arch.fault_gpa = mfspr(SPRN_ASDR); + + } else if (trap == BOOK3S_INTERRUPT_H_FAC_UNAVAIL) { + vcpu->arch.hfscr = mfspr(SPRN_HFSCR); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * Softpatch interrupt for transactional memory emulation cases + * on POWER9 DD2.2. This is early in the guest exit path - we + * haven't saved registers or done a treclaim yet. + */ + } else if (trap == BOOK3S_INTERRUPT_HV_SOFTPATCH) { + vcpu->arch.emul_inst = mfspr(SPRN_HEIR); + + /* + * The cases we want to handle here are those where the guest + * is in real suspend mode and is trying to transition to + * transactional mode. + */ + if (local_paca->kvm_hstate.fake_suspend && + (vcpu->arch.shregs.msr & MSR_TS_S)) { + if (kvmhv_p9_tm_emulation_early(vcpu)) { + /* Prevent it being handled again. */ + trap = 0; + } + } +#endif + } + + accumulate_time(vcpu, &vcpu->arch.rm_exit); + + /* Advance host PURR/SPURR by the amount used by guest */ + purr = mfspr(SPRN_PURR); + spurr = mfspr(SPRN_SPURR); + mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr + + purr - vcpu->arch.purr); + mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr + + spurr - vcpu->arch.spurr); + vcpu->arch.purr = purr; + vcpu->arch.spurr = spurr; + + vcpu->arch.ic = mfspr(SPRN_IC); + vcpu->arch.pid = mfspr(SPRN_PID); + vcpu->arch.psscr = mfspr(SPRN_PSSCR) & PSSCR_GUEST_VIS; + + vcpu->arch.shregs.sprg0 = mfspr(SPRN_SPRG0); + vcpu->arch.shregs.sprg1 = mfspr(SPRN_SPRG1); + vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2); + vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3); + + /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ + mtspr(SPRN_PSSCR, host_psscr | + (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + mtspr(SPRN_HFSCR, host_hfscr); + mtspr(SPRN_CIABR, host_ciabr); + mtspr(SPRN_DAWR0, host_dawr0); + mtspr(SPRN_DAWRX0, host_dawrx0); + if (cpu_has_feature(CPU_FTR_DAWR1)) { + mtspr(SPRN_DAWR1, host_dawr1); + mtspr(SPRN_DAWRX1, host_dawrx1); + } + + if (kvm_is_radix(kvm)) { + /* + * Since this is radix, do a eieio; tlbsync; ptesync sequence + * in case we interrupted the guest between a tlbie and a + * ptesync. + */ + asm volatile("eieio; tlbsync; ptesync"); + } + + /* + * cp_abort is required if the processor supports local copy-paste + * to clear the copy buffer that was under control of the guest. + */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + asm volatile(PPC_CP_ABORT); + + vc->dpdes = mfspr(SPRN_DPDES); + vc->vtb = mfspr(SPRN_VTB); + mtspr(SPRN_DPDES, 0); + if (vc->pcr) + mtspr(SPRN_PCR, PCR_MASK); + + if (vc->tb_offset_applied) { + u64 new_tb = mftb() - vc->tb_offset_applied; + mtspr(SPRN_TBU40, new_tb); + tb = mftb(); + if ((tb & 0xffffff) < (new_tb & 0xffffff)) + mtspr(SPRN_TBU40, new_tb + 0x1000000); + vc->tb_offset_applied = 0; + } + + mtspr(SPRN_HDEC, 0x7fffffff); + + save_clear_guest_mmu(kvm, vcpu); + switch_mmu_to_host(kvm, host_pidr); + local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE; + + /* + * If we are in real mode, only switch MMU on after the MMU is + * switched to host, to avoid the P9_RADIX_PREFETCH_BUG. + */ + __mtmsrd(msr, 0); + + end_timing(vcpu); + + return trap; +} +EXPORT_SYMBOL_GPL(kvmhv_vcpu_entry_p9); diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 7af7c70f1468..8b70de4595f0 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -57,6 +57,10 @@ static int global_invalidates(struct kvm *kvm) else global = 1; + /* LPID has been switched to host if in virt mode so can't do local */ + if (!global && (mfmsr() & (MSR_IR|MSR_DR))) + global = 1; + if (!global) { /* any other core might now have stale TLB entries... */ smp_wmb(); @@ -67,7 +71,7 @@ static int global_invalidates(struct kvm *kvm) * so use the bit for the first thread to represent the core. */ if (cpu_has_feature(CPU_FTR_ARCH_300)) - cpu = cpu_first_thread_sibling(cpu); + cpu = cpu_first_tlb_thread_sibling(cpu); cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush); } @@ -409,6 +413,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, vcpu->arch.pgdir, true, &vcpu->arch.regs.gpr[4]); } +EXPORT_SYMBOL_GPL(kvmppc_h_enter); #ifdef __BIG_ENDIAN__ #define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token)) @@ -553,6 +558,7 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags, return kvmppc_do_h_remove(vcpu->kvm, flags, pte_index, avpn, &vcpu->arch.regs.gpr[4]); } +EXPORT_SYMBOL_GPL(kvmppc_h_remove); long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) { @@ -671,6 +677,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) return ret; } +EXPORT_SYMBOL_GPL(kvmppc_h_bulk_remove); long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long pte_index, unsigned long avpn) @@ -741,6 +748,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, return H_SUCCESS; } +EXPORT_SYMBOL_GPL(kvmppc_h_protect); long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long pte_index) @@ -781,6 +789,7 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, } return H_SUCCESS; } +EXPORT_SYMBOL_GPL(kvmppc_h_read); long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long pte_index) @@ -829,6 +838,7 @@ long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags, unlock_hpte(hpte, v & ~HPTE_V_HVLOCK); return ret; } +EXPORT_SYMBOL_GPL(kvmppc_h_clear_ref); long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long pte_index) @@ -876,6 +886,7 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags, unlock_hpte(hpte, v & ~HPTE_V_HVLOCK); return ret; } +EXPORT_SYMBOL_GPL(kvmppc_h_clear_mod); static int kvmppc_get_hpa(struct kvm_vcpu *vcpu, unsigned long mmu_seq, unsigned long gpa, int writing, unsigned long *hpa, @@ -1294,3 +1305,4 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr, return -1; /* send fault up to host kernel mode */ } +EXPORT_SYMBOL_GPL(kvmppc_hpte_hv_fault); diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index c2c9c733f359..0a11ec88a0ae 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -141,13 +141,6 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu, return; } - if (xive_enabled() && kvmhv_on_pseries()) { - /* No XICS access or hypercalls available, too hard */ - this_icp->rm_action |= XICS_RM_KICK_VCPU; - this_icp->rm_kick_target = vcpu; - return; - } - /* * Check if the core is loaded, * if not, find an available host core to post to wake the VCPU, @@ -771,14 +764,6 @@ static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again) void __iomem *xics_phys; int64_t rc; - if (kvmhv_on_pseries()) { - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - iosync(); - plpar_hcall_raw(H_EOI, retbuf, hwirq); - return; - } - rc = pnv_opal_pci_msi_eoi(c, hwirq); if (rc) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 5e634db4809b..8dd437d7a2c6 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -25,18 +25,10 @@ #include <asm/export.h> #include <asm/tm.h> #include <asm/opal.h> -#include <asm/xive-regs.h> #include <asm/thread_info.h> #include <asm/asm-compat.h> #include <asm/feature-fixups.h> #include <asm/cpuidle.h> -#include <asm/ultravisor-api.h> - -/* Sign-extend HDEC if not on POWER9 */ -#define EXTEND_HDEC(reg) \ -BEGIN_FTR_SECTION; \ - extsw reg, reg; \ -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) /* Values in HSTATE_NAPPING(r13) */ #define NAPPING_CEDE 1 @@ -44,9 +36,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) #define NAPPING_UNSPLIT 3 /* Stack frame offsets for kvmppc_hv_entry */ -#define SFS 208 +#define SFS 160 #define STACK_SLOT_TRAP (SFS-4) -#define STACK_SLOT_SHORT_PATH (SFS-8) #define STACK_SLOT_TID (SFS-16) #define STACK_SLOT_PSSCR (SFS-24) #define STACK_SLOT_PID (SFS-32) @@ -57,10 +48,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) #define STACK_SLOT_HFSCR (SFS-72) #define STACK_SLOT_AMR (SFS-80) #define STACK_SLOT_UAMOR (SFS-88) -#define STACK_SLOT_DAWR1 (SFS-96) -#define STACK_SLOT_DAWRX1 (SFS-104) -/* the following is used by the P9 short path */ -#define STACK_SLOT_NVGPRS (SFS-152) /* 18 gprs */ +#define STACK_SLOT_FSCR (SFS-96) /* * Call kvmppc_hv_entry in real mode. @@ -136,15 +124,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) /* Return the trap number on this thread as the return value */ mr r3, r12 - /* - * If we came back from the guest via a relocation-on interrupt, - * we will be in virtual mode at this point, which makes it a - * little easier to get back to the caller. - */ - mfmsr r0 - andi. r0, r0, MSR_IR /* in real mode? */ - bne .Lvirt_return - /* RFI into the highmem handler */ mfmsr r6 li r0, MSR_RI @@ -154,11 +133,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) mtsrr1 r7 RFI_TO_KERNEL - /* Virtual-mode return */ -.Lvirt_return: - mtlr r8 - blr - kvmppc_primary_no_guest: /* We handle this much like a ceded vcpu */ /* put the HDEC into the DEC, since HDEC interrupts don't wake us */ @@ -245,7 +219,7 @@ kvm_novcpu_wakeup: /* See if our timeslice has expired (HDEC is negative) */ mfspr r0, SPRN_HDEC - EXTEND_HDEC(r0) + extsw r0, r0 li r12, BOOK3S_INTERRUPT_HV_DECREMENTER cmpdi r0, 0 blt kvm_novcpu_exit @@ -347,10 +321,8 @@ kvm_secondary_got_guest: lbz r4, HSTATE_PTID(r13) cmpwi r4, 0 bne 63f - LOAD_REG_ADDR(r6, decrementer_max) - ld r6, 0(r6) + lis r6,0x7fff /* MAX_INT@h */ mtspr SPRN_HDEC, r6 -BEGIN_FTR_SECTION /* and set per-LPAR registers, if doing dynamic micro-threading */ ld r6, HSTATE_SPLIT_MODE(r13) cmpdi r6, 0 @@ -362,7 +334,6 @@ BEGIN_FTR_SECTION ld r0, KVM_SPLIT_LDBAR(r6) mtspr SPRN_LDBAR, r0 isync -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) 63: /* Order load of vcpu after load of vcore */ lwsync @@ -433,7 +404,6 @@ kvm_no_guest: blr 53: -BEGIN_FTR_SECTION HMT_LOW ld r5, HSTATE_KVM_VCORE(r13) cmpdi r5, 0 @@ -448,14 +418,6 @@ BEGIN_FTR_SECTION b kvm_unsplit_nap 60: HMT_MEDIUM b kvm_secondary_got_guest -FTR_SECTION_ELSE - HMT_LOW - ld r5, HSTATE_KVM_VCORE(r13) - cmpdi r5, 0 - beq kvm_no_guest - HMT_MEDIUM - b kvm_secondary_got_guest -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) 54: li r0, KVM_HWTHREAD_IN_KVM stb r0, HSTATE_HWTHREAD_STATE(r13) @@ -581,13 +543,11 @@ kvmppc_hv_entry: bne 10f lwz r7,KVM_LPID(r9) -BEGIN_FTR_SECTION ld r6,KVM_SDR1(r9) li r0,LPID_RSVD /* switch to reserved LPID */ mtspr SPRN_LPID,r0 ptesync mtspr SPRN_SDR1,r6 /* switch to partition page table */ -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) mtspr SPRN_LPID,r7 isync @@ -668,16 +628,6 @@ kvmppc_got_guest: /* Save host values of some registers */ BEGIN_FTR_SECTION - mfspr r5, SPRN_TIDR - mfspr r6, SPRN_PSSCR - mfspr r7, SPRN_PID - std r5, STACK_SLOT_TID(r1) - std r6, STACK_SLOT_PSSCR(r1) - std r7, STACK_SLOT_PID(r1) - mfspr r5, SPRN_HFSCR - std r5, STACK_SLOT_HFSCR(r1) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) -BEGIN_FTR_SECTION mfspr r5, SPRN_CIABR mfspr r6, SPRN_DAWR0 mfspr r7, SPRN_DAWRX0 @@ -686,13 +636,9 @@ BEGIN_FTR_SECTION std r6, STACK_SLOT_DAWR0(r1) std r7, STACK_SLOT_DAWRX0(r1) std r8, STACK_SLOT_IAMR(r1) + mfspr r5, SPRN_FSCR + std r5, STACK_SLOT_FSCR(r1) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -BEGIN_FTR_SECTION - mfspr r6, SPRN_DAWR1 - mfspr r7, SPRN_DAWRX1 - std r6, STACK_SLOT_DAWR1(r1) - std r7, STACK_SLOT_DAWRX1(r1) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S | CPU_FTR_DAWR1) mfspr r5, SPRN_AMR std r5, STACK_SLOT_AMR(r1) @@ -710,13 +656,9 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM -/* - * Branch around the call if both CPU_FTR_TM and - * CPU_FTR_P9_TM_HV_ASSIST are off. - */ BEGIN_FTR_SECTION b 91f -END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0) +END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR) */ @@ -783,12 +725,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) ld r6, VCPU_DAWRX0(r4) mtspr SPRN_DAWR0, r5 mtspr SPRN_DAWRX0, r6 -BEGIN_FTR_SECTION - ld r5, VCPU_DAWR1(r4) - ld r6, VCPU_DAWRX1(r4) - mtspr SPRN_DAWR1, r5 - mtspr SPRN_DAWRX1, r6 -END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) 1: ld r7, VCPU_CIABR(r4) ld r8, VCPU_TAR(r4) @@ -806,7 +742,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) mtspr SPRN_BESCR, r6 mtspr SPRN_PID, r7 mtspr SPRN_WORT, r8 -BEGIN_FTR_SECTION /* POWER8-only registers */ ld r5, VCPU_TCSCR(r4) ld r6, VCPU_ACOP(r4) @@ -817,18 +752,6 @@ BEGIN_FTR_SECTION mtspr SPRN_CSIGR, r7 mtspr SPRN_TACR, r8 nop -FTR_SECTION_ELSE - /* POWER9-only registers */ - ld r5, VCPU_TID(r4) - ld r6, VCPU_PSSCR(r4) - lbz r8, HSTATE_FAKE_SUSPEND(r13) - oris r6, r6, PSSCR_EC@h /* This makes stop trap to HV */ - rldimi r6, r8, PSSCR_FAKE_SUSPEND_LG, 63 - PSSCR_FAKE_SUSPEND_LG - ld r7, VCPU_HFSCR(r4) - mtspr SPRN_TIDR, r5 - mtspr SPRN_PSSCR, r6 - mtspr SPRN_HFSCR, r7 -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) 8: ld r5, VCPU_SPRG0(r4) @@ -898,23 +821,15 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) /* Check if HDEC expires soon */ mfspr r3, SPRN_HDEC - EXTEND_HDEC(r3) + extsw r3, r3 cmpdi r3, 512 /* 1 microsecond */ blt hdec_soon - ld r6, VCPU_KVM(r4) - lbz r0, KVM_RADIX(r6) - cmpwi r0, 0 - bne 9f - - /* For hash guest, clear out and reload the SLB */ -BEGIN_MMU_FTR_SECTION - /* Radix host won't have populated the SLB, so no need to clear */ + /* Clear out and reload the SLB */ li r6, 0 slbmte r6, r6 PPC_SLBIA(6) ptesync -END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) /* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */ lwz r5,VCPU_SLB_MAX(r4) @@ -929,96 +844,9 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) bdnz 1b 9: -#ifdef CONFIG_KVM_XICS - /* We are entering the guest on that thread, push VCPU to XIVE */ - ld r11, VCPU_XIVE_SAVED_STATE(r4) - li r9, TM_QW1_OS - lwz r8, VCPU_XIVE_CAM_WORD(r4) - cmpwi r8, 0 - beq no_xive - li r7, TM_QW1_OS + TM_WORD2 - mfmsr r0 - andi. r0, r0, MSR_DR /* in real mode? */ - beq 2f - ld r10, HSTATE_XIVE_TIMA_VIRT(r13) - cmpldi cr1, r10, 0 - beq cr1, no_xive - eieio - stdx r11,r9,r10 - stwx r8,r7,r10 - b 3f -2: ld r10, HSTATE_XIVE_TIMA_PHYS(r13) - cmpldi cr1, r10, 0 - beq cr1, no_xive - eieio - stdcix r11,r9,r10 - stwcix r8,r7,r10 -3: li r9, 1 - stb r9, VCPU_XIVE_PUSHED(r4) - eieio - - /* - * We clear the irq_pending flag. There is a small chance of a - * race vs. the escalation interrupt happening on another - * processor setting it again, but the only consequence is to - * cause a spurrious wakeup on the next H_CEDE which is not an - * issue. - */ - li r0,0 - stb r0, VCPU_IRQ_PENDING(r4) - - /* - * In single escalation mode, if the escalation interrupt is - * on, we mask it. - */ - lbz r0, VCPU_XIVE_ESC_ON(r4) - cmpwi cr1, r0,0 - beq cr1, 1f - li r9, XIVE_ESB_SET_PQ_01 - beq 4f /* in real mode? */ - ld r10, VCPU_XIVE_ESC_VADDR(r4) - ldx r0, r10, r9 - b 5f -4: ld r10, VCPU_XIVE_ESC_RADDR(r4) - ldcix r0, r10, r9 -5: sync - - /* We have a possible subtle race here: The escalation interrupt might - * have fired and be on its way to the host queue while we mask it, - * and if we unmask it early enough (re-cede right away), there is - * a theorical possibility that it fires again, thus landing in the - * target queue more than once which is a big no-no. - * - * Fortunately, solving this is rather easy. If the above load setting - * PQ to 01 returns a previous value where P is set, then we know the - * escalation interrupt is somewhere on its way to the host. In that - * case we simply don't clear the xive_esc_on flag below. It will be - * eventually cleared by the handler for the escalation interrupt. - * - * Then, when doing a cede, we check that flag again before re-enabling - * the escalation interrupt, and if set, we abort the cede. - */ - andi. r0, r0, XIVE_ESB_VAL_P - bne- 1f - - /* Now P is 0, we can clear the flag */ - li r0, 0 - stb r0, VCPU_XIVE_ESC_ON(r4) -1: -no_xive: -#endif /* CONFIG_KVM_XICS */ - - li r0, 0 - stw r0, STACK_SLOT_SHORT_PATH(r1) - deliver_guest_interrupt: /* r4 = vcpu, r13 = paca */ /* Check if we can deliver an external or decrementer interrupt now */ ld r0, VCPU_PENDING_EXC(r4) -BEGIN_FTR_SECTION - /* On POWER9, also check for emulated doorbell interrupt */ - lbz r3, VCPU_DBELL_REQ(r4) - or r0, r0, r3 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) cmpdi r0, 0 beq 71f mr r3, r4 @@ -1030,7 +858,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) mtspr SPRN_SRR0, r6 mtspr SPRN_SRR1, r7 -fast_guest_entry_c: ld r10, VCPU_PC(r4) ld r11, VCPU_MSR(r4) /* r11 = vcpu->arch.msr & ~MSR_HV */ @@ -1092,18 +919,8 @@ BEGIN_FTR_SECTION mtspr SPRN_PPR, r0 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) -/* Move canary into DSISR to check for later */ -BEGIN_FTR_SECTION - li r0, 0x7fff - mtspr SPRN_HDSISR, r0 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) - - ld r6, VCPU_KVM(r4) - lbz r7, KVM_SECURE_GUEST(r6) - cmpdi r7, 0 ld r6, VCPU_GPR(R6)(r4) ld r7, VCPU_GPR(R7)(r4) - bne ret_to_ultra ld r0, VCPU_CR(r4) mtcr r0 @@ -1114,117 +931,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) ld r4, VCPU_GPR(R4)(r4) HRFI_TO_GUEST b . -/* - * Use UV_RETURN ultracall to return control back to the Ultravisor after - * processing an hypercall or interrupt that was forwarded (a.k.a. reflected) - * to the Hypervisor. - * - * All registers have already been loaded, except: - * R0 = hcall result - * R2 = SRR1, so UV can detect a synthesized interrupt (if any) - * R3 = UV_RETURN - */ -ret_to_ultra: - ld r0, VCPU_CR(r4) - mtcr r0 - - ld r0, VCPU_GPR(R3)(r4) - mfspr r2, SPRN_SRR1 - li r3, 0 - ori r3, r3, UV_RETURN - ld r4, VCPU_GPR(R4)(r4) - sc 2 - -/* - * Enter the guest on a P9 or later system where we have exactly - * one vcpu per vcore and we don't need to go to real mode - * (which implies that host and guest are both using radix MMU mode). - * r3 = vcpu pointer - * Most SPRs and all the VSRs have been loaded already. - */ -_GLOBAL(__kvmhv_vcpu_entry_p9) -EXPORT_SYMBOL_GPL(__kvmhv_vcpu_entry_p9) - mflr r0 - std r0, PPC_LR_STKOFF(r1) - stdu r1, -SFS(r1) - - li r0, 1 - stw r0, STACK_SLOT_SHORT_PATH(r1) - - std r3, HSTATE_KVM_VCPU(r13) - mfcr r4 - stw r4, SFS+8(r1) - - std r1, HSTATE_HOST_R1(r13) - - reg = 14 - .rept 18 - std reg, STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1) - reg = reg + 1 - .endr - - reg = 14 - .rept 18 - ld reg, __VCPU_GPR(reg)(r3) - reg = reg + 1 - .endr - - mfmsr r10 - std r10, HSTATE_HOST_MSR(r13) - - mr r4, r3 - b fast_guest_entry_c -guest_exit_short_path: - /* - * Malicious or buggy radix guests may have inserted SLB entries - * (only 0..3 because radix always runs with UPRT=1), so these must - * be cleared here to avoid side-channels. slbmte is used rather - * than slbia, as it won't clear cached translations. - */ - li r0,0 - slbmte r0,r0 - li r4,1 - slbmte r0,r4 - li r4,2 - slbmte r0,r4 - li r4,3 - slbmte r0,r4 - - li r0, KVM_GUEST_MODE_NONE - stb r0, HSTATE_IN_GUEST(r13) - - reg = 14 - .rept 18 - std reg, __VCPU_GPR(reg)(r9) - reg = reg + 1 - .endr - - reg = 14 - .rept 18 - ld reg, STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1) - reg = reg + 1 - .endr - - lwz r4, SFS+8(r1) - mtcr r4 - - mr r3, r12 /* trap number */ - - addi r1, r1, SFS - ld r0, PPC_LR_STKOFF(r1) - mtlr r0 - - /* If we are in real mode, do a rfid to get back to the caller */ - mfmsr r4 - andi. r5, r4, MSR_IR - bnelr - rldicl r5, r4, 64 - MSR_TS_S_LG, 62 /* extract TS field */ - mtspr SPRN_SRR0, r0 - ld r10, HSTATE_HOST_MSR(r13) - rldimi r10, r5, MSR_TS_S_LG, 63 - MSR_TS_T_LG - mtspr SPRN_SRR1, r10 - RFI_TO_KERNEL - b . secondary_too_late: li r12, 0 @@ -1265,21 +971,16 @@ hdec_soon: kvmppc_interrupt_hv: /* * Register contents: + * R9 = HSTATE_IN_GUEST * R12 = (guest CR << 32) | interrupt vector * R13 = PACA * guest R12 saved in shadow VCPU SCRATCH0 * guest R13 saved in SPRN_SCRATCH0 + * guest R9 saved in HSTATE_SCRATCH2 */ - std r9, HSTATE_SCRATCH2(r13) - lbz r9, HSTATE_IN_GUEST(r13) - cmpwi r9, KVM_GUEST_MODE_HOST_HV - beq kvmppc_bad_host_intr -#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE - cmpwi r9, KVM_GUEST_MODE_GUEST - ld r9, HSTATE_SCRATCH2(r13) - beq kvmppc_interrupt_pr -#endif /* We're now back in the host but in guest MMU context */ + cmpwi r9,KVM_GUEST_MODE_HOST_HV + beq kvmppc_bad_host_intr li r9, KVM_GUEST_MODE_HOST_HV stb r9, HSTATE_IN_GUEST(r13) @@ -1397,7 +1098,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER bne 2f mfspr r3,SPRN_HDEC - EXTEND_HDEC(r3) + extsw r3, r3 cmpdi r3,0 mr r4,r9 bge fast_guest_return @@ -1409,14 +1110,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) /* Hypervisor doorbell - exit only if host IPI flag set */ cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL bne 3f -BEGIN_FTR_SECTION - PPC_MSGSYNC - lwsync - /* always exit if we're running a nested guest */ - ld r0, VCPU_NESTED(r9) - cmpdi r0, 0 - bne guest_exit_cont -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) lbz r0, HSTATE_HOST_IPI(r13) cmpwi r0, 0 beq maybe_reenter_guest @@ -1446,62 +1139,16 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ mr r4, r9 bl kvmhv_accumulate_time #endif -#ifdef CONFIG_KVM_XICS - /* We are exiting, pull the VP from the XIVE */ - lbz r0, VCPU_XIVE_PUSHED(r9) - cmpwi cr0, r0, 0 - beq 1f - li r7, TM_SPC_PULL_OS_CTX - li r6, TM_QW1_OS - mfmsr r0 - andi. r0, r0, MSR_DR /* in real mode? */ - beq 2f - ld r10, HSTATE_XIVE_TIMA_VIRT(r13) - cmpldi cr0, r10, 0 - beq 1f - /* First load to pull the context, we ignore the value */ - eieio - lwzx r11, r7, r10 - /* Second load to recover the context state (Words 0 and 1) */ - ldx r11, r6, r10 - b 3f -2: ld r10, HSTATE_XIVE_TIMA_PHYS(r13) - cmpldi cr0, r10, 0 - beq 1f - /* First load to pull the context, we ignore the value */ - eieio - lwzcix r11, r7, r10 - /* Second load to recover the context state (Words 0 and 1) */ - ldcix r11, r6, r10 -3: std r11, VCPU_XIVE_SAVED_STATE(r9) - /* Fixup some of the state for the next load */ - li r10, 0 - li r0, 0xff - stb r10, VCPU_XIVE_PUSHED(r9) - stb r10, (VCPU_XIVE_SAVED_STATE+3)(r9) - stb r0, (VCPU_XIVE_SAVED_STATE+4)(r9) - eieio -1: -#endif /* CONFIG_KVM_XICS */ /* * Possibly flush the link stack here, before we do a blr in - * guest_exit_short_path. + * kvmhv_switch_to_host. */ 1: nop patch_site 1b patch__call_kvm_flush_link_stack - /* If we came in through the P9 short path, go back out to C now */ - lwz r0, STACK_SLOT_SHORT_PATH(r1) - cmpwi r0, 0 - bne guest_exit_short_path - /* For hash guest, read the guest SLB and save it away */ - ld r5, VCPU_KVM(r9) - lbz r0, KVM_RADIX(r5) li r5, 0 - cmpwi r0, 0 - bne 0f /* for radix, save 0 entries */ lwz r0,VCPU_SLB_NR(r9) /* number of entries in SLB */ mtctr r0 li r6,0 @@ -1525,9 +1172,6 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ stw r5,VCPU_SLB_MAX(r9) /* load host SLB entries */ -BEGIN_MMU_FTR_SECTION - b guest_bypass -END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) ld r8,PACA_SLBSHADOWPTR(r13) .rept SLB_NUM_BOLTED @@ -1540,21 +1184,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) slbmte r6,r5 1: addi r8,r8,16 .endr - b guest_bypass - -0: /* - * Sanitise radix guest SLB, see guest_exit_short_path comment. - * We clear vcpu->arch.slb_max to match earlier behaviour. - */ - li r0,0 - stw r0,VCPU_SLB_MAX(r9) - slbmte r0,r0 - li r4,1 - slbmte r0,r4 - li r4,2 - slbmte r0,r4 - li r4,3 - slbmte r0,r4 guest_bypass: stw r12, STACK_SLOT_TRAP(r1) @@ -1564,12 +1193,6 @@ guest_bypass: ld r3, HSTATE_KVM_VCORE(r13) mfspr r5,SPRN_DEC mftb r6 - /* On P9, if the guest has large decr enabled, don't sign extend */ -BEGIN_FTR_SECTION - ld r4, VCORE_LPCR(r3) - andis. r4, r4, LPCR_LD@h - bne 16f -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) extsw r5,r5 16: add r5,r5,r6 /* r5 is a guest timebase value here, convert to host TB */ @@ -1643,7 +1266,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) std r6, VCPU_BESCR(r9) stw r7, VCPU_GUEST_PID(r9) std r8, VCPU_WORT(r9) -BEGIN_FTR_SECTION mfspr r5, SPRN_TCSCR mfspr r6, SPRN_ACOP mfspr r7, SPRN_CSIGR @@ -1652,17 +1274,10 @@ BEGIN_FTR_SECTION std r6, VCPU_ACOP(r9) std r7, VCPU_CSIGR(r9) std r8, VCPU_TACR(r9) -FTR_SECTION_ELSE - mfspr r5, SPRN_TIDR - mfspr r6, SPRN_PSSCR - std r5, VCPU_TID(r9) - rldicl r6, r6, 4, 50 /* r6 &= PSSCR_GUEST_VIS */ - rotldi r6, r6, 60 - std r6, VCPU_PSSCR(r9) - /* Restore host HFSCR value */ - ld r7, STACK_SLOT_HFSCR(r1) - mtspr SPRN_HFSCR, r7 -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) +BEGIN_FTR_SECTION + ld r5, STACK_SLOT_FSCR(r1) + mtspr SPRN_FSCR, r5 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* * Restore various registers to 0, where non-zero values * set by the guest could disrupt the host. @@ -1670,13 +1285,11 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) li r0, 0 mtspr SPRN_PSPB, r0 mtspr SPRN_WORT, r0 -BEGIN_FTR_SECTION mtspr SPRN_TCSCR, r0 /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ li r0, 1 sldi r0, r0, 31 mtspr SPRN_MMCRS, r0 -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) /* Save and restore AMR, IAMR and UAMOR before turning on the MMU */ ld r8, STACK_SLOT_IAMR(r1) @@ -1733,13 +1346,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) bl kvmppc_save_fp #ifdef CONFIG_PPC_TRANSACTIONAL_MEM -/* - * Branch around the call if both CPU_FTR_TM and - * CPU_FTR_P9_TM_HV_ASSIST are off. - */ BEGIN_FTR_SECTION b 91f -END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0) +END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR) */ @@ -1785,80 +1394,6 @@ BEGIN_FTR_SECTION mtspr SPRN_DAWR0, r6 mtspr SPRN_DAWRX0, r7 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -BEGIN_FTR_SECTION - ld r6, STACK_SLOT_DAWR1(r1) - ld r7, STACK_SLOT_DAWRX1(r1) - mtspr SPRN_DAWR1, r6 - mtspr SPRN_DAWRX1, r7 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S | CPU_FTR_DAWR1) -BEGIN_FTR_SECTION - ld r5, STACK_SLOT_TID(r1) - ld r6, STACK_SLOT_PSSCR(r1) - ld r7, STACK_SLOT_PID(r1) - mtspr SPRN_TIDR, r5 - mtspr SPRN_PSSCR, r6 - mtspr SPRN_PID, r7 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) - -#ifdef CONFIG_PPC_RADIX_MMU - /* - * Are we running hash or radix ? - */ - ld r5, VCPU_KVM(r9) - lbz r0, KVM_RADIX(r5) - cmpwi cr2, r0, 0 - beq cr2, 2f - - /* - * Radix: do eieio; tlbsync; ptesync sequence in case we - * interrupted the guest between a tlbie and a ptesync. - */ - eieio - tlbsync - ptesync - -BEGIN_FTR_SECTION - /* Radix: Handle the case where the guest used an illegal PID */ - LOAD_REG_ADDR(r4, mmu_base_pid) - lwz r3, VCPU_GUEST_PID(r9) - lwz r5, 0(r4) - cmpw cr0,r3,r5 - blt 2f - - /* - * Illegal PID, the HW might have prefetched and cached in the TLB - * some translations for the LPID 0 / guest PID combination which - * Linux doesn't know about, so we need to flush that PID out of - * the TLB. First we need to set LPIDR to 0 so tlbiel applies to - * the right context. - */ - li r0,0 - mtspr SPRN_LPID,r0 - isync - - /* Then do a congruence class local flush */ - ld r6,VCPU_KVM(r9) - lwz r0,KVM_TLB_SETS(r6) - mtctr r0 - li r7,0x400 /* IS field = 0b01 */ - ptesync - sldi r0,r3,32 /* RS has PID */ -1: PPC_TLBIEL(7,0,2,1,1) /* RIC=2, PRS=1, R=1 */ - addi r7,r7,0x1000 - bdnz 1b - ptesync -END_FTR_SECTION_IFSET(CPU_FTR_P9_RADIX_PREFETCH_BUG) - -2: -#endif /* CONFIG_PPC_RADIX_MMU */ - - /* - * cp_abort is required if the processor supports local copy-paste - * to clear the copy buffer that was under control of the guest. - */ -BEGIN_FTR_SECTION - PPC_CP_ABORT -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) /* * POWER7/POWER8 guest -> host partition switch code. @@ -1895,13 +1430,11 @@ kvmhv_switch_to_host: /* Primary thread switches back to host partition */ lwz r7,KVM_HOST_LPID(r4) -BEGIN_FTR_SECTION ld r6,KVM_HOST_SDR1(r4) li r8,LPID_RSVD /* switch to reserved LPID */ mtspr SPRN_LPID,r8 ptesync mtspr SPRN_SDR1,r6 /* switch to host page table */ -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) mtspr SPRN_LPID,r7 isync @@ -2110,26 +1643,13 @@ kvmppc_tm_emul: * reflect the HDSI to the guest as a DSI. */ kvmppc_hdsi: - ld r3, VCPU_KVM(r9) - lbz r0, KVM_RADIX(r3) mfspr r4, SPRN_HDAR mfspr r6, SPRN_HDSISR -BEGIN_FTR_SECTION - /* Look for DSISR canary. If we find it, retry instruction */ - cmpdi r6, 0x7fff - beq 6f -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) - cmpwi r0, 0 - bne .Lradix_hdsi /* on radix, just save DAR/DSISR/ASDR */ /* HPTE not found fault or protection fault? */ andis. r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h beq 1f /* if not, send it to the guest */ andi. r0, r11, MSR_DR /* data relocation enabled? */ beq 3f -BEGIN_FTR_SECTION - mfspr r5, SPRN_ASDR /* on POWER9, use ASDR to get VSID */ - b 4f -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) clrrdi r0, r4, 28 PPC_SLBFEE_DOT(R5, R0) /* if so, look up SLB */ li r0, BOOK3S_INTERRUPT_DATA_SEGMENT @@ -2197,31 +1717,15 @@ fast_interrupt_c_return: stb r0, HSTATE_IN_GUEST(r13) b guest_exit_cont -.Lradix_hdsi: - std r4, VCPU_FAULT_DAR(r9) - stw r6, VCPU_FAULT_DSISR(r9) -.Lradix_hisi: - mfspr r5, SPRN_ASDR - std r5, VCPU_FAULT_GPA(r9) - b guest_exit_cont - /* * Similarly for an HISI, reflect it to the guest as an ISI unless * it is an HPTE not found fault for a page that we have paged out. */ kvmppc_hisi: - ld r3, VCPU_KVM(r9) - lbz r0, KVM_RADIX(r3) - cmpwi r0, 0 - bne .Lradix_hisi /* for radix, just save ASDR */ andis. r0, r11, SRR1_ISI_NOPT@h beq 1f andi. r0, r11, MSR_IR /* instruction relocation enabled? */ beq 3f -BEGIN_FTR_SECTION - mfspr r5, SPRN_ASDR /* on POWER9, use ASDR to get VSID */ - b 4f -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) clrrdi r0, r10, 28 PPC_SLBFEE_DOT(R5, R0) /* if so, look up SLB */ li r0, BOOK3S_INTERRUPT_INST_SEGMENT @@ -2269,10 +1773,6 @@ hcall_try_real_mode: andi. r0,r11,MSR_PR /* sc 1 from userspace - reflect to guest syscall */ bne sc_1_fast_return - /* sc 1 from nested guest - give it to L1 to handle */ - ld r0, VCPU_NESTED(r9) - cmpdi r0, 0 - bne guest_exit_cont clrrdi r3,r3,2 cmpldi r3,hcall_real_table_end - hcall_real_table bge guest_exit_cont @@ -2537,7 +2037,7 @@ hcall_real_table: #else .long 0 /* 0x2fc - H_XIRR_X*/ #endif - .long DOTSYM(kvmppc_h_random) - hcall_real_table + .long DOTSYM(kvmppc_rm_h_random) - hcall_real_table .globl hcall_real_table_end hcall_real_table_end: @@ -2668,13 +2168,9 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */ bl kvmppc_save_fp #ifdef CONFIG_PPC_TRANSACTIONAL_MEM -/* - * Branch around the call if both CPU_FTR_TM and - * CPU_FTR_P9_TM_HV_ASSIST are off. - */ BEGIN_FTR_SECTION b 91f -END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0) +END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR) */ @@ -2694,15 +2190,8 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0) mfspr r3, SPRN_DEC mfspr r4, SPRN_HDEC mftb r5 -BEGIN_FTR_SECTION - /* On P9 check whether the guest has large decrementer mode enabled */ - ld r6, HSTATE_KVM_VCORE(r13) - ld r6, VCORE_LPCR(r6) - andis. r6, r6, LPCR_LD@h - bne 68f -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) extsw r3, r3 -68: EXTEND_HDEC(r4) + extsw r4, r4 cmpd r3, r4 ble 67f mtspr SPRN_DEC, r4 @@ -2747,28 +2236,11 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) kvm_nap_sequence: /* desired LPCR value in r5 */ -BEGIN_FTR_SECTION - /* - * PSSCR bits: exit criterion = 1 (wakeup based on LPCR at sreset) - * enable state loss = 1 (allow SMT mode switch) - * requested level = 0 (just stop dispatching) - */ - lis r3, (PSSCR_EC | PSSCR_ESL)@h - /* Set LPCR_PECE_HVEE bit to enable wakeup by HV interrupts */ - li r4, LPCR_PECE_HVEE@higher - sldi r4, r4, 32 - or r5, r5, r4 -FTR_SECTION_ELSE li r3, PNV_THREAD_NAP -ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) mtspr SPRN_LPCR,r5 isync -BEGIN_FTR_SECTION - bl isa300_idle_stop_mayloss -FTR_SECTION_ELSE bl isa206_idle_insn_mayloss -ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) mfspr r0, SPRN_CTRLF ori r0, r0, 1 @@ -2787,10 +2259,8 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) beq kvm_end_cede cmpwi r0, NAPPING_NOVCPU beq kvm_novcpu_wakeup -BEGIN_FTR_SECTION cmpwi r0, NAPPING_UNSPLIT beq kvm_unsplit_wakeup -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) twi 31,0,0 /* Nap state must not be zero */ 33: mr r4, r3 @@ -2810,13 +2280,9 @@ kvm_end_cede: #endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM -/* - * Branch around the call if both CPU_FTR_TM and - * CPU_FTR_P9_TM_HV_ASSIST are off. - */ BEGIN_FTR_SECTION b 91f -END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0) +END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR) */ @@ -2906,47 +2372,7 @@ kvm_cede_prodded: /* we've ceded but we want to give control to the host */ kvm_cede_exit: ld r9, HSTATE_KVM_VCPU(r13) -#ifdef CONFIG_KVM_XICS - /* are we using XIVE with single escalation? */ - ld r10, VCPU_XIVE_ESC_VADDR(r9) - cmpdi r10, 0 - beq 3f - li r6, XIVE_ESB_SET_PQ_00 - /* - * If we still have a pending escalation, abort the cede, - * and we must set PQ to 10 rather than 00 so that we don't - * potentially end up with two entries for the escalation - * interrupt in the XIVE interrupt queue. In that case - * we also don't want to set xive_esc_on to 1 here in - * case we race with xive_esc_irq(). - */ - lbz r5, VCPU_XIVE_ESC_ON(r9) - cmpwi r5, 0 - beq 4f - li r0, 0 - stb r0, VCPU_CEDED(r9) - /* - * The escalation interrupts are special as we don't EOI them. - * There is no need to use the load-after-store ordering offset - * to set PQ to 10 as we won't use StoreEOI. - */ - li r6, XIVE_ESB_SET_PQ_10 - b 5f -4: li r0, 1 - stb r0, VCPU_XIVE_ESC_ON(r9) - /* make sure store to xive_esc_on is seen before xive_esc_irq runs */ - sync -5: /* Enable XIVE escalation */ - mfmsr r0 - andi. r0, r0, MSR_DR /* in real mode? */ - beq 1f - ldx r0, r10, r6 - b 2f -1: ld r10, VCPU_XIVE_ESC_RADDR(r9) - ldcix r0, r10, r6 -2: sync -#endif /* CONFIG_KVM_XICS */ -3: b guest_exit_cont + b guest_exit_cont /* Try to do machine check recovery in real mode */ machine_check_realmode: @@ -3023,10 +2449,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) PPC_MSGCLR(6) /* see if it's a host IPI */ li r3, 1 -BEGIN_FTR_SECTION - PPC_MSGSYNC - lwsync -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) lbz r0, HSTATE_HOST_IPI(r13) cmpwi r0, 0 bnelr @@ -3335,73 +2757,12 @@ kvmppc_bad_host_intr: std r3, STACK_FRAME_OVERHEAD-16(r1) /* - * On POWER9 do a minimal restore of the MMU and call C code, - * which will print a message and panic. * XXX On POWER7 and POWER8, we just spin here since we don't * know what the other threads are doing (and we don't want to * coordinate with them) - but at least we now have register state * in memory that we might be able to look at from another CPU. */ -BEGIN_FTR_SECTION b . -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) - ld r9, HSTATE_KVM_VCPU(r13) - ld r10, VCPU_KVM(r9) - - li r0, 0 - mtspr SPRN_AMR, r0 - mtspr SPRN_IAMR, r0 - mtspr SPRN_CIABR, r0 - mtspr SPRN_DAWRX0, r0 -BEGIN_FTR_SECTION - mtspr SPRN_DAWRX1, r0 -END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) - - /* Clear hash and radix guest SLB, see guest_exit_short_path comment. */ - slbmte r0, r0 - PPC_SLBIA(6) - -BEGIN_MMU_FTR_SECTION - b 4f -END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) - - ptesync - ld r8, PACA_SLBSHADOWPTR(r13) - .rept SLB_NUM_BOLTED - li r3, SLBSHADOW_SAVEAREA - LDX_BE r5, r8, r3 - addi r3, r3, 8 - LDX_BE r6, r8, r3 - andis. r7, r5, SLB_ESID_V@h - beq 3f - slbmte r6, r5 -3: addi r8, r8, 16 - .endr - -4: lwz r7, KVM_HOST_LPID(r10) - mtspr SPRN_LPID, r7 - mtspr SPRN_PID, r0 - ld r8, KVM_HOST_LPCR(r10) - mtspr SPRN_LPCR, r8 - isync - li r0, KVM_GUEST_MODE_NONE - stb r0, HSTATE_IN_GUEST(r13) - - /* - * Turn on the MMU and jump to C code - */ - bcl 20, 31, .+4 -5: mflr r3 - addi r3, r3, 9f - 5b - li r4, -1 - rldimi r3, r4, 62, 0 /* ensure 0xc000000000000000 bits are set */ - ld r4, PACAKMSR(r13) - mtspr SPRN_SRR0, r3 - mtspr SPRN_SRR1, r4 - RFI_TO_KERNEL -9: addi r3, r1, STACK_FRAME_OVERHEAD - bl kvmppc_bad_interrupt - b 9b /* * This mimics the MSR transition on IRQ delivery. The new guest MSR is taken diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index d7733b07f489..71bcb0140461 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -493,7 +493,7 @@ static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr) if (!vcpu->arch.pending_exceptions) { kvm_vcpu_block(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); - vcpu->stat.halt_wakeup++; + vcpu->stat.generic.halt_wakeup++; /* Unset POW bit after we woke up */ msr &= ~MSR_POW; diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index 031c8015864a..ac14239f3424 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -378,7 +378,7 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) kvmppc_set_msr_fast(vcpu, kvmppc_get_msr(vcpu) | MSR_EE); kvm_vcpu_block(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); - vcpu->stat.halt_wakeup++; + vcpu->stat.generic.halt_wakeup++; return EMULATE_DONE; case H_LOGICAL_CI_LOAD: return kvmppc_h_pr_logical_ci_load(vcpu); diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index 1f492aa4c8d6..202046a83fc1 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -164,12 +164,15 @@ kvmppc_interrupt_pr: /* 64-bit entry. Register usage at this point: * * SPRG_SCRATCH0 = guest R13 + * R9 = HSTATE_IN_GUEST * R12 = (guest CR << 32) | exit handler id * R13 = PACA * HSTATE.SCRATCH0 = guest R12 + * HSTATE.SCRATCH2 = guest R9 */ #ifdef CONFIG_PPC64 /* Match 32-bit entry */ + ld r9,HSTATE_SCRATCH2(r13) rotldi r12, r12, 32 /* Flip R12 halves for stw */ stw r12, HSTATE_SCRATCH1(r13) /* CR is now in the low half */ srdi r12, r12, 32 /* shift trap into low half */ diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index e7219b6f5f9a..9268d386b128 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -128,6 +128,71 @@ void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(kvmppc_xive_push_vcpu); /* + * Pull a vcpu's context from the XIVE on guest exit. + * This assumes we are in virtual mode (MMU on) + */ +void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu) +{ + void __iomem *tima = local_paca->kvm_hstate.xive_tima_virt; + + if (!vcpu->arch.xive_pushed) + return; + + /* + * Should not have been pushed if there is no tima + */ + if (WARN_ON(!tima)) + return; + + eieio(); + /* First load to pull the context, we ignore the value */ + __raw_readl(tima + TM_SPC_PULL_OS_CTX); + /* Second load to recover the context state (Words 0 and 1) */ + vcpu->arch.xive_saved_state.w01 = __raw_readq(tima + TM_QW1_OS); + + /* Fixup some of the state for the next load */ + vcpu->arch.xive_saved_state.lsmfb = 0; + vcpu->arch.xive_saved_state.ack = 0xff; + vcpu->arch.xive_pushed = 0; + eieio(); +} +EXPORT_SYMBOL_GPL(kvmppc_xive_pull_vcpu); + +void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu) +{ + void __iomem *esc_vaddr = (void __iomem *)vcpu->arch.xive_esc_vaddr; + + if (!esc_vaddr) + return; + + /* we are using XIVE with single escalation */ + + if (vcpu->arch.xive_esc_on) { + /* + * If we still have a pending escalation, abort the cede, + * and we must set PQ to 10 rather than 00 so that we don't + * potentially end up with two entries for the escalation + * interrupt in the XIVE interrupt queue. In that case + * we also don't want to set xive_esc_on to 1 here in + * case we race with xive_esc_irq(). + */ + vcpu->arch.ceded = 0; + /* + * The escalation interrupts are special as we don't EOI them. + * There is no need to use the load-after-store ordering offset + * to set PQ to 10 as we won't use StoreEOI. + */ + __raw_readq(esc_vaddr + XIVE_ESB_SET_PQ_10); + } else { + vcpu->arch.xive_esc_on = true; + mb(); + __raw_readq(esc_vaddr + XIVE_ESB_SET_PQ_00); + } + mb(); +} +EXPORT_SYMBOL_GPL(kvmppc_xive_rearm_escalation); + +/* * This is a simple trigger for a generic XIVE IRQ. This must * only be called for interrupts that support a trigger page */ @@ -2075,6 +2140,36 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) return 0; } +int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + + /* The VM should have configured XICS mode before doing XICS hcalls. */ + if (!kvmppc_xics_enabled(vcpu)) + return H_TOO_HARD; + + switch (req) { + case H_XIRR: + return xive_vm_h_xirr(vcpu); + case H_CPPR: + return xive_vm_h_cppr(vcpu, kvmppc_get_gpr(vcpu, 4)); + case H_EOI: + return xive_vm_h_eoi(vcpu, kvmppc_get_gpr(vcpu, 4)); + case H_IPI: + return xive_vm_h_ipi(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5)); + case H_IPOLL: + return xive_vm_h_ipoll(vcpu, kvmppc_get_gpr(vcpu, 4)); + case H_XIRR_X: + xive_vm_h_xirr(vcpu); + kvmppc_set_gpr(vcpu, 5, get_tb() + vc->tb_offset); + return H_SUCCESS; + } + + return H_UNSUPPORTED; +} +EXPORT_SYMBOL_GPL(kvmppc_xive_xics_hcall); + int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; @@ -2257,21 +2352,3 @@ struct kvm_device_ops kvm_xive_ops = { .get_attr = xive_get_attr, .has_attr = xive_has_attr, }; - -void kvmppc_xive_init_module(void) -{ - __xive_vm_h_xirr = xive_vm_h_xirr; - __xive_vm_h_ipoll = xive_vm_h_ipoll; - __xive_vm_h_ipi = xive_vm_h_ipi; - __xive_vm_h_cppr = xive_vm_h_cppr; - __xive_vm_h_eoi = xive_vm_h_eoi; -} - -void kvmppc_xive_exit_module(void) -{ - __xive_vm_h_xirr = NULL; - __xive_vm_h_ipoll = NULL; - __xive_vm_h_ipi = NULL; - __xive_vm_h_cppr = NULL; - __xive_vm_h_eoi = NULL; -} diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index 86c24a4ad809..afe9eeac6d56 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -289,13 +289,6 @@ extern int xive_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, extern int xive_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr); extern int xive_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr); -extern unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu); -extern unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server); -extern int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server, - unsigned long mfrr); -extern int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr); -extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr); - /* * Common Xive routines for XICS-over-XIVE and XIVE native */ diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 76800c84f2a3..1253666dd4d8 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -1281,13 +1281,3 @@ struct kvm_device_ops kvm_xive_native_ops = { .has_attr = kvmppc_xive_native_has_attr, .mmap = kvmppc_xive_native_mmap, }; - -void kvmppc_xive_native_init_module(void) -{ - ; -} - -void kvmppc_xive_native_exit_module(void) -{ - ; -} diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 7d5fe43f85c4..551b30d84aee 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -36,29 +36,59 @@ unsigned long kvmppc_booke_handlers; -struct kvm_stats_debugfs_item debugfs_entries[] = { - VCPU_STAT("mmio", mmio_exits), - VCPU_STAT("sig", signal_exits), - VCPU_STAT("itlb_r", itlb_real_miss_exits), - VCPU_STAT("itlb_v", itlb_virt_miss_exits), - VCPU_STAT("dtlb_r", dtlb_real_miss_exits), - VCPU_STAT("dtlb_v", dtlb_virt_miss_exits), - VCPU_STAT("sysc", syscall_exits), - VCPU_STAT("isi", isi_exits), - VCPU_STAT("dsi", dsi_exits), - VCPU_STAT("inst_emu", emulated_inst_exits), - VCPU_STAT("dec", dec_exits), - VCPU_STAT("ext_intr", ext_intr_exits), - VCPU_STAT("halt_successful_poll", halt_successful_poll), - VCPU_STAT("halt_attempted_poll", halt_attempted_poll), - VCPU_STAT("halt_poll_invalid", halt_poll_invalid), - VCPU_STAT("halt_wakeup", halt_wakeup), - VCPU_STAT("doorbell", dbell_exits), - VCPU_STAT("guest doorbell", gdbell_exits), - VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), - VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), - VM_STAT("remote_tlb_flush", remote_tlb_flush), - { NULL } +const struct _kvm_stats_desc kvm_vm_stats_desc[] = { + KVM_GENERIC_VM_STATS(), + STATS_DESC_ICOUNTER(VM, num_2M_pages), + STATS_DESC_ICOUNTER(VM, num_1G_pages) +}; +static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == + sizeof(struct kvm_vm_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vm_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vm_stats_desc), +}; + +const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { + KVM_GENERIC_VCPU_STATS(), + STATS_DESC_COUNTER(VCPU, sum_exits), + STATS_DESC_COUNTER(VCPU, mmio_exits), + STATS_DESC_COUNTER(VCPU, signal_exits), + STATS_DESC_COUNTER(VCPU, light_exits), + STATS_DESC_COUNTER(VCPU, itlb_real_miss_exits), + STATS_DESC_COUNTER(VCPU, itlb_virt_miss_exits), + STATS_DESC_COUNTER(VCPU, dtlb_real_miss_exits), + STATS_DESC_COUNTER(VCPU, dtlb_virt_miss_exits), + STATS_DESC_COUNTER(VCPU, syscall_exits), + STATS_DESC_COUNTER(VCPU, isi_exits), + STATS_DESC_COUNTER(VCPU, dsi_exits), + STATS_DESC_COUNTER(VCPU, emulated_inst_exits), + STATS_DESC_COUNTER(VCPU, dec_exits), + STATS_DESC_COUNTER(VCPU, ext_intr_exits), + STATS_DESC_TIME_NSEC(VCPU, halt_wait_ns), + STATS_DESC_COUNTER(VCPU, halt_successful_wait), + STATS_DESC_COUNTER(VCPU, dbell_exits), + STATS_DESC_COUNTER(VCPU, gdbell_exits), + STATS_DESC_COUNTER(VCPU, ld), + STATS_DESC_COUNTER(VCPU, st), + STATS_DESC_COUNTER(VCPU, pthru_all), + STATS_DESC_COUNTER(VCPU, pthru_host), + STATS_DESC_COUNTER(VCPU, pthru_bad_aff) +}; +static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == + sizeof(struct kvm_vcpu_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vcpu_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vcpu_stats_desc), }; /* TODO: use vcpu_printf() */ diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index a2a68a958fa0..be33b5321a76 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -682,6 +682,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = !!(hv_enabled && kvmppc_hv_ops->enable_dawr1 && !kvmppc_hv_ops->enable_dawr1(NULL)); break; + case KVM_CAP_PPC_RPT_INVALIDATE: + r = 1; + break; #endif default: r = 0; diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 1fd31b4b0e13..fe26f2fa0f3f 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -14,6 +14,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/sched/mm.h> +#include <linux/stop_machine.h> #include <asm/cputable.h> #include <asm/code-patching.h> #include <asm/page.h> @@ -149,17 +150,17 @@ static void do_stf_entry_barrier_fixups(enum stf_barrier_type types) pr_devel("patching dest %lx\n", (unsigned long)dest); - patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); - - if (types & STF_BARRIER_FALLBACK) + // See comment in do_entry_flush_fixups() RE order of patching + if (types & STF_BARRIER_FALLBACK) { + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); patch_branch((struct ppc_inst *)(dest + 1), - (unsigned long)&stf_barrier_fallback, - BRANCH_SET_LINK); - else - patch_instruction((struct ppc_inst *)(dest + 1), - ppc_inst(instrs[1])); - - patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + (unsigned long)&stf_barrier_fallback, BRANCH_SET_LINK); + } else { + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + } } printk(KERN_DEBUG "stf-barrier: patched %d entry locations (%s barrier)\n", i, @@ -227,11 +228,25 @@ static void do_stf_exit_barrier_fixups(enum stf_barrier_type types) : "unknown"); } +static int __do_stf_barrier_fixups(void *data) +{ + enum stf_barrier_type *types = data; + + do_stf_entry_barrier_fixups(*types); + do_stf_exit_barrier_fixups(*types); + + return 0; +} void do_stf_barrier_fixups(enum stf_barrier_type types) { - do_stf_entry_barrier_fixups(types); - do_stf_exit_barrier_fixups(types); + /* + * The call to the fallback entry flush, and the fallback/sync-ori exit + * flush can not be safely patched in/out while other CPUs are executing + * them. So call __do_stf_barrier_fixups() on one CPU while all other CPUs + * spin in the stop machine core with interrupts hard disabled. + */ + stop_machine(__do_stf_barrier_fixups, &types, NULL); } void do_uaccess_flush_fixups(enum l1d_flush_type types) @@ -284,8 +299,9 @@ void do_uaccess_flush_fixups(enum l1d_flush_type types) : "unknown"); } -void do_entry_flush_fixups(enum l1d_flush_type types) +static int __do_entry_flush_fixups(void *data) { + enum l1d_flush_type types = *(enum l1d_flush_type *)data; unsigned int instrs[3], *dest; long *start, *end; int i; @@ -309,6 +325,31 @@ void do_entry_flush_fixups(enum l1d_flush_type types) if (types & L1D_FLUSH_MTTRIG) instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + /* + * If we're patching in or out the fallback flush we need to be careful about the + * order in which we patch instructions. That's because it's possible we could + * take a page fault after patching one instruction, so the sequence of + * instructions must be safe even in a half patched state. + * + * To make that work, when patching in the fallback flush we patch in this order: + * - the mflr (dest) + * - the mtlr (dest + 2) + * - the branch (dest + 1) + * + * That ensures the sequence is safe to execute at any point. In contrast if we + * patch the mtlr last, it's possible we could return from the branch and not + * restore LR, leading to a crash later. + * + * When patching out the fallback flush (either with nops or another flush type), + * we patch in this order: + * - the branch (dest + 1) + * - the mtlr (dest + 2) + * - the mflr (dest) + * + * Note we are protected by stop_machine() from other CPUs executing the code in a + * semi-patched state. + */ + start = PTRRELOC(&__start___entry_flush_fixup); end = PTRRELOC(&__stop___entry_flush_fixup); for (i = 0; start < end; start++, i++) { @@ -316,15 +357,16 @@ void do_entry_flush_fixups(enum l1d_flush_type types) pr_devel("patching dest %lx\n", (unsigned long)dest); - patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); - - if (types == L1D_FLUSH_FALLBACK) - patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&entry_flush_fallback, - BRANCH_SET_LINK); - else + if (types == L1D_FLUSH_FALLBACK) { + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_branch((struct ppc_inst *)(dest + 1), + (unsigned long)&entry_flush_fallback, BRANCH_SET_LINK); + } else { patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); - - patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + } } start = PTRRELOC(&__start___scv_entry_flush_fixup); @@ -334,15 +376,16 @@ void do_entry_flush_fixups(enum l1d_flush_type types) pr_devel("patching dest %lx\n", (unsigned long)dest); - patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); - - if (types == L1D_FLUSH_FALLBACK) - patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&scv_entry_flush_fallback, - BRANCH_SET_LINK); - else + if (types == L1D_FLUSH_FALLBACK) { + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_branch((struct ppc_inst *)(dest + 1), + (unsigned long)&scv_entry_flush_fallback, BRANCH_SET_LINK); + } else { patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); - - patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + } } @@ -354,6 +397,19 @@ void do_entry_flush_fixups(enum l1d_flush_type types) : "ori type" : (types & L1D_FLUSH_MTTRIG) ? "mttrig type" : "unknown"); + + return 0; +} + +void do_entry_flush_fixups(enum l1d_flush_type types) +{ + /* + * The call to the fallback flush can not be safely patched in/out while + * other CPUs are executing it. So call __do_entry_flush_fixups() on one + * CPU while all other CPUs spin in the stop machine core with interrupts + * hard disabled. + */ + stop_machine(__do_entry_flush_fixups, &types, NULL); } void do_rfi_flush_fixups(enum l1d_flush_type types) diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 5fef8db3b463..6e3495221ab7 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -357,30 +357,19 @@ static void __init radix_init_pgtable(void) } /* Find out how many PID bits are supported */ - if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) { - if (!mmu_pid_bits) - mmu_pid_bits = 20; - mmu_base_pid = 1; - } else if (cpu_has_feature(CPU_FTR_HVMODE)) { - if (!mmu_pid_bits) - mmu_pid_bits = 20; -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + if (!cpu_has_feature(CPU_FTR_HVMODE) && + cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) { /* - * When KVM is possible, we only use the top half of the - * PID space to avoid collisions between host and guest PIDs - * which can cause problems due to prefetch when exiting the - * guest with AIL=3 + * Older versions of KVM on these machines perfer if the + * guest only uses the low 19 PID bits. */ - mmu_base_pid = 1 << (mmu_pid_bits - 1); -#else - mmu_base_pid = 1; -#endif - } else { - /* The guest uses the bottom half of the PID space */ if (!mmu_pid_bits) mmu_pid_bits = 19; - mmu_base_pid = 1; + } else { + if (!mmu_pid_bits) + mmu_pid_bits = 20; } + mmu_base_pid = 1; /* * Allocate Partition table and process table for the @@ -486,6 +475,7 @@ static int __init radix_dt_scan_page_sizes(unsigned long node, def = &mmu_psize_defs[idx]; def->shift = shift; def->ap = ap; + def->h_rpt_pgsize = psize_to_rpti_pgsize(idx); } /* needed ? */ @@ -560,9 +550,13 @@ void __init radix__early_init_devtree(void) */ mmu_psize_defs[MMU_PAGE_4K].shift = 12; mmu_psize_defs[MMU_PAGE_4K].ap = 0x0; + mmu_psize_defs[MMU_PAGE_4K].h_rpt_pgsize = + psize_to_rpti_pgsize(MMU_PAGE_4K); mmu_psize_defs[MMU_PAGE_64K].shift = 16; mmu_psize_defs[MMU_PAGE_64K].ap = 0x5; + mmu_psize_defs[MMU_PAGE_64K].h_rpt_pgsize = + psize_to_rpti_pgsize(MMU_PAGE_64K); } /* diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 409e61210789..318ec4f33661 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -20,10 +20,6 @@ #include "internal.h" -#define RIC_FLUSH_TLB 0 -#define RIC_FLUSH_PWC 1 -#define RIC_FLUSH_ALL 2 - /* * tlbiel instruction for radix, set invalidation * i.e., r=1 and is=01 or is=10 or is=11 @@ -130,6 +126,21 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric) trace_tlbie(0, 0, rb, rs, ric, prs, r); } +static __always_inline void __tlbie_pid_lpid(unsigned long pid, + unsigned long lpid, + unsigned long ric) +{ + unsigned long rb, rs, prs, r; + + rb = PPC_BIT(53); /* IS = 1 */ + rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); + prs = 1; /* process scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(0, 0, rb, rs, ric, prs, r); +} static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric) { unsigned long rb,rs,prs,r; @@ -190,6 +201,23 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid, trace_tlbie(0, 0, rb, rs, ric, prs, r); } +static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid, + unsigned long lpid, + unsigned long ap, unsigned long ric) +{ + unsigned long rb, rs, prs, r; + + rb = va & ~(PPC_BITMASK(52, 63)); + rb |= ap << PPC_BITLSHIFT(58); + rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); + prs = 1; /* process scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(0, 0, rb, rs, ric, prs, r); +} + static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid, unsigned long ap, unsigned long ric) { @@ -235,6 +263,22 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid, } } +static inline void fixup_tlbie_va_range_lpid(unsigned long va, + unsigned long pid, + unsigned long lpid, + unsigned long ap) +{ + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB); + } +} + static inline void fixup_tlbie_pid(unsigned long pid) { /* @@ -254,6 +298,25 @@ static inline void fixup_tlbie_pid(unsigned long pid) } } +static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid) +{ + /* + * We can use any address for the invalidation, pick one which is + * probably unused as an optimisation. + */ + unsigned long va = ((1UL << 52) - 1); + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K), + RIC_FLUSH_TLB); + } +} static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid, unsigned long ap) @@ -344,6 +407,31 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric) asm volatile("eieio; tlbsync; ptesync": : :"memory"); } +static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid, + unsigned long ric) +{ + asm volatile("ptesync" : : : "memory"); + + /* + * Workaround the fact that the "ric" argument to __tlbie_pid + * must be a compile-time contraint to match the "i" constraint + * in the asm statement. + */ + switch (ric) { + case RIC_FLUSH_TLB: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB); + fixup_tlbie_pid_lpid(pid, lpid); + break; + case RIC_FLUSH_PWC: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); + break; + case RIC_FLUSH_ALL: + default: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL); + fixup_tlbie_pid_lpid(pid, lpid); + } + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); +} struct tlbiel_pid { unsigned long pid; unsigned long ric; @@ -469,6 +557,20 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end, fixup_tlbie_va_range(addr - page_size, pid, ap); } +static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end, + unsigned long pid, unsigned long lpid, + unsigned long page_size, + unsigned long psize) +{ + unsigned long addr; + unsigned long ap = mmu_get_ap(psize); + + for (addr = start; addr < end; addr += page_size) + __tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB); + + fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap); +} + static __always_inline void _tlbie_va(unsigned long va, unsigned long pid, unsigned long psize, unsigned long ric) { @@ -549,6 +651,18 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end, asm volatile("eieio; tlbsync; ptesync": : :"memory"); } +static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end, + unsigned long pid, unsigned long lpid, + unsigned long page_size, + unsigned long psize, bool also_pwc) +{ + asm volatile("ptesync" : : : "memory"); + if (also_pwc) + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); + __tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize); + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); +} + static inline void _tlbiel_va_range_multicast(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long pid, unsigned long page_size, @@ -1338,47 +1452,57 @@ void radix__flush_tlb_all(void) } #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE -extern void radix_kvm_prefetch_workaround(struct mm_struct *mm) +/* + * Performs process-scoped invalidations for a given LPID + * as part of H_RPT_INVALIDATE hcall. + */ +void do_h_rpt_invalidate_prt(unsigned long pid, unsigned long lpid, + unsigned long type, unsigned long pg_sizes, + unsigned long start, unsigned long end) { - unsigned long pid = mm->context.id; + unsigned long psize, nr_pages; + struct mmu_psize_def *def; + bool flush_pid; - if (unlikely(pid == MMU_NO_CONTEXT)) + /* + * A H_RPTI_TYPE_ALL request implies RIC=3, hence + * do a single IS=1 based flush. + */ + if ((type & H_RPTI_TYPE_ALL) == H_RPTI_TYPE_ALL) { + _tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL); return; + } - if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) - return; + if (type & H_RPTI_TYPE_PWC) + _tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); - /* - * If this context hasn't run on that CPU before and KVM is - * around, there's a slim chance that the guest on another - * CPU just brought in obsolete translation into the TLB of - * this CPU due to a bad prefetch using the guest PID on - * the way into the hypervisor. - * - * We work around this here. If KVM is possible, we check if - * any sibling thread is in KVM. If it is, the window may exist - * and thus we flush that PID from the core. - * - * A potential future improvement would be to mark which PIDs - * have never been used on the system and avoid it if the PID - * is new and the process has no other cpumask bit set. - */ - if (cpu_has_feature(CPU_FTR_HVMODE) && radix_enabled()) { - int cpu = smp_processor_id(); - int sib = cpu_first_thread_sibling(cpu); - bool flush = false; - - for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) { - if (sib == cpu) - continue; - if (!cpu_possible(sib)) - continue; - if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu) - flush = true; + /* Full PID flush */ + if (start == 0 && end == -1) + return _tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB); + + /* Do range invalidation for all the valid page sizes */ + for (psize = 0; psize < MMU_PAGE_COUNT; psize++) { + def = &mmu_psize_defs[psize]; + if (!(pg_sizes & def->h_rpt_pgsize)) + continue; + + nr_pages = (end - start) >> def->shift; + flush_pid = nr_pages > tlb_single_page_flush_ceiling; + + /* + * If the number of pages spanning the range is above + * the ceiling, convert the request into a full PID flush. + * And since PID flush takes out all the page sizes, there + * is no need to consider remaining page sizes. + */ + if (flush_pid) { + _tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB); + return; } - if (flush) - _tlbiel_pid(pid, RIC_FLUSH_ALL); + _tlbie_va_range_lpid(start, end, pid, lpid, + (1UL << def->shift), psize, false); } } -EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround); +EXPORT_SYMBOL_GPL(do_h_rpt_invalidate_prt); + #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c index a857af401738..74246536b832 100644 --- a/arch/powerpc/mm/mmu_context.c +++ b/arch/powerpc/mm/mmu_context.c @@ -83,9 +83,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (cpu_has_feature(CPU_FTR_ALTIVEC)) asm volatile ("dssall"); - if (new_on_cpu) - radix_kvm_prefetch_workaround(next); - else + if (!new_on_cpu) membarrier_arch_switch_mm(prev, next, tsk); /* diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 999997d9e9a9..528a7e0cf83a 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -604,7 +604,7 @@ struct p9_sprs { u64 uamor; }; -static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) +static unsigned long power9_idle_stop(unsigned long psscr) { int cpu = raw_smp_processor_id(); int first = cpu_first_thread_sibling(cpu); @@ -620,8 +620,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) if (!(psscr & (PSSCR_EC|PSSCR_ESL))) { /* EC=ESL=0 case */ - BUG_ON(!mmu_on); - /* * Wake synchronously. SRESET via xscom may still cause * a 0x100 powersave wakeup with SRR1 reason! @@ -803,8 +801,7 @@ core_woken: __slb_restore_bolted_realmode(); out: - if (mmu_on) - mtmsr(MSR_KERNEL); + mtmsr(MSR_KERNEL); return srr1; } @@ -895,7 +892,7 @@ struct p10_sprs { */ }; -static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on) +static unsigned long power10_idle_stop(unsigned long psscr) { int cpu = raw_smp_processor_id(); int first = cpu_first_thread_sibling(cpu); @@ -909,8 +906,6 @@ static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on) if (!(psscr & (PSSCR_EC|PSSCR_ESL))) { /* EC=ESL=0 case */ - BUG_ON(!mmu_on); - /* * Wake synchronously. SRESET via xscom may still cause * a 0x100 powersave wakeup with SRR1 reason! @@ -991,8 +986,7 @@ core_woken: __slb_restore_bolted_realmode(); out: - if (mmu_on) - mtmsr(MSR_KERNEL); + mtmsr(MSR_KERNEL); return srr1; } @@ -1002,40 +996,10 @@ static unsigned long arch300_offline_stop(unsigned long psscr) { unsigned long srr1; -#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE - __ppc64_runlatch_off(); if (cpu_has_feature(CPU_FTR_ARCH_31)) - srr1 = power10_idle_stop(psscr, true); + srr1 = power10_idle_stop(psscr); else - srr1 = power9_idle_stop(psscr, true); - __ppc64_runlatch_on(); -#else - /* - * Tell KVM we're entering idle. - * This does not have to be done in real mode because the P9 MMU - * is independent per-thread. Some steppings share radix/hash mode - * between threads, but in that case KVM has a barrier sync in real - * mode before and after switching between radix and hash. - * - * kvm_start_guest must still be called in real mode though, hence - * the false argument. - */ - local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE; - - __ppc64_runlatch_off(); - if (cpu_has_feature(CPU_FTR_ARCH_31)) - srr1 = power10_idle_stop(psscr, false); - else - srr1 = power9_idle_stop(psscr, false); - __ppc64_runlatch_on(); - - local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL; - /* Order setting hwthread_state vs. testing hwthread_req */ - smp_mb(); - if (local_paca->kvm_hstate.hwthread_req) - srr1 = idle_kvm_start_guest(srr1); - mtmsr(MSR_KERNEL); -#endif + srr1 = power9_idle_stop(psscr); return srr1; } @@ -1055,9 +1019,9 @@ void arch300_idle_type(unsigned long stop_psscr_val, __ppc64_runlatch_off(); if (cpu_has_feature(CPU_FTR_ARCH_31)) - srr1 = power10_idle_stop(psscr, true); + srr1 = power10_idle_stop(psscr); else - srr1 = power9_idle_stop(psscr, true); + srr1 = power9_idle_stop(psscr); __ppc64_runlatch_on(); fini_irq_for_idle_irqsoff(); diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 2136e42833af..8a2b8d64265b 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -102,6 +102,16 @@ END_FTR_SECTION(0, 1); \ #define HCALL_BRANCH(LABEL) #endif +_GLOBAL_TOC(plpar_hcall_norets_notrace) + HMT_MEDIUM + + mfcr r0 + stw r0,8(r1) + HVSC /* invoke the hypervisor */ + lwz r0,8(r1) + mtcrf 0xff,r0 + blr /* return r3 = status */ + _GLOBAL_TOC(plpar_hcall_norets) HMT_MEDIUM diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 1f3152ad7213..dab356e3ff87 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1829,30 +1829,28 @@ void hcall_tracepoint_unregfunc(void) #endif /* - * Since the tracing code might execute hcalls we need to guard against - * recursion. One example of this are spinlocks calling H_YIELD on - * shared processor partitions. + * Keep track of hcall tracing depth and prevent recursion. Warn if any is + * detected because it may indicate a problem. This will not catch all + * problems with tracing code making hcalls, because the tracing might have + * been invoked from a non-hcall, so the first hcall could recurse into it + * without warning here, but this better than nothing. + * + * Hcalls with specific problems being traced should use the _notrace + * plpar_hcall variants. */ static DEFINE_PER_CPU(unsigned int, hcall_trace_depth); -void __trace_hcall_entry(unsigned long opcode, unsigned long *args) +notrace void __trace_hcall_entry(unsigned long opcode, unsigned long *args) { unsigned long flags; unsigned int *depth; - /* - * We cannot call tracepoints inside RCU idle regions which - * means we must not trace H_CEDE. - */ - if (opcode == H_CEDE) - return; - local_irq_save(flags); depth = this_cpu_ptr(&hcall_trace_depth); - if (*depth) + if (WARN_ON_ONCE(*depth)) goto out; (*depth)++; @@ -1864,19 +1862,16 @@ out: local_irq_restore(flags); } -void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf) +notrace void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf) { unsigned long flags; unsigned int *depth; - if (opcode == H_CEDE) - return; - local_irq_save(flags); depth = this_cpu_ptr(&hcall_trace_depth); - if (*depth) + if (*depth) /* Don't warn again on the way out */ goto out; (*depth)++; diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 8925f3969478..9b4473f76e56 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -361,6 +361,7 @@ struct sie_page { }; struct kvm_vcpu_stat { + struct kvm_vcpu_stat_generic generic; u64 exit_userspace; u64 exit_null; u64 exit_external_request; @@ -370,13 +371,7 @@ struct kvm_vcpu_stat { u64 exit_validity; u64 exit_instruction; u64 exit_pei; - u64 halt_successful_poll; - u64 halt_attempted_poll; - u64 halt_poll_invalid; u64 halt_no_poll_steal; - u64 halt_wakeup; - u64 halt_poll_success_ns; - u64 halt_poll_fail_ns; u64 instruction_lctl; u64 instruction_lctlg; u64 instruction_stctl; @@ -755,12 +750,12 @@ struct kvm_vcpu_arch { }; struct kvm_vm_stat { + struct kvm_vm_stat_generic generic; u64 inject_io; u64 inject_float_mchk; u64 inject_pfault_done; u64 inject_service_signal; u64 inject_virtio; - u64 remote_tlb_flush; }; struct kvm_arch_memory_slot { diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 12decca22e7c..b3aaadc60ead 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -4,7 +4,8 @@ # Copyright IBM Corp. 2008 KVM := ../../../virt/kvm -common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o +common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o \ + $(KVM)/irqchip.o $(KVM)/vfio.o $(KVM)/binary_stats.o ccflags-y := -Ivirt/kvm -Iarch/s390/kvm diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f72f361d39dd..f9fb1e1d960d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -58,112 +58,132 @@ #define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \ (KVM_MAX_VCPUS + LOCAL_IRQS)) -struct kvm_stats_debugfs_item debugfs_entries[] = { - VCPU_STAT("userspace_handled", exit_userspace), - VCPU_STAT("exit_null", exit_null), - VCPU_STAT("pfault_sync", pfault_sync), - VCPU_STAT("exit_validity", exit_validity), - VCPU_STAT("exit_stop_request", exit_stop_request), - VCPU_STAT("exit_external_request", exit_external_request), - VCPU_STAT("exit_io_request", exit_io_request), - VCPU_STAT("exit_external_interrupt", exit_external_interrupt), - VCPU_STAT("exit_instruction", exit_instruction), - VCPU_STAT("exit_pei", exit_pei), - VCPU_STAT("exit_program_interruption", exit_program_interruption), - VCPU_STAT("exit_instr_and_program_int", exit_instr_and_program), - VCPU_STAT("exit_operation_exception", exit_operation_exception), - VCPU_STAT("halt_successful_poll", halt_successful_poll), - VCPU_STAT("halt_attempted_poll", halt_attempted_poll), - VCPU_STAT("halt_poll_invalid", halt_poll_invalid), - VCPU_STAT("halt_no_poll_steal", halt_no_poll_steal), - VCPU_STAT("halt_wakeup", halt_wakeup), - VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), - VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), - VCPU_STAT("instruction_lctlg", instruction_lctlg), - VCPU_STAT("instruction_lctl", instruction_lctl), - VCPU_STAT("instruction_stctl", instruction_stctl), - VCPU_STAT("instruction_stctg", instruction_stctg), - VCPU_STAT("deliver_ckc", deliver_ckc), - VCPU_STAT("deliver_cputm", deliver_cputm), - VCPU_STAT("deliver_emergency_signal", deliver_emergency_signal), - VCPU_STAT("deliver_external_call", deliver_external_call), - VCPU_STAT("deliver_service_signal", deliver_service_signal), - VCPU_STAT("deliver_virtio", deliver_virtio), - VCPU_STAT("deliver_stop_signal", deliver_stop_signal), - VCPU_STAT("deliver_prefix_signal", deliver_prefix_signal), - VCPU_STAT("deliver_restart_signal", deliver_restart_signal), - VCPU_STAT("deliver_program", deliver_program), - VCPU_STAT("deliver_io", deliver_io), - VCPU_STAT("deliver_machine_check", deliver_machine_check), - VCPU_STAT("exit_wait_state", exit_wait_state), - VCPU_STAT("inject_ckc", inject_ckc), - VCPU_STAT("inject_cputm", inject_cputm), - VCPU_STAT("inject_external_call", inject_external_call), - VM_STAT("inject_float_mchk", inject_float_mchk), - VCPU_STAT("inject_emergency_signal", inject_emergency_signal), - VM_STAT("inject_io", inject_io), - VCPU_STAT("inject_mchk", inject_mchk), - VM_STAT("inject_pfault_done", inject_pfault_done), - VCPU_STAT("inject_program", inject_program), - VCPU_STAT("inject_restart", inject_restart), - VM_STAT("inject_service_signal", inject_service_signal), - VCPU_STAT("inject_set_prefix", inject_set_prefix), - VCPU_STAT("inject_stop_signal", inject_stop_signal), - VCPU_STAT("inject_pfault_init", inject_pfault_init), - VM_STAT("inject_virtio", inject_virtio), - VCPU_STAT("instruction_epsw", instruction_epsw), - VCPU_STAT("instruction_gs", instruction_gs), - VCPU_STAT("instruction_io_other", instruction_io_other), - VCPU_STAT("instruction_lpsw", instruction_lpsw), - VCPU_STAT("instruction_lpswe", instruction_lpswe), - VCPU_STAT("instruction_pfmf", instruction_pfmf), - VCPU_STAT("instruction_ptff", instruction_ptff), - VCPU_STAT("instruction_stidp", instruction_stidp), - VCPU_STAT("instruction_sck", instruction_sck), - VCPU_STAT("instruction_sckpf", instruction_sckpf), - VCPU_STAT("instruction_spx", instruction_spx), - VCPU_STAT("instruction_stpx", instruction_stpx), - VCPU_STAT("instruction_stap", instruction_stap), - VCPU_STAT("instruction_iske", instruction_iske), - VCPU_STAT("instruction_ri", instruction_ri), - VCPU_STAT("instruction_rrbe", instruction_rrbe), - VCPU_STAT("instruction_sske", instruction_sske), - VCPU_STAT("instruction_ipte_interlock", instruction_ipte_interlock), - VCPU_STAT("instruction_essa", instruction_essa), - VCPU_STAT("instruction_stsi", instruction_stsi), - VCPU_STAT("instruction_stfl", instruction_stfl), - VCPU_STAT("instruction_tb", instruction_tb), - VCPU_STAT("instruction_tpi", instruction_tpi), - VCPU_STAT("instruction_tprot", instruction_tprot), - VCPU_STAT("instruction_tsch", instruction_tsch), - VCPU_STAT("instruction_sthyi", instruction_sthyi), - VCPU_STAT("instruction_sie", instruction_sie), - VCPU_STAT("instruction_sigp_sense", instruction_sigp_sense), - VCPU_STAT("instruction_sigp_sense_running", instruction_sigp_sense_running), - VCPU_STAT("instruction_sigp_external_call", instruction_sigp_external_call), - VCPU_STAT("instruction_sigp_emergency", instruction_sigp_emergency), - VCPU_STAT("instruction_sigp_cond_emergency", instruction_sigp_cond_emergency), - VCPU_STAT("instruction_sigp_start", instruction_sigp_start), - VCPU_STAT("instruction_sigp_stop", instruction_sigp_stop), - VCPU_STAT("instruction_sigp_stop_store_status", instruction_sigp_stop_store_status), - VCPU_STAT("instruction_sigp_store_status", instruction_sigp_store_status), - VCPU_STAT("instruction_sigp_store_adtl_status", instruction_sigp_store_adtl_status), - VCPU_STAT("instruction_sigp_set_arch", instruction_sigp_arch), - VCPU_STAT("instruction_sigp_set_prefix", instruction_sigp_prefix), - VCPU_STAT("instruction_sigp_restart", instruction_sigp_restart), - VCPU_STAT("instruction_sigp_cpu_reset", instruction_sigp_cpu_reset), - VCPU_STAT("instruction_sigp_init_cpu_reset", instruction_sigp_init_cpu_reset), - VCPU_STAT("instruction_sigp_unknown", instruction_sigp_unknown), - VCPU_STAT("instruction_diag_10", diagnose_10), - VCPU_STAT("instruction_diag_44", diagnose_44), - VCPU_STAT("instruction_diag_9c", diagnose_9c), - VCPU_STAT("diag_9c_ignored", diagnose_9c_ignored), - VCPU_STAT("diag_9c_forward", diagnose_9c_forward), - VCPU_STAT("instruction_diag_258", diagnose_258), - VCPU_STAT("instruction_diag_308", diagnose_308), - VCPU_STAT("instruction_diag_500", diagnose_500), - VCPU_STAT("instruction_diag_other", diagnose_other), - { NULL } +const struct _kvm_stats_desc kvm_vm_stats_desc[] = { + KVM_GENERIC_VM_STATS(), + STATS_DESC_COUNTER(VM, inject_io), + STATS_DESC_COUNTER(VM, inject_float_mchk), + STATS_DESC_COUNTER(VM, inject_pfault_done), + STATS_DESC_COUNTER(VM, inject_service_signal), + STATS_DESC_COUNTER(VM, inject_virtio) +}; +static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == + sizeof(struct kvm_vm_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vm_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vm_stats_desc), +}; + +const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { + KVM_GENERIC_VCPU_STATS(), + STATS_DESC_COUNTER(VCPU, exit_userspace), + STATS_DESC_COUNTER(VCPU, exit_null), + STATS_DESC_COUNTER(VCPU, exit_external_request), + STATS_DESC_COUNTER(VCPU, exit_io_request), + STATS_DESC_COUNTER(VCPU, exit_external_interrupt), + STATS_DESC_COUNTER(VCPU, exit_stop_request), + STATS_DESC_COUNTER(VCPU, exit_validity), + STATS_DESC_COUNTER(VCPU, exit_instruction), + STATS_DESC_COUNTER(VCPU, exit_pei), + STATS_DESC_COUNTER(VCPU, halt_no_poll_steal), + STATS_DESC_COUNTER(VCPU, instruction_lctl), + STATS_DESC_COUNTER(VCPU, instruction_lctlg), + STATS_DESC_COUNTER(VCPU, instruction_stctl), + STATS_DESC_COUNTER(VCPU, instruction_stctg), + STATS_DESC_COUNTER(VCPU, exit_program_interruption), + STATS_DESC_COUNTER(VCPU, exit_instr_and_program), + STATS_DESC_COUNTER(VCPU, exit_operation_exception), + STATS_DESC_COUNTER(VCPU, deliver_ckc), + STATS_DESC_COUNTER(VCPU, deliver_cputm), + STATS_DESC_COUNTER(VCPU, deliver_external_call), + STATS_DESC_COUNTER(VCPU, deliver_emergency_signal), + STATS_DESC_COUNTER(VCPU, deliver_service_signal), + STATS_DESC_COUNTER(VCPU, deliver_virtio), + STATS_DESC_COUNTER(VCPU, deliver_stop_signal), + STATS_DESC_COUNTER(VCPU, deliver_prefix_signal), + STATS_DESC_COUNTER(VCPU, deliver_restart_signal), + STATS_DESC_COUNTER(VCPU, deliver_program), + STATS_DESC_COUNTER(VCPU, deliver_io), + STATS_DESC_COUNTER(VCPU, deliver_machine_check), + STATS_DESC_COUNTER(VCPU, exit_wait_state), + STATS_DESC_COUNTER(VCPU, inject_ckc), + STATS_DESC_COUNTER(VCPU, inject_cputm), + STATS_DESC_COUNTER(VCPU, inject_external_call), + STATS_DESC_COUNTER(VCPU, inject_emergency_signal), + STATS_DESC_COUNTER(VCPU, inject_mchk), + STATS_DESC_COUNTER(VCPU, inject_pfault_init), + STATS_DESC_COUNTER(VCPU, inject_program), + STATS_DESC_COUNTER(VCPU, inject_restart), + STATS_DESC_COUNTER(VCPU, inject_set_prefix), + STATS_DESC_COUNTER(VCPU, inject_stop_signal), + STATS_DESC_COUNTER(VCPU, instruction_epsw), + STATS_DESC_COUNTER(VCPU, instruction_gs), + STATS_DESC_COUNTER(VCPU, instruction_io_other), + STATS_DESC_COUNTER(VCPU, instruction_lpsw), + STATS_DESC_COUNTER(VCPU, instruction_lpswe), + STATS_DESC_COUNTER(VCPU, instruction_pfmf), + STATS_DESC_COUNTER(VCPU, instruction_ptff), + STATS_DESC_COUNTER(VCPU, instruction_sck), + STATS_DESC_COUNTER(VCPU, instruction_sckpf), + STATS_DESC_COUNTER(VCPU, instruction_stidp), + STATS_DESC_COUNTER(VCPU, instruction_spx), + STATS_DESC_COUNTER(VCPU, instruction_stpx), + STATS_DESC_COUNTER(VCPU, instruction_stap), + STATS_DESC_COUNTER(VCPU, instruction_iske), + STATS_DESC_COUNTER(VCPU, instruction_ri), + STATS_DESC_COUNTER(VCPU, instruction_rrbe), + STATS_DESC_COUNTER(VCPU, instruction_sske), + STATS_DESC_COUNTER(VCPU, instruction_ipte_interlock), + STATS_DESC_COUNTER(VCPU, instruction_stsi), + STATS_DESC_COUNTER(VCPU, instruction_stfl), + STATS_DESC_COUNTER(VCPU, instruction_tb), + STATS_DESC_COUNTER(VCPU, instruction_tpi), + STATS_DESC_COUNTER(VCPU, instruction_tprot), + STATS_DESC_COUNTER(VCPU, instruction_tsch), + STATS_DESC_COUNTER(VCPU, instruction_sie), + STATS_DESC_COUNTER(VCPU, instruction_essa), + STATS_DESC_COUNTER(VCPU, instruction_sthyi), + STATS_DESC_COUNTER(VCPU, instruction_sigp_sense), + STATS_DESC_COUNTER(VCPU, instruction_sigp_sense_running), + STATS_DESC_COUNTER(VCPU, instruction_sigp_external_call), + STATS_DESC_COUNTER(VCPU, instruction_sigp_emergency), + STATS_DESC_COUNTER(VCPU, instruction_sigp_cond_emergency), + STATS_DESC_COUNTER(VCPU, instruction_sigp_start), + STATS_DESC_COUNTER(VCPU, instruction_sigp_stop), + STATS_DESC_COUNTER(VCPU, instruction_sigp_stop_store_status), + STATS_DESC_COUNTER(VCPU, instruction_sigp_store_status), + STATS_DESC_COUNTER(VCPU, instruction_sigp_store_adtl_status), + STATS_DESC_COUNTER(VCPU, instruction_sigp_arch), + STATS_DESC_COUNTER(VCPU, instruction_sigp_prefix), + STATS_DESC_COUNTER(VCPU, instruction_sigp_restart), + STATS_DESC_COUNTER(VCPU, instruction_sigp_init_cpu_reset), + STATS_DESC_COUNTER(VCPU, instruction_sigp_cpu_reset), + STATS_DESC_COUNTER(VCPU, instruction_sigp_unknown), + STATS_DESC_COUNTER(VCPU, diagnose_10), + STATS_DESC_COUNTER(VCPU, diagnose_44), + STATS_DESC_COUNTER(VCPU, diagnose_9c), + STATS_DESC_COUNTER(VCPU, diagnose_9c_ignored), + STATS_DESC_COUNTER(VCPU, diagnose_9c_forward), + STATS_DESC_COUNTER(VCPU, diagnose_258), + STATS_DESC_COUNTER(VCPU, diagnose_308), + STATS_DESC_COUNTER(VCPU, diagnose_500), + STATS_DESC_COUNTER(VCPU, diagnose_other), + STATS_DESC_COUNTER(VCPU, pfault_sync) +}; +static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == + sizeof(struct kvm_vcpu_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vcpu_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vcpu_stats_desc), }; /* allow nested virtualization in KVM (if enabled by user space) */ diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c index f5beecdac693..e76b22157099 100644 --- a/arch/sh/kernel/traps.c +++ b/arch/sh/kernel/traps.c @@ -180,7 +180,6 @@ static inline void arch_ftrace_nmi_exit(void) { } BUILD_TRAP_HANDLER(nmi) { - unsigned int cpu = smp_processor_id(); TRAP_HANDLER_DECL; arch_ftrace_nmi_enter(); diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 6e5522aebbbd..431bf7f846c3 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -30,6 +30,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ KBUILD_CFLAGS := -m$(BITS) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIE +KBUILD_CFLAGS += -Wundef KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_32) := -march=i386 cflags-$(CONFIG_X86_64) := -mcmodel=small -mno-red-zone @@ -48,10 +49,10 @@ KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no) KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h KBUILD_CFLAGS += $(CLANG_FLAGS) -# sev-es.c indirectly inludes inat-table.h which is generated during +# sev.c indirectly inludes inat-table.h which is generated during # compilation and stored in $(objtree). Add the directory to the includes so # that the compiler finds it even with out-of-tree builds (make O=/some/path). -CFLAGS_sev-es.o += -I$(objtree)/arch/x86/lib/ +CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/ KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n @@ -93,7 +94,7 @@ ifdef CONFIG_X86_64 vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o vmlinux-objs-y += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o - vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev-es.o + vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index dde042f64cca..743f13ea25c1 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -172,7 +172,7 @@ void __puthex(unsigned long value) } } -#if CONFIG_X86_NEED_RELOCS +#ifdef CONFIG_X86_NEED_RELOCS static void handle_relocations(void *output, unsigned long output_len, unsigned long virt_addr) { diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index e5612f035498..31139256859f 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -79,7 +79,7 @@ struct mem_vector { u64 size; }; -#if CONFIG_RANDOMIZE_BASE +#ifdef CONFIG_RANDOMIZE_BASE /* kaslr.c */ void choose_random_location(unsigned long input, unsigned long input_size, diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev.c index 82041bd380e5..670e998fe930 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev.c @@ -13,7 +13,7 @@ #include "misc.h" #include <asm/pgtable_types.h> -#include <asm/sev-es.h> +#include <asm/sev.h> #include <asm/trapnr.h> #include <asm/trap_pf.h> #include <asm/msr-index.h> @@ -117,7 +117,7 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, #include "../../lib/insn.c" /* Include code for early handlers */ -#include "../../kernel/sev-es-shared.c" +#include "../../kernel/sev-shared.c" static bool early_setup_sev_es(void) { diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 606f5cc579b2..f1366ce609e3 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -52,7 +52,7 @@ * Support for passing hypercall input parameter block via XMM * registers is available */ -#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE BIT(4) +#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4) /* Support for a virtual guest idle state is available */ #define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) /* Frequency MSRs available */ @@ -61,6 +61,11 @@ #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) /* Support for debug MSRs available */ #define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) +/* + * Support for returning hypercall output block via XMM + * registers is available + */ +#define HV_X64_HYPERCALL_XMM_OUTPUT_AVAILABLE BIT(15) /* stimer Direct Mode is available */ #define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) @@ -133,6 +138,15 @@ #define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) #define HV_X64_NESTED_MSR_BITMAP BIT(19) +/* + * This is specific to AMD and specifies that enlightened TLB flush is + * supported. If guest opts in to this feature, ASID invalidations only + * flushes gva -> hpa mapping entries. To flush the TLB entries derived + * from NPT, hypercalls should be used (HvFlushGuestPhysicalAddressSpace + * or HvFlushGuestPhysicalAddressList). + */ +#define HV_X64_NESTED_ENLIGHTENED_TLB BIT(22) + /* HYPERV_CPUID_ISOLATION_CONFIG.EAX bits. */ #define HV_PARAVISOR_PRESENT BIT(0) @@ -314,6 +328,9 @@ struct hv_tsc_emulation_status { #define HV_X64_MSR_TSC_REFERENCE_ENABLE 0x00000001 #define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT 12 +/* Number of XMM registers used in hypercall input/output */ +#define HV_HYPERCALL_MAX_XMM_REGISTERS 6 + struct hv_nested_enlightenments_control { struct { __u32 directhypercall:1; diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 323641097f63..a12a4987154e 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -87,7 +87,10 @@ KVM_X86_OP(set_identity_map_addr) KVM_X86_OP(get_mt_mask) KVM_X86_OP(load_mmu_pgd) KVM_X86_OP_NULL(has_wbinvd_exit) -KVM_X86_OP(write_l1_tsc_offset) +KVM_X86_OP(get_l2_tsc_offset) +KVM_X86_OP(get_l2_tsc_multiplier) +KVM_X86_OP(write_tsc_offset) +KVM_X86_OP(write_tsc_multiplier) KVM_X86_OP(get_exit_info) KVM_X86_OP(check_intercept) KVM_X86_OP(handle_exit_irqoff) @@ -99,14 +102,15 @@ KVM_X86_OP_NULL(post_block) KVM_X86_OP_NULL(vcpu_blocking) KVM_X86_OP_NULL(vcpu_unblocking) KVM_X86_OP_NULL(update_pi_irte) +KVM_X86_OP_NULL(start_assignment) KVM_X86_OP_NULL(apicv_post_state_restore) KVM_X86_OP_NULL(dy_apicv_has_pending_interrupt) KVM_X86_OP_NULL(set_hv_timer) KVM_X86_OP_NULL(cancel_hv_timer) KVM_X86_OP(setup_mce) KVM_X86_OP(smi_allowed) -KVM_X86_OP(pre_enter_smm) -KVM_X86_OP(pre_leave_smm) +KVM_X86_OP(enter_smm) +KVM_X86_OP(leave_smm) KVM_X86_OP(enable_smi_window) KVM_X86_OP_NULL(mem_enc_op) KVM_X86_OP_NULL(mem_enc_reg_region) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index cbbcee0a84f9..974cbfb1eefe 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -85,7 +85,7 @@ #define KVM_REQ_APICV_UPDATE \ KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26) -#define KVM_REQ_HV_TLB_FLUSH \ +#define KVM_REQ_TLB_FLUSH_GUEST \ KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_APF_READY KVM_ARCH_REQ(28) #define KVM_REQ_MSR_FILTER_CHANGED KVM_ARCH_REQ(29) @@ -113,6 +113,7 @@ #define VALID_PAGE(x) ((x) != INVALID_PAGE) #define UNMAPPED_GVA (~(gpa_t)0) +#define INVALID_GPA (~(gpa_t)0) /* KVM Hugepage definitions for x86 */ #define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G @@ -199,6 +200,7 @@ enum x86_intercept_stage; #define KVM_NR_DB_REGS 4 +#define DR6_BUS_LOCK (1 << 11) #define DR6_BD (1 << 13) #define DR6_BS (1 << 14) #define DR6_BT (1 << 15) @@ -212,7 +214,7 @@ enum x86_intercept_stage; * DR6_ACTIVE_LOW is also used as the init/reset value for DR6. */ #define DR6_ACTIVE_LOW 0xffff0ff0 -#define DR6_VOLATILE 0x0001e00f +#define DR6_VOLATILE 0x0001e80f #define DR6_FIXED_1 (DR6_ACTIVE_LOW & ~DR6_VOLATILE) #define DR7_BP_EN_MASK 0x000000ff @@ -267,12 +269,36 @@ enum x86_intercept_stage; struct kvm_kernel_irq_routing_entry; /* - * the pages used as guest page table on soft mmu are tracked by - * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used - * by indirect shadow page can not be more than 15 bits. + * kvm_mmu_page_role tracks the properties of a shadow page (where shadow page + * also includes TDP pages) to determine whether or not a page can be used in + * the given MMU context. This is a subset of the overall kvm_mmu_role to + * minimize the size of kvm_memory_slot.arch.gfn_track, i.e. allows allocating + * 2 bytes per gfn instead of 4 bytes per gfn. * - * Currently, we used 14 bits that are @level, @gpte_is_8_bytes, @quadrant, @access, - * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp. + * Indirect upper-level shadow pages are tracked for write-protection via + * gfn_track. As above, gfn_track is a 16 bit counter, so KVM must not create + * more than 2^16-1 upper-level shadow pages at a single gfn, otherwise + * gfn_track will overflow and explosions will ensure. + * + * A unique shadow page (SP) for a gfn is created if and only if an existing SP + * cannot be reused. The ability to reuse a SP is tracked by its role, which + * incorporates various mode bits and properties of the SP. Roughly speaking, + * the number of unique SPs that can theoretically be created is 2^n, where n + * is the number of bits that are used to compute the role. + * + * But, even though there are 18 bits in the mask below, not all combinations + * of modes and flags are possible. The maximum number of possible upper-level + * shadow pages for a single gfn is in the neighborhood of 2^13. + * + * - invalid shadow pages are not accounted. + * - level is effectively limited to four combinations, not 16 as the number + * bits would imply, as 4k SPs are not tracked (allowed to go unsync). + * - level is effectively unused for non-PAE paging because there is exactly + * one upper level (see 4k SP exception above). + * - quadrant is used only for non-PAE paging and is exclusive with + * gpte_is_8_bytes. + * - execonly and ad_disabled are used only for nested EPT, which makes it + * exclusive with quadrant. */ union kvm_mmu_page_role { u32 word; @@ -283,7 +309,7 @@ union kvm_mmu_page_role { unsigned direct:1; unsigned access:3; unsigned invalid:1; - unsigned nxe:1; + unsigned efer_nx:1; unsigned cr0_wp:1; unsigned smep_andnot_wp:1; unsigned smap_andnot_wp:1; @@ -301,13 +327,26 @@ union kvm_mmu_page_role { }; }; -union kvm_mmu_extended_role { /* - * This structure complements kvm_mmu_page_role caching everything needed for - * MMU configuration. If nothing in both these structures changed, MMU - * re-configuration can be skipped. @valid bit is set on first usage so we don't - * treat all-zero structure as valid data. + * kvm_mmu_extended_role complements kvm_mmu_page_role, tracking properties + * relevant to the current MMU configuration. When loading CR0, CR4, or EFER, + * including on nested transitions, if nothing in the full role changes then + * MMU re-configuration can be skipped. @valid bit is set on first usage so we + * don't treat all-zero structure as valid data. + * + * The properties that are tracked in the extended role but not the page role + * are for things that either (a) do not affect the validity of the shadow page + * or (b) are indirectly reflected in the shadow page's role. For example, + * CR4.PKE only affects permission checks for software walks of the guest page + * tables (because KVM doesn't support Protection Keys with shadow paging), and + * CR0.PG, CR4.PAE, and CR4.PSE are indirectly reflected in role.level. + * + * Note, SMEP and SMAP are not redundant with sm*p_andnot_wp in the page role. + * If CR0.WP=1, KVM can reuse shadow pages for the guest regardless of SMEP and + * SMAP, but the MMU's permission checks for software walks need to be SMEP and + * SMAP aware regardless of CR0.WP. */ +union kvm_mmu_extended_role { u32 word; struct { unsigned int valid:1; @@ -318,7 +357,7 @@ union kvm_mmu_extended_role { unsigned int cr4_pke:1; unsigned int cr4_smap:1; unsigned int cr4_smep:1; - unsigned int maxphyaddr:6; + unsigned int cr4_la57:1; }; }; @@ -407,7 +446,7 @@ struct kvm_mmu { u32 pkru_mask; u64 *pae_root; - u64 *lm_root; + u64 *pml4_root; /* * check zero bits on shadow page table entries, these @@ -418,11 +457,6 @@ struct kvm_mmu { struct rsvd_bits_validate guest_rsvd_check; - /* Can have large pages at levels 2..last_nonleaf_level-1. */ - u8 last_nonleaf_level; - - bool nx; - u64 pdptrs[4]; /* pae */ }; @@ -541,6 +575,15 @@ struct kvm_vcpu_hv { struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); cpumask_t tlb_flush; + bool enforce_cpuid; + struct { + u32 features_eax; /* HYPERV_CPUID_FEATURES.EAX */ + u32 features_ebx; /* HYPERV_CPUID_FEATURES.EBX */ + u32 features_edx; /* HYPERV_CPUID_FEATURES.EDX */ + u32 enlightenments_eax; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ + u32 enlightenments_ebx; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EBX */ + u32 syndbg_cap_eax; /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ + } cpuid_cache; }; /* Xen HVM per vcpu emulation context */ @@ -705,7 +748,7 @@ struct kvm_vcpu_arch { } st; u64 l1_tsc_offset; - u64 tsc_offset; + u64 tsc_offset; /* current tsc offset */ u64 last_guest_tsc; u64 last_host_tsc; u64 tsc_offset_adjustment; @@ -719,7 +762,8 @@ struct kvm_vcpu_arch { u32 virtual_tsc_khz; s64 ia32_tsc_adjust_msr; u64 msr_ia32_power_ctl; - u64 tsc_scaling_ratio; + u64 l1_tsc_scaling_ratio; + u64 tsc_scaling_ratio; /* current scaling ratio */ atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ unsigned nmi_pending; /* NMI queued after currently running handler */ @@ -827,7 +871,7 @@ struct kvm_vcpu_arch { bool l1tf_flush_l1d; /* Host CPU on which VM-entry was most recently attempted */ - unsigned int last_vmentry_cpu; + int last_vmentry_cpu; /* AMD MSRC001_0015 Hardware Configuration */ u64 msr_hwcr; @@ -849,6 +893,16 @@ struct kvm_vcpu_arch { /* Protected Guests */ bool guest_state_protected; + + /* + * Set when PDPTS were loaded directly by the userspace without + * reading the guest memory + */ + bool pdptrs_from_userspace; + +#if IS_ENABLED(CONFIG_HYPERV) + hpa_t hv_root_tdp; +#endif }; struct kvm_lpage_info { @@ -1000,7 +1054,7 @@ struct kvm_arch { struct kvm_apic_map __rcu *apic_map; atomic_t apic_map_dirty; - bool apic_access_page_done; + bool apic_access_memslot_enabled; unsigned long apicv_inhibit_reasons; gpa_t wall_clock; @@ -1060,11 +1114,19 @@ struct kvm_arch { bool exception_payload_enabled; bool bus_lock_detection_enabled; + /* + * If exit_on_emulation_error is set, and the in-kernel instruction + * emulator fails to emulate an instruction, allow userspace + * the opportunity to look at it. + */ + bool exit_on_emulation_error; /* Deflect RDMSR and WRMSR to user space when they trigger a #GP */ u32 user_space_msr_mask; struct kvm_x86_msr_filter __rcu *msr_filter; + u32 hypercall_exit_enabled; + /* Guest can access the SGX PROVISIONKEY. */ bool sgx_provisioning_allowed; @@ -1122,23 +1184,35 @@ struct kvm_arch { */ spinlock_t tdp_mmu_pages_lock; #endif /* CONFIG_X86_64 */ + + /* + * If set, rmaps have been allocated for all memslots and should be + * allocated for any newly created or modified memslots. + */ + bool memslots_have_rmaps; + +#if IS_ENABLED(CONFIG_HYPERV) + hpa_t hv_root_tdp; + spinlock_t hv_root_tdp_lock; +#endif }; struct kvm_vm_stat { - ulong mmu_shadow_zapped; - ulong mmu_pte_write; - ulong mmu_pde_zapped; - ulong mmu_flooded; - ulong mmu_recycled; - ulong mmu_cache_miss; - ulong mmu_unsync; - ulong remote_tlb_flush; - ulong lpages; - ulong nx_lpage_splits; - ulong max_mmu_page_hash_collisions; + struct kvm_vm_stat_generic generic; + u64 mmu_shadow_zapped; + u64 mmu_pte_write; + u64 mmu_pde_zapped; + u64 mmu_flooded; + u64 mmu_recycled; + u64 mmu_cache_miss; + u64 mmu_unsync; + u64 lpages; + u64 nx_lpage_splits; + u64 max_mmu_page_hash_collisions; }; struct kvm_vcpu_stat { + struct kvm_vcpu_stat_generic generic; u64 pf_fixed; u64 pf_guest; u64 tlb_flush; @@ -1152,10 +1226,6 @@ struct kvm_vcpu_stat { u64 nmi_window_exits; u64 l1d_flush; u64 halt_exits; - u64 halt_successful_poll; - u64 halt_attempted_poll; - u64 halt_poll_invalid; - u64 halt_wakeup; u64 request_irq_exits; u64 irq_exits; u64 host_state_reload; @@ -1166,11 +1236,10 @@ struct kvm_vcpu_stat { u64 irq_injections; u64 nmi_injections; u64 req_event; - u64 halt_poll_success_ns; - u64 halt_poll_fail_ns; u64 nested_run; u64 directed_yield_attempted; u64 directed_yield_successful; + u64 guest_mode; }; struct x86_instruction_info; @@ -1302,8 +1371,10 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); - /* Returns actual tsc_offset set in active VMCS */ - u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); + u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu); + u64 (*get_l2_tsc_multiplier)(struct kvm_vcpu *vcpu); + void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); + void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu, u64 multiplier); /* * Retrieve somewhat arbitrary exit information. Intended to be used @@ -1350,6 +1421,7 @@ struct kvm_x86_ops { int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); + void (*start_assignment)(struct kvm *kvm); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); @@ -1360,8 +1432,8 @@ struct kvm_x86_ops { void (*setup_mce)(struct kvm_vcpu *vcpu); int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); - int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); - int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate); + int (*enter_smm)(struct kvm_vcpu *vcpu, char *smstate); + int (*leave_smm)(struct kvm_vcpu *vcpu, const char *smstate); void (*enable_smi_window)(struct kvm_vcpu *vcpu); int (*mem_enc_op)(struct kvm *kvm, void __user *argp); @@ -1417,8 +1489,10 @@ struct kvm_arch_async_pf { bool direct_map; }; +extern u32 __read_mostly kvm_nr_uret_msrs; extern u64 __read_mostly host_efer; extern bool __read_mostly allow_smaller_maxphyaddr; +extern bool __read_mostly enable_apicv; extern struct kvm_x86_ops kvm_x86_ops; #define KVM_X86_OP(func) \ @@ -1459,6 +1533,7 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu); void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); +void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot, @@ -1473,7 +1548,6 @@ unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); -bool pdptrs_changed(struct kvm_vcpu *vcpu); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); @@ -1646,6 +1720,7 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, ulong roots_to_free); +void kvm_mmu_free_guest_mode_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu); gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, @@ -1658,7 +1733,6 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); bool kvm_apicv_activated(struct kvm *kvm); -void kvm_apicv_init(struct kvm *kvm, bool enable); void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); void kvm_request_apicv_update(struct kvm *kvm, bool activate, unsigned long bit); @@ -1671,8 +1745,7 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, gva_t gva, hpa_t root_hpa); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); -void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush, - bool skip_mmu_sync); +void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level, int tdp_huge_page_level); @@ -1775,11 +1848,19 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit); -void kvm_define_user_return_msr(unsigned index, u32 msr); +int kvm_add_user_return_msr(u32 msr); +int kvm_find_user_return_msr(u32 msr); int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask); -u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc); +static inline bool kvm_is_supported_user_return_msr(u32 msr) +{ + return kvm_find_user_return_msr(msr) >= 0; +} + +u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc, u64 ratio); u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); +u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier); +u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier); unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); @@ -1853,4 +1934,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) int kvm_cpu_dirty_log_size(void); +int alloc_all_memslots_rmaps(struct kvm *kvm); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 338119852512..69299878b200 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -7,8 +7,6 @@ #include <linux/interrupt.h> #include <uapi/asm/kvm_para.h> -extern void kvmclock_init(void); - #ifdef CONFIG_KVM_GUEST bool kvm_check_and_clear_guest_paused(void); #else @@ -86,13 +84,14 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, } #ifdef CONFIG_KVM_GUEST +void kvmclock_init(void); +void kvmclock_disable(void); bool kvm_para_available(void); unsigned int kvm_arch_para_features(void); unsigned int kvm_arch_para_hints(void); void kvm_async_pf_task_wait_schedule(u32 token); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_apf_flags(void); -void kvm_disable_steal_time(void); bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token); DECLARE_STATIC_KEY_FALSE(kvm_async_pf_enabled); @@ -137,11 +136,6 @@ static inline u32 kvm_read_and_reset_apf_flags(void) return 0; } -static inline void kvm_disable_steal_time(void) -{ - return; -} - static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token) { return false; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 742d89a00721..211ba3375ee9 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -537,9 +537,9 @@ /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d -#define MSR_K8_SYSCFG 0xc0010010 -#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT 23 -#define MSR_K8_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG 0xc0010010 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 154321d29050..556b2b17c3e2 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -787,8 +787,10 @@ DECLARE_PER_CPU(u64, msr_misc_features_shadow); #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); +extern u32 amd_get_highest_perf(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } +static inline u32 amd_get_highest_perf(void) { return 0; } #endif static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h new file mode 100644 index 000000000000..629c3df243f0 --- /dev/null +++ b/arch/x86/include/asm/sev-common.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD SEV header common between the guest and the hypervisor. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + */ + +#ifndef __ASM_X86_SEV_COMMON_H +#define __ASM_X86_SEV_COMMON_H + +#define GHCB_MSR_INFO_POS 0 +#define GHCB_MSR_INFO_MASK (BIT_ULL(12) - 1) + +#define GHCB_MSR_SEV_INFO_RESP 0x001 +#define GHCB_MSR_SEV_INFO_REQ 0x002 +#define GHCB_MSR_VER_MAX_POS 48 +#define GHCB_MSR_VER_MAX_MASK 0xffff +#define GHCB_MSR_VER_MIN_POS 32 +#define GHCB_MSR_VER_MIN_MASK 0xffff +#define GHCB_MSR_CBIT_POS 24 +#define GHCB_MSR_CBIT_MASK 0xff +#define GHCB_MSR_SEV_INFO(_max, _min, _cbit) \ + ((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) | \ + (((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) | \ + (((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) | \ + GHCB_MSR_SEV_INFO_RESP) +#define GHCB_MSR_INFO(v) ((v) & 0xfffUL) +#define GHCB_MSR_PROTO_MAX(v) (((v) >> GHCB_MSR_VER_MAX_POS) & GHCB_MSR_VER_MAX_MASK) +#define GHCB_MSR_PROTO_MIN(v) (((v) >> GHCB_MSR_VER_MIN_POS) & GHCB_MSR_VER_MIN_MASK) + +#define GHCB_MSR_CPUID_REQ 0x004 +#define GHCB_MSR_CPUID_RESP 0x005 +#define GHCB_MSR_CPUID_FUNC_POS 32 +#define GHCB_MSR_CPUID_FUNC_MASK 0xffffffff +#define GHCB_MSR_CPUID_VALUE_POS 32 +#define GHCB_MSR_CPUID_VALUE_MASK 0xffffffff +#define GHCB_MSR_CPUID_REG_POS 30 +#define GHCB_MSR_CPUID_REG_MASK 0x3 +#define GHCB_CPUID_REQ_EAX 0 +#define GHCB_CPUID_REQ_EBX 1 +#define GHCB_CPUID_REQ_ECX 2 +#define GHCB_CPUID_REQ_EDX 3 +#define GHCB_CPUID_REQ(fn, reg) \ + (GHCB_MSR_CPUID_REQ | \ + (((unsigned long)reg & GHCB_MSR_CPUID_REG_MASK) << GHCB_MSR_CPUID_REG_POS) | \ + (((unsigned long)fn) << GHCB_MSR_CPUID_FUNC_POS)) + +#define GHCB_MSR_TERM_REQ 0x100 +#define GHCB_MSR_TERM_REASON_SET_POS 12 +#define GHCB_MSR_TERM_REASON_SET_MASK 0xf +#define GHCB_MSR_TERM_REASON_POS 16 +#define GHCB_MSR_TERM_REASON_MASK 0xff +#define GHCB_SEV_TERM_REASON(reason_set, reason_val) \ + (((((u64)reason_set) & GHCB_MSR_TERM_REASON_SET_MASK) << GHCB_MSR_TERM_REASON_SET_POS) | \ + ((((u64)reason_val) & GHCB_MSR_TERM_REASON_MASK) << GHCB_MSR_TERM_REASON_POS)) + +#define GHCB_SEV_ES_REASON_GENERAL_REQUEST 0 +#define GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED 1 + +#define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) + +#endif diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev.h index cf1d957c7091..fa5cd05d3b5b 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev.h @@ -10,34 +10,12 @@ #include <linux/types.h> #include <asm/insn.h> +#include <asm/sev-common.h> -#define GHCB_SEV_INFO 0x001UL -#define GHCB_SEV_INFO_REQ 0x002UL -#define GHCB_INFO(v) ((v) & 0xfffUL) -#define GHCB_PROTO_MAX(v) (((v) >> 48) & 0xffffUL) -#define GHCB_PROTO_MIN(v) (((v) >> 32) & 0xffffUL) -#define GHCB_PROTO_OUR 0x0001UL -#define GHCB_SEV_CPUID_REQ 0x004UL -#define GHCB_CPUID_REQ_EAX 0 -#define GHCB_CPUID_REQ_EBX 1 -#define GHCB_CPUID_REQ_ECX 2 -#define GHCB_CPUID_REQ_EDX 3 -#define GHCB_CPUID_REQ(fn, reg) (GHCB_SEV_CPUID_REQ | \ - (((unsigned long)reg & 3) << 30) | \ - (((unsigned long)fn) << 32)) +#define GHCB_PROTO_OUR 0x0001UL +#define GHCB_PROTOCOL_MAX 1ULL +#define GHCB_DEFAULT_USAGE 0ULL -#define GHCB_PROTOCOL_MAX 0x0001UL -#define GHCB_DEFAULT_USAGE 0x0000UL - -#define GHCB_SEV_CPUID_RESP 0x005UL -#define GHCB_SEV_TERMINATE 0x100UL -#define GHCB_SEV_TERMINATE_REASON(reason_set, reason_val) \ - (((((u64)reason_set) & 0x7) << 12) | \ - ((((u64)reason_val) & 0xff) << 16)) -#define GHCB_SEV_ES_REASON_GENERAL_REQUEST 0 -#define GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED 1 - -#define GHCB_SEV_GHCB_RESP_CODE(v) ((v) & 0xfff) #define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); } enum es_result { diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 772e60efe243..e322676039f4 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -156,6 +156,12 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u64 avic_physical_id; /* Offset 0xf8 */ u8 reserved_7[8]; u64 vmsa_pa; /* Used for an SEV-ES guest */ + u8 reserved_8[720]; + /* + * Offset 0x3e0, 32 bytes reserved + * for use by hypervisor/software. + */ + u8 reserved_sw[32]; }; @@ -314,7 +320,7 @@ struct ghcb { #define EXPECTED_VMCB_SAVE_AREA_SIZE 1032 -#define EXPECTED_VMCB_CONTROL_AREA_SIZE 272 +#define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024 #define EXPECTED_GHCB_SIZE PAGE_SIZE static inline void __unused_size_checks(void) @@ -326,7 +332,6 @@ static inline void __unused_size_checks(void) struct vmcb { struct vmcb_control_area control; - u8 reserved_control[1024 - sizeof(struct vmcb_control_area)]; struct vmcb_save_area save; } __packed; diff --git a/arch/x86/include/asm/vdso/clocksource.h b/arch/x86/include/asm/vdso/clocksource.h index 119ac8612d89..136e5e57cfe1 100644 --- a/arch/x86/include/asm/vdso/clocksource.h +++ b/arch/x86/include/asm/vdso/clocksource.h @@ -7,4 +7,6 @@ VDSO_CLOCKMODE_PVCLOCK, \ VDSO_CLOCKMODE_HVCLOCK +#define HAVE_VDSO_CLOCKMODE_HVCLOCK + #endif /* __ASM_VDSO_CLOCKSOURCE_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 5a3022c8af82..a6c327f8ad9e 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -159,6 +159,19 @@ struct kvm_sregs { __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64]; }; +struct kvm_sregs2 { + /* out (KVM_GET_SREGS2) / in (KVM_SET_SREGS2) */ + struct kvm_segment cs, ds, es, fs, gs, ss; + struct kvm_segment tr, ldt; + struct kvm_dtable gdt, idt; + __u64 cr0, cr2, cr3, cr4, cr8; + __u64 efer; + __u64 apic_base; + __u64 flags; + __u64 pdptrs[4]; +}; +#define KVM_SREGS2_FLAGS_PDPTRS_VALID 1 + /* for KVM_GET_FPU and KVM_SET_FPU */ struct kvm_fpu { __u8 fpr[8][16]; @@ -437,6 +450,8 @@ struct kvm_vmx_nested_state_hdr { __u16 flags; } smm; + __u16 pad; + __u32 flags; __u64 preemption_timer_deadline; }; diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 950afebfba88..5146bbab84d4 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -33,6 +33,8 @@ #define KVM_FEATURE_PV_SCHED_YIELD 13 #define KVM_FEATURE_ASYNC_PF_INT 14 #define KVM_FEATURE_MSI_EXT_DEST_ID 15 +#define KVM_FEATURE_HC_MAP_GPA_RANGE 16 +#define KVM_FEATURE_MIGRATION_CONTROL 17 #define KVM_HINTS_REALTIME 0 @@ -54,6 +56,7 @@ #define MSR_KVM_POLL_CONTROL 0x4b564d05 #define MSR_KVM_ASYNC_PF_INT 0x4b564d06 #define MSR_KVM_ASYNC_PF_ACK 0x4b564d07 +#define MSR_KVM_MIGRATION_CONTROL 0x4b564d08 struct kvm_steal_time { __u64 steal; @@ -90,6 +93,16 @@ struct kvm_clock_pairing { /* MSR_KVM_ASYNC_PF_INT */ #define KVM_ASYNC_PF_VEC_MASK GENMASK(7, 0) +/* MSR_KVM_MIGRATION_CONTROL */ +#define KVM_MIGRATION_READY (1 << 0) + +/* KVM_HC_MAP_GPA_RANGE */ +#define KVM_MAP_GPA_RANGE_PAGE_SZ_4K 0 +#define KVM_MAP_GPA_RANGE_PAGE_SZ_2M (1 << 0) +#define KVM_MAP_GPA_RANGE_PAGE_SZ_1G (1 << 1) +#define KVM_MAP_GPA_RANGE_ENC_STAT(n) (n << 4) +#define KVM_MAP_GPA_RANGE_ENCRYPTED KVM_MAP_GPA_RANGE_ENC_STAT(1) +#define KVM_MAP_GPA_RANGE_DECRYPTED KVM_MAP_GPA_RANGE_ENC_STAT(0) /* Operations for KVM_HC_MMU_OP */ #define KVM_MMU_OP_WRITE_PTE 1 diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index 554f75fe013c..efa969325ede 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -110,6 +110,9 @@ #define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1 #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff +/* Exit code reserved for hypervisor/software use */ +#define SVM_EXIT_SW 0xf0000000 + #define SVM_EXIT_ERR -1 #define SVM_EXIT_REASONS \ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0704c2a94272..0f66682ac02a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -20,7 +20,7 @@ CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg -CFLAGS_REMOVE_sev-es.o = -pg +CFLAGS_REMOVE_sev.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n @@ -28,7 +28,7 @@ KASAN_SANITIZE_dumpstack.o := n KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n -KASAN_SANITIZE_sev-es.o := n +KASAN_SANITIZE_sev.o := n # With some compiler versions the generated code results in boot hangs, caused # by several compilation units. To be safe, disable all instrumentation. @@ -148,7 +148,7 @@ obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o -obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev-es.o +obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2d11384dc9ab..c06ac56eae4d 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -593,8 +593,8 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) */ if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) { /* Check if memory encryption is enabled */ - rdmsrl(MSR_K8_SYSCFG, msr); - if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + rdmsrl(MSR_AMD64_SYSCFG, msr); + if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT)) goto clear_all; /* @@ -1165,3 +1165,19 @@ void set_dr_addr_mask(unsigned long mask, int dr) break; } } + +u32 amd_get_highest_perf(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) || + (c->x86_model >= 0x70 && c->x86_model < 0x80))) + return 166; + + if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) || + (c->x86_model >= 0x40 && c->x86_model < 0x70))) + return 166; + + return 255; +} +EXPORT_SYMBOL_GPL(amd_get_highest_perf); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 22f13343b5da..c268c2730048 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -252,6 +252,7 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus) static void __init ms_hyperv_init_platform(void) { + int hv_max_functions_eax; int hv_host_info_eax; int hv_host_info_ebx; int hv_host_info_ecx; @@ -269,6 +270,8 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); + hv_max_functions_eax = cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS); + pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n", ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints, ms_hyperv.misc_features); @@ -298,8 +301,7 @@ static void __init ms_hyperv_init_platform(void) /* * Extract host information. */ - if (cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS) >= - HYPERV_CPUID_VERSION) { + if (hv_max_functions_eax >= HYPERV_CPUID_VERSION) { hv_host_info_eax = cpuid_eax(HYPERV_CPUID_VERSION); hv_host_info_ebx = cpuid_ebx(HYPERV_CPUID_VERSION); hv_host_info_ecx = cpuid_ecx(HYPERV_CPUID_VERSION); @@ -325,9 +327,11 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b); } - if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) { + if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) { ms_hyperv.nested_features = cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); + pr_info("Hyper-V: Nested features: 0x%x\n", + ms_hyperv.nested_features); } /* diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 0c3b372318b7..b5f43049fa5f 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -836,7 +836,7 @@ int __init amd_special_default_mtrr(void) if (boot_cpu_data.x86 < 0xf) return 0; /* In case some hypervisor doesn't pass SYSCFG through: */ - if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0) + if (rdmsr_safe(MSR_AMD64_SYSCFG, &l, &h) < 0) return 0; /* * Memory between 4GB and top of mem is forced WB by this magic bit. diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index b90f3f437765..558108296f3c 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -53,13 +53,13 @@ static inline void k8_check_syscfg_dram_mod_en(void) (boot_cpu_data.x86 >= 0x0f))) return; - rdmsr(MSR_K8_SYSCFG, lo, hi); + rdmsr(MSR_AMD64_SYSCFG, lo, hi); if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) { pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" " not cleared by BIOS, clearing this bit\n", smp_processor_id()); lo &= ~K8_MTRRFIXRANGE_DRAM_MODIFY; - mtrr_wrmsr(MSR_K8_SYSCFG, lo, hi); + mtrr_wrmsr(MSR_AMD64_SYSCFG, lo, hi); } } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 18be44163a50..de01903c3735 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -39,7 +39,7 @@ #include <asm/realmode.h> #include <asm/extable.h> #include <asm/trapnr.h> -#include <asm/sev-es.h> +#include <asm/sev.h> /* * Manage page tables very early on. diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d307c22e5c18..a26643dc6bd6 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -26,6 +26,7 @@ #include <linux/kprobes.h> #include <linux/nmi.h> #include <linux/swait.h> +#include <linux/syscore_ops.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -37,6 +38,7 @@ #include <asm/tlb.h> #include <asm/cpuidle_haltpoll.h> #include <asm/ptrace.h> +#include <asm/reboot.h> #include <asm/svm.h> DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled); @@ -345,7 +347,7 @@ static void kvm_guest_cpu_init(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); - pr_info("KVM setup async PF for cpu %d\n", smp_processor_id()); + pr_info("setup async PF for cpu %d\n", smp_processor_id()); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) { @@ -371,34 +373,17 @@ static void kvm_pv_disable_apf(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, 0); __this_cpu_write(apf_reason.enabled, 0); - pr_info("Unregister pv shared memory for cpu %d\n", smp_processor_id()); + pr_info("disable async PF for cpu %d\n", smp_processor_id()); } -static void kvm_pv_guest_cpu_reboot(void *unused) +static void kvm_disable_steal_time(void) { - /* - * We disable PV EOI before we load a new kernel by kexec, - * since MSR_KVM_PV_EOI_EN stores a pointer into old kernel's memory. - * New kernel can re-enable when it boots. - */ - if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) - wrmsrl(MSR_KVM_PV_EOI_EN, 0); - kvm_pv_disable_apf(); - kvm_disable_steal_time(); -} + if (!has_steal_clock) + return; -static int kvm_pv_reboot_notify(struct notifier_block *nb, - unsigned long code, void *unused) -{ - if (code == SYS_RESTART) - on_each_cpu(kvm_pv_guest_cpu_reboot, NULL, 1); - return NOTIFY_DONE; + wrmsr(MSR_KVM_STEAL_TIME, 0, 0); } -static struct notifier_block kvm_pv_reboot_nb = { - .notifier_call = kvm_pv_reboot_notify, -}; - static u64 kvm_steal_clock(int cpu) { u64 steal; @@ -416,14 +401,6 @@ static u64 kvm_steal_clock(int cpu) return steal; } -void kvm_disable_steal_time(void) -{ - if (!has_steal_clock) - return; - - wrmsr(MSR_KVM_STEAL_TIME, 0, 0); -} - static inline void __set_percpu_decrypted(void *ptr, unsigned long size) { early_set_memory_decrypted((unsigned long) ptr, size); @@ -451,6 +428,27 @@ static void __init sev_map_percpu_data(void) } } +static void kvm_guest_cpu_offline(bool shutdown) +{ + kvm_disable_steal_time(); + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) + wrmsrl(MSR_KVM_PV_EOI_EN, 0); + kvm_pv_disable_apf(); + if (!shutdown) + apf_task_wake_all(); + kvmclock_disable(); +} + +static int kvm_cpu_online(unsigned int cpu) +{ + unsigned long flags; + + local_irq_save(flags); + kvm_guest_cpu_init(); + local_irq_restore(flags); + return 0; +} + #ifdef CONFIG_SMP static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask); @@ -635,31 +633,64 @@ static void __init kvm_smp_prepare_boot_cpu(void) kvm_spinlock_init(); } -static void kvm_guest_cpu_offline(void) +static int kvm_cpu_down_prepare(unsigned int cpu) { - kvm_disable_steal_time(); - if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) - wrmsrl(MSR_KVM_PV_EOI_EN, 0); - kvm_pv_disable_apf(); - apf_task_wake_all(); + unsigned long flags; + + local_irq_save(flags); + kvm_guest_cpu_offline(false); + local_irq_restore(flags); + return 0; } -static int kvm_cpu_online(unsigned int cpu) +#endif + +static int kvm_suspend(void) { - local_irq_disable(); - kvm_guest_cpu_init(); - local_irq_enable(); + kvm_guest_cpu_offline(false); + return 0; } -static int kvm_cpu_down_prepare(unsigned int cpu) +static void kvm_resume(void) { - local_irq_disable(); - kvm_guest_cpu_offline(); - local_irq_enable(); - return 0; + kvm_cpu_online(raw_smp_processor_id()); +} + +static struct syscore_ops kvm_syscore_ops = { + .suspend = kvm_suspend, + .resume = kvm_resume, +}; + +static void kvm_pv_guest_cpu_reboot(void *unused) +{ + kvm_guest_cpu_offline(true); +} + +static int kvm_pv_reboot_notify(struct notifier_block *nb, + unsigned long code, void *unused) +{ + if (code == SYS_RESTART) + on_each_cpu(kvm_pv_guest_cpu_reboot, NULL, 1); + return NOTIFY_DONE; } +static struct notifier_block kvm_pv_reboot_nb = { + .notifier_call = kvm_pv_reboot_notify, +}; + +/* + * After a PV feature is registered, the host will keep writing to the + * registered memory location. If the guest happens to shutdown, this memory + * won't be valid. In cases like kexec, in which you install a new kernel, this + * means a random memory location will be kept being written. + */ +#ifdef CONFIG_KEXEC_CORE +static void kvm_crash_shutdown(struct pt_regs *regs) +{ + kvm_guest_cpu_offline(true); + native_machine_crash_shutdown(regs); +} #endif static void __init kvm_guest_init(void) @@ -704,6 +735,12 @@ static void __init kvm_guest_init(void) kvm_guest_cpu_init(); #endif +#ifdef CONFIG_KEXEC_CORE + machine_ops.crash_shutdown = kvm_crash_shutdown; +#endif + + register_syscore_ops(&kvm_syscore_ops); + /* * Hard lockup detection is enabled by default. Disable it, as guests * can get false positives too easily, for example if the host is diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d37ed4e1d033..ad273e5861c1 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -20,7 +20,6 @@ #include <asm/hypervisor.h> #include <asm/mem_encrypt.h> #include <asm/x86_init.h> -#include <asm/reboot.h> #include <asm/kvmclock.h> static int kvmclock __initdata = 1; @@ -203,28 +202,9 @@ static void kvm_setup_secondary_clock(void) } #endif -/* - * After the clock is registered, the host will keep writing to the - * registered memory location. If the guest happens to shutdown, this memory - * won't be valid. In cases like kexec, in which you install a new kernel, this - * means a random memory location will be kept being written. So before any - * kind of shutdown from our side, we unregister the clock by writing anything - * that does not have the 'enable' bit set in the msr - */ -#ifdef CONFIG_KEXEC_CORE -static void kvm_crash_shutdown(struct pt_regs *regs) -{ - native_write_msr(msr_kvm_system_time, 0, 0); - kvm_disable_steal_time(); - native_machine_crash_shutdown(regs); -} -#endif - -static void kvm_shutdown(void) +void kvmclock_disable(void) { native_write_msr(msr_kvm_system_time, 0, 0); - kvm_disable_steal_time(); - native_machine_shutdown(); } static void __init kvmclock_init_mem(void) @@ -351,10 +331,6 @@ void __init kvmclock_init(void) #endif x86_platform.save_sched_clock_state = kvm_save_sched_clock_state; x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state; - machine_ops.shutdown = kvm_shutdown; -#ifdef CONFIG_KEXEC_CORE - machine_ops.crash_shutdown = kvm_crash_shutdown; -#endif kvm_get_preset_lpj(); /* diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index b5cb49e57df8..c94dec6a1834 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -95,7 +95,7 @@ static void get_fam10h_pci_mmconf_base(void) return; /* SYS_CFG */ - address = MSR_K8_SYSCFG; + address = MSR_AMD64_SYSCFG; rdmsrl(address, val); /* TOP_MEM2 is not enabled? */ diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 2ef961cf4cfc..4bce802d25fb 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -33,7 +33,7 @@ #include <asm/reboot.h> #include <asm/cache.h> #include <asm/nospec-branch.h> -#include <asm/sev-es.h> +#include <asm/sev.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-shared.c index 0aa9f13efd57..6ec8b3bfd76e 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -26,13 +26,13 @@ static bool __init sev_es_check_cpu_features(void) static void __noreturn sev_es_terminate(unsigned int reason) { - u64 val = GHCB_SEV_TERMINATE; + u64 val = GHCB_MSR_TERM_REQ; /* * Tell the hypervisor what went wrong - only reason-set 0 is * currently supported. */ - val |= GHCB_SEV_TERMINATE_REASON(0, reason); + val |= GHCB_SEV_TERM_REASON(0, reason); /* Request Guest Termination from Hypvervisor */ sev_es_wr_ghcb_msr(val); @@ -47,15 +47,15 @@ static bool sev_es_negotiate_protocol(void) u64 val; /* Do the GHCB protocol version negotiation */ - sev_es_wr_ghcb_msr(GHCB_SEV_INFO_REQ); + sev_es_wr_ghcb_msr(GHCB_MSR_SEV_INFO_REQ); VMGEXIT(); val = sev_es_rd_ghcb_msr(); - if (GHCB_INFO(val) != GHCB_SEV_INFO) + if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP) return false; - if (GHCB_PROTO_MAX(val) < GHCB_PROTO_OUR || - GHCB_PROTO_MIN(val) > GHCB_PROTO_OUR) + if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTO_OUR || + GHCB_MSR_PROTO_MIN(val) > GHCB_PROTO_OUR) return false; return true; @@ -153,28 +153,28 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EAX)); VMGEXIT(); val = sev_es_rd_ghcb_msr(); - if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) goto fail; regs->ax = val >> 32; sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EBX)); VMGEXIT(); val = sev_es_rd_ghcb_msr(); - if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) goto fail; regs->bx = val >> 32; sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_ECX)); VMGEXIT(); val = sev_es_rd_ghcb_msr(); - if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) goto fail; regs->cx = val >> 32; sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EDX)); VMGEXIT(); val = sev_es_rd_ghcb_msr(); - if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) goto fail; regs->dx = val >> 32; diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev.c index 73873b007838..9578c82832aa 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev.c @@ -22,7 +22,7 @@ #include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> -#include <asm/sev-es.h> +#include <asm/sev.h> #include <asm/insn-eval.h> #include <asm/fpu/internal.h> #include <asm/processor.h> @@ -459,7 +459,7 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt } /* Include code shared with pre-decompression boot stage */ -#include "sev-es-shared.c" +#include "sev-shared.c" void noinstr __sev_es_nmi_complete(void) { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0ad5214f598a..7770245cc7fa 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -2043,7 +2043,7 @@ static bool amd_set_max_freq_ratio(void) return false; } - highest_perf = perf_caps.highest_perf; + highest_perf = amd_get_highest_perf(); nominal_perf = perf_caps.nominal_perf; if (!highest_perf || !nominal_perf) { diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index f6b93a35ce14..7a78b88c0f1a 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -46,6 +46,7 @@ config KVM select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO select SRCU + select HAVE_KVM_PM_NOTIFIER if PM help Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index c589db5d91b3..75dfd27b6e8a 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -11,13 +11,18 @@ KVM := ../../../virt/kvm kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \ - $(KVM)/dirty_ring.o + $(KVM)/dirty_ring.o $(KVM)/binary_stats.o kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \ mmu/spte.o + +ifdef CONFIG_HYPERV +kvm-y += kvm_onhyperv.o +endif + kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o kvm-$(CONFIG_KVM_XEN) += xen.o @@ -27,6 +32,10 @@ kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o svm/sev.o +ifdef CONFIG_HYPERV +kvm-amd-y += svm/svm_onhyperv.o +endif + obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM_INTEL) += kvm-intel.o obj-$(CONFIG_KVM_AMD) += kvm-amd.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 19606a341888..c42613cfb5ba 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -202,10 +202,10 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) static_call(kvm_x86_vcpu_after_set_cpuid)(vcpu); /* - * Except for the MMU, which needs to be reset after any vendor - * specific adjustments to the reserved GPA bits. + * Except for the MMU, which needs to do its thing any vendor specific + * adjustments to the reserved GPA bits. */ - kvm_mmu_reset_context(vcpu); + kvm_mmu_after_set_cpuid(vcpu); } static int is_efer_nx(void) @@ -458,7 +458,7 @@ void kvm_set_cpu_caps(void) F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/ | - F(SGX_LC) + F(SGX_LC) | F(BUS_LOCK_DETECT) ); /* Set LA57 based on hardware capability. */ if (cpuid_ecx(7) & F(LA57)) @@ -567,6 +567,21 @@ void kvm_set_cpu_caps(void) F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | F(PMM) | F(PMM_EN) ); + + /* + * Hide RDTSCP and RDPID if either feature is reported as supported but + * probing MSR_TSC_AUX failed. This is purely a sanity check and + * should never happen, but the guest will likely crash if RDTSCP or + * RDPID is misreported, and KVM has botched MSR_TSC_AUX emulation in + * the past. For example, the sanity check may fire if this instance of + * KVM is running as L1 on top of an older, broken KVM. + */ + if (WARN_ON((kvm_cpu_cap_has(X86_FEATURE_RDTSCP) || + kvm_cpu_cap_has(X86_FEATURE_RDPID)) && + !kvm_is_supported_user_return_msr(MSR_TSC_AUX))) { + kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); + kvm_cpu_cap_clear(X86_FEATURE_RDPID); + } } EXPORT_SYMBOL_GPL(kvm_set_cpu_caps); @@ -637,8 +652,10 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; entry->eax = 0; - entry->ecx = F(RDPID); + if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) + entry->ecx = F(RDPID); ++array->nent; + break; default: break; } diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 7e818d64bb4d..95a98413dc32 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -17,6 +17,15 @@ static int vcpu_get_timer_advance_ns(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(vcpu_timer_advance_ns_fops, vcpu_get_timer_advance_ns, NULL, "%llu\n"); +static int vcpu_get_guest_mode(void *data, u64 *val) +{ + struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data; + *val = vcpu->stat.guest_mode; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(vcpu_guest_mode_fops, vcpu_get_guest_mode, NULL, "%lld\n"); + static int vcpu_get_tsc_offset(void *data, u64 *val) { struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data; @@ -45,6 +54,8 @@ DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_scaling_frac_fops, vcpu_get_tsc_scaling_frac_bi void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) { + debugfs_create_file("guest_mode", 0444, debugfs_dentry, vcpu, + &vcpu_guest_mode_fops); debugfs_create_file("tsc-offset", 0444, debugfs_dentry, vcpu, &vcpu_tsc_offset_fops); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 77e1c89a95a7..2837110e66ed 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -22,7 +22,6 @@ #include "kvm_cache_regs.h" #include "kvm_emulate.h" #include <linux/stringify.h> -#include <asm/fpu/api.h> #include <asm/debugreg.h> #include <asm/nospec-branch.h> @@ -1081,116 +1080,14 @@ static void fetch_register_operand(struct operand *op) } } -static void emulator_get_fpu(void) -{ - fpregs_lock(); - - fpregs_assert_state_consistent(); - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_return(); -} - -static void emulator_put_fpu(void) -{ - fpregs_unlock(); -} - -static void read_sse_reg(sse128_t *data, int reg) -{ - emulator_get_fpu(); - switch (reg) { - case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; - case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; - case 2: asm("movdqa %%xmm2, %0" : "=m"(*data)); break; - case 3: asm("movdqa %%xmm3, %0" : "=m"(*data)); break; - case 4: asm("movdqa %%xmm4, %0" : "=m"(*data)); break; - case 5: asm("movdqa %%xmm5, %0" : "=m"(*data)); break; - case 6: asm("movdqa %%xmm6, %0" : "=m"(*data)); break; - case 7: asm("movdqa %%xmm7, %0" : "=m"(*data)); break; -#ifdef CONFIG_X86_64 - case 8: asm("movdqa %%xmm8, %0" : "=m"(*data)); break; - case 9: asm("movdqa %%xmm9, %0" : "=m"(*data)); break; - case 10: asm("movdqa %%xmm10, %0" : "=m"(*data)); break; - case 11: asm("movdqa %%xmm11, %0" : "=m"(*data)); break; - case 12: asm("movdqa %%xmm12, %0" : "=m"(*data)); break; - case 13: asm("movdqa %%xmm13, %0" : "=m"(*data)); break; - case 14: asm("movdqa %%xmm14, %0" : "=m"(*data)); break; - case 15: asm("movdqa %%xmm15, %0" : "=m"(*data)); break; -#endif - default: BUG(); - } - emulator_put_fpu(); -} - -static void write_sse_reg(sse128_t *data, int reg) -{ - emulator_get_fpu(); - switch (reg) { - case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; - case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; - case 2: asm("movdqa %0, %%xmm2" : : "m"(*data)); break; - case 3: asm("movdqa %0, %%xmm3" : : "m"(*data)); break; - case 4: asm("movdqa %0, %%xmm4" : : "m"(*data)); break; - case 5: asm("movdqa %0, %%xmm5" : : "m"(*data)); break; - case 6: asm("movdqa %0, %%xmm6" : : "m"(*data)); break; - case 7: asm("movdqa %0, %%xmm7" : : "m"(*data)); break; -#ifdef CONFIG_X86_64 - case 8: asm("movdqa %0, %%xmm8" : : "m"(*data)); break; - case 9: asm("movdqa %0, %%xmm9" : : "m"(*data)); break; - case 10: asm("movdqa %0, %%xmm10" : : "m"(*data)); break; - case 11: asm("movdqa %0, %%xmm11" : : "m"(*data)); break; - case 12: asm("movdqa %0, %%xmm12" : : "m"(*data)); break; - case 13: asm("movdqa %0, %%xmm13" : : "m"(*data)); break; - case 14: asm("movdqa %0, %%xmm14" : : "m"(*data)); break; - case 15: asm("movdqa %0, %%xmm15" : : "m"(*data)); break; -#endif - default: BUG(); - } - emulator_put_fpu(); -} - -static void read_mmx_reg(u64 *data, int reg) -{ - emulator_get_fpu(); - switch (reg) { - case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; - case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; - case 2: asm("movq %%mm2, %0" : "=m"(*data)); break; - case 3: asm("movq %%mm3, %0" : "=m"(*data)); break; - case 4: asm("movq %%mm4, %0" : "=m"(*data)); break; - case 5: asm("movq %%mm5, %0" : "=m"(*data)); break; - case 6: asm("movq %%mm6, %0" : "=m"(*data)); break; - case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; - default: BUG(); - } - emulator_put_fpu(); -} - -static void write_mmx_reg(u64 *data, int reg) -{ - emulator_get_fpu(); - switch (reg) { - case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; - case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; - case 2: asm("movq %0, %%mm2" : : "m"(*data)); break; - case 3: asm("movq %0, %%mm3" : : "m"(*data)); break; - case 4: asm("movq %0, %%mm4" : : "m"(*data)); break; - case 5: asm("movq %0, %%mm5" : : "m"(*data)); break; - case 6: asm("movq %0, %%mm6" : : "m"(*data)); break; - case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; - default: BUG(); - } - emulator_put_fpu(); -} - static int em_fninit(struct x86_emulate_ctxt *ctxt) { if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); - emulator_get_fpu(); + kvm_fpu_get(); asm volatile("fninit"); - emulator_put_fpu(); + kvm_fpu_put(); return X86EMUL_CONTINUE; } @@ -1201,9 +1098,9 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); - emulator_get_fpu(); + kvm_fpu_get(); asm volatile("fnstcw %0": "+m"(fcw)); - emulator_put_fpu(); + kvm_fpu_put(); ctxt->dst.val = fcw; @@ -1217,9 +1114,9 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); - emulator_get_fpu(); + kvm_fpu_get(); asm volatile("fnstsw %0": "+m"(fsw)); - emulator_put_fpu(); + kvm_fpu_put(); ctxt->dst.val = fsw; @@ -1238,7 +1135,7 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, op->type = OP_XMM; op->bytes = 16; op->addr.xmm = reg; - read_sse_reg(&op->vec_val, reg); + kvm_read_sse_reg(reg, &op->vec_val); return; } if (ctxt->d & Mmx) { @@ -1289,7 +1186,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, op->type = OP_XMM; op->bytes = 16; op->addr.xmm = ctxt->modrm_rm; - read_sse_reg(&op->vec_val, ctxt->modrm_rm); + kvm_read_sse_reg(ctxt->modrm_rm, &op->vec_val); return rc; } if (ctxt->d & Mmx) { @@ -1866,10 +1763,10 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) op->bytes * op->count); break; case OP_XMM: - write_sse_reg(&op->vec_val, op->addr.xmm); + kvm_write_sse_reg(op->addr.xmm, &op->vec_val); break; case OP_MM: - write_mmx_reg(&op->mm_val, op->addr.mm); + kvm_write_mmx_reg(op->addr.mm, &op->mm_val); break; case OP_NONE: /* no writeback */ @@ -2638,8 +2535,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) ctxt->ops->set_nmi_mask(ctxt, false); - ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) & - ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK)); + ctxt->ops->exiting_smm(ctxt); /* * Get back to real mode, to prepare a safe state in which to load @@ -2678,12 +2574,12 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) } /* - * Give pre_leave_smm() a chance to make ISA-specific changes to the - * vCPU state (e.g. enter guest mode) before loading state from the SMM + * Give leave_smm() a chance to make ISA-specific changes to the vCPU + * state (e.g. enter guest mode) before loading state from the SMM * state-save area. */ - if (ctxt->ops->pre_leave_smm(ctxt, buf)) - return X86EMUL_UNHANDLEABLE; + if (ctxt->ops->leave_smm(ctxt, buf)) + goto emulate_shutdown; #ifdef CONFIG_X86_64 if (emulator_has_longmode(ctxt)) @@ -2692,13 +2588,21 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) #endif ret = rsm_load_state_32(ctxt, buf); - if (ret != X86EMUL_CONTINUE) { - /* FIXME: should triple fault */ - return X86EMUL_UNHANDLEABLE; - } + if (ret != X86EMUL_CONTINUE) + goto emulate_shutdown; - ctxt->ops->post_leave_smm(ctxt); + /* + * Note, the ctxt->ops callbacks are responsible for handling side + * effects when writing MSRs and CRs, e.g. MMU context resets, CPUID + * runtime updates, etc... If that changes, e.g. this flow is moved + * out of the emulator to make it look more like enter_smm(), then + * those side effects need to be explicitly handled for both success + * and shutdown. + */ + return X86EMUL_CONTINUE; +emulate_shutdown: + ctxt->ops->triple_fault(ctxt); return X86EMUL_CONTINUE; } @@ -4124,11 +4028,11 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - emulator_get_fpu(); + kvm_fpu_get(); rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); - emulator_put_fpu(); + kvm_fpu_put(); if (rc != X86EMUL_CONTINUE) return rc; @@ -4172,7 +4076,7 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - emulator_get_fpu(); + kvm_fpu_get(); if (size < __fxstate_size(16)) { rc = fxregs_fixup(&fx_state, size); @@ -4189,7 +4093,7 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); out: - emulator_put_fpu(); + kvm_fpu_put(); return rc; } @@ -4502,7 +4406,7 @@ static const struct opcode group8[] = { * from the register case of group9. */ static const struct gprefix pfx_0f_c7_7 = { - N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdtscp), + N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdpid), }; @@ -5111,7 +5015,7 @@ done: return rc; } -int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) +int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type) { int rc = X86EMUL_CONTINUE; int mode = ctxt->mode; @@ -5322,7 +5226,8 @@ done_prefixes: ctxt->execute = opcode.u.execute; - if (unlikely(ctxt->ud) && likely(!(ctxt->d & EmulateOnUD))) + if (unlikely(emulation_type & EMULTYPE_TRAP_UD) && + likely(!(ctxt->d & EmulateOnUD))) return EMULATION_FAILED; if (unlikely(ctxt->d & @@ -5436,9 +5341,9 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) { int rc; - emulator_get_fpu(); + kvm_fpu_get(); rc = asm_safe("fwait"); - emulator_put_fpu(); + kvm_fpu_put(); if (unlikely(rc != X86EMUL_CONTINUE)) return emulate_exception(ctxt, MF_VECTOR, 0, false); @@ -5449,7 +5354,7 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) static void fetch_possible_mmx_operand(struct operand *op) { if (op->type == OP_MM) - read_mmx_reg(&op->mm_val, op->addr.mm); + kvm_read_mmx_reg(op->addr.mm, &op->mm_val); } static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop) diff --git a/arch/x86/kvm/fpu.h b/arch/x86/kvm/fpu.h new file mode 100644 index 000000000000..3ba12888bf66 --- /dev/null +++ b/arch/x86/kvm/fpu.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __KVM_FPU_H_ +#define __KVM_FPU_H_ + +#include <asm/fpu/api.h> + +typedef u32 __attribute__((vector_size(16))) sse128_t; +#define __sse128_u union { sse128_t vec; u64 as_u64[2]; u32 as_u32[4]; } +#define sse128_lo(x) ({ __sse128_u t; t.vec = x; t.as_u64[0]; }) +#define sse128_hi(x) ({ __sse128_u t; t.vec = x; t.as_u64[1]; }) +#define sse128_l0(x) ({ __sse128_u t; t.vec = x; t.as_u32[0]; }) +#define sse128_l1(x) ({ __sse128_u t; t.vec = x; t.as_u32[1]; }) +#define sse128_l2(x) ({ __sse128_u t; t.vec = x; t.as_u32[2]; }) +#define sse128_l3(x) ({ __sse128_u t; t.vec = x; t.as_u32[3]; }) +#define sse128(lo, hi) ({ __sse128_u t; t.as_u64[0] = lo; t.as_u64[1] = hi; t.vec; }) + +static inline void _kvm_read_sse_reg(int reg, sse128_t *data) +{ + switch (reg) { + case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; + case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; + case 2: asm("movdqa %%xmm2, %0" : "=m"(*data)); break; + case 3: asm("movdqa %%xmm3, %0" : "=m"(*data)); break; + case 4: asm("movdqa %%xmm4, %0" : "=m"(*data)); break; + case 5: asm("movdqa %%xmm5, %0" : "=m"(*data)); break; + case 6: asm("movdqa %%xmm6, %0" : "=m"(*data)); break; + case 7: asm("movdqa %%xmm7, %0" : "=m"(*data)); break; +#ifdef CONFIG_X86_64 + case 8: asm("movdqa %%xmm8, %0" : "=m"(*data)); break; + case 9: asm("movdqa %%xmm9, %0" : "=m"(*data)); break; + case 10: asm("movdqa %%xmm10, %0" : "=m"(*data)); break; + case 11: asm("movdqa %%xmm11, %0" : "=m"(*data)); break; + case 12: asm("movdqa %%xmm12, %0" : "=m"(*data)); break; + case 13: asm("movdqa %%xmm13, %0" : "=m"(*data)); break; + case 14: asm("movdqa %%xmm14, %0" : "=m"(*data)); break; + case 15: asm("movdqa %%xmm15, %0" : "=m"(*data)); break; +#endif + default: BUG(); + } +} + +static inline void _kvm_write_sse_reg(int reg, const sse128_t *data) +{ + switch (reg) { + case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; + case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; + case 2: asm("movdqa %0, %%xmm2" : : "m"(*data)); break; + case 3: asm("movdqa %0, %%xmm3" : : "m"(*data)); break; + case 4: asm("movdqa %0, %%xmm4" : : "m"(*data)); break; + case 5: asm("movdqa %0, %%xmm5" : : "m"(*data)); break; + case 6: asm("movdqa %0, %%xmm6" : : "m"(*data)); break; + case 7: asm("movdqa %0, %%xmm7" : : "m"(*data)); break; +#ifdef CONFIG_X86_64 + case 8: asm("movdqa %0, %%xmm8" : : "m"(*data)); break; + case 9: asm("movdqa %0, %%xmm9" : : "m"(*data)); break; + case 10: asm("movdqa %0, %%xmm10" : : "m"(*data)); break; + case 11: asm("movdqa %0, %%xmm11" : : "m"(*data)); break; + case 12: asm("movdqa %0, %%xmm12" : : "m"(*data)); break; + case 13: asm("movdqa %0, %%xmm13" : : "m"(*data)); break; + case 14: asm("movdqa %0, %%xmm14" : : "m"(*data)); break; + case 15: asm("movdqa %0, %%xmm15" : : "m"(*data)); break; +#endif + default: BUG(); + } +} + +static inline void _kvm_read_mmx_reg(int reg, u64 *data) +{ + switch (reg) { + case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; + case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; + case 2: asm("movq %%mm2, %0" : "=m"(*data)); break; + case 3: asm("movq %%mm3, %0" : "=m"(*data)); break; + case 4: asm("movq %%mm4, %0" : "=m"(*data)); break; + case 5: asm("movq %%mm5, %0" : "=m"(*data)); break; + case 6: asm("movq %%mm6, %0" : "=m"(*data)); break; + case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; + default: BUG(); + } +} + +static inline void _kvm_write_mmx_reg(int reg, const u64 *data) +{ + switch (reg) { + case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; + case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; + case 2: asm("movq %0, %%mm2" : : "m"(*data)); break; + case 3: asm("movq %0, %%mm3" : : "m"(*data)); break; + case 4: asm("movq %0, %%mm4" : : "m"(*data)); break; + case 5: asm("movq %0, %%mm5" : : "m"(*data)); break; + case 6: asm("movq %0, %%mm6" : : "m"(*data)); break; + case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; + default: BUG(); + } +} + +static inline void kvm_fpu_get(void) +{ + fpregs_lock(); + + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); +} + +static inline void kvm_fpu_put(void) +{ + fpregs_unlock(); +} + +static inline void kvm_read_sse_reg(int reg, sse128_t *data) +{ + kvm_fpu_get(); + _kvm_read_sse_reg(reg, data); + kvm_fpu_put(); +} + +static inline void kvm_write_sse_reg(int reg, const sse128_t *data) +{ + kvm_fpu_get(); + _kvm_write_sse_reg(reg, data); + kvm_fpu_put(); +} + +static inline void kvm_read_mmx_reg(int reg, u64 *data) +{ + kvm_fpu_get(); + _kvm_read_mmx_reg(reg, data); + kvm_fpu_put(); +} + +static inline void kvm_write_mmx_reg(int reg, const u64 *data) +{ + kvm_fpu_get(); + _kvm_write_mmx_reg(reg, data); + kvm_fpu_put(); +} + +#endif diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index f98370a39936..b07592ca92f0 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -36,6 +36,7 @@ #include "trace.h" #include "irq.h" +#include "fpu.h" /* "Hv#1" signature */ #define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 @@ -273,15 +274,10 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, static bool kvm_hv_is_syndbg_enabled(struct kvm_vcpu *vcpu) { - struct kvm_cpuid_entry2 *entry; - - entry = kvm_find_cpuid_entry(vcpu, - HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, - 0); - if (!entry) - return false; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); - return entry->eax & HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + return hv_vcpu->cpuid_cache.syndbg_cap_eax & + HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; } static int kvm_hv_syndbg_complete_userspace(struct kvm_vcpu *vcpu) @@ -635,11 +631,17 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, union hv_stimer_config new_config = {.as_uint64 = config}, old_config = {.as_uint64 = stimer->config.as_uint64}; struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); if (!synic->active && !host) return 1; + if (unlikely(!host && hv_vcpu->enforce_cpuid && new_config.direct_mode && + !(hv_vcpu->cpuid_cache.features_edx & + HV_STIMER_DIRECT_MODE_AVAILABLE))) + return 1; + trace_kvm_hv_stimer_set_config(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, config, host); @@ -1172,6 +1174,7 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm) { struct kvm_hv *hv = to_kvm_hv(kvm); u64 gfn; + int idx; if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET || @@ -1190,20 +1193,105 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm) gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; hv->tsc_ref.tsc_sequence = 0; + + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&kvm->srcu); if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; + srcu_read_unlock(&kvm->srcu, idx); out_unlock: mutex_unlock(&hv->hv_lock); } + +static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) +{ + if (!hv_vcpu->enforce_cpuid) + return true; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + case HV_X64_MSR_HYPERCALL: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_HYPERCALL_AVAILABLE; + case HV_X64_MSR_VP_RUNTIME: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_VP_RUNTIME_AVAILABLE; + case HV_X64_MSR_TIME_REF_COUNT: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_TIME_REF_COUNT_AVAILABLE; + case HV_X64_MSR_VP_INDEX: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_VP_INDEX_AVAILABLE; + case HV_X64_MSR_RESET: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_RESET_AVAILABLE; + case HV_X64_MSR_REFERENCE_TSC: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_REFERENCE_TSC_AVAILABLE; + case HV_X64_MSR_SCONTROL: + case HV_X64_MSR_SVERSION: + case HV_X64_MSR_SIEFP: + case HV_X64_MSR_SIMP: + case HV_X64_MSR_EOM: + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_SYNIC_AVAILABLE; + case HV_X64_MSR_STIMER0_CONFIG: + case HV_X64_MSR_STIMER1_CONFIG: + case HV_X64_MSR_STIMER2_CONFIG: + case HV_X64_MSR_STIMER3_CONFIG: + case HV_X64_MSR_STIMER0_COUNT: + case HV_X64_MSR_STIMER1_COUNT: + case HV_X64_MSR_STIMER2_COUNT: + case HV_X64_MSR_STIMER3_COUNT: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_SYNTIMER_AVAILABLE; + case HV_X64_MSR_EOI: + case HV_X64_MSR_ICR: + case HV_X64_MSR_TPR: + case HV_X64_MSR_VP_ASSIST_PAGE: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_APIC_ACCESS_AVAILABLE; + break; + case HV_X64_MSR_TSC_FREQUENCY: + case HV_X64_MSR_APIC_FREQUENCY: + return hv_vcpu->cpuid_cache.features_eax & + HV_ACCESS_FREQUENCY_MSRS; + case HV_X64_MSR_REENLIGHTENMENT_CONTROL: + case HV_X64_MSR_TSC_EMULATION_CONTROL: + case HV_X64_MSR_TSC_EMULATION_STATUS: + return hv_vcpu->cpuid_cache.features_eax & + HV_ACCESS_REENLIGHTENMENT; + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + case HV_X64_MSR_CRASH_CTL: + return hv_vcpu->cpuid_cache.features_edx & + HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + case HV_X64_MSR_SYNDBG_OPTIONS: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: + return hv_vcpu->cpuid_cache.features_edx & + HV_FEATURE_DEBUG_MSRS_AVAILABLE; + default: + break; + } + + return false; +} + static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { struct kvm *kvm = vcpu->kvm; struct kvm_hv *hv = to_kvm_hv(kvm); + if (unlikely(!host && !hv_check_msr_access(to_hv_vcpu(vcpu), msr))) + return 1; + switch (msr) { case HV_X64_MSR_GUEST_OS_ID: hv->hv_guest_os_id = data; @@ -1332,6 +1420,9 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + if (unlikely(!host && !hv_check_msr_access(hv_vcpu, msr))) + return 1; + switch (msr) { case HV_X64_MSR_VP_INDEX: { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); @@ -1446,6 +1537,9 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, struct kvm *kvm = vcpu->kvm; struct kvm_hv *hv = to_kvm_hv(kvm); + if (unlikely(!host && !hv_check_msr_access(to_hv_vcpu(vcpu), msr))) + return 1; + switch (msr) { case HV_X64_MSR_GUEST_OS_ID: data = hv->hv_guest_os_id; @@ -1495,6 +1589,9 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, u64 data = 0; struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + if (unlikely(!host && !hv_check_msr_access(hv_vcpu, msr))) + return 1; + switch (msr) { case HV_X64_MSR_VP_INDEX: data = hv_vcpu->vp_index; @@ -1623,8 +1720,22 @@ static __always_inline unsigned long *sparse_set_to_vcpu_mask( return vcpu_bitmap; } -static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, u64 ingpa, u16 rep_cnt, bool ex) +struct kvm_hv_hcall { + u64 param; + u64 ingpa; + u64 outgpa; + u16 code; + u16 rep_cnt; + u16 rep_idx; + bool fast; + bool rep; + sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS]; +}; + +static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool ex) { + int i; + gpa_t gpa; struct kvm *kvm = vcpu->kvm; struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct hv_tlb_flush_ex flush_ex; @@ -1638,8 +1749,15 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, u64 ingpa, u16 rep_cnt, bool bool all_cpus; if (!ex) { - if (unlikely(kvm_read_guest(kvm, ingpa, &flush, sizeof(flush)))) - return HV_STATUS_INVALID_HYPERCALL_INPUT; + if (hc->fast) { + flush.address_space = hc->ingpa; + flush.flags = hc->outgpa; + flush.processor_mask = sse128_lo(hc->xmm[0]); + } else { + if (unlikely(kvm_read_guest(kvm, hc->ingpa, + &flush, sizeof(flush)))) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } trace_kvm_hv_flush_tlb(flush.processor_mask, flush.address_space, flush.flags); @@ -1657,9 +1775,16 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, u64 ingpa, u16 rep_cnt, bool all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) || flush.processor_mask == 0; } else { - if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex, - sizeof(flush_ex)))) - return HV_STATUS_INVALID_HYPERCALL_INPUT; + if (hc->fast) { + flush_ex.address_space = hc->ingpa; + flush_ex.flags = hc->outgpa; + memcpy(&flush_ex.hv_vp_set, + &hc->xmm[0], sizeof(hc->xmm[0])); + } else { + if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex, + sizeof(flush_ex)))) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask, flush_ex.hv_vp_set.format, @@ -1670,20 +1795,28 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, u64 ingpa, u16 rep_cnt, bool all_cpus = flush_ex.hv_vp_set.format != HV_GENERIC_SET_SPARSE_4K; - sparse_banks_len = - bitmap_weight((unsigned long *)&valid_bank_mask, 64) * - sizeof(sparse_banks[0]); + sparse_banks_len = bitmap_weight((unsigned long *)&valid_bank_mask, 64); if (!sparse_banks_len && !all_cpus) goto ret_success; - if (!all_cpus && - kvm_read_guest(kvm, - ingpa + offsetof(struct hv_tlb_flush_ex, - hv_vp_set.bank_contents), - sparse_banks, - sparse_banks_len)) - return HV_STATUS_INVALID_HYPERCALL_INPUT; + if (!all_cpus) { + if (hc->fast) { + if (sparse_banks_len > HV_HYPERCALL_MAX_XMM_REGISTERS - 1) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + for (i = 0; i < sparse_banks_len; i += 2) { + sparse_banks[i] = sse128_lo(hc->xmm[i / 2 + 1]); + sparse_banks[i + 1] = sse128_hi(hc->xmm[i / 2 + 1]); + } + } else { + gpa = hc->ingpa + offsetof(struct hv_tlb_flush_ex, + hv_vp_set.bank_contents); + if (unlikely(kvm_read_guest(kvm, gpa, sparse_banks, + sparse_banks_len * + sizeof(sparse_banks[0])))) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } + } } cpumask_clear(&hv_vcpu->tlb_flush); @@ -1696,13 +1829,13 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, u64 ingpa, u16 rep_cnt, bool * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't * analyze it here, flush TLB regardless of the specified address space. */ - kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, + kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, NULL, vcpu_mask, &hv_vcpu->tlb_flush); ret_success: - /* We always do full TLB flush, set rep_done = rep_cnt. */ + /* We always do full TLB flush, set 'Reps completed' = 'Rep Count' */ return (u64)HV_STATUS_SUCCESS | - ((u64)rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET); + ((u64)hc->rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET); } static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, @@ -1724,8 +1857,7 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, } } -static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, u64 ingpa, u64 outgpa, - bool ex, bool fast) +static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool ex) { struct kvm *kvm = vcpu->kvm; struct hv_send_ipi_ex send_ipi_ex; @@ -1740,25 +1872,25 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, u64 ingpa, u64 outgpa, bool all_cpus; if (!ex) { - if (!fast) { - if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi, + if (!hc->fast) { + if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi, sizeof(send_ipi)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; sparse_banks[0] = send_ipi.cpu_mask; vector = send_ipi.vector; } else { /* 'reserved' part of hv_send_ipi should be 0 */ - if (unlikely(ingpa >> 32 != 0)) + if (unlikely(hc->ingpa >> 32 != 0)) return HV_STATUS_INVALID_HYPERCALL_INPUT; - sparse_banks[0] = outgpa; - vector = (u32)ingpa; + sparse_banks[0] = hc->outgpa; + vector = (u32)hc->ingpa; } all_cpus = false; valid_bank_mask = BIT_ULL(0); trace_kvm_hv_send_ipi(vector, sparse_banks[0]); } else { - if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi_ex, + if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi_ex, sizeof(send_ipi_ex)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; @@ -1778,8 +1910,8 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, u64 ingpa, u64 outgpa, if (!all_cpus && kvm_read_guest(kvm, - ingpa + offsetof(struct hv_send_ipi_ex, - vp_set.bank_contents), + hc->ingpa + offsetof(struct hv_send_ipi_ex, + vp_set.bank_contents), sparse_banks, sparse_banks_len)) return HV_STATUS_INVALID_HYPERCALL_INPUT; @@ -1801,12 +1933,67 @@ ret_success: void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *entry; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE, 0); - if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) + if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) { vcpu->arch.hyperv_enabled = true; - else + } else { vcpu->arch.hyperv_enabled = false; + return; + } + + if (!to_hv_vcpu(vcpu) && kvm_hv_vcpu_init(vcpu)) + return; + + hv_vcpu = to_hv_vcpu(vcpu); + + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES, 0); + if (entry) { + hv_vcpu->cpuid_cache.features_eax = entry->eax; + hv_vcpu->cpuid_cache.features_ebx = entry->ebx; + hv_vcpu->cpuid_cache.features_edx = entry->edx; + } else { + hv_vcpu->cpuid_cache.features_eax = 0; + hv_vcpu->cpuid_cache.features_ebx = 0; + hv_vcpu->cpuid_cache.features_edx = 0; + } + + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO, 0); + if (entry) { + hv_vcpu->cpuid_cache.enlightenments_eax = entry->eax; + hv_vcpu->cpuid_cache.enlightenments_ebx = entry->ebx; + } else { + hv_vcpu->cpuid_cache.enlightenments_eax = 0; + hv_vcpu->cpuid_cache.enlightenments_ebx = 0; + } + + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, 0); + if (entry) + hv_vcpu->cpuid_cache.syndbg_cap_eax = entry->eax; + else + hv_vcpu->cpuid_cache.syndbg_cap_eax = 0; +} + +int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce) +{ + struct kvm_vcpu_hv *hv_vcpu; + int ret = 0; + + if (!to_hv_vcpu(vcpu)) { + if (enforce) { + ret = kvm_hv_vcpu_init(vcpu); + if (ret) + return ret; + } else { + return 0; + } + } + + hv_vcpu = to_hv_vcpu(vcpu); + hv_vcpu->enforce_cpuid = enforce; + + return ret; } bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu) @@ -1839,20 +2026,21 @@ static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu) return kvm_hv_hypercall_complete(vcpu, vcpu->run->hyperv.u.hcall.result); } -static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) +static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); struct eventfd_ctx *eventfd; - if (unlikely(!fast)) { + if (unlikely(!hc->fast)) { int ret; - gpa_t gpa = param; + gpa_t gpa = hc->ingpa; - if ((gpa & (__alignof__(param) - 1)) || - offset_in_page(gpa) + sizeof(param) > PAGE_SIZE) + if ((gpa & (__alignof__(hc->ingpa) - 1)) || + offset_in_page(gpa) + sizeof(hc->ingpa) > PAGE_SIZE) return HV_STATUS_INVALID_ALIGNMENT; - ret = kvm_vcpu_read_guest(vcpu, gpa, ¶m, sizeof(param)); + ret = kvm_vcpu_read_guest(vcpu, gpa, + &hc->ingpa, sizeof(hc->ingpa)); if (ret < 0) return HV_STATUS_INVALID_ALIGNMENT; } @@ -1862,15 +2050,15 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) * have no use for it, and in all known usecases it is zero, so just * report lookup failure if it isn't. */ - if (param & 0xffff00000000ULL) + if (hc->ingpa & 0xffff00000000ULL) return HV_STATUS_INVALID_PORT_ID; /* remaining bits are reserved-zero */ - if (param & ~KVM_HYPERV_CONN_ID_MASK) + if (hc->ingpa & ~KVM_HYPERV_CONN_ID_MASK) return HV_STATUS_INVALID_HYPERCALL_INPUT; /* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */ rcu_read_lock(); - eventfd = idr_find(&hv->conn_to_evt, param); + eventfd = idr_find(&hv->conn_to_evt, hc->ingpa); rcu_read_unlock(); if (!eventfd) return HV_STATUS_INVALID_PORT_ID; @@ -1879,11 +2067,80 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) return HV_STATUS_SUCCESS; } +static bool is_xmm_fast_hypercall(struct kvm_hv_hcall *hc) +{ + switch (hc->code) { + case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: + case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: + return true; + } + + return false; +} + +static void kvm_hv_hypercall_read_xmm(struct kvm_hv_hcall *hc) +{ + int reg; + + kvm_fpu_get(); + for (reg = 0; reg < HV_HYPERCALL_MAX_XMM_REGISTERS; reg++) + _kvm_read_sse_reg(reg, &hc->xmm[reg]); + kvm_fpu_put(); +} + +static bool hv_check_hypercall_access(struct kvm_vcpu_hv *hv_vcpu, u16 code) +{ + if (!hv_vcpu->enforce_cpuid) + return true; + + switch (code) { + case HVCALL_NOTIFY_LONG_SPIN_WAIT: + return hv_vcpu->cpuid_cache.enlightenments_ebx && + hv_vcpu->cpuid_cache.enlightenments_ebx != U32_MAX; + case HVCALL_POST_MESSAGE: + return hv_vcpu->cpuid_cache.features_ebx & HV_POST_MESSAGES; + case HVCALL_SIGNAL_EVENT: + return hv_vcpu->cpuid_cache.features_ebx & HV_SIGNAL_EVENTS; + case HVCALL_POST_DEBUG_DATA: + case HVCALL_RETRIEVE_DEBUG_DATA: + case HVCALL_RESET_DEBUG_SESSION: + /* + * Return 'true' when SynDBG is disabled so the resulting code + * will be HV_STATUS_INVALID_HYPERCALL_CODE. + */ + return !kvm_hv_is_syndbg_enabled(hv_vcpu->vcpu) || + hv_vcpu->cpuid_cache.features_ebx & HV_DEBUGGING; + case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: + if (!(hv_vcpu->cpuid_cache.enlightenments_eax & + HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + return false; + fallthrough; + case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: + return hv_vcpu->cpuid_cache.enlightenments_eax & + HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + case HVCALL_SEND_IPI_EX: + if (!(hv_vcpu->cpuid_cache.enlightenments_eax & + HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + return false; + fallthrough; + case HVCALL_SEND_IPI: + return hv_vcpu->cpuid_cache.enlightenments_eax & + HV_X64_CLUSTER_IPI_RECOMMENDED; + default: + break; + } + + return true; +} + int kvm_hv_hypercall(struct kvm_vcpu *vcpu) { - u64 param, ingpa, outgpa, ret = HV_STATUS_SUCCESS; - uint16_t code, rep_idx, rep_cnt; - bool fast, rep; + struct kvm_hv_hcall hc; + u64 ret = HV_STATUS_SUCCESS; /* * hypercall generates UD from non zero cpl and real mode @@ -1896,104 +2153,113 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 if (is_64_bit_mode(vcpu)) { - param = kvm_rcx_read(vcpu); - ingpa = kvm_rdx_read(vcpu); - outgpa = kvm_r8_read(vcpu); + hc.param = kvm_rcx_read(vcpu); + hc.ingpa = kvm_rdx_read(vcpu); + hc.outgpa = kvm_r8_read(vcpu); } else #endif { - param = ((u64)kvm_rdx_read(vcpu) << 32) | - (kvm_rax_read(vcpu) & 0xffffffff); - ingpa = ((u64)kvm_rbx_read(vcpu) << 32) | - (kvm_rcx_read(vcpu) & 0xffffffff); - outgpa = ((u64)kvm_rdi_read(vcpu) << 32) | - (kvm_rsi_read(vcpu) & 0xffffffff); + hc.param = ((u64)kvm_rdx_read(vcpu) << 32) | + (kvm_rax_read(vcpu) & 0xffffffff); + hc.ingpa = ((u64)kvm_rbx_read(vcpu) << 32) | + (kvm_rcx_read(vcpu) & 0xffffffff); + hc.outgpa = ((u64)kvm_rdi_read(vcpu) << 32) | + (kvm_rsi_read(vcpu) & 0xffffffff); } - code = param & 0xffff; - fast = !!(param & HV_HYPERCALL_FAST_BIT); - rep_cnt = (param >> HV_HYPERCALL_REP_COMP_OFFSET) & 0xfff; - rep_idx = (param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff; - rep = !!(rep_cnt || rep_idx); + hc.code = hc.param & 0xffff; + hc.fast = !!(hc.param & HV_HYPERCALL_FAST_BIT); + hc.rep_cnt = (hc.param >> HV_HYPERCALL_REP_COMP_OFFSET) & 0xfff; + hc.rep_idx = (hc.param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff; + hc.rep = !!(hc.rep_cnt || hc.rep_idx); - trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); + if (hc.fast && is_xmm_fast_hypercall(&hc)) + kvm_hv_hypercall_read_xmm(&hc); - switch (code) { + trace_kvm_hv_hypercall(hc.code, hc.fast, hc.rep_cnt, hc.rep_idx, + hc.ingpa, hc.outgpa); + + if (unlikely(!hv_check_hypercall_access(to_hv_vcpu(vcpu), hc.code))) { + ret = HV_STATUS_ACCESS_DENIED; + goto hypercall_complete; + } + + switch (hc.code) { case HVCALL_NOTIFY_LONG_SPIN_WAIT: - if (unlikely(rep)) { + if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } kvm_vcpu_on_spin(vcpu, true); break; case HVCALL_SIGNAL_EVENT: - if (unlikely(rep)) { + if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hvcall_signal_event(vcpu, fast, ingpa); + ret = kvm_hvcall_signal_event(vcpu, &hc); if (ret != HV_STATUS_INVALID_PORT_ID) break; fallthrough; /* maybe userspace knows this conn_id */ case HVCALL_POST_MESSAGE: /* don't bother userspace if it has no way to handle it */ - if (unlikely(rep || !to_hv_synic(vcpu)->active)) { + if (unlikely(hc.rep || !to_hv_synic(vcpu)->active)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } vcpu->run->exit_reason = KVM_EXIT_HYPERV; vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; - vcpu->run->hyperv.u.hcall.input = param; - vcpu->run->hyperv.u.hcall.params[0] = ingpa; - vcpu->run->hyperv.u.hcall.params[1] = outgpa; + vcpu->run->hyperv.u.hcall.input = hc.param; + vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; + vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace; return 0; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: - if (unlikely(fast || !rep_cnt || rep_idx)) { + if (unlikely(!hc.rep_cnt || hc.rep_idx)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, false); + ret = kvm_hv_flush_tlb(vcpu, &hc, false); break; case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: - if (unlikely(fast || rep)) { + if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, false); + ret = kvm_hv_flush_tlb(vcpu, &hc, false); break; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: - if (unlikely(fast || !rep_cnt || rep_idx)) { + if (unlikely(!hc.rep_cnt || hc.rep_idx)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true); + ret = kvm_hv_flush_tlb(vcpu, &hc, true); break; case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: - if (unlikely(fast || rep)) { + if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true); + ret = kvm_hv_flush_tlb(vcpu, &hc, true); break; case HVCALL_SEND_IPI: - if (unlikely(rep)) { + if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, false, fast); + ret = kvm_hv_send_ipi(vcpu, &hc, false); break; case HVCALL_SEND_IPI_EX: - if (unlikely(fast || rep)) { + if (unlikely(hc.fast || hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, true, false); + ret = kvm_hv_send_ipi(vcpu, &hc, true); break; case HVCALL_POST_DEBUG_DATA: case HVCALL_RETRIEVE_DEBUG_DATA: - if (unlikely(fast)) { + if (unlikely(hc.fast)) { ret = HV_STATUS_INVALID_PARAMETER; break; } @@ -2012,9 +2278,9 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) } vcpu->run->exit_reason = KVM_EXIT_HYPERV; vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; - vcpu->run->hyperv.u.hcall.input = param; - vcpu->run->hyperv.u.hcall.params[0] = ingpa; - vcpu->run->hyperv.u.hcall.params[1] = outgpa; + vcpu->run->hyperv.u.hcall.input = hc.param; + vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; + vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace; return 0; @@ -2024,6 +2290,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) break; } +hypercall_complete: return kvm_hv_hypercall_complete(vcpu, ret); } @@ -2172,6 +2439,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->ebx |= HV_POST_MESSAGES; ent->ebx |= HV_SIGNAL_EVENTS; + ent->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 60547d5cb6d7..730da8537d05 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -138,6 +138,7 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm); void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu); +int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce); int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args); int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 3db5c42c9ecd..90e1ffdc05b7 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -55,6 +55,13 @@ static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); } +static inline void kvm_register_clear_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, enum kvm_reg reg) { @@ -118,6 +125,11 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) return vcpu->arch.walk_mmu->pdptrs[index]; } +static inline void kvm_pdptr_write(struct kvm_vcpu *vcpu, int index, u64 value) +{ + vcpu->arch.walk_mmu->pdptrs[index] = value; +} + static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS; @@ -162,6 +174,7 @@ static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu) static inline void enter_guest_mode(struct kvm_vcpu *vcpu) { vcpu->arch.hflags |= HF_GUEST_MASK; + vcpu->stat.guest_mode = 1; } static inline void leave_guest_mode(struct kvm_vcpu *vcpu) @@ -172,6 +185,8 @@ static inline void leave_guest_mode(struct kvm_vcpu *vcpu) vcpu->arch.load_eoi_exitmap_pending = false; kvm_make_request(KVM_REQ_LOAD_EOI_EXITMAP, vcpu); } + + vcpu->stat.guest_mode = 0; } static inline bool is_guest_mode(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 0d359115429a..68b420289d7e 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -13,6 +13,7 @@ #define _ASM_X86_KVM_X86_EMULATE_H #include <asm/desc_defs.h> +#include "fpu.h" struct x86_emulate_ctxt; enum x86_intercept; @@ -229,15 +230,12 @@ struct x86_emulate_ops { void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); - void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags); - int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, - const char *smstate); - void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt); + void (*exiting_smm)(struct x86_emulate_ctxt *ctxt); + int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const char *smstate); + void (*triple_fault)(struct x86_emulate_ctxt *ctxt); int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); }; -typedef u32 __attribute__((vector_size(16))) sse128_t; - /* Type, address-of, and value of an instruction's operand. */ struct operand { enum { OP_REG, OP_MEM, OP_MEM_STR, OP_IMM, OP_XMM, OP_MM, OP_NONE } type; @@ -314,7 +312,6 @@ struct x86_emulate_ctxt { int interruptibility; bool perm_ok; /* do not check permissions if true */ - bool ud; /* inject an #UD if host doesn't support insn */ bool tf; /* TF value before instruction (after for syscall/sysret) */ bool have_exception; @@ -468,6 +465,7 @@ enum x86_intercept { x86_intercept_clgi, x86_intercept_skinit, x86_intercept_rdtscp, + x86_intercept_rdpid, x86_intercept_icebp, x86_intercept_wbinvd, x86_intercept_monitor, @@ -490,7 +488,7 @@ enum x86_intercept { #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64 #endif -int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len); +int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type); bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt); #define EMULATION_FAILED -1 #define EMULATION_OK 0 diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c new file mode 100644 index 000000000000..c7db2df50a7a --- /dev/null +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM L1 hypervisor optimizations on Hyper-V. + */ + +#include <linux/kvm_host.h> +#include <asm/mshyperv.h> + +#include "hyperv.h" +#include "kvm_onhyperv.h" + +static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush, + void *data) +{ + struct kvm_tlb_range *range = data; + + return hyperv_fill_flush_guest_mapping_list(flush, range->start_gfn, + range->pages); +} + +static inline int hv_remote_flush_root_tdp(hpa_t root_tdp, + struct kvm_tlb_range *range) +{ + if (range) + return hyperv_flush_guest_mapping_range(root_tdp, + kvm_fill_hv_flush_list_func, (void *)range); + else + return hyperv_flush_guest_mapping(root_tdp); +} + +int hv_remote_flush_tlb_with_range(struct kvm *kvm, + struct kvm_tlb_range *range) +{ + struct kvm_arch *kvm_arch = &kvm->arch; + struct kvm_vcpu *vcpu; + int ret = 0, i, nr_unique_valid_roots; + hpa_t root; + + spin_lock(&kvm_arch->hv_root_tdp_lock); + + if (!VALID_PAGE(kvm_arch->hv_root_tdp)) { + nr_unique_valid_roots = 0; + + /* + * Flush all valid roots, and see if all vCPUs have converged + * on a common root, in which case future flushes can skip the + * loop and flush the common root. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + root = vcpu->arch.hv_root_tdp; + if (!VALID_PAGE(root) || root == kvm_arch->hv_root_tdp) + continue; + + /* + * Set the tracked root to the first valid root. Keep + * this root for the entirety of the loop even if more + * roots are encountered as a low effort optimization + * to avoid flushing the same (first) root again. + */ + if (++nr_unique_valid_roots == 1) + kvm_arch->hv_root_tdp = root; + + if (!ret) + ret = hv_remote_flush_root_tdp(root, range); + + /* + * Stop processing roots if a failure occurred and + * multiple valid roots have already been detected. + */ + if (ret && nr_unique_valid_roots > 1) + break; + } + + /* + * The optimized flush of a single root can't be used if there + * are multiple valid roots (obviously). + */ + if (nr_unique_valid_roots > 1) + kvm_arch->hv_root_tdp = INVALID_PAGE; + } else { + ret = hv_remote_flush_root_tdp(kvm_arch->hv_root_tdp, range); + } + + spin_unlock(&kvm_arch->hv_root_tdp_lock); + return ret; +} +EXPORT_SYMBOL_GPL(hv_remote_flush_tlb_with_range); + +int hv_remote_flush_tlb(struct kvm *kvm) +{ + return hv_remote_flush_tlb_with_range(kvm, NULL); +} +EXPORT_SYMBOL_GPL(hv_remote_flush_tlb); diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h new file mode 100644 index 000000000000..1c67abf2eba9 --- /dev/null +++ b/arch/x86/kvm/kvm_onhyperv.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * KVM L1 hypervisor optimizations on Hyper-V. + */ + +#ifndef __ARCH_X86_KVM_KVM_ONHYPERV_H__ +#define __ARCH_X86_KVM_KVM_ONHYPERV_H__ + +#if IS_ENABLED(CONFIG_HYPERV) +int hv_remote_flush_tlb_with_range(struct kvm *kvm, + struct kvm_tlb_range *range); +int hv_remote_flush_tlb(struct kvm *kvm); + +static inline void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp) +{ + struct kvm_arch *kvm_arch = &vcpu->kvm->arch; + + if (kvm_x86_ops.tlb_remote_flush == hv_remote_flush_tlb) { + spin_lock(&kvm_arch->hv_root_tdp_lock); + vcpu->arch.hv_root_tdp = root_tdp; + if (root_tdp != kvm_arch->hv_root_tdp) + kvm_arch->hv_root_tdp = INVALID_PAGE; + spin_unlock(&kvm_arch->hv_root_tdp_lock); + } +} +#else /* !CONFIG_HYPERV */ +static inline void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp) +{ +} +#endif /* !CONFIG_HYPERV */ + +#endif diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 152591f9243a..ba5a27879f1d 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1410,6 +1410,9 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, if (!apic_x2apic_mode(apic)) valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI); + if (alignment + len > 4) + return 1; + if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset))) return 1; @@ -1494,6 +1497,15 @@ static void limit_periodic_timer_frequency(struct kvm_lapic *apic) static void cancel_hv_timer(struct kvm_lapic *apic); +static void cancel_apic_timer(struct kvm_lapic *apic) +{ + hrtimer_cancel(&apic->lapic_timer.timer); + preempt_disable(); + if (apic->lapic_timer.hv_timer_in_use) + cancel_hv_timer(apic); + preempt_enable(); +} + static void apic_update_lvtt(struct kvm_lapic *apic) { u32 timer_mode = kvm_lapic_get_reg(apic, APIC_LVTT) & @@ -1502,11 +1514,7 @@ static void apic_update_lvtt(struct kvm_lapic *apic) if (apic->lapic_timer.timer_mode != timer_mode) { if (apic_lvtt_tscdeadline(apic) != (timer_mode == APIC_LVT_TIMER_TSCDEADLINE)) { - hrtimer_cancel(&apic->lapic_timer.timer); - preempt_disable(); - if (apic->lapic_timer.hv_timer_in_use) - cancel_hv_timer(apic); - preempt_enable(); + cancel_apic_timer(apic); kvm_lapic_set_reg(apic, APIC_TMICT, 0); apic->lapic_timer.period = 0; apic->lapic_timer.tscdeadline = 0; @@ -1598,11 +1606,19 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); apic->lapic_timer.advance_expire_delta = guest_tsc - tsc_deadline; + if (lapic_timer_advance_dynamic) { + adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta); + /* + * If the timer fired early, reread the TSC to account for the + * overhead of the above adjustment to avoid waiting longer + * than is necessary. + */ + if (guest_tsc < tsc_deadline) + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); + } + if (guest_tsc < tsc_deadline) __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); - - if (lapic_timer_advance_dynamic) - adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta); } void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) @@ -1661,7 +1677,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn) } atomic_inc(&apic->lapic_timer.pending); - kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_make_request(KVM_REQ_UNBLOCK, vcpu); if (from_timer_fn) kvm_vcpu_kick(vcpu); } @@ -1913,8 +1929,8 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) if (!apic->lapic_timer.hv_timer_in_use) goto out; WARN_ON(rcuwait_active(&vcpu->wait)); - cancel_hv_timer(apic); apic_timer_expired(apic, false); + cancel_hv_timer(apic); if (apic_lvtt_period(apic) && apic->lapic_timer.period) { advance_periodic_target_expiration(apic); @@ -2084,7 +2100,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) if (apic_lvtt_tscdeadline(apic)) break; - hrtimer_cancel(&apic->lapic_timer.timer); + cancel_apic_timer(apic); kvm_lapic_set_reg(apic, APIC_TMICT, val); start_apic_timer(apic); break; @@ -2615,6 +2631,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); update_divide_count(apic); __start_apic_timer(apic, APIC_TMCCT); + kvm_lapic_set_reg(apic, APIC_TMCCT, 0); kvm_apic_update_apicv(vcpu); apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { @@ -2856,7 +2873,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len) return kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len); } -void kvm_apic_accept_events(struct kvm_vcpu *vcpu) +int kvm_apic_accept_events(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; u8 sipi_vector; @@ -2864,7 +2881,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) unsigned long pe; if (!lapic_in_kernel(vcpu)) - return; + return 0; /* * Read pending events before calling the check_events @@ -2872,12 +2889,12 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) */ pe = smp_load_acquire(&apic->pending_events); if (!pe) - return; + return 0; if (is_guest_mode(vcpu)) { r = kvm_check_nested_events(vcpu); if (r < 0) - return; + return r == -EBUSY ? 0 : r; /* * If an event has happened and caused a vmexit, * we know INITs are latched and therefore @@ -2898,7 +2915,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); if (test_bit(KVM_APIC_SIPI, &pe)) clear_bit(KVM_APIC_SIPI, &apic->pending_events); - return; + return 0; } if (test_bit(KVM_APIC_INIT, &pe)) { @@ -2919,6 +2936,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } } + return 0; } void kvm_lapic_exit(void) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 997c45a5963a..d7c25d0c1354 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -76,7 +76,7 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); -void kvm_apic_accept_events(struct kvm_vcpu *vcpu); +int kvm_apic_accept_events(struct kvm_vcpu *vcpu); void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 88d0ed5225a4..83e6c6965f1e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -44,6 +44,12 @@ #define PT32_ROOT_LEVEL 2 #define PT32E_ROOT_LEVEL 3 +#define KVM_MMU_CR4_ROLE_BITS (X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | \ + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE | \ + X86_CR4_LA57) + +#define KVM_MMU_CR0_ROLE_BITS (X86_CR0_PG | X86_CR0_WP) + static __always_inline u64 rsvd_bits(int s, int e) { BUILD_BUG_ON(__builtin_constant_p(e) && __builtin_constant_p(s) && e < s); @@ -62,12 +68,9 @@ static __always_inline u64 rsvd_bits(int s, int e) void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask); void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only); -void -reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); - -void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots); -void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer, - gpa_t nested_cr3); +void kvm_init_mmu(struct kvm_vcpu *vcpu); +void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, + unsigned long cr4, u64 efer, gpa_t nested_cr3); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool accessed_dirty, gpa_t new_eptp); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); @@ -162,11 +165,6 @@ static inline bool is_writable_pte(unsigned long pte) return pte & PT_WRITABLE_MASK; } -static inline bool is_write_protection(struct kvm_vcpu *vcpu) -{ - return kvm_read_cr0_bits(vcpu, X86_CR0_WP); -} - /* * Check if a given access (described through the I/D, W/R and U/S bits of a * page fault error code pfec) causes a permission fault with the given PTE @@ -232,4 +230,14 @@ int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); +static inline bool kvm_memslots_have_rmaps(struct kvm *kvm) +{ + /* + * Read memslot_have_rmaps before rmap pointers. Hence, threads reading + * memslots_have_rmaps in any lock context are guaranteed to see the + * pointers. Pairs with smp_store_release in alloc_all_memslots_rmaps. + */ + return smp_load_acquire(&kvm->arch.memslots_have_rmaps); +} + #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4b3ee244ebe0..00732757cc60 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -55,7 +55,7 @@ extern bool itlb_multihit_kvm_mitigation; -static int __read_mostly nx_huge_pages = -1; +int __read_mostly nx_huge_pages = -1; #ifdef CONFIG_PREEMPT_RT /* Recovery can cause latency spikes, disable it for PREEMPT_RT. */ static uint __read_mostly nx_huge_pages_recovery_ratio = 0; @@ -176,9 +176,80 @@ static void mmu_spte_set(u64 *sptep, u64 spte); static union kvm_mmu_page_role kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu); +struct kvm_mmu_role_regs { + const unsigned long cr0; + const unsigned long cr4; + const u64 efer; +}; + #define CREATE_TRACE_POINTS #include "mmutrace.h" +/* + * Yes, lot's of underscores. They're a hint that you probably shouldn't be + * reading from the role_regs. Once the mmu_role is constructed, it becomes + * the single source of truth for the MMU's state. + */ +#define BUILD_MMU_ROLE_REGS_ACCESSOR(reg, name, flag) \ +static inline bool ____is_##reg##_##name(struct kvm_mmu_role_regs *regs)\ +{ \ + return !!(regs->reg & flag); \ +} +BUILD_MMU_ROLE_REGS_ACCESSOR(cr0, pg, X86_CR0_PG); +BUILD_MMU_ROLE_REGS_ACCESSOR(cr0, wp, X86_CR0_WP); +BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pse, X86_CR4_PSE); +BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pae, X86_CR4_PAE); +BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, smep, X86_CR4_SMEP); +BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, smap, X86_CR4_SMAP); +BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pke, X86_CR4_PKE); +BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, la57, X86_CR4_LA57); +BUILD_MMU_ROLE_REGS_ACCESSOR(efer, nx, EFER_NX); +BUILD_MMU_ROLE_REGS_ACCESSOR(efer, lma, EFER_LMA); + +/* + * The MMU itself (with a valid role) is the single source of truth for the + * MMU. Do not use the regs used to build the MMU/role, nor the vCPU. The + * regs don't account for dependencies, e.g. clearing CR4 bits if CR0.PG=1, + * and the vCPU may be incorrect/irrelevant. + */ +#define BUILD_MMU_ROLE_ACCESSOR(base_or_ext, reg, name) \ +static inline bool is_##reg##_##name(struct kvm_mmu *mmu) \ +{ \ + return !!(mmu->mmu_role. base_or_ext . reg##_##name); \ +} +BUILD_MMU_ROLE_ACCESSOR(ext, cr0, pg); +BUILD_MMU_ROLE_ACCESSOR(base, cr0, wp); +BUILD_MMU_ROLE_ACCESSOR(ext, cr4, pse); +BUILD_MMU_ROLE_ACCESSOR(ext, cr4, pae); +BUILD_MMU_ROLE_ACCESSOR(ext, cr4, smep); +BUILD_MMU_ROLE_ACCESSOR(ext, cr4, smap); +BUILD_MMU_ROLE_ACCESSOR(ext, cr4, pke); +BUILD_MMU_ROLE_ACCESSOR(ext, cr4, la57); +BUILD_MMU_ROLE_ACCESSOR(base, efer, nx); + +static struct kvm_mmu_role_regs vcpu_to_role_regs(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu_role_regs regs = { + .cr0 = kvm_read_cr0_bits(vcpu, KVM_MMU_CR0_ROLE_BITS), + .cr4 = kvm_read_cr4_bits(vcpu, KVM_MMU_CR4_ROLE_BITS), + .efer = vcpu->arch.efer, + }; + + return regs; +} + +static int role_regs_to_root_level(struct kvm_mmu_role_regs *regs) +{ + if (!____is_cr0_pg(regs)) + return 0; + else if (____is_efer_lma(regs)) + return ____is_cr4_la57(regs) ? PT64_ROOT_5LEVEL : + PT64_ROOT_4LEVEL; + else if (____is_cr4_pae(regs)) + return PT32E_ROOT_LEVEL; + else + return PT32_ROOT_LEVEL; +} static inline bool kvm_available_flush_tlb_with_range(void) { @@ -208,11 +279,6 @@ void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, kvm_flush_remote_tlbs_with_range(kvm, &range); } -bool is_nx_huge_page_enabled(void) -{ - return READ_ONCE(nx_huge_pages); -} - static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, unsigned int access) { @@ -269,11 +335,6 @@ static int is_cpuid_PSE36(void) return 1; } -static int is_nx(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.efer & EFER_NX; -} - static gfn_t pse36_gfn_delta(u32 gpte) { int shift = 32 - PT32_DIR_PSE36_SHIFT - PAGE_SHIFT; @@ -1177,8 +1238,7 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head, * @gfn_offset: start of the BITS_PER_LONG pages we care about * @mask: indicates which pages we should protect * - * Used when we do not need to care about huge page mappings: e.g. during dirty - * logging we do not have any such mappings. + * Used when we do not need to care about huge page mappings. */ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, @@ -1189,6 +1249,10 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, true); + + if (!kvm_memslots_have_rmaps(kvm)) + return; + while (mask) { rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PG_LEVEL_4K, slot); @@ -1218,6 +1282,10 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, false); + + if (!kvm_memslots_have_rmaps(kvm)) + return; + while (mask) { rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PG_LEVEL_4K, slot); @@ -1235,13 +1303,36 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to * enable dirty logging for them. * - * Used when we do not need to care about huge page mappings: e.g. during dirty - * logging we do not have any such mappings. + * We need to care about huge page mappings: e.g. during dirty logging we may + * have such mappings. */ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { + /* + * Huge pages are NOT write protected when we start dirty logging in + * initially-all-set mode; must write protect them here so that they + * are split to 4K on the first write. + * + * The gfn_offset is guaranteed to be aligned to 64, but the base_gfn + * of memslot has no such restriction, so the range can cross two large + * pages. + */ + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) { + gfn_t start = slot->base_gfn + gfn_offset + __ffs(mask); + gfn_t end = slot->base_gfn + gfn_offset + __fls(mask); + + kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M); + + /* Cross two large pages? */ + if (ALIGN(start << PAGE_SHIFT, PMD_SIZE) != + ALIGN(end << PAGE_SHIFT, PMD_SIZE)) + kvm_mmu_slot_gfn_write_protect(kvm, slot, end, + PG_LEVEL_2M); + } + + /* Now handle 4K PTEs. */ if (kvm_x86_ops.cpu_dirty_log_size) kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask); else @@ -1254,20 +1345,23 @@ int kvm_cpu_dirty_log_size(void) } bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, - struct kvm_memory_slot *slot, u64 gfn) + struct kvm_memory_slot *slot, u64 gfn, + int min_level) { struct kvm_rmap_head *rmap_head; int i; bool write_protected = false; - for (i = PG_LEVEL_4K; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { - rmap_head = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(kvm, rmap_head, true); + if (kvm_memslots_have_rmaps(kvm)) { + for (i = min_level; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { + rmap_head = __gfn_to_rmap(gfn, i, slot); + write_protected |= __rmap_write_protect(kvm, rmap_head, true); + } } if (is_tdp_mmu_enabled(kvm)) write_protected |= - kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn); + kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn, min_level); return write_protected; } @@ -1277,7 +1371,7 @@ static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) struct kvm_memory_slot *slot; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn); + return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn, PG_LEVEL_4K); } static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, @@ -1433,9 +1527,10 @@ static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm, bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { - bool flush; + bool flush = false; - flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp); + if (kvm_memslots_have_rmaps(kvm)) + 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); @@ -1445,9 +1540,10 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { - bool flush; + bool flush = false; - flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmapp); + if (kvm_memslots_have_rmaps(kvm)) + flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmapp); if (is_tdp_mmu_enabled(kvm)) flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range); @@ -1500,9 +1596,10 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { - bool young; + bool young = false; - young = kvm_handle_gfn_range(kvm, range, kvm_age_rmapp); + if (kvm_memslots_have_rmaps(kvm)) + young = kvm_handle_gfn_range(kvm, range, kvm_age_rmapp); if (is_tdp_mmu_enabled(kvm)) young |= kvm_tdp_mmu_age_gfn_range(kvm, range); @@ -1512,9 +1609,10 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { - bool young; + bool young = false; - young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmapp); + if (kvm_memslots_have_rmaps(kvm)) + young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmapp); if (is_tdp_mmu_enabled(kvm)) young |= kvm_tdp_mmu_test_age_gfn(kvm, range); @@ -1748,17 +1846,10 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \ if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else -static inline bool is_ept_sp(struct kvm_mmu_page *sp) -{ - return sp->role.cr0_wp && sp->role.smap_andnot_wp; -} - -/* @sp->gfn should be write-protected at the call site */ -static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct list_head *invalid_list) +static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + struct list_head *invalid_list) { - if ((!is_ept_sp(sp) && sp->role.gpte_is_8_bytes != !!is_pae(vcpu)) || - vcpu->arch.mmu->sync_page(vcpu, sp) == 0) { + if (vcpu->arch.mmu->sync_page(vcpu, sp) == 0) { kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return false; } @@ -1804,31 +1895,6 @@ static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); } -static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct list_head *invalid_list) -{ - kvm_unlink_unsync_page(vcpu->kvm, sp); - return __kvm_sync_page(vcpu, sp, invalid_list); -} - -/* @gfn should be write-protected at the call site */ -static bool kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, - struct list_head *invalid_list) -{ - struct kvm_mmu_page *s; - bool ret = false; - - for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) { - if (!s->unsync) - continue; - - WARN_ON(s->role.level != PG_LEVEL_4K); - ret |= kvm_sync_page(vcpu, s, invalid_list); - } - - return ret; -} - struct mmu_page_path { struct kvm_mmu_page *parent[PT64_ROOT_MAX_LEVEL]; unsigned int idx[PT64_ROOT_MAX_LEVEL]; @@ -1923,6 +1989,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, } for_each_sp(pages, sp, parents, i) { + kvm_unlink_unsync_page(vcpu->kvm, sp); flush |= kvm_sync_page(vcpu, sp, &invalid_list); mmu_pages_clear_parents(&parents); } @@ -1958,8 +2025,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, struct hlist_head *sp_list; unsigned quadrant; struct kvm_mmu_page *sp; - bool need_sync = false; - bool flush = false; int collisions = 0; LIST_HEAD(invalid_list); @@ -1982,20 +2047,39 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, continue; } - if (!need_sync && sp->unsync) - need_sync = true; - - if (sp->role.word != role.word) + if (sp->role.word != role.word) { + /* + * If the guest is creating an upper-level page, zap + * unsync pages for the same gfn. While it's possible + * the guest is using recursive page tables, in all + * likelihood the guest has stopped using the unsync + * page and is installing a completely unrelated page. + * Unsync pages must not be left as is, because the new + * upper-level page will be write-protected. + */ + if (level > PG_LEVEL_4K && sp->unsync) + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, + &invalid_list); continue; + } if (direct_mmu) goto trace_get_page; if (sp->unsync) { - /* The page is good, but __kvm_sync_page might still end - * up zapping it. If so, break in order to rebuild it. + /* + * The page is good, but is stale. kvm_sync_page does + * get the latest guest state, but (unlike mmu_unsync_children) + * it doesn't write-protect the page or mark it synchronized! + * This way the validity of the mapping is ensured, but the + * overhead of write protection is not incurred until the + * guest invalidates the TLB mapping. This allows multiple + * SPs for a single gfn to be unsync. + * + * If the sync fails, the page is zapped. If so, break + * in order to rebuild it. */ - if (!__kvm_sync_page(vcpu, sp, &invalid_list)) + if (!kvm_sync_page(vcpu, sp, &invalid_list)) break; WARN_ON(!list_empty(&invalid_list)); @@ -2020,22 +2104,14 @@ trace_get_page: sp->role = role; hlist_add_head(&sp->hash_link, sp_list); if (!direct) { - /* - * we should do write protection before syncing pages - * otherwise the content of the synced shadow page may - * be inconsistent with guest page table. - */ account_shadowed(vcpu->kvm, sp); if (level == PG_LEVEL_4K && rmap_write_protect(vcpu, gfn)) kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn, 1); - - if (level > PG_LEVEL_4K && need_sync) - flush |= kvm_sync_pages(vcpu, gfn, &invalid_list); } trace_kvm_mmu_get_page(sp, true); - - kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); out: + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + if (collisions > vcpu->kvm->stat.max_mmu_page_hash_collisions) vcpu->kvm->stat.max_mmu_page_hash_collisions = collisions; return sp; @@ -2448,17 +2524,33 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) kvm_mmu_mark_parents_unsync(sp); } -bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, - bool can_unsync) +/* + * Attempt to unsync any shadow pages that can be reached by the specified gfn, + * KVM is creating a writable mapping for said gfn. Returns 0 if all pages + * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must + * be write-protected. + */ +int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) { struct kvm_mmu_page *sp; + /* + * Force write-protection if the page is being tracked. Note, the page + * track machinery is used to write-protect upper-level shadow pages, + * i.e. this guards the role.level == 4K assertion below! + */ if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE)) - return true; + return -EPERM; + /* + * The page is not write-tracked, mark existing shadow pages unsync + * unless KVM is synchronizing an unsync SP (can_unsync = false). In + * that case, KVM must complete emulation of the guest TLB flush before + * allowing shadow pages to become unsync (writable by the guest). + */ for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { if (!can_unsync) - return true; + return -EPERM; if (sp->unsync) continue; @@ -2489,8 +2581,8 @@ bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, * 2.2 Guest issues TLB flush. * That causes a VM Exit. * - * 2.3 kvm_mmu_sync_pages() reads sp->unsync. - * Since it is false, so it just returns. + * 2.3 Walking of unsync pages sees sp->unsync is + * false and skips the page. * * 2.4 Guest accesses GVA X. * Since the mapping in the SP was not updated, @@ -2506,7 +2598,7 @@ bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, */ smp_wmb(); - return false; + return 0; } static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, @@ -2827,9 +2919,6 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, gfn_t gfn = gpa >> PAGE_SHIFT; gfn_t base_gfn = gfn; - if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) - return RET_PF_RETRY; - level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn, huge_page_disallowed, &req_level); @@ -3180,6 +3269,33 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } EXPORT_SYMBOL_GPL(kvm_mmu_free_roots); +void kvm_mmu_free_guest_mode_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) +{ + unsigned long roots_to_free = 0; + hpa_t root_hpa; + int i; + + /* + * This should not be called while L2 is active, L2 can't invalidate + * _only_ its own roots, e.g. INVVPID unconditionally exits. + */ + WARN_ON_ONCE(mmu->mmu_role.base.guest_mode); + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + root_hpa = mmu->prev_roots[i].hpa; + if (!VALID_PAGE(root_hpa)) + continue; + + if (!to_shadow_page(root_hpa) || + to_shadow_page(root_hpa)->role.guest_mode) + roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); + } + + kvm_mmu_free_roots(vcpu, mmu, roots_to_free); +} +EXPORT_SYMBOL_GPL(kvm_mmu_free_guest_mode_roots); + + static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn) { int ret = 0; @@ -3280,6 +3396,10 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) } } + r = alloc_all_memslots_rmaps(vcpu->kvm); + if (r) + return r; + write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); if (r < 0) @@ -3310,12 +3430,12 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) if (mmu->shadow_root_level == PT64_ROOT_4LEVEL) { pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK; - if (WARN_ON_ONCE(!mmu->lm_root)) { + if (WARN_ON_ONCE(!mmu->pml4_root)) { r = -EIO; goto out_unlock; } - mmu->lm_root[0] = __pa(mmu->pae_root) | pm_mask; + mmu->pml4_root[0] = __pa(mmu->pae_root) | pm_mask; } for (i = 0; i < 4; ++i) { @@ -3335,7 +3455,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) } if (mmu->shadow_root_level == PT64_ROOT_4LEVEL) - mmu->root_hpa = __pa(mmu->lm_root); + mmu->root_hpa = __pa(mmu->pml4_root); else mmu->root_hpa = __pa(mmu->pae_root); @@ -3350,7 +3470,7 @@ out_unlock: static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; - u64 *lm_root, *pae_root; + u64 *pml4_root, *pae_root; /* * When shadowing 32-bit or PAE NPT with 64-bit NPT, the PML4 and PDP @@ -3369,14 +3489,14 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) if (WARN_ON_ONCE(mmu->shadow_root_level != PT64_ROOT_4LEVEL)) return -EIO; - if (mmu->pae_root && mmu->lm_root) + if (mmu->pae_root && mmu->pml4_root) return 0; /* * The special roots should always be allocated in concert. Yell and * bail if KVM ends up in a state where only one of the roots is valid. */ - if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->lm_root)) + if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->pml4_root)) return -EIO; /* @@ -3387,14 +3507,14 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) if (!pae_root) return -ENOMEM; - lm_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); - if (!lm_root) { + pml4_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (!pml4_root) { free_page((unsigned long)pae_root); return -ENOMEM; } mmu->pae_root = pae_root; - mmu->lm_root = lm_root; + mmu->pml4_root = pml4_root; return 0; } @@ -3423,8 +3543,8 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) * flush strictly after those changes are made. We only need to * ensure that the other CPU sets these flags before any actual * changes to the page tables are made. The comments in - * mmu_need_write_protect() describe what could go wrong if this - * requirement isn't satisfied. + * mmu_try_to_unsync_pages() describe what could go wrong if + * this requirement isn't satisfied. */ if (!smp_load_acquire(&sp->unsync) && !smp_load_acquire(&sp->unsync_children)) @@ -3474,19 +3594,6 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr, return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception); } -static bool -__is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level) -{ - int bit7 = (pte >> 7) & 1; - - return pte & rsvd_check->rsvd_bits_mask[bit7][level-1]; -} - -static bool __is_bad_mt_xwr(struct rsvd_bits_validate *rsvd_check, u64 pte) -{ - return rsvd_check->bad_mt_xwr & BIT_ULL(pte & 0x3f); -} - static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) { /* @@ -3540,12 +3647,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) int root, leaf, level; bool reserved = false; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) { - *sptep = 0ull; - return reserved; - } - - if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + if (is_tdp_mmu(vcpu->arch.mmu)) leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); else leaf = get_walk(vcpu, addr, sptes, &root); @@ -3569,13 +3671,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) rsvd_check = &vcpu->arch.mmu->shadow_zero_check; for (level = root; level >= leaf; level--) - /* - * Use a bitwise-OR instead of a logical-OR to aggregate the - * reserved bit and EPT's invalid memtype/XWR checks to avoid - * adding a Jcc in the loop. - */ - reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) | - __is_rsvd_bits_set(rsvd_check, sptes[level], level); + reserved |= is_rsvd_spte(rsvd_check, sptes[level], level); if (reserved) { pr_err("%s: reserved bits set on MMU-present spte, addr 0x%llx, hierarchy:\n", @@ -3583,7 +3679,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) for (level = root; level >= leaf; level--) pr_err("------ spte = 0x%llx level = %d, rsvd bits = 0x%llx", sptes[level], level, - rsvd_check->rsvd_bits_mask[(sptes[level] >> 7) & 1][level-1]); + get_rsvd_bits(rsvd_check, sptes[level], level)); } return reserved; @@ -3717,6 +3813,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, bool prefault, int max_level, bool is_tdp) { + bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu); bool write = error_code & PFERR_WRITE_MASK; bool map_writable; @@ -3729,7 +3826,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, if (page_fault_handle_page_track(vcpu, error_code, gfn)) return RET_PF_EMULATE; - if (!is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) { + if (!is_tdp_mmu_fault) { r = fast_page_fault(vcpu, gpa, error_code); if (r != RET_PF_INVALID) return r; @@ -3751,7 +3848,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, r = RET_PF_RETRY; - if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + if (is_tdp_mmu_fault) read_lock(&vcpu->kvm->mmu_lock); else write_lock(&vcpu->kvm->mmu_lock); @@ -3762,7 +3859,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, if (r) goto out_unlock; - if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + if (is_tdp_mmu_fault) r = kvm_tdp_mmu_map(vcpu, gpa, error_code, map_writable, max_level, pfn, prefault); else @@ -3770,7 +3867,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, prefault, is_tdp); out_unlock: - if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + if (is_tdp_mmu_fault) read_unlock(&vcpu->kvm->mmu_lock); else write_unlock(&vcpu->kvm->mmu_lock); @@ -3840,17 +3937,13 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, max_level, true); } -static void nonpaging_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void nonpaging_init_context(struct kvm_mmu *context) { context->page_fault = nonpaging_page_fault; context->gva_to_gpa = nonpaging_gva_to_gpa; context->sync_page = nonpaging_sync_page; context->invlpg = NULL; - context->root_level = 0; - context->shadow_root_level = PT32E_ROOT_LEVEL; context->direct_map = true; - context->nx = false; } static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd, @@ -3913,8 +4006,7 @@ static bool fast_pgd_switch(struct kvm_vcpu *vcpu, gpa_t new_pgd, } static void __kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, - union kvm_mmu_page_role new_role, - bool skip_tlb_flush, bool skip_mmu_sync) + union kvm_mmu_page_role new_role) { if (!fast_pgd_switch(vcpu, new_pgd, new_role)) { kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, KVM_MMU_ROOT_CURRENT); @@ -3929,10 +4021,10 @@ static void __kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, */ kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); - if (!skip_mmu_sync || force_flush_and_sync_on_reuse) + if (force_flush_and_sync_on_reuse) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - if (!skip_tlb_flush || force_flush_and_sync_on_reuse) kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + } /* * The last MMIO access's GVA and GPA are cached in the VCPU. When @@ -3951,11 +4043,9 @@ static void __kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, to_shadow_page(vcpu->arch.mmu->root_hpa)); } -void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush, - bool skip_mmu_sync) +void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) { - __kvm_mmu_new_pgd(vcpu, new_pgd, kvm_mmu_calc_root_page_role(vcpu), - skip_tlb_flush, skip_mmu_sync); + __kvm_mmu_new_pgd(vcpu, new_pgd, kvm_mmu_calc_root_page_role(vcpu)); } EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); @@ -3981,26 +4071,6 @@ static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, return false; } -static inline bool is_last_gpte(struct kvm_mmu *mmu, - unsigned level, unsigned gpte) -{ - /* - * The RHS has bit 7 set iff level < mmu->last_nonleaf_level. - * If it is clear, there are no large pages at this level, so clear - * PT_PAGE_SIZE_MASK in gpte if that is the case. - */ - gpte &= level - mmu->last_nonleaf_level; - - /* - * PG_LEVEL_4K always terminates. The RHS has bit 7 set - * iff level <= PG_LEVEL_4K, which for our purpose means - * level == PG_LEVEL_4K; set PT_PAGE_SIZE_MASK in gpte then. - */ - gpte |= level - PG_LEVEL_4K - 1; - - return gpte & PT_PAGE_SIZE_MASK; -} - #define PTTYPE_EPT 18 /* arbitrary */ #define PTTYPE PTTYPE_EPT #include "paging_tmpl.h" @@ -4015,8 +4085,7 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, #undef PTTYPE static void -__reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, - struct rsvd_bits_validate *rsvd_check, +__reset_rsvds_bits_mask(struct rsvd_bits_validate *rsvd_check, u64 pa_bits_rsvd, int level, bool nx, bool gbpages, bool pse, bool amd) { @@ -4105,14 +4174,29 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, } } +static bool guest_can_use_gbpages(struct kvm_vcpu *vcpu) +{ + /* + * If TDP is enabled, let the guest use GBPAGES if they're supported in + * hardware. The hardware page walker doesn't let KVM disable GBPAGES, + * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA + * walk for performance and complexity reasons. Not to mention KVM + * _can't_ solve the problem because GVA->GPA walks aren't visible to + * KVM once a TDP translation is installed. Mimic hardware behavior so + * that KVM's is at least consistent, i.e. doesn't randomly inject #PF. + */ + return tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) : + guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES); +} + static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { - __reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check, + __reset_rsvds_bits_mask(&context->guest_rsvd_check, vcpu->arch.reserved_gpa_bits, - context->root_level, context->nx, - guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), - is_pse(vcpu), + context->root_level, is_efer_nx(context), + guest_can_use_gbpages(vcpu), + is_cr4_pse(context), guest_cpuid_is_amd_or_hygon(vcpu)); } @@ -4165,24 +4249,32 @@ static inline u64 reserved_hpa_bits(void) * table in guest or amd nested guest, its mmu features completely * follow the features in guest. */ -void -reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) +static void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - bool uses_nx = context->nx || - context->mmu_role.base.smep_andnot_wp; + /* + * KVM uses NX when TDP is disabled to handle a variety of scenarios, + * notably for huge SPTEs if iTLB multi-hit mitigation is enabled and + * to generate correct permissions for CR0.WP=0/CR4.SMEP=1/EFER.NX=0. + * The iTLB multi-hit workaround can be toggled at any time, so assume + * NX can be used by any non-nested shadow MMU to avoid having to reset + * MMU contexts. Note, KVM forces EFER.NX=1 when TDP is disabled. + */ + bool uses_nx = is_efer_nx(context) || !tdp_enabled; + + /* @amd adds a check on bit of SPTEs, which KVM shouldn't use anyways. */ + bool is_amd = true; + /* KVM doesn't use 2-level page tables for the shadow MMU. */ + bool is_pse = false; struct rsvd_bits_validate *shadow_zero_check; int i; - /* - * Passing "true" to the last argument is okay; it adds a check - * on bit 8 of the SPTEs which KVM doesn't use anyway. - */ + WARN_ON_ONCE(context->shadow_root_level < PT32E_ROOT_LEVEL); + shadow_zero_check = &context->shadow_zero_check; - __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - reserved_hpa_bits(), + __reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(), context->shadow_root_level, uses_nx, - guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), - is_pse(vcpu), true); + guest_can_use_gbpages(vcpu), is_pse, is_amd); if (!shadow_me_mask) return; @@ -4193,7 +4285,6 @@ reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) } } -EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask); static inline bool boot_cpu_is_amd(void) { @@ -4215,11 +4306,10 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, shadow_zero_check = &context->shadow_zero_check; if (boot_cpu_is_amd()) - __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - reserved_hpa_bits(), + __reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(), context->shadow_root_level, false, boot_cpu_has(X86_FEATURE_GBPAGES), - true, true); + false, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, reserved_hpa_bits(), false); @@ -4255,8 +4345,7 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, (7 & (access) ? 128 : 0)) -static void update_permission_bitmask(struct kvm_vcpu *vcpu, - struct kvm_mmu *mmu, bool ept) +static void update_permission_bitmask(struct kvm_mmu *mmu, bool ept) { unsigned byte; @@ -4264,9 +4353,10 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu, const u8 w = BYTE_MASK(ACC_WRITE_MASK); const u8 u = BYTE_MASK(ACC_USER_MASK); - bool cr4_smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP) != 0; - bool cr4_smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP) != 0; - bool cr0_wp = is_write_protection(vcpu); + bool cr4_smep = is_cr4_smep(mmu); + bool cr4_smap = is_cr4_smap(mmu); + bool cr0_wp = is_cr0_wp(mmu); + bool efer_nx = is_efer_nx(mmu); for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) { unsigned pfec = byte << 1; @@ -4292,7 +4382,7 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu, u8 kf = (pfec & PFERR_USER_MASK) ? 0 : u; /* Not really needed: !nx will cause pte.nx to fault */ - if (!mmu->nx) + if (!efer_nx) ff = 0; /* Allow supervisor writes if !cr0.wp */ @@ -4351,24 +4441,17 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu, * away both AD and WD. For all reads or if the last condition holds, WD * only will be masked away. */ -static void update_pkru_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - bool ept) +static void update_pkru_bitmask(struct kvm_mmu *mmu) { unsigned bit; bool wp; - if (ept) { - mmu->pkru_mask = 0; - return; - } - - /* PKEY is enabled only if CR4.PKE and EFER.LMA are both set. */ - if (!kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || !is_long_mode(vcpu)) { + if (!is_cr4_pke(mmu)) { mmu->pkru_mask = 0; return; } - wp = is_write_protection(vcpu); + wp = is_cr0_wp(mmu); for (bit = 0; bit < ARRAY_SIZE(mmu->permissions); ++bit) { unsigned pfec, pkey_bits; @@ -4402,81 +4485,51 @@ static void update_pkru_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } } -static void update_last_nonleaf_level(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) +static void reset_guest_paging_metadata(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) { - unsigned root_level = mmu->root_level; + if (!is_cr0_pg(mmu)) + return; - mmu->last_nonleaf_level = root_level; - if (root_level == PT32_ROOT_LEVEL && is_pse(vcpu)) - mmu->last_nonleaf_level++; + reset_rsvds_bits_mask(vcpu, mmu); + update_permission_bitmask(mmu, false); + update_pkru_bitmask(mmu); } -static void paging64_init_context_common(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, - int level) +static void paging64_init_context(struct kvm_mmu *context) { - context->nx = is_nx(vcpu); - context->root_level = level; - - reset_rsvds_bits_mask(vcpu, context); - update_permission_bitmask(vcpu, context, false); - update_pkru_bitmask(vcpu, context, false); - update_last_nonleaf_level(vcpu, context); - - MMU_WARN_ON(!is_pae(vcpu)); context->page_fault = paging64_page_fault; context->gva_to_gpa = paging64_gva_to_gpa; context->sync_page = paging64_sync_page; context->invlpg = paging64_invlpg; - context->shadow_root_level = level; context->direct_map = false; } -static void paging64_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void paging32_init_context(struct kvm_mmu *context) { - int root_level = is_la57_mode(vcpu) ? - PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; - - paging64_init_context_common(vcpu, context, root_level); -} - -static void paging32_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) -{ - context->nx = false; - context->root_level = PT32_ROOT_LEVEL; - - reset_rsvds_bits_mask(vcpu, context); - update_permission_bitmask(vcpu, context, false); - update_pkru_bitmask(vcpu, context, false); - update_last_nonleaf_level(vcpu, context); - context->page_fault = paging32_page_fault; context->gva_to_gpa = paging32_gva_to_gpa; context->sync_page = paging32_sync_page; context->invlpg = paging32_invlpg; - context->shadow_root_level = PT32E_ROOT_LEVEL; context->direct_map = false; } -static void paging32E_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) -{ - paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL); -} - -static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu) +static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu, + struct kvm_mmu_role_regs *regs) { union kvm_mmu_extended_role ext = {0}; - ext.cr0_pg = !!is_paging(vcpu); - ext.cr4_pae = !!is_pae(vcpu); - ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); - ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); - ext.cr4_pse = !!is_pse(vcpu); - ext.cr4_pke = !!kvm_read_cr4_bits(vcpu, X86_CR4_PKE); - ext.maxphyaddr = cpuid_maxphyaddr(vcpu); + if (____is_cr0_pg(regs)) { + ext.cr0_pg = 1; + ext.cr4_pae = ____is_cr4_pae(regs); + ext.cr4_smep = ____is_cr4_smep(regs); + ext.cr4_smap = ____is_cr4_smap(regs); + ext.cr4_pse = ____is_cr4_pse(regs); + + /* PKEY and LA57 are active iff long mode is active. */ + ext.cr4_pke = ____is_efer_lma(regs) && ____is_cr4_pke(regs); + ext.cr4_la57 = ____is_efer_lma(regs) && ____is_cr4_la57(regs); + } ext.valid = 1; @@ -4484,20 +4537,23 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu) } static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu, + struct kvm_mmu_role_regs *regs, bool base_only) { union kvm_mmu_role role = {0}; role.base.access = ACC_ALL; - role.base.nxe = !!is_nx(vcpu); - role.base.cr0_wp = is_write_protection(vcpu); + if (____is_cr0_pg(regs)) { + role.base.efer_nx = ____is_efer_nx(regs); + role.base.cr0_wp = ____is_cr0_wp(regs); + } role.base.smm = is_smm(vcpu); role.base.guest_mode = is_guest_mode(vcpu); if (base_only) return role; - role.ext = kvm_calc_mmu_role_ext(vcpu); + role.ext = kvm_calc_mmu_role_ext(vcpu, regs); return role; } @@ -4512,9 +4568,10 @@ static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) } static union kvm_mmu_role -kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) +kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, + struct kvm_mmu_role_regs *regs, bool base_only) { - union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only); + union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, regs, base_only); role.base.ad_disabled = (shadow_accessed_mask == 0); role.base.level = kvm_mmu_get_tdp_level(vcpu); @@ -4527,8 +4584,9 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) { struct kvm_mmu *context = &vcpu->arch.root_mmu; + struct kvm_mmu_role_regs regs = vcpu_to_role_regs(vcpu); union kvm_mmu_role new_role = - kvm_calc_tdp_mmu_root_page_role(vcpu, false); + kvm_calc_tdp_mmu_root_page_role(vcpu, ®s, false); if (new_role.as_u64 == context->mmu_role.as_u64) return; @@ -4542,60 +4600,44 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->get_guest_pgd = get_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; + context->root_level = role_regs_to_root_level(®s); - if (!is_paging(vcpu)) { - context->nx = false; + if (!is_cr0_pg(context)) context->gva_to_gpa = nonpaging_gva_to_gpa; - context->root_level = 0; - } else if (is_long_mode(vcpu)) { - context->nx = is_nx(vcpu); - context->root_level = is_la57_mode(vcpu) ? - PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; - reset_rsvds_bits_mask(vcpu, context); - context->gva_to_gpa = paging64_gva_to_gpa; - } else if (is_pae(vcpu)) { - context->nx = is_nx(vcpu); - context->root_level = PT32E_ROOT_LEVEL; - reset_rsvds_bits_mask(vcpu, context); + else if (is_cr4_pae(context)) context->gva_to_gpa = paging64_gva_to_gpa; - } else { - context->nx = false; - context->root_level = PT32_ROOT_LEVEL; - reset_rsvds_bits_mask(vcpu, context); + else context->gva_to_gpa = paging32_gva_to_gpa; - } - update_permission_bitmask(vcpu, context, false); - update_pkru_bitmask(vcpu, context, false); - update_last_nonleaf_level(vcpu, context); + reset_guest_paging_metadata(vcpu, context); reset_tdp_shadow_zero_bits_mask(vcpu, context); } static union kvm_mmu_role -kvm_calc_shadow_root_page_role_common(struct kvm_vcpu *vcpu, bool base_only) +kvm_calc_shadow_root_page_role_common(struct kvm_vcpu *vcpu, + struct kvm_mmu_role_regs *regs, bool base_only) { - union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only); + union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, regs, base_only); - role.base.smep_andnot_wp = role.ext.cr4_smep && - !is_write_protection(vcpu); - role.base.smap_andnot_wp = role.ext.cr4_smap && - !is_write_protection(vcpu); - role.base.gpte_is_8_bytes = !!is_pae(vcpu); + role.base.smep_andnot_wp = role.ext.cr4_smep && !____is_cr0_wp(regs); + role.base.smap_andnot_wp = role.ext.cr4_smap && !____is_cr0_wp(regs); + role.base.gpte_is_8_bytes = ____is_cr0_pg(regs) && ____is_cr4_pae(regs); return role; } static union kvm_mmu_role -kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) +kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, + struct kvm_mmu_role_regs *regs, bool base_only) { union kvm_mmu_role role = - kvm_calc_shadow_root_page_role_common(vcpu, base_only); + kvm_calc_shadow_root_page_role_common(vcpu, regs, base_only); - role.base.direct = !is_paging(vcpu); + role.base.direct = !____is_cr0_pg(regs); - if (!is_long_mode(vcpu)) + if (!____is_efer_lma(regs)) role.base.level = PT32E_ROOT_LEVEL; - else if (is_la57_mode(vcpu)) + else if (____is_cr4_la57(regs)) role.base.level = PT64_ROOT_5LEVEL; else role.base.level = PT64_ROOT_4LEVEL; @@ -4604,37 +4646,44 @@ kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) } static void shadow_mmu_init_context(struct kvm_vcpu *vcpu, struct kvm_mmu *context, - u32 cr0, u32 cr4, u32 efer, + struct kvm_mmu_role_regs *regs, union kvm_mmu_role new_role) { - if (!(cr0 & X86_CR0_PG)) - nonpaging_init_context(vcpu, context); - else if (efer & EFER_LMA) - paging64_init_context(vcpu, context); - else if (cr4 & X86_CR4_PAE) - paging32E_init_context(vcpu, context); - else - paging32_init_context(vcpu, context); + if (new_role.as_u64 == context->mmu_role.as_u64) + return; context->mmu_role.as_u64 = new_role.as_u64; + + if (!is_cr0_pg(context)) + nonpaging_init_context(context); + else if (is_cr4_pae(context)) + paging64_init_context(context); + else + paging32_init_context(context); + context->root_level = role_regs_to_root_level(regs); + + reset_guest_paging_metadata(vcpu, context); + context->shadow_root_level = new_role.base.level; + reset_shadow_zero_bits_mask(vcpu, context); } -static void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer) +static void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, + struct kvm_mmu_role_regs *regs) { struct kvm_mmu *context = &vcpu->arch.root_mmu; union kvm_mmu_role new_role = - kvm_calc_shadow_mmu_root_page_role(vcpu, false); + kvm_calc_shadow_mmu_root_page_role(vcpu, regs, false); - if (new_role.as_u64 != context->mmu_role.as_u64) - shadow_mmu_init_context(vcpu, context, cr0, cr4, efer, new_role); + shadow_mmu_init_context(vcpu, context, regs, new_role); } static union kvm_mmu_role -kvm_calc_shadow_npt_root_page_role(struct kvm_vcpu *vcpu) +kvm_calc_shadow_npt_root_page_role(struct kvm_vcpu *vcpu, + struct kvm_mmu_role_regs *regs) { union kvm_mmu_role role = - kvm_calc_shadow_root_page_role_common(vcpu, false); + kvm_calc_shadow_root_page_role_common(vcpu, regs, false); role.base.direct = false; role.base.level = kvm_mmu_get_tdp_level(vcpu); @@ -4642,23 +4691,22 @@ kvm_calc_shadow_npt_root_page_role(struct kvm_vcpu *vcpu) return role; } -void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer, - gpa_t nested_cr3) +void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, + unsigned long cr4, u64 efer, gpa_t nested_cr3) { struct kvm_mmu *context = &vcpu->arch.guest_mmu; - union kvm_mmu_role new_role = kvm_calc_shadow_npt_root_page_role(vcpu); + struct kvm_mmu_role_regs regs = { + .cr0 = cr0, + .cr4 = cr4, + .efer = efer, + }; + union kvm_mmu_role new_role; - __kvm_mmu_new_pgd(vcpu, nested_cr3, new_role.base, false, false); + new_role = kvm_calc_shadow_npt_root_page_role(vcpu, ®s); - if (new_role.as_u64 != context->mmu_role.as_u64) { - shadow_mmu_init_context(vcpu, context, cr0, cr4, efer, new_role); + __kvm_mmu_new_pgd(vcpu, nested_cr3, new_role.base); - /* - * Override the level set by the common init helper, nested TDP - * always uses the host's TDP configuration. - */ - context->shadow_root_level = new_role.base.level; - } + shadow_mmu_init_context(vcpu, context, ®s, new_role); } EXPORT_SYMBOL_GPL(kvm_init_shadow_npt_mmu); @@ -4678,15 +4726,10 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, role.base.guest_mode = true; role.base.access = ACC_ALL; - /* - * WP=1 and NOT_WP=1 is an impossible combination, use WP and the - * SMAP variation to denote shadow EPT entries. - */ - role.base.cr0_wp = true; - role.base.smap_andnot_wp = true; - - role.ext = kvm_calc_mmu_role_ext(vcpu); + /* EPT, and thus nested EPT, does not consume CR0, CR4, nor EFER. */ + role.ext.word = 0; role.ext.execonly = execonly; + role.ext.valid = 1; return role; } @@ -4700,14 +4743,15 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty, execonly, level); - __kvm_mmu_new_pgd(vcpu, new_eptp, new_role.base, true, true); + __kvm_mmu_new_pgd(vcpu, new_eptp, new_role.base); if (new_role.as_u64 == context->mmu_role.as_u64) return; + context->mmu_role.as_u64 = new_role.as_u64; + context->shadow_root_level = level; - context->nx = true; context->ept_ad = accessed_dirty; context->page_fault = ept_page_fault; context->gva_to_gpa = ept_gva_to_gpa; @@ -4715,11 +4759,9 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->invlpg = ept_invlpg; context->root_level = level; context->direct_map = false; - context->mmu_role.as_u64 = new_role.as_u64; - update_permission_bitmask(vcpu, context, true); - update_pkru_bitmask(vcpu, context, true); - update_last_nonleaf_level(vcpu, context); + update_permission_bitmask(context, true); + update_pkru_bitmask(context); reset_rsvds_bits_mask_ept(vcpu, context, execonly); reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } @@ -4728,20 +4770,36 @@ EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); static void init_kvm_softmmu(struct kvm_vcpu *vcpu) { struct kvm_mmu *context = &vcpu->arch.root_mmu; + struct kvm_mmu_role_regs regs = vcpu_to_role_regs(vcpu); - kvm_init_shadow_mmu(vcpu, - kvm_read_cr0_bits(vcpu, X86_CR0_PG), - kvm_read_cr4_bits(vcpu, X86_CR4_PAE), - vcpu->arch.efer); + kvm_init_shadow_mmu(vcpu, ®s); context->get_guest_pgd = get_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; } +static union kvm_mmu_role +kvm_calc_nested_mmu_role(struct kvm_vcpu *vcpu, struct kvm_mmu_role_regs *regs) +{ + union kvm_mmu_role role; + + role = kvm_calc_shadow_root_page_role_common(vcpu, regs, false); + + /* + * Nested MMUs are used only for walking L2's gva->gpa, they never have + * shadow pages of their own and so "direct" has no meaning. Set it + * to "true" to try to detect bogus usage of the nested MMU. + */ + role.base.direct = true; + role.base.level = role_regs_to_root_level(regs); + return role; +} + static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) { - union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false); + struct kvm_mmu_role_regs regs = vcpu_to_role_regs(vcpu); + union kvm_mmu_role new_role = kvm_calc_nested_mmu_role(vcpu, ®s); struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; if (new_role.as_u64 == g_context->mmu_role.as_u64) @@ -4751,6 +4809,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) g_context->get_guest_pgd = get_cr3; g_context->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault; + g_context->root_level = new_role.base.level; /* * L2 page tables are never shadowed, so there is no need to sync @@ -4766,44 +4825,20 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) * nested page tables as the second level of translation. Basically * the gva_to_gpa functions between mmu and nested_mmu are swapped. */ - if (!is_paging(vcpu)) { - g_context->nx = false; - g_context->root_level = 0; + if (!is_paging(vcpu)) g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested; - } else if (is_long_mode(vcpu)) { - g_context->nx = is_nx(vcpu); - g_context->root_level = is_la57_mode(vcpu) ? - PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; - reset_rsvds_bits_mask(vcpu, g_context); + else if (is_long_mode(vcpu)) g_context->gva_to_gpa = paging64_gva_to_gpa_nested; - } else if (is_pae(vcpu)) { - g_context->nx = is_nx(vcpu); - g_context->root_level = PT32E_ROOT_LEVEL; - reset_rsvds_bits_mask(vcpu, g_context); + else if (is_pae(vcpu)) g_context->gva_to_gpa = paging64_gva_to_gpa_nested; - } else { - g_context->nx = false; - g_context->root_level = PT32_ROOT_LEVEL; - reset_rsvds_bits_mask(vcpu, g_context); + else g_context->gva_to_gpa = paging32_gva_to_gpa_nested; - } - update_permission_bitmask(vcpu, g_context, false); - update_pkru_bitmask(vcpu, g_context, false); - update_last_nonleaf_level(vcpu, g_context); + reset_guest_paging_metadata(vcpu, g_context); } -void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots) +void kvm_init_mmu(struct kvm_vcpu *vcpu) { - if (reset_roots) { - uint i; - - vcpu->arch.mmu->root_hpa = INVALID_PAGE; - - for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) - vcpu->arch.mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; - } - if (mmu_is_nested(vcpu)) init_kvm_nested_mmu(vcpu); else if (tdp_enabled) @@ -4816,20 +4851,53 @@ EXPORT_SYMBOL_GPL(kvm_init_mmu); static union kvm_mmu_page_role kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu) { + struct kvm_mmu_role_regs regs = vcpu_to_role_regs(vcpu); union kvm_mmu_role role; if (tdp_enabled) - role = kvm_calc_tdp_mmu_root_page_role(vcpu, true); + role = kvm_calc_tdp_mmu_root_page_role(vcpu, ®s, true); else - role = kvm_calc_shadow_mmu_root_page_role(vcpu, true); + role = kvm_calc_shadow_mmu_root_page_role(vcpu, ®s, true); return role.base; } +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. + */ + vcpu->arch.root_mmu.mmu_role.ext.valid = 0; + vcpu->arch.guest_mmu.mmu_role.ext.valid = 0; + vcpu->arch.nested_mmu.mmu_role.ext.valid = 0; + kvm_mmu_reset_context(vcpu); + + /* + * 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. 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) { + 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) { kvm_mmu_unload(vcpu); - kvm_init_mmu(vcpu, true); + kvm_init_mmu(vcpu); } EXPORT_SYMBOL_GPL(kvm_mmu_reset_context); @@ -5261,7 +5329,7 @@ static void free_mmu_pages(struct kvm_mmu *mmu) if (!tdp_enabled && mmu->pae_root) set_memory_encrypted((unsigned long)mmu->pae_root, 1); free_page((unsigned long)mmu->pae_root); - free_page((unsigned long)mmu->lm_root); + free_page((unsigned long)mmu->pml4_root); } static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) @@ -5467,7 +5535,13 @@ void kvm_mmu_init_vm(struct kvm *kvm) { struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; - kvm_mmu_init_tdp_mmu(kvm); + if (!kvm_mmu_init_tdp_mmu(kvm)) + /* + * No smp_load/store wrappers needed here as we are in + * VM init and there cannot be any memslots / other threads + * accessing this struct kvm yet. + */ + kvm->arch.memslots_have_rmaps = true; node->track_write = kvm_mmu_pte_write; node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; @@ -5490,29 +5564,29 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) int i; bool flush = false; - write_lock(&kvm->mmu_lock); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, slots) { - gfn_t start, end; - - start = max(gfn_start, memslot->base_gfn); - end = min(gfn_end, memslot->base_gfn + memslot->npages); - if (start >= end) - continue; + if (kvm_memslots_have_rmaps(kvm)) { + write_lock(&kvm->mmu_lock); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(memslot, slots) { + gfn_t start, end; + + start = max(gfn_start, memslot->base_gfn); + end = min(gfn_end, memslot->base_gfn + memslot->npages); + if (start >= end) + continue; - flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, - PG_LEVEL_4K, - KVM_MAX_HUGEPAGE_LEVEL, - start, end - 1, true, flush); + flush = slot_handle_level_range(kvm, memslot, + kvm_zap_rmapp, PG_LEVEL_4K, + KVM_MAX_HUGEPAGE_LEVEL, start, + end - 1, true, flush); + } } + if (flush) + kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end); + write_unlock(&kvm->mmu_lock); } - if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end); - - write_unlock(&kvm->mmu_lock); - if (is_tdp_mmu_enabled(kvm)) { flush = false; @@ -5539,12 +5613,15 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot, int start_level) { - bool flush; + bool flush = false; - write_lock(&kvm->mmu_lock); - flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, - start_level, KVM_MAX_HUGEPAGE_LEVEL, false); - write_unlock(&kvm->mmu_lock); + if (kvm_memslots_have_rmaps(kvm)) { + write_lock(&kvm->mmu_lock); + flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, + start_level, KVM_MAX_HUGEPAGE_LEVEL, + false); + write_unlock(&kvm->mmu_lock); + } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); @@ -5612,18 +5689,17 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, { /* FIXME: const-ify all uses of struct kvm_memory_slot. */ struct kvm_memory_slot *slot = (struct kvm_memory_slot *)memslot; - bool flush; - - write_lock(&kvm->mmu_lock); - flush = slot_handle_leaf(kvm, slot, kvm_mmu_zap_collapsible_spte, true); + bool flush = false; - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, slot); - write_unlock(&kvm->mmu_lock); + if (kvm_memslots_have_rmaps(kvm)) { + write_lock(&kvm->mmu_lock); + flush = slot_handle_leaf(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)) { - flush = false; - read_lock(&kvm->mmu_lock); flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush); if (flush) @@ -5650,11 +5726,14 @@ void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { - bool flush; + bool flush = false; - write_lock(&kvm->mmu_lock); - flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false); - write_unlock(&kvm->mmu_lock); + if (kvm_memslots_have_rmaps(kvm)) { + write_lock(&kvm->mmu_lock); + flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, + false); + write_unlock(&kvm->mmu_lock); + } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); @@ -5957,6 +6036,7 @@ static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel static void kvm_recover_nx_lpages(struct kvm *kvm) { + unsigned long nx_lpage_splits = kvm->stat.nx_lpage_splits; int rcu_idx; struct kvm_mmu_page *sp; unsigned int ratio; @@ -5968,7 +6048,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) write_lock(&kvm->mmu_lock); ratio = READ_ONCE(nx_huge_pages_recovery_ratio); - to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; + to_zap = ratio ? DIV_ROUND_UP(nx_lpage_splits, ratio) : 0; for ( ; to_zap; --to_zap) { if (list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) break; diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index d64ccb417c60..35567293c1fd 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -116,14 +116,19 @@ static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) kvm_x86_ops.cpu_dirty_log_size; } -bool is_nx_huge_page_enabled(void); -bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, - bool can_unsync); +extern int nx_huge_pages; +static inline bool is_nx_huge_page_enabled(void) +{ + return READ_ONCE(nx_huge_pages); +} + +int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync); void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, - struct kvm_memory_slot *slot, u64 gfn); + struct kvm_memory_slot *slot, u64 gfn, + int min_level); void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, u64 start_gfn, u64 pages); @@ -158,8 +163,6 @@ int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, void disallowed_hugepage_adjust(u64 spte, gfn_t gfn, int cur_level, kvm_pfn_t *pfnp, int *goal_levelp); -bool is_nx_huge_page_enabled(void); - void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp); diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index e798489b56b5..efbad33a0645 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -40,7 +40,7 @@ role.direct ? " direct" : "", \ access_str[role.access], \ role.invalid ? " invalid" : "", \ - role.nxe ? "" : "!", \ + role.efer_nx ? "" : "!", \ role.ad_disabled ? "!" : "", \ __entry->root_count, \ __entry->unsync ? "unsync" : "sync", 0); \ diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 34bb0ec69bd8..91a9f7e0fd91 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -100,7 +100,7 @@ void kvm_slot_page_track_add_page(struct kvm *kvm, kvm_mmu_gfn_disallow_lpage(slot, gfn); if (mode == KVM_PAGE_TRACK_WRITE) - if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn)) + if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) kvm_flush_remote_tlbs(kvm); } EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 70b7e44e3035..490a028ddabe 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -90,8 +90,8 @@ struct guest_walker { gpa_t pte_gpa[PT_MAX_FULL_LEVELS]; pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS]; bool pte_writable[PT_MAX_FULL_LEVELS]; - unsigned pt_access; - unsigned pte_access; + unsigned int pt_access[PT_MAX_FULL_LEVELS]; + unsigned int pte_access; gfn_t gfn; struct x86_exception fault; }; @@ -305,6 +305,35 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte) return pkeys; } +static inline bool FNAME(is_last_gpte)(struct kvm_mmu *mmu, + unsigned int level, unsigned int gpte) +{ + /* + * For EPT and PAE paging (both variants), bit 7 is either reserved at + * all level or indicates a huge page (ignoring CR3/EPTP). In either + * case, bit 7 being set terminates the walk. + */ +#if PTTYPE == 32 + /* + * 32-bit paging requires special handling because bit 7 is ignored if + * CR4.PSE=0, not reserved. Clear bit 7 in the gpte if the level is + * greater than the last level for which bit 7 is the PAGE_SIZE bit. + * + * The RHS has bit 7 set iff level < (2 + PSE). If it is clear, bit 7 + * is not reserved and does not indicate a large page at this level, + * so clear PT_PAGE_SIZE_MASK in gpte if that is the case. + */ + gpte &= level - (PT32_ROOT_LEVEL + mmu->mmu_role.ext.cr4_pse); +#endif + /* + * PG_LEVEL_4K always terminates. The RHS has bit 7 set + * iff level <= PG_LEVEL_4K, which for our purpose means + * level == PG_LEVEL_4K; set PT_PAGE_SIZE_MASK in gpte then. + */ + gpte |= level - PG_LEVEL_4K - 1; + + return gpte & PT_PAGE_SIZE_MASK; +} /* * Fetch a guest pte for a guest virtual address, or for an L2's GPA. */ @@ -418,13 +447,15 @@ retry_walk: } walker->ptes[walker->level - 1] = pte; - } while (!is_last_gpte(mmu, walker->level, pte)); + + /* Convert to ACC_*_MASK flags for struct guest_walker. */ + walker->pt_access[walker->level - 1] = FNAME(gpte_access)(pt_access ^ walk_nx_mask); + } while (!FNAME(is_last_gpte)(mmu, walker->level, pte)); pte_pkey = FNAME(gpte_pkeys)(vcpu, pte); accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0; /* Convert to ACC_*_MASK flags for struct guest_walker. */ - walker->pt_access = FNAME(gpte_access)(pt_access ^ walk_nx_mask); walker->pte_access = FNAME(gpte_access)(pte_access ^ walk_nx_mask); errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access); if (unlikely(errcode)) @@ -463,13 +494,13 @@ retry_walk: } pgprintk("%s: pte %llx pte_access %x pt_access %x\n", - __func__, (u64)pte, walker->pte_access, walker->pt_access); + __func__, (u64)pte, walker->pte_access, + walker->pt_access[walker->level - 1]); return 1; error: errcode |= write_fault | user_fault; - if (fetch_fault && (mmu->nx || - kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))) + if (fetch_fault && (is_efer_nx(mmu) || is_cr4_smep(mmu))) errcode |= PFERR_FETCH_MASK; walker->fault.vector = PF_VECTOR; @@ -643,7 +674,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled; struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; - unsigned direct_access, access = gw->pt_access; + unsigned int direct_access, access; int top_level, level, req_level, ret; gfn_t base_gfn = gw->gfn; @@ -675,6 +706,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, sp = NULL; if (!is_shadow_present_pte(*it.sptep)) { table_gfn = gw->table_gfn[it.level - 2]; + access = gw->pt_access[it.level - 2]; sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, false, access); } @@ -763,7 +795,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, bool self_changed = false; if (!(walker->pte_access & ACC_WRITE_MASK || - (!is_write_protection(vcpu) && !user_fault))) + (!is_cr0_wp(vcpu->arch.mmu) && !user_fault))) return false; for (level = walker->level; level <= walker->max_level; level++) { @@ -861,8 +893,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, * we will cache the incorrect access into mmio spte. */ if (write_fault && !(walker.pte_access & ACC_WRITE_MASK) && - !is_write_protection(vcpu) && !user_fault && - !is_noslot_pfn(pfn)) { + !is_cr0_wp(vcpu->arch.mmu) && !user_fault && !is_noslot_pfn(pfn)) { walker.pte_access |= ACC_WRITE_MASK; walker.pte_access &= ~ACC_USER_MASK; @@ -872,7 +903,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, * then we should prevent the kernel from executing it * if SMEP is enabled. */ - if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP)) + if (is_cr4_smep(vcpu->arch.mmu)) walker.pte_access &= ~ACC_EXEC_MASK; } @@ -1027,13 +1058,36 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, */ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { + union kvm_mmu_page_role mmu_role = vcpu->arch.mmu->mmu_role.base; int i, nr_present = 0; bool host_writable; gpa_t first_pte_gpa; int set_spte_ret = 0; - /* direct kvm_mmu_page can not be unsync. */ - BUG_ON(sp->role.direct); + /* + * Ignore various flags when verifying that it's safe to sync a shadow + * page using the current MMU context. + * + * - level: not part of the overall MMU role and will never match as the MMU's + * level tracks the root level + * - access: updated based on the new guest PTE + * - quadrant: not part of the overall MMU role (similar to level) + */ + const union kvm_mmu_page_role sync_role_ign = { + .level = 0xf, + .access = 0x7, + .quadrant = 0x3, + }; + + /* + * Direct pages can never be unsync, and KVM should never attempt to + * sync a shadow page for a different MMU context, e.g. if the role + * differs then the memslot lookup (SMM vs. non-SMM) will be bogus, the + * reserved bits checks will be wrong, etc... + */ + if (WARN_ON_ONCE(sp->role.direct || + (sp->role.word ^ mmu_role.word) & ~sync_role_ign.word)) + return 0; first_pte_gpa = FNAME(get_level1_sp_gpa)(sp); diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 66d43cec0c31..3e97cdb13eb7 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -103,13 +103,6 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level, spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK; /* - * Bits 62:52 of PAE SPTEs are reserved. WARN if said bits are set - * if PAE paging may be employed (shadow paging or any 32-bit KVM). - */ - WARN_ON_ONCE((!tdp_enabled || !IS_ENABLED(CONFIG_X86_64)) && - (spte & SPTE_TDP_AD_MASK)); - - /* * For the EPT case, shadow_present_mask is 0 if hardware * supports exec-only page table entries. In that case, * ACC_USER_MASK and shadow_user_mask are used to represent @@ -154,13 +147,19 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level, /* * Optimization: for pte sync, if spte was writable the hash * lookup is unnecessary (and expensive). Write protection - * is responsibility of mmu_get_page / kvm_sync_page. + * is responsibility of kvm_mmu_get_page / kvm_mmu_sync_roots. * Same reasoning can be applied to dirty page accounting. */ if (!can_unsync && is_writable_pte(old_spte)) goto out; - if (mmu_need_write_protect(vcpu, gfn, can_unsync)) { + /* + * Unsync shadow pages that are reachable by the new, writable + * SPTE. Write-protect the SPTE if the page can't be unsync'd, + * e.g. it's write-tracked (upper-level SPs) or has one or more + * shadow pages and unsync'ing pages is not allowed. + */ + if (mmu_try_to_unsync_pages(vcpu, gfn, can_unsync)) { pgprintk("%s: found shadow page for %llx, marking ro\n", __func__, gfn); ret |= SET_SPTE_WRITE_PROTECTED_PT; @@ -176,7 +175,10 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level, spte = mark_spte_for_access_track(spte); out: - WARN_ON(is_mmio_spte(spte)); + WARN_ONCE(is_rsvd_spte(&vcpu->arch.mmu->shadow_zero_check, spte, level), + "spte = 0x%llx, level = %d, rsvd bits = 0x%llx", spte, level, + get_rsvd_bits(&vcpu->arch.mmu->shadow_zero_check, spte, level)); + *new_spte = spte; return ret; } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index bca0ba11cccf..7a5ce9314107 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -293,6 +293,38 @@ static inline bool is_dirty_spte(u64 spte) return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK; } +static inline u64 get_rsvd_bits(struct rsvd_bits_validate *rsvd_check, u64 pte, + int level) +{ + int bit7 = (pte >> 7) & 1; + + return rsvd_check->rsvd_bits_mask[bit7][level-1]; +} + +static inline bool __is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, + u64 pte, int level) +{ + return pte & get_rsvd_bits(rsvd_check, pte, level); +} + +static inline bool __is_bad_mt_xwr(struct rsvd_bits_validate *rsvd_check, + u64 pte) +{ + return rsvd_check->bad_mt_xwr & BIT_ULL(pte & 0x3f); +} + +static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, + u64 spte, int level) +{ + /* + * Use a bitwise-OR instead of a logical-OR to aggregate the reserved + * bits and EPT's invalid memtype/XWR checks to avoid an extra Jcc + * (this is extremely unlikely to be short-circuited as true). + */ + return __is_bad_mt_xwr(rsvd_check, spte) | + __is_rsvd_bits_set(rsvd_check, spte, level); +} + static inline bool spte_can_locklessly_be_made_writable(u64 spte) { return (spte & shadow_host_writable_mask) && diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 88f69a6cc492..caac4ddb46df 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -14,10 +14,10 @@ static bool __read_mostly tdp_mmu_enabled = false; module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644); /* Initializes the TDP MMU for the VM, if enabled. */ -void kvm_mmu_init_tdp_mmu(struct kvm *kvm) +bool kvm_mmu_init_tdp_mmu(struct kvm *kvm) { if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled)) - return; + return false; /* This should not be changed for the lifetime of the VM. */ kvm->arch.tdp_mmu_enabled = true; @@ -25,6 +25,8 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm) INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages); + + return true; } static __always_inline void kvm_lockdep_assert_mmu_lock_held(struct kvm *kvm, @@ -335,7 +337,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, for (i = 0; i < PT64_ENT_PER_PAGE; i++) { sptep = rcu_dereference(pt) + i; - gfn = base_gfn + (i * KVM_PAGES_PER_HPAGE(level - 1)); + gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); if (shared) { /* @@ -377,18 +379,18 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, WRITE_ONCE(*sptep, REMOVED_SPTE); } handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, - old_child_spte, REMOVED_SPTE, level - 1, + old_child_spte, REMOVED_SPTE, level, shared); } kvm_flush_remote_tlbs_with_address(kvm, gfn, - KVM_PAGES_PER_HPAGE(level)); + KVM_PAGES_PER_HPAGE(level + 1)); call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); } /** - * handle_changed_spte - handle bookkeeping associated with an SPTE change + * __handle_changed_spte - handle bookkeeping associated with an SPTE change * @kvm: kvm instance * @as_id: the address space of the paging structure the SPTE was a part of * @gfn: the base GFN that was mapped by the SPTE @@ -444,6 +446,13 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, trace_kvm_tdp_mmu_spte_changed(as_id, gfn, level, old_spte, new_spte); + if (is_large_pte(old_spte) != is_large_pte(new_spte)) { + if (is_large_pte(old_spte)) + atomic64_sub(1, (atomic64_t*)&kvm->stat.lpages); + else + atomic64_add(1, (atomic64_t*)&kvm->stat.lpages); + } + /* * The only times a SPTE should be changed from a non-present to * non-present state is when an MMIO entry is installed/modified/ @@ -905,7 +914,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, kvm_pfn_t pfn, bool prefault) { u64 new_spte; - int ret = 0; + int ret = RET_PF_FIXED; int make_spte_ret = 0; if (unlikely(is_noslot_pfn(pfn))) @@ -942,7 +951,11 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, rcu_dereference(iter->sptep)); } - if (!prefault) + /* + * Increase pf_fixed in both RET_PF_EMULATE and RET_PF_FIXED to be + * consistent with legacy MMU behavior. + */ + if (ret != RET_PF_SPURIOUS) vcpu->stat.pf_fixed++; return ret; @@ -970,11 +983,6 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, int level; int req_level; - if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) - return RET_PF_RETRY; - if (WARN_ON(!is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa))) - return RET_PF_RETRY; - level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn, huge_page_disallowed, &req_level); @@ -1009,7 +1017,15 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, } if (!is_shadow_present_pte(iter.old_spte)) { - sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level); + /* + * If SPTE has been forzen by another thread, just + * give up and retry, avoiding unnecessary page table + * allocation and free. + */ + if (is_removed_spte(iter.old_spte)) + break; + + sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level - 1); child_pt = sp->spt; new_spte = make_nonleaf_spte(child_pt, @@ -1177,9 +1193,9 @@ bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) } /* - * Remove write access from all the SPTEs mapping GFNs [start, end). If - * skip_4k is set, SPTEs that map 4k pages, will not be write-protected. - * Returns true if an SPTE has been changed and the TLBs need to be flushed. + * Remove write access from all SPTEs at or above min_level that map GFNs + * [start, end). Returns true if an SPTE has been changed and the TLBs need to + * be flushed. */ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, int min_level) @@ -1447,15 +1463,22 @@ bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, * Returns true if an SPTE was set and a TLB flush is needed. */ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t gfn) + gfn_t gfn, int min_level) { struct tdp_iter iter; u64 new_spte; bool spte_set = false; + BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL); + rcu_read_lock(); - tdp_root_for_each_leaf_pte(iter, root, gfn, gfn + 1) { + for_each_tdp_pte_min_level(iter, root->spt, root->role.level, + min_level, gfn, gfn + 1) { + if (!is_shadow_present_pte(iter.old_spte) || + !is_last_spte(iter.old_spte, iter.level)) + continue; + if (!is_writable_pte(iter.old_spte)) break; @@ -1477,14 +1500,15 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, * Returns true if an SPTE was set and a TLB flush is needed. */ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn) + struct kvm_memory_slot *slot, gfn_t gfn, + int min_level) { struct kvm_mmu_page *root; bool spte_set = false; lockdep_assert_held_write(&kvm->mmu_lock); for_each_tdp_mmu_root(kvm, root, slot->as_id) - spte_set |= write_protect_gfn(kvm, root, gfn); + spte_set |= write_protect_gfn(kvm, root, gfn, min_level); return spte_set; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 5fdf63090451..1cae4485b3bc 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -31,7 +31,7 @@ static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, } static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { - gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level); + gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level + 1); /* * Don't allow yielding, as the caller may have a flush pending. Note, @@ -74,37 +74,40 @@ bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, bool flush); bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn); + struct kvm_memory_slot *slot, gfn_t gfn, + int min_level); int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level); #ifdef CONFIG_X86_64 -void kvm_mmu_init_tdp_mmu(struct kvm *kvm); +bool kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return kvm->arch.tdp_mmu_enabled; } static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; } -#else -static inline void kvm_mmu_init_tdp_mmu(struct kvm *kvm) {} -static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {} -static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return false; } -static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; } -#endif -static inline bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) +static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { struct kvm_mmu_page *sp; + hpa_t hpa = mmu->root_hpa; - if (!is_tdp_mmu_enabled(kvm)) - return false; if (WARN_ON(!VALID_PAGE(hpa))) return false; + /* + * A NULL shadow page is legal when shadowing a non-paging guest with + * PAE paging, as the MMU will be direct with root_hpa pointing at the + * pae_root page, not a shadow page. + */ sp = to_shadow_page(hpa); - if (WARN_ON(!sp)) - return false; - - return is_tdp_mmu_page(sp) && sp->root_count; + return sp && is_tdp_mmu_page(sp) && sp->root_count; } +#else +static inline bool kvm_mmu_init_tdp_mmu(struct kvm *kvm) { return false; } +static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {} +static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return false; } +static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; } +static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { return false; } +#endif #endif /* __KVM_X86_MMU_TDP_MMU_H */ diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 712b4e0de481..1d01da64c333 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -27,12 +27,6 @@ #include "irq.h" #include "svm.h" -/* enable / disable AVIC */ -int avic; -#ifdef CONFIG_X86_LOCAL_APIC -module_param(avic, int, S_IRUGO); -#endif - #define SVM_AVIC_DOORBELL 0xc001011b #define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) @@ -126,7 +120,7 @@ void avic_vm_destroy(struct kvm *kvm) unsigned long flags; struct kvm_svm *kvm_svm = to_kvm_svm(kvm); - if (!avic) + if (!enable_apicv) return; if (kvm_svm->avic_logical_id_table_page) @@ -149,7 +143,7 @@ int avic_vm_init(struct kvm *kvm) struct page *l_page; u32 vm_id; - if (!avic) + if (!enable_apicv) return 0; /* Allocating physical APIC ID table (4KB) */ @@ -223,7 +217,7 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, return &avic_physical_id_table[index]; } -/** +/* * Note: * AVIC hardware walks the nested page table to check permissions, * but does not use the SPA address specified in the leaf page @@ -242,7 +236,7 @@ static int avic_update_access_page(struct kvm *kvm, bool activate) * APICv mode change, which update APIC_ACCESS_PAGE_PRIVATE_MEMSLOT * memory region. So, we need to ensure that kvm->mm == current->mm. */ - if ((kvm->arch.apic_access_page_done == activate) || + if ((kvm->arch.apic_access_memslot_enabled == activate) || (kvm->mm != current->mm)) goto out; @@ -255,7 +249,7 @@ static int avic_update_access_page(struct kvm *kvm, bool activate) goto out; } - kvm->arch.apic_access_page_done = activate; + kvm->arch.apic_access_memslot_enabled = activate; out: mutex_unlock(&kvm->slots_lock); return r; @@ -571,7 +565,7 @@ int avic_init_vcpu(struct vcpu_svm *svm) int ret; struct kvm_vcpu *vcpu = &svm->vcpu; - if (!avic || !irqchip_in_kernel(vcpu->kvm)) + if (!enable_apicv || !irqchip_in_kernel(vcpu->kvm)) return 0; ret = avic_init_backing_page(vcpu); @@ -595,7 +589,7 @@ void avic_post_state_restore(struct kvm_vcpu *vcpu) void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate) { - if (!avic || !lapic_in_kernel(vcpu)) + if (!enable_apicv || !lapic_in_kernel(vcpu)) return; srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -655,7 +649,7 @@ void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) struct vmcb *vmcb = svm->vmcb; bool activated = kvm_vcpu_apicv_active(vcpu); - if (!avic) + if (!enable_apicv) return; if (activated) { @@ -766,7 +760,7 @@ out: return ret; } -/** +/* * Note: * The HW cannot support posting multicast/broadcast * interrupts to a vCPU. So, we still use legacy interrupt @@ -1007,7 +1001,7 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) WRITE_ONCE(*(svm->avic_physical_id_cache), entry); } -/** +/* * This function is called during VCPU halt/unhalt. */ static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 540d43ba2cf4..21d03e3a5dfd 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -98,13 +98,18 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) WARN_ON(mmu_is_nested(vcpu)); vcpu->arch.mmu = &vcpu->arch.guest_mmu; + + /* + * The NPT format depends on L1's CR4 and EFER, which is in vmcb01. Note, + * when called via KVM_SET_NESTED_STATE, that state may _not_ match current + * vCPU state. CR0.WP is explicitly ignored, while CR0.PG is required. + */ kvm_init_shadow_npt_mmu(vcpu, X86_CR0_PG, svm->vmcb01.ptr->save.cr4, svm->vmcb01.ptr->save.efer, svm->nested.ctl.nested_cr3); vcpu->arch.mmu->get_guest_pgd = nested_svm_get_tdp_cr3; vcpu->arch.mmu->get_pdptr = nested_svm_get_tdp_pdptr; vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit; - reset_shadow_zero_bits_mask(vcpu, vcpu->arch.mmu); vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; } @@ -380,33 +385,47 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm) return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE; } +static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu) +{ + /* + * TODO: optimize unconditional TLB flush/MMU sync. A partial list of + * things to fix before this can be conditional: + * + * - Flush TLBs for both L1 and L2 remote TLB flush + * - Honor L1's request to flush an ASID on nested VMRUN + * - Sync nested NPT MMU on VMRUN that flushes L2's ASID[*] + * - Don't crush a pending TLB flush in vmcb02 on nested VMRUN + * - Flush L1's ASID on KVM_REQ_TLB_FLUSH_GUEST + * + * [*] Unlike nested EPT, SVM's ASID management can invalidate nested + * NPT guest-physical mappings on VMRUN. + */ + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); +} + /* * Load guest's/host's cr3 on nested vmentry or vmexit. @nested_npt is true * if we are emulating VM-Entry into a guest with NPT enabled. */ static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, - bool nested_npt) + bool nested_npt, bool reload_pdptrs) { if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) return -EINVAL; - if (!nested_npt && is_pae_paging(vcpu) && - (cr3 != kvm_read_cr3(vcpu) || pdptrs_changed(vcpu))) { - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) - return -EINVAL; - } + if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) && + CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) + return -EINVAL; - /* - * TODO: optimize unconditional TLB flush/MMU sync here and in - * kvm_init_shadow_npt_mmu(). - */ if (!nested_npt) - kvm_mmu_new_pgd(vcpu, cr3, false, false); + kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); - kvm_init_mmu(vcpu, false); + /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ + kvm_init_mmu(vcpu); return 0; } @@ -481,6 +500,7 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) { const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK; + struct kvm_vcpu *vcpu = &svm->vcpu; /* * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2, @@ -505,10 +525,10 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) /* nested_cr3. */ if (nested_npt_enabled(svm)) - nested_svm_init_mmu_context(&svm->vcpu); + nested_svm_init_mmu_context(vcpu); - svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset = - svm->vcpu.arch.l1_tsc_offset + svm->nested.ctl.tsc_offset; + svm->vmcb->control.tsc_offset = vcpu->arch.tsc_offset = + vcpu->arch.l1_tsc_offset + svm->nested.ctl.tsc_offset; svm->vmcb->control.int_ctl = (svm->nested.ctl.int_ctl & ~mask) | @@ -523,8 +543,10 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) svm->vmcb->control.pause_filter_count = svm->nested.ctl.pause_filter_count; svm->vmcb->control.pause_filter_thresh = svm->nested.ctl.pause_filter_thresh; + nested_svm_transition_tlb_flush(vcpu); + /* Enter Guest-Mode */ - enter_guest_mode(&svm->vcpu); + enter_guest_mode(vcpu); /* * Merge guest and host intercepts - must be called with vcpu in @@ -576,7 +598,7 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, nested_vmcb02_prepare_save(svm, vmcb12); ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, - nested_npt_enabled(svm)); + nested_npt_enabled(svm), true); if (ret) return ret; @@ -596,8 +618,6 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) struct kvm_host_map map; u64 vmcb12_gpa; - ++vcpu->stat.nested_run; - if (is_smm(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; @@ -764,7 +784,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm) nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr); svm_switch_vmcb(svm, &svm->vmcb01); - WARN_ON_ONCE(svm->vmcb->control.exit_code != SVM_EXIT_VMRUN); /* * On vmexit the GIF is set to false and @@ -804,9 +823,11 @@ int nested_svm_vmexit(struct vcpu_svm *svm) kvm_vcpu_unmap(vcpu, &map, true); + nested_svm_transition_tlb_flush(vcpu); + nested_svm_uninit_mmu_context(vcpu); - rc = nested_svm_load_cr3(vcpu, svm->vmcb->save.cr3, false); + rc = nested_svm_load_cr3(vcpu, svm->vmcb->save.cr3, false, true); if (rc) return 1; @@ -872,6 +893,15 @@ void svm_free_nested(struct vcpu_svm *svm) __free_page(virt_to_page(svm->nested.vmcb02.ptr)); svm->nested.vmcb02.ptr = NULL; + /* + * When last_vmcb12_gpa matches the current vmcb12 gpa, + * some vmcb12 fields are not loaded if they are marked clean + * in the vmcb12, since in this case they are up to date already. + * + * When the vmcb02 is freed, this optimization becomes invalid. + */ + svm->nested.last_vmcb12_gpa = INVALID_GPA; + svm->nested.initialized = false; } @@ -884,9 +914,11 @@ void svm_leave_nested(struct vcpu_svm *svm) if (is_guest_mode(vcpu)) { svm->nested.nested_run_pending = 0; + svm->nested.vmcb12_gpa = INVALID_GPA; + leave_guest_mode(vcpu); - svm_switch_vmcb(svm, &svm->nested.vmcb02); + svm_switch_vmcb(svm, &svm->vmcb01); nested_svm_uninit_mmu_context(vcpu); vmcb_mark_all_dirty(svm->vmcb); @@ -1218,8 +1250,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, &user_kvm_nested_state->data.svm[0]; struct vmcb_control_area *ctl; struct vmcb_save_area *save; + unsigned long cr0; int ret; - u32 cr0; BUILD_BUG_ON(sizeof(struct vmcb_control_area) + sizeof(struct vmcb_save_area) > KVM_STATE_NESTED_SVM_VMCB_SIZE); @@ -1292,18 +1324,36 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, goto out_free; /* + * While the nested guest CR3 is already checked and set by + * KVM_SET_SREGS, it was set when nested state was yet loaded, + * thus MMU might not be initialized correctly. + * Set it again to fix this. + */ + + ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, + nested_npt_enabled(svm), false); + if (WARN_ON_ONCE(ret)) + goto out_free; + + + /* * All checks done, we can enter guest mode. Userspace provides * vmcb12.control, which will be combined with L1 and stored into * vmcb02, and the L1 save state which we store in vmcb01. * L2 registers if needed are moved from the current VMCB to VMCB02. */ + if (is_guest_mode(vcpu)) + svm_leave_nested(svm); + else + svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save; + + svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); + svm->nested.nested_run_pending = !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; - if (svm->current_vmcb == &svm->vmcb01) - svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save; svm->vmcb01.ptr->save.es = save->es; svm->vmcb01.ptr->save.cs = save->cs; @@ -1343,9 +1393,15 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) if (WARN_ON(!is_guest_mode(vcpu))) return true; - if (nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, - nested_npt_enabled(svm))) - return false; + if (!vcpu->arch.pdptrs_from_userspace && + !nested_npt_enabled(svm) && is_pae_paging(vcpu)) + /* + * Reload the guest's PDPTRs since after a migration + * the guest CR3 might be restored prior to setting the nested + * state which can lead to a load of wrong PDPTRs. + */ + if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + return false; if (!nested_svm_vmrun_msrpm(svm)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 1356ee095cd5..8d36f0c73071 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -199,9 +199,19 @@ static void sev_asid_free(struct kvm_sev_info *sev) sev->misc_cg = NULL; } -static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +static void sev_decommission(unsigned int handle) { struct sev_data_decommission decommission; + + if (!handle) + return; + + decommission.handle = handle; + sev_guest_decommission(&decommission, NULL); +} + +static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +{ struct sev_data_deactivate deactivate; if (!handle) @@ -214,9 +224,7 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) sev_guest_deactivate(&deactivate, NULL); up_read(&sev_deactivate_lock); - /* decommission handle */ - decommission.handle = handle; - sev_guest_decommission(&decommission, NULL); + sev_decommission(handle); } static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) @@ -341,8 +349,10 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Bind ASID to this guest */ ret = sev_bind_asid(kvm, start.handle, error); - if (ret) + if (ret) { + sev_decommission(start.handle); goto e_free_session; + } /* return handle to userspace */ params.handle = start.handle; @@ -763,7 +773,7 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, } static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, - unsigned long __user dst_uaddr, + void __user *dst_uaddr, unsigned long dst_paddr, int size, int *err) { @@ -787,8 +797,7 @@ static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, if (tpage) { offset = paddr & 15; - if (copy_to_user((void __user *)(uintptr_t)dst_uaddr, - page_address(tpage) + offset, size)) + if (copy_to_user(dst_uaddr, page_address(tpage) + offset, size)) ret = -EFAULT; } @@ -800,9 +809,9 @@ e_free: } static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, - unsigned long __user vaddr, + void __user *vaddr, unsigned long dst_paddr, - unsigned long __user dst_vaddr, + void __user *dst_vaddr, int size, int *error) { struct page *src_tpage = NULL; @@ -810,13 +819,12 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, int ret, len = size; /* If source buffer is not aligned then use an intermediate buffer */ - if (!IS_ALIGNED(vaddr, 16)) { + if (!IS_ALIGNED((unsigned long)vaddr, 16)) { src_tpage = alloc_page(GFP_KERNEL); if (!src_tpage) return -ENOMEM; - if (copy_from_user(page_address(src_tpage), - (void __user *)(uintptr_t)vaddr, size)) { + if (copy_from_user(page_address(src_tpage), vaddr, size)) { __free_page(src_tpage); return -EFAULT; } @@ -830,7 +838,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, * - copy the source buffer in an intermediate buffer * - use the intermediate buffer as source buffer */ - if (!IS_ALIGNED(dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { + if (!IS_ALIGNED((unsigned long)dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { int dst_offset; dst_tpage = alloc_page(GFP_KERNEL); @@ -855,7 +863,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, page_address(src_tpage), size); else { if (copy_from_user(page_address(dst_tpage) + dst_offset, - (void __user *)(uintptr_t)vaddr, size)) { + vaddr, size)) { ret = -EFAULT; goto e_free; } @@ -935,15 +943,15 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) if (dec) ret = __sev_dbg_decrypt_user(kvm, __sme_page_pa(src_p[0]) + s_off, - dst_vaddr, + (void __user *)dst_vaddr, __sme_page_pa(dst_p[0]) + d_off, len, &argp->error); else ret = __sev_dbg_encrypt_user(kvm, __sme_page_pa(src_p[0]) + s_off, - vaddr, + (void __user *)vaddr, __sme_page_pa(dst_p[0]) + d_off, - dst_vaddr, + (void __user *)dst_vaddr, len, &argp->error); sev_unpin_memory(kvm, src_p, n); @@ -1105,10 +1113,9 @@ __sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp, struct sev_data_send_start data; int ret; + memset(&data, 0, sizeof(data)); data.handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error); - if (ret < 0) - return ret; params->session_len = data.session_len; if (copy_to_user((void __user *)(uintptr_t)argp->data, params, @@ -1217,10 +1224,9 @@ __sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp, struct sev_data_send_update_data data; int ret; + memset(&data, 0, sizeof(data)); data.handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error); - if (ret < 0) - return ret; params->hdr_len = data.hdr_len; params->trans_len = data.trans_len; @@ -1764,7 +1770,8 @@ e_mirror_unlock: e_source_unlock: mutex_unlock(&source_kvm->lock); e_source_put: - fput(source_kvm_file); + if (source_kvm_file) + fput(source_kvm_file); return ret; } @@ -2198,7 +2205,7 @@ vmgexit_err: return -EINVAL; } -static void pre_sev_es_run(struct vcpu_svm *svm) +void sev_es_unmap_ghcb(struct vcpu_svm *svm) { if (!svm->ghcb) return; @@ -2234,9 +2241,6 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int asid = sev_get_asid(svm->vcpu.kvm); - /* Perform any SEV-ES pre-run actions */ - pre_sev_es_run(svm); - /* Assign the asid allocated with this SEV guest */ svm->asid = asid; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b649f92287a2..8834822c00cd 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -43,6 +43,9 @@ #include "svm.h" #include "svm_ops.h" +#include "kvm_onhyperv.h" +#include "svm_onhyperv.h" + #define __ex(x) __kvm_handle_fault_on_reboot(x) MODULE_AUTHOR("Qumranet"); @@ -185,6 +188,13 @@ module_param(vls, int, 0444); static int vgif = true; module_param(vgif, int, 0444); +/* + * enable / disable AVIC. Because the defaults differ for APICv + * support between VMX and SVM we cannot use module_param_named. + */ +static bool avic; +module_param(avic, bool, 0444); + bool __read_mostly dump_invalid_vmcb; module_param(dump_invalid_vmcb, bool, 0644); @@ -212,7 +222,7 @@ DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); * RDTSCP and RDPID are not used in the kernel, specifically to allow KVM to * defer the restoration of TSC_AUX until the CPU returns to userspace. */ -#define TSC_AUX_URET_SLOT 0 +static int tsc_aux_uret_slot __read_mostly = -1; static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; @@ -447,6 +457,11 @@ static int has_svm(void) return 0; } + if (pgtable_l5_enabled()) { + pr_info("KVM doesn't yet support 5-level paging on AMD SVM\n"); + return 0; + } + return 1; } @@ -668,6 +683,9 @@ static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm, write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp); msrpm[offset] = tmp; + + svm_hv_vmcb_dirty_nested_enlightenments(vcpu); + } void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, @@ -858,8 +876,8 @@ static __init void svm_adjust_mmio_mask(void) return; /* If memory encryption is not enabled, use existing mask */ - rdmsrl(MSR_K8_SYSCFG, msr); - if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + rdmsrl(MSR_AMD64_SYSCFG, msr); + if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT)) return; enc_bit = cpuid_ebx(0x8000001f) & 0x3f; @@ -934,6 +952,16 @@ static __init int svm_hardware_setup(void) int r; unsigned int order = get_order(IOPM_SIZE); + /* + * NX is required for shadow paging and for NPT if the NX huge pages + * mitigation is enabled. + */ + if (!boot_cpu_has(X86_FEATURE_NX)) { + pr_err_ratelimited("NX (Execute Disable) not supported\n"); + return -EOPNOTSUPP; + } + kvm_enable_efer_bits(EFER_NX); + iopm_pages = alloc_pages(GFP_KERNEL, order); if (!iopm_pages) @@ -947,9 +975,6 @@ static __init int svm_hardware_setup(void) supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); - if (boot_cpu_has(X86_FEATURE_NX)) - kvm_enable_efer_bits(EFER_NX); - if (boot_cpu_has(X86_FEATURE_FXSR_OPT)) kvm_enable_efer_bits(EFER_FFXSR); @@ -959,8 +984,7 @@ static __init int svm_hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 32; } - if (boot_cpu_has(X86_FEATURE_RDTSCP)) - kvm_define_user_return_msr(TSC_AUX_URET_SLOT, MSR_TSC_AUX); + tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX); /* Check for pause filtering support */ if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) { @@ -992,6 +1016,8 @@ static __init int svm_hardware_setup(void) /* Note, SEV setup consumes npt_enabled. */ sev_hardware_setup(); + svm_hv_hardware_setup(); + svm_adjust_mmio_mask(); for_each_possible_cpu(cpu) { @@ -1005,16 +1031,12 @@ static __init int svm_hardware_setup(void) nrips = false; } - if (avic) { - if (!npt_enabled || - !boot_cpu_has(X86_FEATURE_AVIC) || - !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) { - avic = false; - } else { - pr_info("AVIC enabled\n"); + enable_apicv = avic = avic && npt_enabled && boot_cpu_has(X86_FEATURE_AVIC); - amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); - } + if (enable_apicv) { + pr_info("AVIC enabled\n"); + + amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); } if (vls) { @@ -1078,29 +1100,35 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } -static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +static u64 svm_get_l2_tsc_offset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - u64 g_tsc_offset = 0; - if (is_guest_mode(vcpu)) { - /* Write L1's TSC offset. */ - g_tsc_offset = svm->vmcb->control.tsc_offset - - svm->vmcb01.ptr->control.tsc_offset; - svm->vmcb01.ptr->control.tsc_offset = offset; - } + return svm->nested.ctl.tsc_offset; +} - trace_kvm_write_tsc_offset(vcpu->vcpu_id, - svm->vmcb->control.tsc_offset - g_tsc_offset, - offset); +static u64 svm_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) +{ + return kvm_default_tsc_scaling_ratio; +} - svm->vmcb->control.tsc_offset = offset + g_tsc_offset; +static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +{ + struct vcpu_svm *svm = to_svm(vcpu); + svm->vmcb01.ptr->control.tsc_offset = vcpu->arch.l1_tsc_offset; + svm->vmcb->control.tsc_offset = offset; vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); - return svm->vmcb->control.tsc_offset; } -static void svm_check_invpcid(struct vcpu_svm *svm) +static void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) +{ + wrmsrl(MSR_AMD64_TSC_RATIO, multiplier); +} + +/* Evaluate instruction intercepts that depend on guest CPUID features. */ +static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, + struct vcpu_svm *svm) { /* * Intercept INVPCID if shadow paging is enabled to sync/free shadow @@ -1113,6 +1141,13 @@ static void svm_check_invpcid(struct vcpu_svm *svm) else svm_clr_intercept(svm, INTERCEPT_INVPCID); } + + if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) { + if (guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) + svm_clr_intercept(svm, INTERCEPT_RDTSCP); + else + svm_set_intercept(svm, INTERCEPT_RDTSCP); + } } static void init_vmcb(struct kvm_vcpu *vcpu) @@ -1235,8 +1270,8 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm->current_vmcb->asid_generation = 0; svm->asid = 0; - svm->nested.vmcb12_gpa = 0; - svm->nested.last_vmcb12_gpa = 0; + svm->nested.vmcb12_gpa = INVALID_GPA; + svm->nested.last_vmcb12_gpa = INVALID_GPA; vcpu->arch.hflags = 0; if (!kvm_pause_in_guest(vcpu->kvm)) { @@ -1248,7 +1283,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm_clr_intercept(svm, INTERCEPT_PAUSE); } - svm_check_invpcid(svm); + svm_recalc_instruction_intercepts(vcpu, svm); /* * If the host supports V_SPEC_CTRL then disable the interception @@ -1276,6 +1311,8 @@ static void init_vmcb(struct kvm_vcpu *vcpu) } } + svm_hv_init_vmcb(svm->vmcb); + vmcb_mark_all_dirty(svm->vmcb); enable_gif(svm); @@ -1424,6 +1461,9 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); + if (sev_es_guest(vcpu->kvm)) + sev_es_unmap_ghcb(svm); + if (svm->guest_state_loaded) return; @@ -1445,8 +1485,8 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) } } - if (static_cpu_has(X86_FEATURE_RDTSCP)) - kvm_set_user_return_msr(TSC_AUX_URET_SLOT, svm->tsc_aux, -1ull); + if (likely(tsc_aux_uret_slot >= 0)) + kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); svm->guest_state_loaded = true; } @@ -2655,11 +2695,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data |= (u64)svm->sysenter_esp_hi << 32; break; case MSR_TSC_AUX: - if (!boot_cpu_has(X86_FEATURE_RDTSCP)) - return 1; - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; msr_info->data = svm->tsc_aux; break; /* @@ -2876,30 +2911,13 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->sysenter_esp_hi = guest_cpuid_is_intel(vcpu) ? (data >> 32) : 0; break; case MSR_TSC_AUX: - if (!boot_cpu_has(X86_FEATURE_RDTSCP)) - return 1; - - if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - - /* - * Per Intel's SDM, bits 63:32 are reserved, but AMD's APM has - * incomplete and conflicting architectural behavior. Current - * AMD CPUs completely ignore bits 63:32, i.e. they aren't - * reserved and always read as zeros. Emulate AMD CPU behavior - * to avoid explosions if the vCPU is migrated from an AMD host - * to an Intel host. - */ - data = (u32)data; - /* * TSC_AUX is usually changed only during boot and never read * directly. Intercept TSC_AUX instead of exposing it to the * guest via direct_access_msrs, and switch it via user return. */ preempt_disable(); - r = kvm_set_user_return_msr(TSC_AUX_URET_SLOT, data, -1ull); + r = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull); preempt_enable(); if (r) return 1; @@ -3084,6 +3102,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_STGI] = stgi_interception, [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = skinit_interception, + [SVM_EXIT_RDTSCP] = kvm_handle_invalid_op, [SVM_EXIT_WBINVD] = kvm_emulate_wbinvd, [SVM_EXIT_MONITOR] = kvm_emulate_monitor, [SVM_EXIT_MWAIT] = kvm_emulate_mwait, @@ -3113,6 +3132,8 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) return; } + pr_err("VMCB %p, last attempted VMRUN on CPU %d\n", + svm->current_vmcb->ptr, vcpu->arch.last_vmentry_cpu); pr_err("VMCB Control Area:\n"); pr_err("%-20s%04x\n", "cr_read:", control->intercepts[INTERCEPT_CR] & 0xffff); pr_err("%-20s%04x\n", "cr_write:", control->intercepts[INTERCEPT_CR] >> 16); @@ -3769,6 +3790,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) } svm->vmcb->save.cr2 = vcpu->arch.cr2; + svm_hv_update_vp_id(svm->vmcb, vcpu); + /* * Run with all-zero DR6 unless needed, so that we can get the exact cause * of a #DB. @@ -3842,6 +3865,12 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) svm->next_rip = 0; if (is_guest_mode(vcpu)) { nested_sync_control_from_vmcb02(svm); + + /* Track VMRUNs that have made past consistency checking */ + if (svm->nested.nested_run_pending && + svm->vmcb->control.exit_code != SVM_EXIT_ERR) + ++vcpu->stat.nested_run; + svm->nested.nested_run_pending = 0; } @@ -3853,10 +3882,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); - if (npt_enabled) { - vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); - vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR); - } + if (npt_enabled) + kvm_register_clear_available(vcpu, VCPU_EXREG_PDPTR); /* * We need to handle MC intercepts here before the vcpu has a chance to @@ -3884,6 +3911,8 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, svm->vmcb->control.nested_cr3 = __sme_set(root_hpa); vmcb_mark_dirty(svm->vmcb, VMCB_NPT); + hv_track_root_tdp(vcpu, root_hpa); + /* Loading L2's CR3 is handled by enter_svm_guest_mode. */ if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) return; @@ -3972,8 +4001,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) && guest_cpuid_has(vcpu, X86_FEATURE_NRIPS); - /* Check again if INVPCID interception if required */ - svm_check_invpcid(svm); + svm_recalc_instruction_intercepts(vcpu, svm); /* For sev guests, the memory encryption bit is not reserved in CR3. */ if (sev_guest(vcpu->kvm)) { @@ -4257,7 +4285,7 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !svm_smi_blocked(vcpu); } -static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); int ret; @@ -4279,7 +4307,7 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) +static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_host_map map; @@ -4435,13 +4463,12 @@ static int svm_vm_init(struct kvm *kvm) if (!pause_filter_count || !pause_filter_thresh) kvm->arch.pause_in_guest = true; - if (avic) { + if (enable_apicv) { int ret = avic_vm_init(kvm); if (ret) return ret; } - kvm_apicv_init(kvm, avic); return 0; } @@ -4532,7 +4559,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .has_wbinvd_exit = svm_has_wbinvd_exit, - .write_l1_tsc_offset = svm_write_l1_tsc_offset, + .get_l2_tsc_offset = svm_get_l2_tsc_offset, + .get_l2_tsc_multiplier = svm_get_l2_tsc_multiplier, + .write_tsc_offset = svm_write_tsc_offset, + .write_tsc_multiplier = svm_write_tsc_multiplier, .load_mmu_pgd = svm_load_mmu_pgd, @@ -4552,8 +4582,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .setup_mce = svm_setup_mce, .smi_allowed = svm_smi_allowed, - .pre_enter_smm = svm_pre_enter_smm, - .pre_leave_smm = svm_pre_leave_smm, + .enter_smm = svm_enter_smm, + .leave_smm = svm_leave_smm, .enable_smi_window = svm_enable_smi_window, .mem_enc_op = svm_mem_enc_op, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 84b3133c2251..f89b623bb591 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -20,6 +20,7 @@ #include <linux/bits.h> #include <asm/svm.h> +#include <asm/sev-common.h> #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) @@ -31,6 +32,11 @@ extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; +/* + * Clean bits in VMCB. + * VMCB_ALL_CLEAN_MASK might also need to + * be updated if this enum is modified. + */ enum { VMCB_INTERCEPTS, /* Intercept vectors, TSC offset, pause filter count */ @@ -48,9 +54,17 @@ enum { * AVIC PHYSICAL_TABLE pointer, * AVIC LOGICAL_TABLE pointer */ - VMCB_DIRTY_MAX, + VMCB_SW = 31, /* Reserved for hypervisor/software use */ }; +#define VMCB_ALL_CLEAN_MASK ( \ + (1U << VMCB_INTERCEPTS) | (1U << VMCB_PERM_MAP) | \ + (1U << VMCB_ASID) | (1U << VMCB_INTR) | \ + (1U << VMCB_NPT) | (1U << VMCB_CR) | (1U << VMCB_DR) | \ + (1U << VMCB_DT) | (1U << VMCB_SEG) | (1U << VMCB_CR2) | \ + (1U << VMCB_LBR) | (1U << VMCB_AVIC) | \ + (1U << VMCB_SW)) + /* TPR and CR2 are always written before VMRUN */ #define VMCB_ALWAYS_DIRTY_MASK ((1U << VMCB_INTR) | (1U << VMCB_CR2)) @@ -237,10 +251,15 @@ static inline void vmcb_mark_all_dirty(struct vmcb *vmcb) static inline void vmcb_mark_all_clean(struct vmcb *vmcb) { - vmcb->control.clean = ((1 << VMCB_DIRTY_MAX) - 1) + vmcb->control.clean = VMCB_ALL_CLEAN_MASK & ~VMCB_ALWAYS_DIRTY_MASK; } +static inline bool vmcb_is_clean(struct vmcb *vmcb, int bit) +{ + return (vmcb->control.clean & (1 << bit)); +} + static inline void vmcb_mark_dirty(struct vmcb *vmcb, int bit) { vmcb->control.clean &= ~(1 << bit); @@ -479,8 +498,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops; #define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL -extern int avic; - static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data) { svm->vmcb->control.avic_vapic_bar = data & VMCB_AVIC_APIC_BAR_MASK; @@ -525,40 +542,9 @@ void svm_vcpu_unblocking(struct kvm_vcpu *vcpu); /* sev.c */ -#define GHCB_VERSION_MAX 1ULL -#define GHCB_VERSION_MIN 1ULL - -#define GHCB_MSR_INFO_POS 0 -#define GHCB_MSR_INFO_MASK (BIT_ULL(12) - 1) - -#define GHCB_MSR_SEV_INFO_RESP 0x001 -#define GHCB_MSR_SEV_INFO_REQ 0x002 -#define GHCB_MSR_VER_MAX_POS 48 -#define GHCB_MSR_VER_MAX_MASK 0xffff -#define GHCB_MSR_VER_MIN_POS 32 -#define GHCB_MSR_VER_MIN_MASK 0xffff -#define GHCB_MSR_CBIT_POS 24 -#define GHCB_MSR_CBIT_MASK 0xff -#define GHCB_MSR_SEV_INFO(_max, _min, _cbit) \ - ((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) | \ - (((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) | \ - (((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) | \ - GHCB_MSR_SEV_INFO_RESP) - -#define GHCB_MSR_CPUID_REQ 0x004 -#define GHCB_MSR_CPUID_RESP 0x005 -#define GHCB_MSR_CPUID_FUNC_POS 32 -#define GHCB_MSR_CPUID_FUNC_MASK 0xffffffff -#define GHCB_MSR_CPUID_VALUE_POS 32 -#define GHCB_MSR_CPUID_VALUE_MASK 0xffffffff -#define GHCB_MSR_CPUID_REG_POS 30 -#define GHCB_MSR_CPUID_REG_MASK 0x3 - -#define GHCB_MSR_TERM_REQ 0x100 -#define GHCB_MSR_TERM_REASON_SET_POS 12 -#define GHCB_MSR_TERM_REASON_SET_MASK 0xf -#define GHCB_MSR_TERM_REASON_POS 16 -#define GHCB_MSR_TERM_REASON_MASK 0xff +#define GHCB_VERSION_MAX 1ULL +#define GHCB_VERSION_MIN 1ULL + extern unsigned int max_sev_asid; @@ -581,6 +567,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_create_vcpu(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu); +void sev_es_unmap_ghcb(struct vcpu_svm *svm); /* vmenter.S */ diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c new file mode 100644 index 000000000000..98aa981c04ec --- /dev/null +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM L1 hypervisor optimizations on Hyper-V for SVM. + */ + +#include <linux/kvm_host.h> +#include "kvm_cache_regs.h" + +#include <asm/mshyperv.h> + +#include "svm.h" +#include "svm_ops.h" + +#include "hyperv.h" +#include "kvm_onhyperv.h" +#include "svm_onhyperv.h" + +int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) +{ + struct hv_enlightenments *hve; + struct hv_partition_assist_pg **p_hv_pa_pg = + &to_kvm_hv(vcpu->kvm)->hv_pa_pg; + + if (!*p_hv_pa_pg) + *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL); + + if (!*p_hv_pa_pg) + return -ENOMEM; + + hve = (struct hv_enlightenments *)to_svm(vcpu)->vmcb->control.reserved_sw; + + hve->partition_assist_page = __pa(*p_hv_pa_pg); + hve->hv_vm_id = (unsigned long)vcpu->kvm; + if (!hve->hv_enlightenments_control.nested_flush_hypercall) { + hve->hv_enlightenments_control.nested_flush_hypercall = 1; + vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); + } + + return 0; +} + diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h new file mode 100644 index 000000000000..9b9a55abc29f --- /dev/null +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * KVM L1 hypervisor optimizations on Hyper-V for SVM. + */ + +#ifndef __ARCH_X86_KVM_SVM_ONHYPERV_H__ +#define __ARCH_X86_KVM_SVM_ONHYPERV_H__ + +#if IS_ENABLED(CONFIG_HYPERV) +#include <asm/mshyperv.h> + +#include "hyperv.h" +#include "kvm_onhyperv.h" + +static struct kvm_x86_ops svm_x86_ops; + +/* + * Hyper-V uses the software reserved 32 bytes in VMCB + * control area to expose SVM enlightenments to guests. + */ +struct hv_enlightenments { + struct __packed hv_enlightenments_control { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 enlightened_npt_tlb: 1; + u32 reserved:29; + } __packed hv_enlightenments_control; + u32 hv_vp_id; + u64 hv_vm_id; + u64 partition_assist_page; + u64 reserved; +} __packed; + +/* + * Hyper-V uses the software reserved clean bit in VMCB + */ +#define VMCB_HV_NESTED_ENLIGHTENMENTS VMCB_SW + +int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu); + +static inline void svm_hv_init_vmcb(struct vmcb *vmcb) +{ + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + + if (npt_enabled && + ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) + hve->hv_enlightenments_control.enlightened_npt_tlb = 1; +} + +static inline void svm_hv_hardware_setup(void) +{ + if (npt_enabled && + ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) { + pr_info("kvm: Hyper-V enlightened NPT TLB flush enabled\n"); + svm_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; + svm_x86_ops.tlb_remote_flush_with_range = + hv_remote_flush_tlb_with_range; + } + + if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) { + int cpu; + + pr_info("kvm: Hyper-V Direct TLB Flush enabled\n"); + for_each_online_cpu(cpu) { + struct hv_vp_assist_page *vp_ap = + hv_get_vp_assist_page(cpu); + + if (!vp_ap) + continue; + + vp_ap->nested_control.features.directhypercall = 1; + } + svm_x86_ops.enable_direct_tlbflush = + svm_hv_enable_direct_tlbflush; + } +} + +static inline void svm_hv_vmcb_dirty_nested_enlightenments( + struct kvm_vcpu *vcpu) +{ + struct vmcb *vmcb = to_svm(vcpu)->vmcb; + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + + /* + * vmcb can be NULL if called during early vcpu init. + * And its okay not to mark vmcb dirty during vcpu init + * as we mark it dirty unconditionally towards end of vcpu + * init phase. + */ + if (vmcb && vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) && + hve->hv_enlightenments_control.msr_bitmap) + vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); +} + +static inline void svm_hv_update_vp_id(struct vmcb *vmcb, + struct kvm_vcpu *vcpu) +{ + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + u32 vp_index = kvm_hv_get_vpindex(vcpu); + + if (hve->hv_vp_id != vp_index) { + hve->hv_vp_id = vp_index; + vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); + } +} +#else + +static inline void svm_hv_init_vmcb(struct vmcb *vmcb) +{ +} + +static inline void svm_hv_hardware_setup(void) +{ +} + +static inline void svm_hv_vmcb_dirty_nested_enlightenments( + struct kvm_vcpu *vcpu) +{ +} + +static inline void svm_hv_update_vp_id(struct vmcb *vmcb, + struct kvm_vcpu *vcpu) +{ +} +#endif /* CONFIG_HYPERV */ + +#endif /* __ARCH_X86_KVM_SVM_ONHYPERV_H__ */ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index a61c015870e3..b484141ea15b 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -997,7 +997,7 @@ TRACE_EVENT(kvm_wait_lapic_expire, __entry->delta < 0 ? "early" : "late") ); -TRACE_EVENT(kvm_enter_smm, +TRACE_EVENT(kvm_smm_transition, TP_PROTO(unsigned int vcpu_id, u64 smbase, bool entering), TP_ARGS(vcpu_id, smbase, entering), @@ -1550,16 +1550,16 @@ TRACE_EVENT(kvm_nested_vmenter_failed, TP_ARGS(msg, err), TP_STRUCT__entry( - __field(const char *, msg) + __string(msg, msg) __field(u32, err) ), TP_fast_assign( - __entry->msg = msg; + __assign_str(msg, msg); __entry->err = err; ), - TP_printk("%s%s", __entry->msg, !__entry->err ? "" : + TP_printk("%s%s", __get_str(msg), !__entry->err ? "" : __print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS)) ); diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index d1d77985e889..4705ad55abb5 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -12,7 +12,6 @@ extern bool __read_mostly enable_ept; extern bool __read_mostly enable_unrestricted_guest; extern bool __read_mostly enable_ept_ad_bits; extern bool __read_mostly enable_pml; -extern bool __read_mostly enable_apicv; extern int __read_mostly pt_mode; #define PT_MODE_SYSTEM 0 @@ -90,8 +89,7 @@ static inline bool cpu_has_vmx_preemption_timer(void) static inline bool cpu_has_vmx_posted_intr(void) { - return IS_ENABLED(CONFIG_X86_LOCAL_APIC) && - vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; + return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; } static inline bool cpu_has_load_ia32_efer(void) @@ -398,6 +396,9 @@ static inline u64 vmx_supported_debugctl(void) { u64 debugctl = 0; + if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) + debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; + if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) debugctl |= DEBUGCTLMSR_LBR_MASK; diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 41f24661af04..896b2a50b4aa 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -319,6 +319,9 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa) if (unlikely(!assist_page.enlighten_vmentry)) return false; + if (unlikely(!evmptr_is_valid(assist_page.current_nested_vmcs))) + return false; + *evmcs_gpa = assist_page.current_nested_vmcs; return true; diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index bd41d9462355..2ec9b46f0d0c 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -197,6 +197,14 @@ static inline void evmcs_load(u64 phys_addr) {} static inline void evmcs_touch_msr_bitmap(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ +#define EVMPTR_INVALID (-1ULL) +#define EVMPTR_MAP_PENDING (-2ULL) + +static inline bool evmptr_is_valid(u64 evmptr) +{ + return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING; +} + enum nested_evmptrld_status { EVMPTRLD_DISABLED, EVMPTRLD_SUCCEEDED, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index bced76637823..1a52134b0c42 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -173,9 +173,13 @@ static int nested_vmx_failValid(struct kvm_vcpu *vcpu, | X86_EFLAGS_ZF); get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error; /* - * We don't need to force a shadow sync because - * VM_INSTRUCTION_ERROR is not shadowed + * We don't need to force sync to shadow VMCS because + * VM_INSTRUCTION_ERROR is not shadowed. Enlightened VMCS 'shadows' all + * fields and thus must be synced. */ + if (to_vmx(vcpu)->nested.hv_evmcs_vmptr != EVMPTR_INVALID) + to_vmx(vcpu)->nested.need_vmcs12_to_shadow_sync = true; + return kvm_skip_emulated_instruction(vcpu); } @@ -187,7 +191,8 @@ static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error) * failValid writes the error number to the current VMCS, which * can't be done if there isn't a current VMCS. */ - if (vmx->nested.current_vmptr == -1ull && !vmx->nested.hv_evmcs) + if (vmx->nested.current_vmptr == -1ull && + !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) return nested_vmx_failInvalid(vcpu); return nested_vmx_failValid(vcpu, vm_instruction_error); @@ -221,12 +226,12 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!vmx->nested.hv_evmcs) - return; + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); + vmx->nested.hv_evmcs = NULL; + } - kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); - vmx->nested.hv_evmcs_vmptr = 0; - vmx->nested.hv_evmcs = NULL; + vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; } static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, @@ -346,16 +351,21 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, vmcs12->guest_physical_address = fault->address; } +static void nested_ept_new_eptp(struct kvm_vcpu *vcpu) +{ + kvm_init_shadow_ept_mmu(vcpu, + to_vmx(vcpu)->nested.msrs.ept_caps & + VMX_EPT_EXECUTE_ONLY_BIT, + nested_ept_ad_enabled(vcpu), + nested_ept_get_eptp(vcpu)); +} + static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) { WARN_ON(mmu_is_nested(vcpu)); vcpu->arch.mmu = &vcpu->arch.guest_mmu; - kvm_init_shadow_ept_mmu(vcpu, - to_vmx(vcpu)->nested.msrs.ept_caps & - VMX_EPT_EXECUTE_ONLY_BIT, - nested_ept_ad_enabled(vcpu), - nested_ept_get_eptp(vcpu)); + nested_ept_new_eptp(vcpu); vcpu->arch.mmu->get_guest_pgd = nested_ept_get_eptp; vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault; vcpu->arch.mmu->get_pdptr = kvm_pdptr_read; @@ -1058,54 +1068,13 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, } /* - * Returns true if the MMU needs to be sync'd on nested VM-Enter/VM-Exit. - * tl;dr: the MMU needs a sync if L0 is using shadow paging and L1 didn't - * enable VPID for L2 (implying it expects a TLB flush on VMX transitions). - * Here's why. - * - * If EPT is enabled by L0 a sync is never needed: - * - if it is disabled by L1, then L0 is not shadowing L1 or L2 PTEs, there - * cannot be unsync'd SPTEs for either L1 or L2. - * - * - if it is also enabled by L1, then L0 doesn't need to sync on VM-Enter - * VM-Enter as VM-Enter isn't required to invalidate guest-physical mappings - * (irrespective of VPID), i.e. L1 can't rely on the (virtual) CPU to flush - * stale guest-physical mappings for L2 from the TLB. And as above, L0 isn't - * shadowing L1 PTEs so there are no unsync'd SPTEs to sync on VM-Exit. - * - * If EPT is disabled by L0: - * - if VPID is enabled by L1 (for L2), the situation is similar to when L1 - * enables EPT: L0 doesn't need to sync as VM-Enter and VM-Exit aren't - * required to invalidate linear mappings (EPT is disabled so there are - * no combined or guest-physical mappings), i.e. L1 can't rely on the - * (virtual) CPU to flush stale linear mappings for either L2 or itself (L1). - * - * - however if VPID is disabled by L1, then a sync is needed as L1 expects all - * linear mappings (EPT is disabled so there are no combined or guest-physical - * mappings) to be invalidated on both VM-Enter and VM-Exit. - * - * Note, this logic is subtly different than nested_has_guest_tlb_tag(), which - * additionally checks that L2 has been assigned a VPID (when EPT is disabled). - * Whether or not L2 has been assigned a VPID by L0 is irrelevant with respect - * to L1's expectations, e.g. L0 needs to invalidate hardware TLB entries if L2 - * doesn't have a unique VPID to prevent reusing L1's entries (assuming L1 has - * been assigned a VPID), but L0 doesn't need to do a MMU sync because L1 - * doesn't expect stale (virtual) TLB entries to be flushed, i.e. L1 doesn't - * know that L0 will flush the TLB and so L1 will do INVVPID as needed to flush - * stale TLB entries, at which point L0 will sync L2's MMU. - */ -static bool nested_vmx_transition_mmu_sync(struct kvm_vcpu *vcpu) -{ - return !enable_ept && !nested_cpu_has_vpid(get_vmcs12(vcpu)); -} - -/* * Load guest's/host's cr3 at nested entry/exit. @nested_ept is true if we are * emulating VM-Entry into a guest with EPT enabled. On failure, the expected * Exit Qualification (for a VM-Entry consistency check VM-Exit) is assigned to * @entry_failure_code. */ -static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, +static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, + bool nested_ept, bool reload_pdptrs, enum vm_entry_failure_code *entry_failure_code) { if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) { @@ -1117,27 +1086,20 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * If PAE paging and EPT are both on, CR3 is not used by the CPU and * must not be dereferenced. */ - if (!nested_ept && is_pae_paging(vcpu) && - (cr3 != kvm_read_cr3(vcpu) || pdptrs_changed(vcpu))) { - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { - *entry_failure_code = ENTRY_FAIL_PDPTE; - return -EINVAL; - } + if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) && + CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { + *entry_failure_code = ENTRY_FAIL_PDPTE; + return -EINVAL; } - /* - * Unconditionally skip the TLB flush on fast CR3 switch, all TLB - * flushes are handled by nested_vmx_transition_tlb_flush(). See - * nested_vmx_transition_mmu_sync for details on skipping the MMU sync. - */ if (!nested_ept) - kvm_mmu_new_pgd(vcpu, cr3, true, - !nested_vmx_transition_mmu_sync(vcpu)); + kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); - kvm_init_mmu(vcpu, false); + /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ + kvm_init_mmu(vcpu); return 0; } @@ -1170,17 +1132,28 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx = to_vmx(vcpu); /* - * If VPID is disabled, linear and combined mappings are flushed on - * VM-Enter/VM-Exit, and guest-physical mappings are valid only for - * their associated EPTP. + * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings + * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a + * full TLB flush from the guest's perspective. This is required even + * if VPID is disabled in the host as KVM may need to synchronize the + * MMU in response to the guest TLB flush. + * + * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use. + * EPT is a special snowflake, as guest-physical mappings aren't + * flushed on VPID invalidations, including VM-Enter or VM-Exit with + * VPID disabled. As a result, KVM _never_ needs to sync nEPT + * entries on VM-Enter because L1 can't rely on VM-Enter to flush + * those mappings. */ - if (!enable_vpid) + if (!nested_cpu_has_vpid(vmcs12)) { + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return; + } + + /* L2 should never have a VPID if VPID is disabled. */ + WARN_ON(!enable_vpid); /* - * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings - * for *all* contexts to be flushed on VM-Enter/VM-Exit. - * * If VPID is enabled and used by vmc12, but L2 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 @@ -1192,13 +1165,12 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, * * 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 sync'd. There is no direct + * "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. + * 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_cpu_has_vpid(vmcs12)) { - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - } else if (!nested_has_guest_tlb_tag(vcpu)) { + if (!nested_has_guest_tlb_tag(vcpu)) { kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } else if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) { @@ -1586,7 +1558,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) vmcs_load(vmx->loaded_vmcs->vmcs); } -static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) +static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields) { struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; @@ -1595,7 +1567,7 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) vmcs12->tpr_threshold = evmcs->tpr_threshold; vmcs12->guest_rip = evmcs->guest_rip; - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) { vmcs12->guest_rsp = evmcs->guest_rsp; vmcs12->guest_rflags = evmcs->guest_rflags; @@ -1603,23 +1575,23 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) evmcs->guest_interruptibility_info; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) { vmcs12->cpu_based_vm_exec_control = evmcs->cpu_based_vm_exec_control; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN))) { vmcs12->exception_bitmap = evmcs->exception_bitmap; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY))) { vmcs12->vm_entry_controls = evmcs->vm_entry_controls; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT))) { vmcs12->vm_entry_intr_info_field = evmcs->vm_entry_intr_info_field; @@ -1629,7 +1601,7 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) evmcs->vm_entry_instruction_len; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) { vmcs12->host_ia32_pat = evmcs->host_ia32_pat; vmcs12->host_ia32_efer = evmcs->host_ia32_efer; @@ -1649,7 +1621,7 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) vmcs12->host_tr_selector = evmcs->host_tr_selector; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1))) { vmcs12->pin_based_vm_exec_control = evmcs->pin_based_vm_exec_control; @@ -1658,18 +1630,18 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) evmcs->secondary_vm_exec_control; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP))) { vmcs12->io_bitmap_a = evmcs->io_bitmap_a; vmcs12->io_bitmap_b = evmcs->io_bitmap_b; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP))) { vmcs12->msr_bitmap = evmcs->msr_bitmap; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2))) { vmcs12->guest_es_base = evmcs->guest_es_base; vmcs12->guest_cs_base = evmcs->guest_cs_base; @@ -1709,14 +1681,14 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) vmcs12->guest_tr_selector = evmcs->guest_tr_selector; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2))) { vmcs12->tsc_offset = evmcs->tsc_offset; vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr; vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR))) { vmcs12->cr0_guest_host_mask = evmcs->cr0_guest_host_mask; vmcs12->cr4_guest_host_mask = evmcs->cr4_guest_host_mask; @@ -1728,7 +1700,7 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) vmcs12->guest_dr7 = evmcs->guest_dr7; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER))) { vmcs12->host_fs_base = evmcs->host_fs_base; vmcs12->host_gs_base = evmcs->host_gs_base; @@ -1738,13 +1710,13 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) vmcs12->host_rsp = evmcs->host_rsp; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT))) { vmcs12->ept_pointer = evmcs->ept_pointer; vmcs12->virtual_processor_id = evmcs->virtual_processor_id; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1))) { vmcs12->vmcs_link_pointer = evmcs->vmcs_link_pointer; vmcs12->guest_ia32_debugctl = evmcs->guest_ia32_debugctl; @@ -1799,10 +1771,10 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) * vmcs12->exit_io_instruction_eip = evmcs->exit_io_instruction_eip; */ - return 0; + return; } -static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) +static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) { struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; @@ -1962,7 +1934,7 @@ static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs; - return 0; + return; } /* @@ -1979,13 +1951,13 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( if (likely(!vmx->nested.enlightened_vmcs_enabled)) return EVMPTRLD_DISABLED; - if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) + if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) { + nested_release_evmcs(vcpu); return EVMPTRLD_DISABLED; + } - if (unlikely(!vmx->nested.hv_evmcs || - evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { - if (!vmx->nested.hv_evmcs) - vmx->nested.current_vmptr = -1ull; + if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { + vmx->nested.current_vmptr = -1ull; nested_release_evmcs(vcpu); @@ -2023,7 +1995,6 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( return EVMPTRLD_VMFAIL; } - vmx->nested.dirty_vmcs12 = true; vmx->nested.hv_evmcs_vmptr = evmcs_gpa; evmcs_gpa_changed = true; @@ -2056,14 +2027,10 @@ void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vmx->nested.hv_evmcs) { + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) copy_vmcs12_to_enlightened(vmx); - /* All fields are clean */ - vmx->nested.hv_evmcs->hv_clean_fields |= - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; - } else { + else copy_vmcs12_to_shadow(vmx); - } vmx->nested.need_vmcs12_to_shadow_sync = false; } @@ -2208,7 +2175,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) u32 exec_control; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); - if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs) + if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) prepare_vmcs02_early_rare(vmx, vmcs12); /* @@ -2277,7 +2244,8 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_ENABLE_VMFUNC); + SECONDARY_EXEC_ENABLE_VMFUNC | + SECONDARY_EXEC_TSC_SCALING); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -2488,18 +2456,18 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * is assigned to entry_failure_code on failure. */ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + bool from_vmentry, enum vm_entry_failure_code *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs; bool load_guest_pdptrs_vmcs12 = false; - if (vmx->nested.dirty_vmcs12 || hv_evmcs) { + if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { prepare_vmcs02_rare(vmx, vmcs12); vmx->nested.dirty_vmcs12 = false; - load_guest_pdptrs_vmcs12 = !hv_evmcs || - !(hv_evmcs->hv_clean_fields & + load_guest_pdptrs_vmcs12 = !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) || + !(vmx->nested.hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); } @@ -2532,10 +2500,18 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); } - vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); + vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( + vcpu->arch.l1_tsc_offset, + vmx_get_l2_tsc_offset(vcpu), + vmx_get_l2_tsc_multiplier(vcpu)); + + vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier( + vcpu->arch.l1_tsc_scaling_ratio, + vmx_get_l2_tsc_multiplier(vcpu)); + vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); if (kvm_has_tsc_control) - decache_tsc_multiplier(vmx); + vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); nested_vmx_transition_tlb_flush(vcpu, vmcs12, true); @@ -2572,7 +2548,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, /* Shadow page tables on either EPT or shadow page tables. */ if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12), - entry_failure_code)) + from_vmentry, entry_failure_code)) return -EINVAL; /* @@ -2604,6 +2580,17 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, kvm_rsp_write(vcpu, vmcs12->guest_rsp); kvm_rip_write(vcpu, vmcs12->guest_rip); + + /* + * It was observed that genuine Hyper-V running in L1 doesn't reset + * 'hv_clean_fields' by itself, it only sets the corresponding dirty + * bits when it changes a field in eVMCS. Mark all fields as clean + * here. + */ + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + vmx->nested.hv_evmcs->hv_clean_fields |= + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + return 0; } @@ -3093,20 +3080,20 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) * L2 was running), map it here to make sure vmcs12 changes are * properly reflected. */ - if (vmx->nested.enlightened_vmcs_enabled && !vmx->nested.hv_evmcs) { + if (vmx->nested.enlightened_vmcs_enabled && + vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) { enum nested_evmptrld_status evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, false); if (evmptrld_status == EVMPTRLD_VMFAIL || - evmptrld_status == EVMPTRLD_ERROR) { - pr_debug_ratelimited("%s: enlightened vmptrld failed\n", - __func__); - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + evmptrld_status == EVMPTRLD_ERROR) return false; - } + + /* + * Post migration VMCS12 always provides the most actual + * information, copy it to eVMCS upon entry. + */ + vmx->nested.need_vmcs12_to_shadow_sync = true; } return true; @@ -3120,6 +3107,18 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) struct page *page; u64 hpa; + if (!vcpu->arch.pdptrs_from_userspace && + !nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { + /* + * Reload the guest's PDPTRs since after a migration + * the guest CR3 might be restored prior to setting the nested + * state which can lead to a load of wrong PDPTRs. + */ + if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + return false; + } + + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { /* * Translate L1 physical address to host physical @@ -3182,6 +3181,15 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) offset_in_page(vmcs12->posted_intr_desc_addr)); vmcs_write64(POSTED_INTR_DESC_ADDR, pfn_to_hpa(map->pfn) + offset_in_page(vmcs12->posted_intr_desc_addr)); + } else { + /* + * Defer the KVM_INTERNAL_EXIT until KVM tries to + * access the contents of the VMCS12 posted interrupt + * descriptor. (Note that KVM may do this when it + * should not, per the architectural specification.) + */ + vmx->nested.pi_desc = NULL; + pin_controls_clearbit(vmx, PIN_BASED_POSTED_INTR); } } if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) @@ -3194,8 +3202,16 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { - if (!nested_get_evmcs_page(vcpu)) + if (!nested_get_evmcs_page(vcpu)) { + pr_debug_ratelimited("%s: enlightened vmptrld failed\n", + __func__); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return false; + } if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) return false; @@ -3353,10 +3369,8 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, } enter_guest_mode(vcpu); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) - vcpu->arch.tsc_offset += vmcs12->tsc_offset; - if (prepare_vmcs02(vcpu, vmcs12, &entry_failure_code)) { + if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &entry_failure_code)) { exit_reason.basic = EXIT_REASON_INVALID_STATE; vmcs12->exit_qualification = entry_failure_code; goto vmentry_fail_vmexit_guest_mode; @@ -3436,7 +3450,7 @@ vmentry_fail_vmexit: load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason.full; - if (enable_shadow_vmcs || vmx->nested.hv_evmcs) + if (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) vmx->nested.need_vmcs12_to_shadow_sync = true; return NVMX_VMENTRY_VMEXIT; } @@ -3453,8 +3467,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu); enum nested_evmptrld_status evmptrld_status; - ++vcpu->stat.nested_run; - if (!nested_vmx_check_permission(vcpu)) return 1; @@ -3466,7 +3478,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return nested_vmx_failInvalid(vcpu); } - if (CC(!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull)) + if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) && + vmx->nested.current_vmptr == -1ull)) return nested_vmx_failInvalid(vcpu); vmcs12 = get_vmcs12(vcpu); @@ -3480,8 +3493,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (CC(vmcs12->hdr.shadow_vmcs)) return nested_vmx_failInvalid(vcpu); - if (vmx->nested.hv_evmcs) { - copy_enlightened_to_vmcs12(vmx); + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + copy_enlightened_to_vmcs12(vmx, vmx->nested.hv_evmcs->hv_clean_fields); /* Enlightened VMCS doesn't have launch state */ vmcs12->launch_state = !launch; } else if (enable_shadow_vmcs) { @@ -3681,25 +3694,29 @@ void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) } } -static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) +static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; void *vapic_page; u16 status; - if (!vmx->nested.pi_desc || !vmx->nested.pi_pending) - return; + if (!vmx->nested.pi_pending) + return 0; + + if (!vmx->nested.pi_desc) + goto mmio_needed; vmx->nested.pi_pending = false; + if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return; + return 0; max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); if (max_irr != 256) { vapic_page = vmx->nested.virtual_apic_map.hva; if (!vapic_page) - return; + goto mmio_needed; __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page, &max_irr); @@ -3712,6 +3729,11 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) } nested_mark_vmcs12_pages_dirty(vcpu); + return 0; + +mmio_needed: + kvm_handle_memory_failure(vcpu, X86EMUL_IO_NEEDED, NULL); + return -ENXIO; } static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, @@ -3886,8 +3908,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) } no_vmexit: - vmx_complete_nested_posted_interrupt(vcpu); - return 0; + return vmx_complete_nested_posted_interrupt(vcpu); } static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) @@ -4031,10 +4052,11 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vmx->nested.hv_evmcs) + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - vmx->nested.need_sync_vmcs02_to_vmcs12_rare = !vmx->nested.hv_evmcs; + vmx->nested.need_sync_vmcs02_to_vmcs12_rare = + !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr); vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); @@ -4205,7 +4227,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * Only PDPTE load can fail as the value of cr3 was checked on entry and * couldn't have changed. */ - if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &ignored)) + if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, true, &ignored)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); nested_vmx_transition_tlb_flush(vcpu, vmcs12, false); @@ -4435,7 +4457,15 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* Similarly, triple faults in L2 should never escape. */ WARN_ON_ONCE(kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)); - kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { + /* + * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map + * Enlightened VMCS after migration and we still need to + * do that when something is forcing L2->L1 exit prior to + * the first L2 run. + */ + (void)nested_get_evmcs_page(vcpu); + } /* Service the TLB flush request for L2 before switching to L1. */ if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) @@ -4454,8 +4484,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, if (nested_cpu_has_preemption_timer(vmcs12)) hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) - vcpu->arch.tsc_offset -= vmcs12->tsc_offset; + if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING)) { + vcpu->arch.tsc_offset = vcpu->arch.l1_tsc_offset; + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING)) + vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio; + } if (likely(!vmx->fail)) { sync_vmcs02_to_vmcs12(vcpu, vmcs12); @@ -4492,12 +4525,12 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); + if (kvm_has_tsc_control) + vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); + if (vmx->nested.l1_tpr_threshold != -1) vmcs_write32(TPR_THRESHOLD, vmx->nested.l1_tpr_threshold); - if (kvm_has_tsc_control) - decache_tsc_multiplier(vmx); - if (vmx->nested.change_vmcs01_virtual_apic_mode) { vmx->nested.change_vmcs01_virtual_apic_mode = false; vmx_set_virtual_apic_mode(vcpu); @@ -4523,7 +4556,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, } if ((vm_exit_reason != -1) && - (enable_shadow_vmcs || vmx->nested.hv_evmcs)) + (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))) vmx->nested.need_vmcs12_to_shadow_sync = true; /* in case we halted in L2 */ @@ -4978,6 +5011,8 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); + } else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) { + nested_release_evmcs(vcpu); } return nested_vmx_succeed(vcpu); @@ -5219,7 +5254,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_VMXON_POINTER); /* Forbid normal VMPTRLD if Enlightened version was used */ - if (vmx->nested.hv_evmcs) + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) return 1; if (vmx->nested.current_vmptr != vmptr) { @@ -5275,7 +5310,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (unlikely(to_vmx(vcpu)->nested.hv_evmcs)) + if (unlikely(evmptr_is_valid(to_vmx(vcpu)->nested.hv_evmcs_vmptr))) return 1; if (get_vmx_mem_address(vcpu, exit_qual, instr_info, @@ -5452,8 +5487,8 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) /* * Sync the shadow page tables if EPT is disabled, L1 is invalidating - * linear mappings for L2 (tagged with L2's VPID). Free all roots as - * VPIDs are not tracked in the MMU role. + * linear mappings for L2 (tagged with L2's VPID). Free all guest + * roots as VPIDs are not tracked in the MMU role. * * Note, this operates on root_mmu, not guest_mmu, as L1 and L2 share * an MMU when EPT is disabled. @@ -5461,8 +5496,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) * TODO: sync only the affected SPTEs for INVDIVIDUAL_ADDR. */ if (!enable_ept) - kvm_mmu_free_roots(vcpu, &vcpu->arch.root_mmu, - KVM_MMU_ROOTS_ALL); + kvm_mmu_free_guest_mode_roots(vcpu, &vcpu->arch.root_mmu); return nested_vmx_succeed(vcpu); } @@ -5472,23 +5506,16 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu, { u32 index = kvm_rcx_read(vcpu); u64 new_eptp; - bool accessed_dirty; - struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - if (!nested_cpu_has_eptp_switching(vmcs12) || - !nested_cpu_has_ept(vmcs12)) + if (WARN_ON_ONCE(!nested_cpu_has_ept(vmcs12))) return 1; - if (index >= VMFUNC_EPTP_ENTRIES) return 1; - if (kvm_vcpu_read_guest_page(vcpu, vmcs12->eptp_list_address >> PAGE_SHIFT, &new_eptp, index * 8, 8)) return 1; - accessed_dirty = !!(new_eptp & VMX_EPTP_AD_ENABLE_BIT); - /* * If the (L2) guest does a vmfunc to the currently * active ept pointer, we don't have to do anything else @@ -5497,11 +5524,11 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu, if (!nested_vmx_check_eptp(vcpu, new_eptp)) return 1; - mmu->ept_ad = accessed_dirty; - mmu->mmu_role.base.ad_disabled = !accessed_dirty; vmcs12->ept_pointer = new_eptp; + nested_ept_new_eptp(vcpu); - kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); + if (!nested_cpu_has_vpid(vmcs12)) + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } return 0; @@ -5524,7 +5551,17 @@ static int handle_vmfunc(struct kvm_vcpu *vcpu) } vmcs12 = get_vmcs12(vcpu); - if ((vmcs12->vm_function_control & (1 << function)) == 0) + + /* + * #UD on out-of-bounds function has priority over VM-Exit, and VMFUNC + * is enabled in vmcs02 if and only if it's enabled in vmcs12. + */ + if (WARN_ON_ONCE((function > 63) || !nested_cpu_has_vmfunc(vmcs12))) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + if (!(vmcs12->vm_function_control & BIT_ULL(function))) goto fail; switch (function) { @@ -5797,6 +5834,9 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, else if (is_breakpoint(intr_info) && vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) return true; + else if (is_alignment_check(intr_info) && + !vmx_guest_inject_ac(vcpu)) + return true; return false; case EXIT_REASON_EXTERNAL_INTERRUPT: return true; @@ -6047,7 +6087,8 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (vmx_has_valid_vmcs12(vcpu)) { kvm_state.size += sizeof(user_vmx_nested_state->vmcs12); - if (vmx->nested.hv_evmcs) + /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ + if (vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID) kvm_state.flags |= KVM_STATE_NESTED_EVMCS; if (is_guest_mode(vcpu) && @@ -6103,8 +6144,15 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, } else { copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); if (!vmx->nested.need_vmcs12_to_shadow_sync) { - if (vmx->nested.hv_evmcs) - copy_enlightened_to_vmcs12(vmx); + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + /* + * L1 hypervisor is not obliged to keep eVMCS + * clean fields data always up-to-date while + * not in guest mode, 'hv_clean_fields' is only + * supposed to be actual upon vmentry so we need + * to ignore it here and do full copy. + */ + copy_enlightened_to_vmcs12(vmx, 0); else if (enable_shadow_vmcs) copy_shadow_to_vmcs12(vmx); } @@ -6246,6 +6294,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, * restored yet. EVMCS will be mapped from * nested_get_vmcs12_pages(). */ + vmx->nested.hv_evmcs_vmptr = EVMPTR_MAP_PENDING; kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); } else { return -EINVAL; @@ -6330,6 +6379,40 @@ void nested_vmx_set_vmcs_shadowing_bitmap(void) } /* + * Indexing into the vmcs12 uses the VMCS encoding rotated left by 6. Undo + * that madness to get the encoding for comparison. + */ +#define VMCS12_IDX_TO_ENC(idx) ((u16)(((u16)(idx) >> 6) | ((u16)(idx) << 10))) + +static u64 nested_vmx_calc_vmcs_enum_msr(void) +{ + /* + * Note these are the so called "index" of the VMCS field encoding, not + * the index into vmcs12. + */ + unsigned int max_idx, idx; + int i; + + /* + * For better or worse, KVM allows VMREAD/VMWRITE to all fields in + * vmcs12, regardless of whether or not the associated feature is + * exposed to L1. Simply find the field with the highest index. + */ + max_idx = 0; + for (i = 0; i < nr_vmcs12_fields; i++) { + /* The vmcs12 table is very, very sparsely populated. */ + if (!vmcs_field_to_offset_table[i]) + continue; + + idx = vmcs_field_index(VMCS12_IDX_TO_ENC(i)); + if (idx > max_idx) + max_idx = idx; + } + + return (u64)max_idx << VMCS_FIELD_INDEX_SHIFT; +} + +/* * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be * returned for the various VMX controls MSRs when nested VMX is enabled. * The same values should also be used to verify that vmcs12 control fields are @@ -6465,7 +6548,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) SECONDARY_EXEC_RDRAND_EXITING | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_RDSEED_EXITING | - SECONDARY_EXEC_XSAVES; + SECONDARY_EXEC_XSAVES | + SECONDARY_EXEC_TSC_SCALING; /* * We can emulate "VMCS shadowing," even if the hardware @@ -6573,8 +6657,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) rdmsrl(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1); rdmsrl(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1); - /* highest index: VMX_PREEMPTION_TIMER_VALUE */ - msrs->vmcs_enum = VMCS12_MAX_FIELD_INDEX << 1; + msrs->vmcs_enum = nested_vmx_calc_vmcs_enum_msr(); } void nested_vmx_hardware_unsetup(void) diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 184418baeb3c..b69a80f43b37 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -56,14 +56,9 @@ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * In case we do two consecutive get/set_nested_state()s while L2 was - * running hv_evmcs may end up not being mapped (we map it from - * nested_vmx_run()/vmx_vcpu_run()). Check is_guest_mode() as we always - * have vmcs12 if it is true. - */ - return is_guest_mode(vcpu) || vmx->nested.current_vmptr != -1ull || - vmx->nested.hv_evmcs; + /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ + return vmx->nested.current_vmptr != -1ull || + vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID; } static inline u16 nested_get_vpid02(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 459748680daf..5f81ef092bd4 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -238,6 +238,20 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu) /* + * Bail out of the block loop if the VM has an assigned + * device, but the blocking vCPU didn't reconfigure the + * PI.NV to the wakeup vector, i.e. the assigned device + * came along after the initial check in pi_pre_block(). + */ +void vmx_pi_start_assignment(struct kvm *kvm) +{ + if (!irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK); +} + +/* * pi_update_irte - set IRTE for Posted-Interrupts * * @kvm: kvm diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 0bdc41391c5b..7f7b2326caf5 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -95,5 +95,6 @@ void __init pi_init_cpu(int cpu); bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu); int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); +void vmx_pi_start_assignment(struct kvm *kvm); #endif /* __KVM_X86_VMX_POSTED_INTR_H */ diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 1472c6c376f7..4b9957e2bf5b 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -117,6 +117,11 @@ static inline bool is_gp_fault(u32 intr_info) return is_exception_n(intr_info, GP_VECTOR); } +static inline bool is_alignment_check(u32 intr_info) +{ + return is_exception_n(intr_info, AC_VECTOR); +} + static inline bool is_machine_check(u32 intr_info) { return is_exception_n(intr_info, MC_VECTOR); @@ -164,4 +169,12 @@ static inline int vmcs_field_readonly(unsigned long field) return (((field >> 10) & 0x3) == 1); } +#define VMCS_FIELD_INDEX_SHIFT (1) +#define VMCS_FIELD_INDEX_MASK GENMASK(9, 1) + +static inline unsigned int vmcs_field_index(unsigned long field) +{ + return (field & VMCS_FIELD_INDEX_MASK) >> VMCS_FIELD_INDEX_SHIFT; +} + #endif /* __KVM_X86_VMX_VMCS_H */ diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c index 034adb6404dc..d9f5d7c56ae3 100644 --- a/arch/x86/kvm/vmx/vmcs12.c +++ b/arch/x86/kvm/vmx/vmcs12.c @@ -37,6 +37,7 @@ const unsigned short vmcs_field_to_offset_table[] = { FIELD64(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr), FIELD64(PML_ADDRESS, pml_address), FIELD64(TSC_OFFSET, tsc_offset), + FIELD64(TSC_MULTIPLIER, tsc_multiplier), FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr), FIELD64(APIC_ACCESS_ADDR, apic_access_addr), FIELD64(POSTED_INTR_DESC_ADDR, posted_intr_desc_addr), diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index 13494956d0e9..5e0e1b39f495 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -70,7 +70,8 @@ struct __packed vmcs12 { u64 eptp_list_address; u64 pml_address; u64 encls_exiting_bitmap; - u64 padding64[2]; /* room for future expansion */ + u64 tsc_multiplier; + u64 padding64[1]; /* room for future expansion */ /* * To allow migration of L1 (complete with its L2 guests) between * machines of different natural widths (32 or 64 bit), we cannot have @@ -205,12 +206,6 @@ struct __packed vmcs12 { #define VMCS12_SIZE KVM_STATE_NESTED_VMX_VMCS_SIZE /* - * VMCS12_MAX_FIELD_INDEX is the highest index value used in any - * supported VMCS12 field encoding. - */ -#define VMCS12_MAX_FIELD_INDEX 0x17 - -/* * For save/restore compatibility, the vmcs12 field offsets must not change. */ #define CHECK_OFFSET(field, loc) \ @@ -258,6 +253,7 @@ static inline void vmx_check_vmcs12_offsets(void) CHECK_OFFSET(eptp_list_address, 304); CHECK_OFFSET(pml_address, 312); CHECK_OFFSET(encls_exiting_bitmap, 320); + CHECK_OFFSET(tsc_multiplier, 328); CHECK_OFFSET(cr0_guest_host_mask, 344); CHECK_OFFSET(cr4_guest_host_mask, 352); CHECK_OFFSET(cr0_read_shadow, 360); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d000cddbd734..927a552393b9 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -52,6 +52,7 @@ #include "cpuid.h" #include "evmcs.h" #include "hyperv.h" +#include "kvm_onhyperv.h" #include "irq.h" #include "kvm_cache_regs.h" #include "lapic.h" @@ -101,7 +102,6 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); -bool __read_mostly enable_apicv = 1; module_param(enable_apicv, bool, S_IRUGO); /* @@ -455,105 +455,10 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static unsigned long host_idt_base; -/* - * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm - * will emulate SYSCALL in legacy mode if the vendor string in guest - * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To - * support this emulation, IA32_STAR must always be included in - * vmx_uret_msrs_list[], even in i386 builds. - */ -static const u32 vmx_uret_msrs_list[] = { -#ifdef CONFIG_X86_64 - MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, -#endif - MSR_EFER, MSR_TSC_AUX, MSR_STAR, - MSR_IA32_TSX_CTRL, -}; - #if IS_ENABLED(CONFIG_HYPERV) static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); -static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush, - void *data) -{ - struct kvm_tlb_range *range = data; - - return hyperv_fill_flush_guest_mapping_list(flush, range->start_gfn, - range->pages); -} - -static inline int hv_remote_flush_root_ept(hpa_t root_ept, - struct kvm_tlb_range *range) -{ - if (range) - return hyperv_flush_guest_mapping_range(root_ept, - kvm_fill_hv_flush_list_func, (void *)range); - else - return hyperv_flush_guest_mapping(root_ept); -} - -static int hv_remote_flush_tlb_with_range(struct kvm *kvm, - struct kvm_tlb_range *range) -{ - struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); - struct kvm_vcpu *vcpu; - int ret = 0, i, nr_unique_valid_roots; - hpa_t root; - - spin_lock(&kvm_vmx->hv_root_ept_lock); - - if (!VALID_PAGE(kvm_vmx->hv_root_ept)) { - nr_unique_valid_roots = 0; - - /* - * Flush all valid roots, and see if all vCPUs have converged - * on a common root, in which case future flushes can skip the - * loop and flush the common root. - */ - kvm_for_each_vcpu(i, vcpu, kvm) { - root = to_vmx(vcpu)->hv_root_ept; - if (!VALID_PAGE(root) || root == kvm_vmx->hv_root_ept) - continue; - - /* - * Set the tracked root to the first valid root. Keep - * this root for the entirety of the loop even if more - * roots are encountered as a low effort optimization - * to avoid flushing the same (first) root again. - */ - if (++nr_unique_valid_roots == 1) - kvm_vmx->hv_root_ept = root; - - if (!ret) - ret = hv_remote_flush_root_ept(root, range); - - /* - * Stop processing roots if a failure occurred and - * multiple valid roots have already been detected. - */ - if (ret && nr_unique_valid_roots > 1) - break; - } - - /* - * The optimized flush of a single root can't be used if there - * are multiple valid roots (obviously). - */ - if (nr_unique_valid_roots > 1) - kvm_vmx->hv_root_ept = INVALID_PAGE; - } else { - ret = hv_remote_flush_root_ept(kvm_vmx->hv_root_ept, range); - } - - spin_unlock(&kvm_vmx->hv_root_ept_lock); - return ret; -} -static int hv_remote_flush_tlb(struct kvm *kvm) -{ - return hv_remote_flush_tlb_with_range(kvm, NULL); -} - static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; @@ -581,21 +486,6 @@ static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) #endif /* IS_ENABLED(CONFIG_HYPERV) */ -static void hv_track_root_ept(struct kvm_vcpu *vcpu, hpa_t root_ept) -{ -#if IS_ENABLED(CONFIG_HYPERV) - struct kvm_vmx *kvm_vmx = to_kvm_vmx(vcpu->kvm); - - if (kvm_x86_ops.tlb_remote_flush == hv_remote_flush_tlb) { - spin_lock(&kvm_vmx->hv_root_ept_lock); - to_vmx(vcpu)->hv_root_ept = root_ept; - if (root_ept != kvm_vmx->hv_root_ept) - kvm_vmx->hv_root_ept = INVALID_PAGE; - spin_unlock(&kvm_vmx->hv_root_ept_lock); - } -#endif -} - /* * Comment's format: document - errata name - stepping - processor name. * Refer from @@ -697,21 +587,11 @@ static bool is_valid_passthrough_msr(u32 msr) return r; } -static inline int __vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) -{ - int i; - - for (i = 0; i < vmx->nr_uret_msrs; ++i) - if (vmx_uret_msrs_list[vmx->guest_uret_msrs[i].slot] == msr) - return i; - return -1; -} - struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) { int i; - i = __vmx_find_uret_msr(vmx, msr); + i = kvm_find_user_return_msr(msr); if (i >= 0) return &vmx->guest_uret_msrs[i]; return NULL; @@ -720,13 +600,14 @@ struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, struct vmx_uret_msr *msr, u64 data) { + unsigned int slot = msr - vmx->guest_uret_msrs; int ret = 0; u64 old_msr_data = msr->data; msr->data = data; - if (msr - vmx->guest_uret_msrs < vmx->nr_active_uret_msrs) { + if (msr->load_into_hardware) { preempt_disable(); - ret = kvm_set_user_return_msr(msr->slot, msr->data, msr->mask); + ret = kvm_set_user_return_msr(slot, msr->data, msr->mask); preempt_enable(); if (ret) msr->data = old_msr_data; @@ -866,16 +747,21 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; else { - /* - * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched - * between guest and host. In that case we only care about present - * faults. For vmcs02, however, PFEC_MASK and PFEC_MATCH are set in - * prepare_vmcs02_rare. - */ - bool selective_pf_trap = enable_ept && (eb & (1u << PF_VECTOR)); - int mask = selective_pf_trap ? PFERR_PRESENT_MASK : 0; + int mask = 0, match = 0; + + if (enable_ept && (eb & (1u << PF_VECTOR))) { + /* + * If EPT is enabled, #PF is currently only intercepted + * if MAXPHYADDR is smaller on the guest than on the + * host. In that case we only care about present, + * non-reserved faults. For vmcs02, however, PFEC_MASK + * and PFEC_MATCH are set in prepare_vmcs02_rare. + */ + mask = PFERR_PRESENT_MASK | PFERR_RSVD_MASK; + match = PFERR_PRESENT_MASK; + } vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, mask); - vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, mask); + vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, match); } vmcs_write32(EXCEPTION_BITMAP, eb); @@ -1078,7 +964,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx) return false; } - i = __vmx_find_uret_msr(vmx, MSR_EFER); + i = kvm_find_user_return_msr(MSR_EFER); if (i < 0) return false; @@ -1240,11 +1126,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) */ if (!vmx->guest_uret_msrs_loaded) { vmx->guest_uret_msrs_loaded = true; - for (i = 0; i < vmx->nr_active_uret_msrs; ++i) - kvm_set_user_return_msr(vmx->guest_uret_msrs[i].slot, + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + if (!vmx->guest_uret_msrs[i].load_into_hardware) + continue; + + kvm_set_user_return_msr(i, vmx->guest_uret_msrs[i].data, vmx->guest_uret_msrs[i].mask); - + } } if (vmx->nested.need_vmcs12_to_shadow_sync) @@ -1411,11 +1300,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, vmx->loaded_vmcs->cpu = cpu; } - - /* Setup TSC multiplier */ - if (kvm_has_tsc_control && - vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) - decache_tsc_multiplier(vmx); } /* @@ -1751,19 +1635,16 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) vmx_clear_hlt(vcpu); } -static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr) +static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr, + bool load_into_hardware) { - struct vmx_uret_msr tmp; - int from, to; + struct vmx_uret_msr *uret_msr; - from = __vmx_find_uret_msr(vmx, msr); - if (from < 0) + uret_msr = vmx_find_uret_msr(vmx, msr); + if (!uret_msr) return; - to = vmx->nr_active_uret_msrs++; - tmp = vmx->guest_uret_msrs[to]; - vmx->guest_uret_msrs[to] = vmx->guest_uret_msrs[from]; - vmx->guest_uret_msrs[from] = tmp; + uret_msr->load_into_hardware = load_into_hardware; } /* @@ -1773,51 +1654,73 @@ static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr) */ static void setup_msrs(struct vcpu_vmx *vmx) { - vmx->guest_uret_msrs_loaded = false; - vmx->nr_active_uret_msrs = 0; #ifdef CONFIG_X86_64 + bool load_syscall_msrs; + /* * The SYSCALL MSRs are only needed on long mode guests, and only * when EFER.SCE is set. */ - if (is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE)) { - vmx_setup_uret_msr(vmx, MSR_STAR); - vmx_setup_uret_msr(vmx, MSR_LSTAR); - vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK); - } + load_syscall_msrs = is_long_mode(&vmx->vcpu) && + (vmx->vcpu.arch.efer & EFER_SCE); + + vmx_setup_uret_msr(vmx, MSR_STAR, load_syscall_msrs); + vmx_setup_uret_msr(vmx, MSR_LSTAR, load_syscall_msrs); + vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK, load_syscall_msrs); #endif - if (update_transition_efer(vmx)) - vmx_setup_uret_msr(vmx, MSR_EFER); + vmx_setup_uret_msr(vmx, MSR_EFER, update_transition_efer(vmx)); - if (guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) - vmx_setup_uret_msr(vmx, MSR_TSC_AUX); + vmx_setup_uret_msr(vmx, MSR_TSC_AUX, + guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID)); - vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL); + /* + * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations of new + * kernel and old userspace. If those guests run on a tsx=off host, do + * allow guests to use TSX_CTRL, but don't change the value in hardware + * so that TSX remains always disabled. + */ + vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL, boot_cpu_has(X86_FEATURE_RTM)); if (cpu_has_vmx_msr_bitmap()) vmx_update_msr_bitmap(&vmx->vcpu); + + /* + * The set of MSRs to load may have changed, reload MSRs before the + * next VM-Enter. + */ + vmx->guest_uret_msrs_loaded = false; } -static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u64 g_tsc_offset = 0; - /* - * We're here if L1 chose not to trap WRMSR to TSC. According - * to the spec, this should set L1's TSC; The offset that L1 - * set for L2 remains unchanged, and still needs to be added - * to the newly set TSC to get L2's TSC. - */ - if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) - g_tsc_offset = vmcs12->tsc_offset; + if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING)) + return vmcs12->tsc_offset; - trace_kvm_write_tsc_offset(vcpu->vcpu_id, - vcpu->arch.tsc_offset - g_tsc_offset, - offset); - vmcs_write64(TSC_OFFSET, offset + g_tsc_offset); - return offset + g_tsc_offset; + return 0; +} + +u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING) && + nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING)) + return vmcs12->tsc_multiplier; + + return kvm_default_tsc_scaling_ratio; +} + +static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +{ + vmcs_write64(TSC_OFFSET, offset); +} + +static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) +{ + vmcs_write64(TSC_MULTIPLIER, multiplier); } /* @@ -1993,11 +1896,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) else msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; - case MSR_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - goto find_uret_msr; case MSR_IA32_DEBUGCTLMSR: msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); break; @@ -2031,6 +1929,9 @@ static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu) if (!intel_pmu_lbr_is_enabled(vcpu)) debugctl &= ~DEBUGCTLMSR_LBR_MASK; + if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT; + return debugctl; } @@ -2313,14 +2214,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) else vmx->pt_desc.guest.addr_a[index / 2] = data; break; - case MSR_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - /* Check reserved bit, higher 32 bits should be zero */ - if ((data >> 32) != 0) - return 1; - goto find_uret_msr; case MSR_IA32_PERF_CAPABILITIES: if (data && !vcpu_to_pmu(vcpu)->version) return 1; @@ -3202,7 +3095,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, eptp = construct_eptp(vcpu, root_hpa, root_level); vmcs_write64(EPT_POINTER, eptp); - hv_track_root_ept(vcpu, root_hpa); + hv_track_root_tdp(vcpu, root_hpa); if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; @@ -3728,7 +3621,7 @@ static int alloc_apic_access_page(struct kvm *kvm) int ret = 0; mutex_lock(&kvm->slots_lock); - if (kvm->arch.apic_access_page_done) + if (kvm->arch.apic_access_memslot_enabled) goto out; hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); @@ -3748,7 +3641,7 @@ static int alloc_apic_access_page(struct kvm *kvm) * is able to migrate it. */ put_page(page); - kvm->arch.apic_access_page_done = true; + kvm->arch.apic_access_memslot_enabled = true; out: mutex_unlock(&kvm->slots_lock); return ret; @@ -4369,7 +4262,23 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) xsaves_enabled, false); } - vmx_adjust_sec_exec_feature(vmx, &exec_control, rdtscp, RDTSCP); + /* + * RDPID is also gated by ENABLE_RDTSCP, turn on the control if either + * feature is exposed to the guest. This creates a virtualization hole + * if both are supported in hardware but only one is exposed to the + * guest, but letting the guest execute RDTSCP or RDPID when either one + * is advertised is preferable to emulating the advertised instruction + * in KVM on #UD, and obviously better than incorrectly injecting #UD. + */ + if (cpu_has_vmx_rdtscp()) { + bool rdpid_or_rdtscp_enabled = + guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + + vmx_adjust_secondary_exec_control(vmx, &exec_control, + SECONDARY_EXEC_ENABLE_RDTSCP, + rdpid_or_rdtscp_enabled, false); + } vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND); @@ -4834,7 +4743,7 @@ static int handle_machine_check(struct kvm_vcpu *vcpu) * - Guest has #AC detection enabled in CR0 * - Guest EFLAGS has AC bit set */ -static inline bool guest_inject_ac(struct kvm_vcpu *vcpu) +bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu) { if (!boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) return true; @@ -4848,7 +4757,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_run *kvm_run = vcpu->run; u32 intr_info, ex_no, error_code; - unsigned long cr2, rip, dr6; + unsigned long cr2, dr6; u32 vect_info; vect_info = vmx->idt_vectoring_info; @@ -4938,12 +4847,11 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) vmx->vcpu.arch.event_exit_inst_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); kvm_run->exit_reason = KVM_EXIT_DEBUG; - rip = kvm_rip_read(vcpu); - kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; + kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = ex_no; break; case AC_VECTOR: - if (guest_inject_ac(vcpu)) { + if (vmx_guest_inject_ac(vcpu)) { kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); return 1; } @@ -5816,6 +5724,8 @@ void dump_vmcs(struct kvm_vcpu *vcpu) if (cpu_has_secondary_exec_ctrls()) secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + pr_err("VMCS %p, last attempted VM-entry on CPU %d\n", + vmx->loaded_vmcs->vmcs, vcpu->arch.last_vmentry_cpu); pr_err("*** Guest State ***\n"); pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW), @@ -6253,6 +6163,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) switch (kvm_get_apic_mode(vcpu)) { case LAPIC_MODE_INVALID: WARN_ONCE(true, "Invalid local APIC state"); + break; case LAPIC_MODE_DISABLED: break; case LAPIC_MODE_XAPIC: @@ -6811,7 +6722,18 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_load_host_xsave_state(vcpu); - vmx->nested.nested_run_pending = 0; + if (is_guest_mode(vcpu)) { + /* + * Track VMLAUNCH/VMRESUME that have made past guest state + * checking. + */ + if (vmx->nested.nested_run_pending && + !vmx->exit_reason.failed_vmentry) + ++vcpu->stat.nested_run; + + vmx->nested.nested_run_pending = 0; + } + vmx->idt_vectoring_info = 0; if (unlikely(vmx->fail)) { @@ -6855,6 +6777,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) static int vmx_create_vcpu(struct kvm_vcpu *vcpu) { + struct vmx_uret_msr *tsx_ctrl; struct vcpu_vmx *vmx; int i, cpu, err; @@ -6877,43 +6800,19 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) goto free_vpid; } - BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS); - - for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) { - u32 index = vmx_uret_msrs_list[i]; - u32 data_low, data_high; - int j = vmx->nr_uret_msrs; - - if (rdmsr_safe(index, &data_low, &data_high) < 0) - continue; - if (wrmsr_safe(index, data_low, data_high) < 0) - continue; - - vmx->guest_uret_msrs[j].slot = i; - vmx->guest_uret_msrs[j].data = 0; - switch (index) { - case MSR_IA32_TSX_CTRL: - /* - * TSX_CTRL_CPUID_CLEAR is handled in the CPUID - * interception. Keep the host value unchanged to avoid - * changing CPUID bits under the host kernel's feet. - * - * hle=0, rtm=0, tsx_ctrl=1 can be found with some - * combinations of new kernel and old userspace. If - * those guests run on a tsx=off host, do allow guests - * to use TSX_CTRL, but do not change the value on the - * host so that TSX remains always disabled. - */ - if (boot_cpu_has(X86_FEATURE_RTM)) - vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; - else - vmx->guest_uret_msrs[j].mask = 0; - break; - default: - vmx->guest_uret_msrs[j].mask = -1ull; - break; - } - ++vmx->nr_uret_msrs; + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + vmx->guest_uret_msrs[i].data = 0; + vmx->guest_uret_msrs[i].mask = -1ull; + } + if (boot_cpu_has(X86_FEATURE_RTM)) { + /* + * TSX_CTRL_CPUID_CLEAR is handled in the CPUID interception. + * Keep the host value unchanged to avoid changing CPUID bits + * under the host kernel's feet. + */ + tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); + if (tsx_ctrl) + vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; } err = alloc_loaded_vmcs(&vmx->vmcs01); @@ -6969,6 +6868,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; + vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; @@ -6980,9 +6880,6 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) vmx->pi_desc.nv = POSTED_INTR_VECTOR; vmx->pi_desc.sn = 1; -#if IS_ENABLED(CONFIG_HYPERV) - vmx->hv_root_ept = INVALID_PAGE; -#endif return 0; free_vmcs: @@ -6999,10 +6896,6 @@ free_vpid: static int vmx_vm_init(struct kvm *kvm) { -#if IS_ENABLED(CONFIG_HYPERV) - spin_lock_init(&to_kvm_vmx(kvm)->hv_root_ept_lock); -#endif - if (!ple_gap) kvm->arch.pause_in_guest = true; @@ -7029,7 +6922,6 @@ static int vmx_vm_init(struct kvm *kvm) break; } } - kvm_apicv_init(kvm, enable_apicv); return 0; } @@ -7344,9 +7236,11 @@ static __init void vmx_set_cpu_caps(void) if (!cpu_has_vmx_xsaves()) kvm_cpu_cap_clear(X86_FEATURE_XSAVES); - /* CPUID 0x80000001 */ - if (!cpu_has_vmx_rdtscp()) + /* CPUID 0x80000001 and 0x7 (RDPID) */ + if (!cpu_has_vmx_rdtscp()) { kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); + kvm_cpu_cap_clear(X86_FEATURE_RDPID); + } if (cpu_has_vmx_waitpkg()) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); @@ -7402,8 +7296,9 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, /* * RDPID causes #UD if disabled through secondary execution controls. * Because it is marked as EmulateOnUD, we need to intercept it here. + * Note, RDPID is hidden behind ENABLE_RDTSCP. */ - case x86_intercept_rdtscp: + case x86_intercept_rdpid: if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_RDTSCP)) { exception->vector = UD_VECTOR; exception->error_code_valid = false; @@ -7478,10 +7373,10 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, delta_tsc = 0; /* Convert to host delta tsc if tsc scaling is enabled */ - if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && + if (vcpu->arch.l1_tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && delta_tsc && u64_shl_div_u64(delta_tsc, kvm_tsc_scaling_ratio_frac_bits, - vcpu->arch.tsc_scaling_ratio, &delta_tsc)) + vcpu->arch.l1_tsc_scaling_ratio, &delta_tsc)) return -ERANGE; /* @@ -7567,7 +7462,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !is_smm(vcpu); } -static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7581,7 +7476,7 @@ static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) +static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; @@ -7725,7 +7620,10 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - .write_l1_tsc_offset = vmx_write_l1_tsc_offset, + .get_l2_tsc_offset = vmx_get_l2_tsc_offset, + .get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier, + .write_tsc_offset = vmx_write_tsc_offset, + .write_tsc_multiplier = vmx_write_tsc_multiplier, .load_mmu_pgd = vmx_load_mmu_pgd, @@ -7746,6 +7644,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .nested_ops = &vmx_nested_ops, .update_pi_irte = pi_update_irte, + .start_assignment = vmx_pi_start_assignment, #ifdef CONFIG_X86_64 .set_hv_timer = vmx_set_hv_timer, @@ -7755,8 +7654,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .setup_mce = vmx_setup_mce, .smi_allowed = vmx_smi_allowed, - .pre_enter_smm = vmx_pre_enter_smm, - .pre_leave_smm = vmx_pre_leave_smm, + .enter_smm = vmx_enter_smm, + .leave_smm = vmx_leave_smm, .enable_smi_window = vmx_enable_smi_window, .can_emulate_instruction = vmx_can_emulate_instruction, @@ -7769,17 +7668,42 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; +static __init void vmx_setup_user_return_msrs(void) +{ + + /* + * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm + * will emulate SYSCALL in legacy mode if the vendor string in guest + * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To + * support this emulation, MSR_STAR is included in the list for i386, + * but is never loaded into hardware. MSR_CSTAR is also never loaded + * into hardware and is here purely for emulation purposes. + */ + const u32 vmx_uret_msrs_list[] = { + #ifdef CONFIG_X86_64 + MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, + #endif + MSR_EFER, MSR_TSC_AUX, MSR_STAR, + MSR_IA32_TSX_CTRL, + }; + int i; + + BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS); + + for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) + kvm_add_user_return_msr(vmx_uret_msrs_list[i]); +} + static __init int hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; - int r, i, ept_lpage_level; + int r, ept_lpage_level; store_idt(&dt); host_idt_base = dt.address; - for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) - kvm_define_user_return_msr(i, vmx_uret_msrs_list[i]); + vmx_setup_user_return_msrs(); if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) return -EIO; @@ -7806,6 +7730,12 @@ static __init int hardware_setup(void) !cpu_has_vmx_invept_global()) enable_ept = 0; + /* NX support is required for shadow paging. */ + if (!enable_ept && !boot_cpu_has(X86_FEATURE_NX)) { + pr_err_ratelimited("kvm: NX (Execute Disable) not supported\n"); + return -EOPNOTSUPP; + } + if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) enable_ept_ad_bits = 0; @@ -7995,6 +7925,8 @@ static void vmx_exit(void) } #endif vmx_cleanup_l1d_flush(); + + allow_smaller_maxphyaddr = false; } module_exit(vmx_exit); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 008cb87ff088..3979a947933a 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -36,7 +36,7 @@ struct vmx_msrs { }; struct vmx_uret_msr { - unsigned int slot; /* The MSR's slot in kvm_user_return_msrs. */ + bool load_into_hardware; u64 data; u64 mask; }; @@ -245,8 +245,16 @@ struct vcpu_vmx { u32 idt_vectoring_info; ulong rflags; + /* + * User return MSRs are always emulated when enabled in the guest, but + * only loaded into hardware when necessary, e.g. SYSCALL #UDs outside + * of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to + * be loaded into hardware if those conditions aren't met. + * nr_active_uret_msrs tracks the number of MSRs that need to be loaded + * into hardware when running the guest. guest_uret_msrs[] is resorted + * whenever the number of "active" uret MSRs is modified. + */ struct vmx_uret_msr guest_uret_msrs[MAX_NR_USER_RETURN_MSRS]; - int nr_uret_msrs; int nr_active_uret_msrs; bool guest_uret_msrs_loaded; #ifdef CONFIG_X86_64 @@ -314,8 +322,6 @@ struct vcpu_vmx { /* apic deadline value in host tsc */ u64 hv_deadline_tsc; - u64 current_tsc_ratio; - unsigned long host_debugctlmsr; /* @@ -328,10 +334,6 @@ struct vcpu_vmx { /* SGX Launch Control public key hash */ u64 msr_ia32_sgxlepubkeyhash[4]; -#if IS_ENABLED(CONFIG_HYPERV) - u64 hv_root_ept; -#endif - struct pt_desc pt_desc; struct lbr_desc lbr_desc; @@ -349,11 +351,6 @@ struct kvm_vmx { unsigned int tss_addr; bool ept_identity_pagetable_done; gpa_t ept_identity_map_addr; - -#if IS_ENABLED(CONFIG_HYPERV) - hpa_t hv_root_ept; - spinlock_t hv_root_ept_lock; -#endif }; bool nested_vmx_allowed(struct kvm_vcpu *vcpu); @@ -379,6 +376,7 @@ void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); +bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu); void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); bool vmx_nmi_blocked(struct kvm_vcpu *vcpu); @@ -396,6 +394,9 @@ void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu); void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type); void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type); +u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu); +u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu); + static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool value) { @@ -521,12 +522,6 @@ static inline struct vmcs *alloc_vmcs(bool shadow) GFP_KERNEL_ACCOUNT); } -static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx) -{ - vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio; - vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); -} - static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) { return vmx->secondary_exec_control & diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6eda2834fc05..17468d983fbd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -58,6 +58,7 @@ #include <linux/sched/isolation.h> #include <linux/mem_encrypt.h> #include <linux/entry-kvm.h> +#include <linux/suspend.h> #include <trace/events/kvm.h> @@ -102,6 +103,8 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; +#define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE) + #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -113,6 +116,9 @@ static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); +static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); +static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); + struct kvm_x86_ops kvm_x86_ops __read_mostly; EXPORT_SYMBOL_GPL(kvm_x86_ops); @@ -184,11 +190,6 @@ module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR); */ #define KVM_MAX_NR_USER_RETURN_MSRS 16 -struct kvm_user_return_msrs_global { - int nr; - u32 msrs[KVM_MAX_NR_USER_RETURN_MSRS]; -}; - struct kvm_user_return_msrs { struct user_return_notifier urn; bool registered; @@ -198,7 +199,9 @@ struct kvm_user_return_msrs { } values[KVM_MAX_NR_USER_RETURN_MSRS]; }; -static struct kvm_user_return_msrs_global __read_mostly user_return_msrs_global; +u32 __read_mostly kvm_nr_uret_msrs; +EXPORT_SYMBOL_GPL(kvm_nr_uret_msrs); +static u32 __read_mostly kvm_uret_msrs_list[KVM_MAX_NR_USER_RETURN_MSRS]; static struct kvm_user_return_msrs __percpu *user_return_msrs; #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ @@ -212,55 +215,78 @@ EXPORT_SYMBOL_GPL(host_efer); bool __read_mostly allow_smaller_maxphyaddr = 0; EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); +bool __read_mostly enable_apicv = true; +EXPORT_SYMBOL_GPL(enable_apicv); + u64 __read_mostly host_xss; EXPORT_SYMBOL_GPL(host_xss); u64 __read_mostly supported_xss; EXPORT_SYMBOL_GPL(supported_xss); -struct kvm_stats_debugfs_item debugfs_entries[] = { - VCPU_STAT("pf_fixed", pf_fixed), - VCPU_STAT("pf_guest", pf_guest), - VCPU_STAT("tlb_flush", tlb_flush), - VCPU_STAT("invlpg", invlpg), - VCPU_STAT("exits", exits), - VCPU_STAT("io_exits", io_exits), - VCPU_STAT("mmio_exits", mmio_exits), - VCPU_STAT("signal_exits", signal_exits), - VCPU_STAT("irq_window", irq_window_exits), - VCPU_STAT("nmi_window", nmi_window_exits), - VCPU_STAT("halt_exits", halt_exits), - VCPU_STAT("halt_successful_poll", halt_successful_poll), - VCPU_STAT("halt_attempted_poll", halt_attempted_poll), - VCPU_STAT("halt_poll_invalid", halt_poll_invalid), - VCPU_STAT("halt_wakeup", halt_wakeup), - VCPU_STAT("hypercalls", hypercalls), - VCPU_STAT("request_irq", request_irq_exits), - VCPU_STAT("irq_exits", irq_exits), - VCPU_STAT("host_state_reload", host_state_reload), - VCPU_STAT("fpu_reload", fpu_reload), - VCPU_STAT("insn_emulation", insn_emulation), - VCPU_STAT("insn_emulation_fail", insn_emulation_fail), - VCPU_STAT("irq_injections", irq_injections), - VCPU_STAT("nmi_injections", nmi_injections), - VCPU_STAT("req_event", req_event), - VCPU_STAT("l1d_flush", l1d_flush), - VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), - VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), - VCPU_STAT("nested_run", nested_run), - VCPU_STAT("directed_yield_attempted", directed_yield_attempted), - VCPU_STAT("directed_yield_successful", directed_yield_successful), - VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped), - VM_STAT("mmu_pte_write", mmu_pte_write), - VM_STAT("mmu_pde_zapped", mmu_pde_zapped), - VM_STAT("mmu_flooded", mmu_flooded), - VM_STAT("mmu_recycled", mmu_recycled), - VM_STAT("mmu_cache_miss", mmu_cache_miss), - VM_STAT("mmu_unsync", mmu_unsync), - VM_STAT("remote_tlb_flush", remote_tlb_flush), - VM_STAT("largepages", lpages, .mode = 0444), - VM_STAT("nx_largepages_splitted", nx_lpage_splits, .mode = 0444), - VM_STAT("max_mmu_page_hash_collisions", max_mmu_page_hash_collisions), - { NULL } +const struct _kvm_stats_desc kvm_vm_stats_desc[] = { + KVM_GENERIC_VM_STATS(), + STATS_DESC_COUNTER(VM, mmu_shadow_zapped), + STATS_DESC_COUNTER(VM, mmu_pte_write), + STATS_DESC_COUNTER(VM, mmu_pde_zapped), + STATS_DESC_COUNTER(VM, mmu_flooded), + STATS_DESC_COUNTER(VM, mmu_recycled), + STATS_DESC_COUNTER(VM, mmu_cache_miss), + STATS_DESC_ICOUNTER(VM, mmu_unsync), + STATS_DESC_ICOUNTER(VM, lpages), + STATS_DESC_ICOUNTER(VM, nx_lpage_splits), + STATS_DESC_PCOUNTER(VM, max_mmu_page_hash_collisions) +}; +static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == + sizeof(struct kvm_vm_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vm_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vm_stats_desc), +}; + +const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { + KVM_GENERIC_VCPU_STATS(), + STATS_DESC_COUNTER(VCPU, pf_fixed), + STATS_DESC_COUNTER(VCPU, pf_guest), + STATS_DESC_COUNTER(VCPU, tlb_flush), + STATS_DESC_COUNTER(VCPU, invlpg), + STATS_DESC_COUNTER(VCPU, exits), + STATS_DESC_COUNTER(VCPU, io_exits), + STATS_DESC_COUNTER(VCPU, mmio_exits), + STATS_DESC_COUNTER(VCPU, signal_exits), + STATS_DESC_COUNTER(VCPU, irq_window_exits), + STATS_DESC_COUNTER(VCPU, nmi_window_exits), + STATS_DESC_COUNTER(VCPU, l1d_flush), + STATS_DESC_COUNTER(VCPU, halt_exits), + STATS_DESC_COUNTER(VCPU, request_irq_exits), + STATS_DESC_COUNTER(VCPU, irq_exits), + STATS_DESC_COUNTER(VCPU, host_state_reload), + STATS_DESC_COUNTER(VCPU, fpu_reload), + STATS_DESC_COUNTER(VCPU, insn_emulation), + STATS_DESC_COUNTER(VCPU, insn_emulation_fail), + STATS_DESC_COUNTER(VCPU, hypercalls), + STATS_DESC_COUNTER(VCPU, irq_injections), + STATS_DESC_COUNTER(VCPU, nmi_injections), + STATS_DESC_COUNTER(VCPU, req_event), + STATS_DESC_COUNTER(VCPU, nested_run), + STATS_DESC_COUNTER(VCPU, directed_yield_attempted), + STATS_DESC_COUNTER(VCPU, directed_yield_successful), + STATS_DESC_ICOUNTER(VCPU, guest_mode) +}; +static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == + sizeof(struct kvm_vcpu_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vcpu_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vcpu_stats_desc), }; u64 __read_mostly host_xcr0; @@ -330,23 +356,53 @@ static void kvm_on_user_return(struct user_return_notifier *urn) user_return_notifier_unregister(urn); } local_irq_restore(flags); - for (slot = 0; slot < user_return_msrs_global.nr; ++slot) { + for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) { values = &msrs->values[slot]; if (values->host != values->curr) { - wrmsrl(user_return_msrs_global.msrs[slot], values->host); + wrmsrl(kvm_uret_msrs_list[slot], values->host); values->curr = values->host; } } } -void kvm_define_user_return_msr(unsigned slot, u32 msr) +static int kvm_probe_user_return_msr(u32 msr) +{ + u64 val; + int ret; + + preempt_disable(); + ret = rdmsrl_safe(msr, &val); + if (ret) + goto out; + ret = wrmsrl_safe(msr, val); +out: + preempt_enable(); + return ret; +} + +int kvm_add_user_return_msr(u32 msr) { - BUG_ON(slot >= KVM_MAX_NR_USER_RETURN_MSRS); - user_return_msrs_global.msrs[slot] = msr; - if (slot >= user_return_msrs_global.nr) - user_return_msrs_global.nr = slot + 1; + BUG_ON(kvm_nr_uret_msrs >= KVM_MAX_NR_USER_RETURN_MSRS); + + if (kvm_probe_user_return_msr(msr)) + return -1; + + kvm_uret_msrs_list[kvm_nr_uret_msrs] = msr; + return kvm_nr_uret_msrs++; } -EXPORT_SYMBOL_GPL(kvm_define_user_return_msr); +EXPORT_SYMBOL_GPL(kvm_add_user_return_msr); + +int kvm_find_user_return_msr(u32 msr) +{ + int i; + + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + if (kvm_uret_msrs_list[i] == msr) + return i; + } + return -1; +} +EXPORT_SYMBOL_GPL(kvm_find_user_return_msr); static void kvm_user_return_msr_cpu_online(void) { @@ -355,8 +411,8 @@ static void kvm_user_return_msr_cpu_online(void) u64 value; int i; - for (i = 0; i < user_return_msrs_global.nr; ++i) { - rdmsrl_safe(user_return_msrs_global.msrs[i], &value); + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + rdmsrl_safe(kvm_uret_msrs_list[i], &value); msrs->values[i].host = value; msrs->values[i].curr = value; } @@ -371,7 +427,7 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) value = (value & mask) | (msrs->values[slot].host & ~mask); if (value == msrs->values[slot].curr) return 0; - err = wrmsrl_safe(user_return_msrs_global.msrs[slot], value); + err = wrmsrl_safe(kvm_uret_msrs_list[slot], value); if (err) return 1; @@ -751,13 +807,6 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu); -static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, - void *data, int offset, int len, u32 access) -{ - return kvm_read_guest_page_mmu(vcpu, vcpu->arch.walk_mmu, gfn, - data, offset, len, access); -} - static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2); @@ -792,6 +841,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + vcpu->arch.pdptrs_from_userspace = false; out: @@ -799,40 +849,14 @@ out: } EXPORT_SYMBOL_GPL(load_pdptrs); -bool pdptrs_changed(struct kvm_vcpu *vcpu) -{ - u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)]; - int offset; - gfn_t gfn; - int r; - - if (!is_pae_paging(vcpu)) - return false; - - if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) - return true; - - gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT; - offset = (kvm_read_cr3(vcpu) & 0xffffffe0ul) & (PAGE_SIZE - 1); - r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), - PFERR_USER_MASK | PFERR_WRITE_MASK); - if (r < 0) - return true; - - return memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; -} -EXPORT_SYMBOL_GPL(pdptrs_changed); - void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0) { - unsigned long update_bits = X86_CR0_PG | X86_CR0_WP; - if ((cr0 ^ old_cr0) & X86_CR0_PG) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); } - if ((cr0 ^ old_cr0) & update_bits) + if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS) kvm_mmu_reset_context(vcpu); if (((cr0 ^ old_cr0) & X86_CR0_CD) && @@ -1011,10 +1035,7 @@ EXPORT_SYMBOL_GPL(kvm_is_valid_cr4); void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4) { - unsigned long mmu_role_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; - - if (((cr4 ^ old_cr4) & mmu_role_bits) || + if (((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); } @@ -1057,25 +1078,46 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) } EXPORT_SYMBOL_GPL(kvm_set_cr4); +static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid) +{ + struct kvm_mmu *mmu = vcpu->arch.mmu; + unsigned long roots_to_free = 0; + int i; + + /* + * If neither the current CR3 nor any of the prev_roots use the given + * PCID, then nothing needs to be done here because a resync will + * happen anyway before switching to any other CR3. + */ + if (kvm_get_active_pcid(vcpu) == pcid) { + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + } + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + if (kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd) == pcid) + roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); + + kvm_mmu_free_roots(vcpu, mmu, roots_to_free); +} + int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { bool skip_tlb_flush = false; + unsigned long pcid = 0; #ifdef CONFIG_X86_64 bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); if (pcid_enabled) { skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH; cr3 &= ~X86_CR3_PCID_NOFLUSH; + pcid = cr3 & X86_CR3_PCID_MASK; } #endif - if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) { - if (!skip_tlb_flush) { - kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } - return 0; - } + /* PDPTRs are always reloaded for PAE paging. */ + if (cr3 == kvm_read_cr3(vcpu) && !is_pae_paging(vcpu)) + goto handle_tlb_flush; /* * Do not condition the GPA check on long mode, this helper is used to @@ -1088,10 +1130,23 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) return 1; - kvm_mmu_new_pgd(vcpu, cr3, skip_tlb_flush, skip_tlb_flush); + if (cr3 != kvm_read_cr3(vcpu)) + kvm_mmu_new_pgd(vcpu, cr3); + vcpu->arch.cr3 = cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); +handle_tlb_flush: + /* + * A load of CR3 that flushes the TLB flushes only the current PCID, + * even if PCID is disabled, in which case PCID=0 is flushed. It's a + * moot point in the end because _disabling_ PCID will flush all PCIDs, + * and it's impossible to use a non-zero PCID when PCID is disabled, + * i.e. only PCID=0 can be relevant. + */ + if (!skip_tlb_flush) + kvm_invalidate_pcid(vcpu, pcid); + return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr3); @@ -1149,6 +1204,9 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM)) fixed |= DR6_RTM; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + fixed |= DR6_BUS_LOCK; return fixed; } @@ -1615,6 +1673,30 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, * invokes 64-bit SYSENTER. */ data = get_canonical(data, vcpu_virt_addr_bits(vcpu)); + break; + case MSR_TSC_AUX: + if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) + return 1; + + if (!host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + return 1; + + /* + * Per Intel's SDM, bits 63:32 are reserved, but AMD's APM has + * incomplete and conflicting architectural behavior. Current + * AMD CPUs completely ignore bits 63:32, i.e. they aren't + * reserved and always read as zeros. Enforce Intel's reserved + * bits check if and only if the guest CPU is Intel, and clear + * the bits in all other cases. This ensures cross-vendor + * migration will provide consistent behavior for the guest. + */ + if (guest_cpuid_is_intel(vcpu) && (data >> 32) != 0) + return 1; + + data = (u32)data; + break; } msr.data = data; @@ -1651,6 +1733,18 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) return KVM_MSR_RET_FILTERED; + switch (index) { + case MSR_TSC_AUX: + if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) + return 1; + + if (!host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + return 1; + break; + } + msr.index = index; msr.host_initiated = host_initiated; @@ -2113,13 +2207,15 @@ static u32 adjust_tsc_khz(u32 khz, s32 ppm) return v; } +static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier); + static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) { u64 ratio; /* Guest TSC same frequency as host TSC? */ if (!scale) { - vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, kvm_default_tsc_scaling_ratio); return 0; } @@ -2145,7 +2241,7 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) return -1; } - vcpu->arch.tsc_scaling_ratio = ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, ratio); return 0; } @@ -2157,7 +2253,7 @@ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) /* tsc_khz can be zero if TSC calibration fails */ if (user_tsc_khz == 0) { /* set tsc_scaling_ratio to a safe value */ - vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, kvm_default_tsc_scaling_ratio); return -1; } @@ -2239,10 +2335,9 @@ static inline u64 __scale_tsc(u64 ratio, u64 tsc) return mul_u64_u64_shr(tsc, ratio, kvm_tsc_scaling_ratio_frac_bits); } -u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) +u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc, u64 ratio) { u64 _tsc = tsc; - u64 ratio = vcpu->arch.tsc_scaling_ratio; if (ratio != kvm_default_tsc_scaling_ratio) _tsc = __scale_tsc(ratio, tsc); @@ -2251,25 +2346,86 @@ u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) } EXPORT_SYMBOL_GPL(kvm_scale_tsc); -static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) +static u64 kvm_compute_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) { u64 tsc; - tsc = kvm_scale_tsc(vcpu, rdtsc()); + tsc = kvm_scale_tsc(vcpu, rdtsc(), vcpu->arch.l1_tsc_scaling_ratio); return target_tsc - tsc; } u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { - return vcpu->arch.l1_tsc_offset + kvm_scale_tsc(vcpu, host_tsc); + return vcpu->arch.l1_tsc_offset + + kvm_scale_tsc(vcpu, host_tsc, vcpu->arch.l1_tsc_scaling_ratio); } EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); -static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier) +{ + u64 nested_offset; + + if (l2_multiplier == kvm_default_tsc_scaling_ratio) + nested_offset = l1_offset; + else + nested_offset = mul_s64_u64_shr((s64) l1_offset, l2_multiplier, + kvm_tsc_scaling_ratio_frac_bits); + + nested_offset += l2_offset; + return nested_offset; +} +EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_offset); + +u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier) { - vcpu->arch.l1_tsc_offset = offset; - vcpu->arch.tsc_offset = static_call(kvm_x86_write_l1_tsc_offset)(vcpu, offset); + if (l2_multiplier != kvm_default_tsc_scaling_ratio) + return mul_u64_u64_shr(l1_multiplier, l2_multiplier, + kvm_tsc_scaling_ratio_frac_bits); + + return l1_multiplier; +} +EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_multiplier); + +static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset) +{ + trace_kvm_write_tsc_offset(vcpu->vcpu_id, + vcpu->arch.l1_tsc_offset, + l1_offset); + + vcpu->arch.l1_tsc_offset = l1_offset; + + /* + * If we are here because L1 chose not to trap WRMSR to TSC then + * according to the spec this should set L1's TSC (as opposed to + * setting L1's offset for L2). + */ + if (is_guest_mode(vcpu)) + vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( + l1_offset, + static_call(kvm_x86_get_l2_tsc_offset)(vcpu), + static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu)); + else + vcpu->arch.tsc_offset = l1_offset; + + static_call(kvm_x86_write_tsc_offset)(vcpu, vcpu->arch.tsc_offset); +} + +static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier) +{ + vcpu->arch.l1_tsc_scaling_ratio = l1_multiplier; + + /* Userspace is changing the multiplier while L2 is active */ + if (is_guest_mode(vcpu)) + vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier( + l1_multiplier, + static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu)); + else + vcpu->arch.tsc_scaling_ratio = l1_multiplier; + + if (kvm_has_tsc_control) + static_call(kvm_x86_write_tsc_multiplier)( + vcpu, vcpu->arch.tsc_scaling_ratio); } static inline bool kvm_check_tsc_unstable(void) @@ -2295,7 +2451,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) bool synchronizing = false; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); - offset = kvm_compute_tsc_offset(vcpu, data); + offset = kvm_compute_l1_tsc_offset(vcpu, data); ns = get_kvmclock_base_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; @@ -2334,7 +2490,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) } else { u64 delta = nsec_to_cycles(vcpu, elapsed); data += delta; - offset = kvm_compute_tsc_offset(vcpu, data); + offset = kvm_compute_l1_tsc_offset(vcpu, data); } matched = true; already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation); @@ -2393,9 +2549,10 @@ static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) { - if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) + if (vcpu->arch.l1_tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) WARN_ON(adjustment < 0); - adjustment = kvm_scale_tsc(vcpu, (u64) adjustment); + adjustment = kvm_scale_tsc(vcpu, (u64) adjustment, + vcpu->arch.l1_tsc_scaling_ratio); adjust_tsc_offset_guest(vcpu, adjustment); } @@ -2778,7 +2935,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* With all the info we got, fill in the values */ if (kvm_has_tsc_control) - tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz); + tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz, + v->arch.l1_tsc_scaling_ratio); if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) { kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL, @@ -3006,6 +3164,19 @@ static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; + + if (!tdp_enabled) { + /* + * A TLB flush on behalf of the guest is equivalent to + * INVPCID(all), toggling CR4.PGE, etc., which requires + * a forced sync of the shadow page tables. Unload the + * entire MMU here and the subsequent load will sync the + * shadow page tables, and also flush the TLB. + */ + kvm_mmu_unload(vcpu); + return; + } + static_call(kvm_x86_tlb_flush_guest)(vcpu); } @@ -3035,10 +3206,14 @@ static void record_steal_time(struct kvm_vcpu *vcpu) * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { + u8 st_preempted = xchg(&st->preempted, 0); + trace_kvm_pv_tlb_flush(vcpu->vcpu_id, - st->preempted & KVM_VCPU_FLUSH_TLB); - if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) + st_preempted & KVM_VCPU_FLUSH_TLB); + if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); + } else { + st->preempted = 0; } vcpu->arch.st.preempted = 0; @@ -3167,7 +3342,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (msr_info->host_initiated) { kvm_synchronize_tsc(vcpu, data); } else { - u64 adj = kvm_compute_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; + u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; adjust_tsc_offset_guest(vcpu, adj); vcpu->arch.ia32_tsc_adjust_msr += adj; } @@ -3402,7 +3577,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_LASTBRANCHTOIP: case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: - case MSR_K8_SYSCFG: + case MSR_AMD64_SYSCFG: case MSR_K8_TSEG_ADDR: case MSR_K8_TSEG_MASK: case MSR_VM_HSAVE_PA: @@ -3469,10 +3644,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * return L1's TSC value to ensure backwards-compatible * behavior for migration. */ - u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset : - vcpu->arch.tsc_offset; + u64 offset, ratio; - msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset; + if (msr_info->host_initiated) { + offset = vcpu->arch.l1_tsc_offset; + ratio = vcpu->arch.l1_tsc_scaling_ratio; + } else { + offset = vcpu->arch.tsc_offset; + ratio = vcpu->arch.tsc_scaling_ratio; + } + + msr_info->data = kvm_scale_tsc(vcpu, rdtsc(), ratio) + offset; break; } case MSR_MTRRcap: @@ -3796,6 +3978,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: case KVM_CAP_HYPERV_CPUID: + case KVM_CAP_HYPERV_ENFORCE_CPUID: case KVM_CAP_SYS_HYPERV_CPUID: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: @@ -3826,8 +4009,13 @@ 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_SREGS2: + case KVM_CAP_EXIT_ON_EMULATION_FAILURE: r = 1; break; + case KVM_CAP_EXIT_HYPERCALL: + r = KVM_EXIT_HYPERCALL_VALID_MASK; + break; case KVM_CAP_SET_GUEST_DEBUG2: return KVM_GUESTDBG_VALID_MASK; #ifdef CONFIG_KVM_XEN @@ -4055,7 +4243,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) mark_tsc_unstable("KVM discovered backwards TSC"); if (kvm_check_tsc_unstable()) { - u64 offset = kvm_compute_tsc_offset(vcpu, + u64 offset = kvm_compute_l1_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_vcpu_write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; @@ -4374,7 +4562,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, memset(&events->reserved, 0, sizeof(events->reserved)); } -static void kvm_smm_changed(struct kvm_vcpu *vcpu); +static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm); static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) @@ -4434,13 +4622,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { - if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { - if (events->smi.smm) - vcpu->arch.hflags |= HF_SMM_MASK; - else - vcpu->arch.hflags &= ~HF_SMM_MASK; - kvm_smm_changed(vcpu); - } + if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) + kvm_smm_changed(vcpu, events->smi.smm); vcpu->arch.smi_pending = events->smi.pending; @@ -4724,6 +4907,9 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return static_call(kvm_x86_enable_direct_tlbflush)(vcpu); + case KVM_CAP_HYPERV_ENFORCE_CPUID: + return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); + case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; if (vcpu->arch.pv_cpuid.enforce) @@ -4742,6 +4928,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int r; union { + struct kvm_sregs2 *sregs2; struct kvm_lapic_state *lapic; struct kvm_xsave *xsave; struct kvm_xcrs *xcrs; @@ -5114,6 +5301,28 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } #endif + case KVM_GET_SREGS2: { + u.sregs2 = kzalloc(sizeof(struct kvm_sregs2), GFP_KERNEL); + r = -ENOMEM; + if (!u.sregs2) + goto out; + __get_sregs2(vcpu, u.sregs2); + r = -EFAULT; + if (copy_to_user(argp, u.sregs2, sizeof(struct kvm_sregs2))) + goto out; + r = 0; + break; + } + case KVM_SET_SREGS2: { + u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2)); + if (IS_ERR(u.sregs2)) { + r = PTR_ERR(u.sregs2); + u.sregs2 = NULL; + goto out; + } + r = __set_sregs2(vcpu, u.sregs2); + break; + } default: r = -EINVAL; } @@ -5433,6 +5642,21 @@ split_irqchip_unlock: if (kvm_x86_ops.vm_copy_enc_context_from) r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]); return r; + case KVM_CAP_EXIT_HYPERCALL: + if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { + r = -EINVAL; + break; + } + kvm->arch.hypercall_exit_enabled = cap->args[0]; + r = 0; + break; + case KVM_CAP_EXIT_ON_EMULATION_FAILURE: + r = -EINVAL; + if (cap->args[0] & ~1) + break; + kvm->arch.exit_on_emulation_error = cap->args[0]; + r = 0; + break; default: r = -EINVAL; break; @@ -5468,14 +5692,18 @@ static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, struct kvm_msr_filter_range *user_range) { - struct msr_bitmap_range range; unsigned long *bitmap = NULL; size_t bitmap_size; - int r; if (!user_range->nmsrs) return 0; + if (user_range->flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) + return -EINVAL; + + if (!user_range->flags) + return -EINVAL; + bitmap_size = BITS_TO_LONGS(user_range->nmsrs) * sizeof(long); if (!bitmap_size || bitmap_size > KVM_MSR_FILTER_MAX_BITMAP_SIZE) return -EINVAL; @@ -5484,31 +5712,15 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, if (IS_ERR(bitmap)) return PTR_ERR(bitmap); - range = (struct msr_bitmap_range) { + msr_filter->ranges[msr_filter->count] = (struct msr_bitmap_range) { .flags = user_range->flags, .base = user_range->base, .nmsrs = user_range->nmsrs, .bitmap = bitmap, }; - if (range.flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) { - r = -EINVAL; - goto err; - } - - if (!range.flags) { - r = -EINVAL; - goto err; - } - - /* Everything ok, add this range identifier. */ - msr_filter->ranges[msr_filter->count] = range; msr_filter->count++; - return 0; -err: - kfree(bitmap); - return r; } static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) @@ -5559,6 +5771,41 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) return 0; } +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +static int kvm_arch_suspend_notifier(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i, ret = 0; + + mutex_lock(&kvm->lock); + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!vcpu->arch.pv_time_enabled) + continue; + + ret = kvm_set_guest_paused(vcpu); + if (ret) { + kvm_err("Failed to pause guest VCPU%d: %d\n", + vcpu->vcpu_id, ret); + break; + } + } + mutex_unlock(&kvm->lock); + + return ret ? NOTIFY_BAD : NOTIFY_DONE; +} + +int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state) +{ + switch (state) { + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: + return kvm_arch_suspend_notifier(kvm); + } + + return NOTIFY_DONE; +} +#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -5937,7 +6184,8 @@ static void kvm_init_msr_list(void) continue; break; case MSR_TSC_AUX: - if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) + if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && + !kvm_cpu_cap_has(X86_FEATURE_RDPID)) continue; break; case MSR_IA32_UMWAIT_CONTROL: @@ -7032,20 +7280,22 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) return emul_to_vcpu(ctxt)->arch.hflags; } -static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags) +static void emulator_exiting_smm(struct x86_emulate_ctxt *ctxt) { - emul_to_vcpu(ctxt)->arch.hflags = emul_flags; + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + kvm_smm_changed(vcpu, false); } -static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, +static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt, const char *smstate) { - return static_call(kvm_x86_pre_leave_smm)(emul_to_vcpu(ctxt), smstate); + return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smstate); } -static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) +static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt) { - kvm_smm_changed(emul_to_vcpu(ctxt)); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, emul_to_vcpu(ctxt)); } static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr) @@ -7094,9 +7344,9 @@ static const struct x86_emulate_ops emulate_ops = { .guest_has_fxsr = emulator_guest_has_fxsr, .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, - .set_hflags = emulator_set_hflags, - .pre_leave_smm = emulator_pre_leave_smm, - .post_leave_smm = emulator_post_leave_smm, + .exiting_smm = emulator_exiting_smm, + .leave_smm = emulator_leave_smm, + .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, }; @@ -7171,6 +7421,11 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); + ctxt->interruptibility = 0; + ctxt->have_exception = false; + ctxt->exception.vector = -1; + ctxt->perm_ok = false; + init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } @@ -7197,8 +7452,33 @@ void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) } EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); +static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + u32 insn_size = ctxt->fetch.end - ctxt->fetch.data; + struct kvm_run *run = vcpu->run; + + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION; + run->emulation_failure.ndata = 0; + run->emulation_failure.flags = 0; + + if (insn_size) { + run->emulation_failure.ndata = 3; + run->emulation_failure.flags |= + KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES; + run->emulation_failure.insn_size = insn_size; + memset(run->emulation_failure.insn_bytes, 0x90, + sizeof(run->emulation_failure.insn_bytes)); + memcpy(run->emulation_failure.insn_bytes, + ctxt->fetch.data, insn_size); + } +} + static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { + struct kvm *kvm = vcpu->kvm; + ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); @@ -7207,10 +7487,9 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) return 1; } - if (emulation_type & EMULTYPE_SKIP) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + if (kvm->arch.exit_on_emulation_error || + (emulation_type & EMULTYPE_SKIP)) { + prepare_emulation_failure_exit(vcpu); return 0; } @@ -7352,11 +7631,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); -static void kvm_smm_changed(struct kvm_vcpu *vcpu) +static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) { - if (!(vcpu->arch.hflags & HF_SMM_MASK)) { - /* This is a good place to trace that we are exiting SMM. */ - trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false); + trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm); + + if (entering_smm) { + vcpu->arch.hflags |= HF_SMM_MASK; + } else { + vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK); /* Process a latched INIT or SMI, if any. */ kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -7506,14 +7788,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, kvm_vcpu_check_breakpoint(vcpu, &r)) return r; - ctxt->interruptibility = 0; - ctxt->have_exception = false; - ctxt->exception.vector = -1; - ctxt->perm_ok = false; - - ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; - - r = x86_decode_insn(ctxt, insn, insn_len); + r = x86_decode_insn(ctxt, insn, insn_len, emulation_type); trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; @@ -8040,6 +8315,18 @@ static void pvclock_gtod_update_fn(struct work_struct *work) static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); /* + * Indirection to move queue_work() out of the tk_core.seq write held + * region to prevent possible deadlocks against time accessors which + * are invoked with work related locks held. + */ +static void pvclock_irq_work_fn(struct irq_work *w) +{ + queue_work(system_long_wq, &pvclock_gtod_work); +} + +static DEFINE_IRQ_WORK(pvclock_irq_work, pvclock_irq_work_fn); + +/* * Notification about pvclock gtod data update. */ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, @@ -8050,13 +8337,14 @@ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, update_pvclock_gtod(tk); - /* disable master clock if host does not trust, or does not - * use, TSC based clocksource. + /* + * Disable master clock if host does not trust, or does not use, + * TSC based clocksource. Delegate queue_work() to irq_work as + * this is invoked with tk_core.seq write held. */ if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) && atomic_read(&kvm_guest_has_master_clock) != 0) - queue_work(system_long_wq, &pvclock_gtod_work); - + irq_work_queue(&pvclock_irq_work); return 0; } @@ -8118,6 +8406,7 @@ int kvm_arch_init(void *opaque) printk(KERN_ERR "kvm: failed to allocate percpu kvm_user_return_msrs\n"); goto out_free_x86_emulator_cache; } + kvm_nr_uret_msrs = 0; r = kvm_mmu_module_init(); if (r) @@ -8168,10 +8457,13 @@ void kvm_arch_exit(void) cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); + irq_work_sync(&pvclock_irq_work); + cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_ops.hardware_enable = NULL; kvm_mmu_module_exit(); free_percpu(user_return_msrs); + kmem_cache_destroy(x86_emulator_cache); kmem_cache_destroy(x86_fpu_cache); #ifdef CONFIG_KVM_XEN static_key_deferred_flush(&kvm_xen_enabled); @@ -8271,16 +8563,15 @@ bool kvm_apicv_activated(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_apicv_activated); -void kvm_apicv_init(struct kvm *kvm, bool enable) +static void kvm_apicv_init(struct kvm *kvm) { - if (enable) + if (enable_apicv) clear_bit(APICV_INHIBIT_REASON_DISABLE, &kvm->arch.apicv_inhibit_reasons); else set_bit(APICV_INHIBIT_REASON_DISABLE, &kvm->arch.apicv_inhibit_reasons); } -EXPORT_SYMBOL_GPL(kvm_apicv_init); static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) { @@ -8289,6 +8580,9 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) vcpu->stat.directed_yield_attempted++; + if (single_task_running()) + goto no_yield; + rcu_read_lock(); map = rcu_dereference(vcpu->kvm->arch.apic_map); @@ -8313,6 +8607,17 @@ no_yield: return; } +static int complete_hypercall_exit(struct kvm_vcpu *vcpu) +{ + u64 ret = vcpu->run->hypercall.ret; + + if (!is_64_bit_mode(vcpu)) + ret = (u32)ret; + kvm_rax_write(vcpu, ret); + ++vcpu->stat.hypercalls; + return kvm_skip_emulated_instruction(vcpu); +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; @@ -8378,6 +8683,28 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) kvm_sched_yield(vcpu, a0); ret = 0; break; + case KVM_HC_MAP_GPA_RANGE: { + u64 gpa = a0, npages = a1, attrs = a2; + + ret = -KVM_ENOSYS; + if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) + break; + + if (!PAGE_ALIGNED(gpa) || !npages || + gpa_to_gfn(gpa) + npages <= gpa_to_gfn(gpa)) { + ret = -KVM_EINVAL; + break; + } + + vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; + vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + vcpu->run->hypercall.args[0] = gpa; + vcpu->run->hypercall.args[1] = npages; + vcpu->run->hypercall.args[2] = attrs; + vcpu->run->hypercall.longmode = op_64_bit; + vcpu->arch.complete_userspace_io = complete_hypercall_exit; + return 0; + } default: ret = -KVM_ENOSYS; break; @@ -8461,9 +8788,6 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) int kvm_check_nested_events(struct kvm_vcpu *vcpu) { - if (WARN_ON_ONCE(!is_guest_mode(vcpu))) - return -EIO; - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { kvm_x86_ops.nested_ops->triple_fault(vcpu); return 1; @@ -8479,7 +8803,7 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu) static_call(kvm_x86_queue_exception)(vcpu); } -static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) +static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) { int r; bool can_inject = true; @@ -8526,7 +8850,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (is_guest_mode(vcpu)) { r = kvm_check_nested_events(vcpu); if (r < 0) - goto busy; + goto out; } /* try to inject new event if pending */ @@ -8568,7 +8892,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (vcpu->arch.smi_pending) { r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY; if (r < 0) - goto busy; + goto out; if (r) { vcpu->arch.smi_pending = false; ++vcpu->arch.smi_count; @@ -8581,7 +8905,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (vcpu->arch.nmi_pending) { r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY; if (r < 0) - goto busy; + goto out; if (r) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; @@ -8596,7 +8920,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (kvm_cpu_has_injectable_intr(vcpu)) { r = can_inject ? static_call(kvm_x86_interrupt_allowed)(vcpu, true) : -EBUSY; if (r < 0) - goto busy; + goto out; if (r) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); static_call(kvm_x86_set_irq)(vcpu); @@ -8612,11 +8936,14 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit *req_immediate_exit = true; WARN_ON(vcpu->arch.exception.pending); - return; + return 0; -busy: - *req_immediate_exit = true; - return; +out: + if (r == -EBUSY) { + *req_immediate_exit = true; + r = 0; + } + return r; } static void process_nmi(struct kvm_vcpu *vcpu) @@ -8795,10 +9122,9 @@ static void enter_smm(struct kvm_vcpu *vcpu) { struct kvm_segment cs, ds; struct desc_ptr dt; + unsigned long cr0; char buf[512]; - u32 cr0; - trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true); memset(buf, 0, 512); #ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) @@ -8808,13 +9134,13 @@ static void enter_smm(struct kvm_vcpu *vcpu) enter_smm_save_state_32(vcpu, buf); /* - * Give pre_enter_smm() a chance to make ISA-specific changes to the - * vCPU state (e.g. leave guest mode) after we've saved the state into - * the SMM state-save area. + * Give enter_smm() a chance to make ISA-specific changes to the vCPU + * state (e.g. leave guest mode) after we've saved the state into the + * SMM state-save area. */ - static_call(kvm_x86_pre_enter_smm)(vcpu, buf); + static_call(kvm_x86_enter_smm)(vcpu, buf); - vcpu->arch.hflags |= HF_SMM_MASK; + kvm_smm_changed(vcpu, true); kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); if (static_call(kvm_x86_get_nmi_mask)(vcpu)) @@ -8903,6 +9229,15 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) vcpu->arch.apicv_active = kvm_apicv_activated(vcpu->kvm); kvm_apic_update_apicv(vcpu); static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu); + + /* + * When APICv gets disabled, we may still have injected interrupts + * pending. At the same time, KVM_REQ_EVENT may not be set as APICv was + * still active when the interrupt got accepted. Make sure + * inject_pending_event() is called to check for that. + */ + if (!vcpu->arch.apicv_active) + kvm_make_request(KVM_REQ_EVENT, vcpu); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); @@ -9078,7 +9413,7 @@ static int vcpu_enter_guest(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_HV_TLB_FLUSH, 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)) { @@ -9171,13 +9506,21 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || kvm_xen_has_interrupt(vcpu)) { ++vcpu->stat.req_event; - kvm_apic_accept_events(vcpu); + r = kvm_apic_accept_events(vcpu); + if (r < 0) { + r = 0; + goto out; + } if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { r = 1; goto out; } - inject_pending_event(vcpu, &req_immediate_exit); + r = inject_pending_event(vcpu, &req_immediate_exit); + if (r < 0) { + r = 0; + goto out; + } if (req_int_win) static_call(kvm_x86_enable_irq_window)(vcpu); @@ -9379,7 +9722,8 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) return 1; } - kvm_apic_accept_events(vcpu); + if (kvm_apic_accept_events(vcpu) < 0) + return 0; switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: case KVM_MP_STATE_AP_RESET_HOLD: @@ -9425,7 +9769,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (r <= 0) break; - kvm_clear_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_clear_request(KVM_REQ_UNBLOCK, vcpu); if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); @@ -9603,7 +9947,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) goto out; } kvm_vcpu_block(vcpu); - kvm_apic_accept_events(vcpu); + if (kvm_apic_accept_events(vcpu) < 0) { + r = 0; + goto out; + } kvm_clear_request(KVM_REQ_UNHALT, vcpu); r = -EAGAIN; if (signal_pending(current)) { @@ -9752,7 +10099,7 @@ void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) } EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); -static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static void __get_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { struct desc_ptr dt; @@ -9785,14 +10132,36 @@ skip_protected_regs: sregs->cr8 = kvm_get_cr8(vcpu); sregs->efer = vcpu->arch.efer; sregs->apic_base = kvm_get_apic_base(vcpu); +} - memset(sregs->interrupt_bitmap, 0, sizeof(sregs->interrupt_bitmap)); +static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + __get_sregs_common(vcpu, sregs); + + if (vcpu->arch.guest_state_protected) + return; if (vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft) set_bit(vcpu->arch.interrupt.nr, (unsigned long *)sregs->interrupt_bitmap); } +static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) +{ + int i; + + __get_sregs_common(vcpu, (struct kvm_sregs *)sregs2); + + if (vcpu->arch.guest_state_protected) + return; + + if (is_pae_paging(vcpu)) { + for (i = 0 ; i < 4 ; i++) + sregs2->pdptrs[i] = kvm_pdptr_read(vcpu, i); + sregs2->flags |= KVM_SREGS2_FLAGS_PDPTRS_VALID; + } +} + int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { @@ -9805,11 +10174,17 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + int r; + vcpu_load(vcpu); if (kvm_mpx_supported()) kvm_load_guest_fpu(vcpu); - kvm_apic_accept_events(vcpu); + r = kvm_apic_accept_events(vcpu); + if (r < 0) + goto out; + r = 0; + if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED || vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) && vcpu->arch.pv.pv_unhalted) @@ -9817,10 +10192,11 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, else mp_state->mp_state = vcpu->arch.mp_state; +out: if (kvm_mpx_supported()) kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); - return 0; + return r; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, @@ -9904,24 +10280,23 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return kvm_is_valid_cr4(vcpu, sregs->cr4); } -static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, + int *mmu_reset_needed, bool update_pdptrs) { struct msr_data apic_base_msr; - int mmu_reset_needed = 0; - int pending_vec, max_bits, idx; + int idx; struct desc_ptr dt; - int ret = -EINVAL; if (!kvm_is_valid_sregs(vcpu, sregs)) - goto out; + return -EINVAL; apic_base_msr.data = sregs->apic_base; apic_base_msr.host_initiated = true; if (kvm_set_apic_base(vcpu, &apic_base_msr)) - goto out; + return -EINVAL; if (vcpu->arch.guest_state_protected) - goto skip_protected_regs; + return 0; dt.size = sregs->idt.limit; dt.address = sregs->idt.base; @@ -9931,31 +10306,30 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) static_call(kvm_x86_set_gdt)(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; - mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; + *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); kvm_set_cr8(vcpu, sregs->cr8); - mmu_reset_needed |= vcpu->arch.efer != sregs->efer; + *mmu_reset_needed |= vcpu->arch.efer != sregs->efer; static_call(kvm_x86_set_efer)(vcpu, sregs->efer); - mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; + *mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0); vcpu->arch.cr0 = sregs->cr0; - mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; + *mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4); - idx = srcu_read_lock(&vcpu->kvm->srcu); - if (is_pae_paging(vcpu)) { - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); - mmu_reset_needed = 1; + if (update_pdptrs) { + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (is_pae_paging(vcpu)) { + load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + *mmu_reset_needed = 1; + } + srcu_read_unlock(&vcpu->kvm->srcu, idx); } - srcu_read_unlock(&vcpu->kvm->srcu, idx); - - if (mmu_reset_needed) - kvm_mmu_reset_context(vcpu); kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); @@ -9975,20 +10349,63 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) !is_protmode(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; -skip_protected_regs: + return 0; +} + +static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + int pending_vec, max_bits; + int mmu_reset_needed = 0; + int ret = __set_sregs_common(vcpu, sregs, &mmu_reset_needed, true); + + if (ret) + return ret; + + if (mmu_reset_needed) + kvm_mmu_reset_context(vcpu); + max_bits = KVM_NR_INTERRUPTS; pending_vec = find_first_bit( (const unsigned long *)sregs->interrupt_bitmap, max_bits); + if (pending_vec < max_bits) { kvm_queue_interrupt(vcpu, pending_vec, false); pr_debug("Set back pending irq %d\n", pending_vec); + kvm_make_request(KVM_REQ_EVENT, vcpu); } + return 0; +} - kvm_make_request(KVM_REQ_EVENT, vcpu); +static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) +{ + int mmu_reset_needed = 0; + bool valid_pdptrs = sregs2->flags & KVM_SREGS2_FLAGS_PDPTRS_VALID; + bool pae = (sregs2->cr0 & X86_CR0_PG) && (sregs2->cr4 & X86_CR4_PAE) && + !(sregs2->efer & EFER_LMA); + int i, ret; - ret = 0; -out: - return ret; + if (sregs2->flags & ~KVM_SREGS2_FLAGS_PDPTRS_VALID) + return -EINVAL; + + if (valid_pdptrs && (!pae || vcpu->arch.guest_state_protected)) + return -EINVAL; + + ret = __set_sregs_common(vcpu, (struct kvm_sregs *)sregs2, + &mmu_reset_needed, !valid_pdptrs); + if (ret) + return ret; + + if (valid_pdptrs) { + for (i = 0; i < 4 ; i++) + kvm_pdptr_write(vcpu, i, sregs2->pdptrs[i]); + + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + mmu_reset_needed = 1; + vcpu->arch.pdptrs_from_userspace = true; + } + if (mmu_reset_needed) + kvm_mmu_reset_context(vcpu); + return 0; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, @@ -10044,8 +10461,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, kvm_update_dr7(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) + - get_segment_base(vcpu, VCPU_SREG_CS); + vcpu->arch.singlestep_rip = kvm_get_linear_rip(vcpu); /* * Trigger an rflags update that will inject or remove the trace @@ -10213,13 +10629,13 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) struct page *page; int r; + vcpu->arch.last_vmentry_cpu = -1; + if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; - kvm_set_tsc_khz(vcpu, max_tsc_khz); - r = kvm_mmu_create(vcpu); if (r < 0) return r; @@ -10279,6 +10695,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.pending_external_vector = -1; vcpu->arch.preempted_in_kernel = false; +#if IS_ENABLED(CONFIG_HYPERV) + vcpu->arch.hv_root_tdp = INVALID_PAGE; +#endif + r = static_call(kvm_x86_vcpu_create)(vcpu); if (r) goto free_guest_fpu; @@ -10287,8 +10707,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); + kvm_set_tsc_khz(vcpu, max_tsc_khz); kvm_vcpu_reset(vcpu, false); - kvm_init_mmu(vcpu, false); + kvm_init_mmu(vcpu); vcpu_put(vcpu); return 0; @@ -10362,6 +10783,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { + unsigned long old_cr0 = kvm_read_cr0(vcpu); + kvm_lapic_reset(vcpu, init_event); vcpu->arch.hflags = 0; @@ -10430,6 +10853,17 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.ia32_xss = 0; static_call(kvm_x86_vcpu_reset)(vcpu, init_event); + + /* + * Reset the MMU context if paging was enabled prior to INIT (which is + * implied if CR0.PG=1 as CR0 will be '0' prior to RESET). Unlike the + * standard CR0/CR4/EFER modification paths, only CR0.PG needs to be + * checked because it is unconditionally cleared on INIT and all other + * paging related bits are ignored if paging is disabled, i.e. CR0.WP, + * CR4, and EFER changes are all irrelevant if CR0.PG was '0'. + */ + if (old_cr0 & X86_CR0_PG) + kvm_mmu_reset_context(vcpu); } void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -10547,6 +10981,9 @@ int kvm_arch_hardware_setup(void *opaque) int r; rdmsrl_safe(MSR_EFER, &host_efer); + if (WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_NX) && + !(host_efer & EFER_NX))) + return -EIO; if (boot_cpu_has(X86_FEATURE_XSAVES)) rdmsrl(MSR_IA32_XSS, host_xss); @@ -10662,9 +11099,15 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.guest_can_read_msr_platform_info = true; +#if IS_ENABLED(CONFIG_HYPERV) + spin_lock_init(&kvm->arch.hv_root_tdp_lock); + kvm->arch.hv_root_tdp = INVALID_PAGE; +#endif + INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); + kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); @@ -10825,17 +11268,23 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_hv_destroy_vm(kvm); } -void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) +static void memslot_rmap_free(struct kvm_memory_slot *slot) { int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { kvfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; + } +} - if (i == 0) - continue; +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) +{ + int i; + + memslot_rmap_free(slot); + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { kvfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } @@ -10843,11 +11292,79 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) kvm_page_track_free_memslot(slot); } -static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, - unsigned long npages) +static int memslot_rmap_alloc(struct kvm_memory_slot *slot, + unsigned long npages) { + const int sz = sizeof(*slot->arch.rmap[0]); int i; + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + int level = i + 1; + int lpages = gfn_to_index(slot->base_gfn + npages - 1, + slot->base_gfn, level) + 1; + + WARN_ON(slot->arch.rmap[i]); + + slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT); + if (!slot->arch.rmap[i]) { + memslot_rmap_free(slot); + return -ENOMEM; + } + } + + return 0; +} + +int alloc_all_memslots_rmaps(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; + int r, i; + + /* + * Check if memslots alreday have rmaps early before acquiring + * the slots_arch_lock below. + */ + if (kvm_memslots_have_rmaps(kvm)) + return 0; + + mutex_lock(&kvm->slots_arch_lock); + + /* + * Read memslots_have_rmaps again, under the slots arch lock, + * before allocating the rmaps + */ + if (kvm_memslots_have_rmaps(kvm)) { + mutex_unlock(&kvm->slots_arch_lock); + return 0; + } + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(slot, slots) { + r = memslot_rmap_alloc(slot, slot->npages); + if (r) { + mutex_unlock(&kvm->slots_arch_lock); + return r; + } + } + } + + /* + * Ensure that memslots_have_rmaps becomes true strictly after + * all the rmap pointers are set. + */ + smp_store_release(&kvm->arch.memslots_have_rmaps, true); + mutex_unlock(&kvm->slots_arch_lock); + return 0; +} + +static int kvm_alloc_memslot_metadata(struct kvm *kvm, + struct kvm_memory_slot *slot, + unsigned long npages) +{ + int i, r; + /* * Clear out the previous array pointers for the KVM_MR_MOVE case. The * old arrays will be freed by __kvm_set_memory_region() if installing @@ -10855,7 +11372,13 @@ static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, */ memset(&slot->arch, 0, sizeof(slot->arch)); - for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + if (kvm_memslots_have_rmaps(kvm)) { + r = memslot_rmap_alloc(slot, npages); + if (r) + return r; + } + + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { struct kvm_lpage_info *linfo; unsigned long ugfn; int lpages; @@ -10864,14 +11387,6 @@ static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, lpages = gfn_to_index(slot->base_gfn + npages - 1, slot->base_gfn, level) + 1; - slot->arch.rmap[i] = - kvcalloc(lpages, sizeof(*slot->arch.rmap[i]), - GFP_KERNEL_ACCOUNT); - if (!slot->arch.rmap[i]) - goto out_free; - if (i == 0) - continue; - linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); if (!linfo) goto out_free; @@ -10901,12 +11416,9 @@ static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, return 0; out_free: - for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.rmap[i]); - slot->arch.rmap[i] = NULL; - if (i == 0) - continue; + memslot_rmap_free(slot); + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { kvfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } @@ -10935,7 +11447,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, enum kvm_mr_change change) { if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) - return kvm_alloc_memslot_metadata(memslot, + return kvm_alloc_memslot_metadata(kvm, memslot, mem->memory_size >> PAGE_SHIFT); return 0; } @@ -11011,36 +11523,19 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, */ kvm_mmu_zap_collapsible_sptes(kvm, new); } else { - /* By default, write-protect everything to log writes. */ - int level = PG_LEVEL_4K; + /* + * Initially-all-set does not require write protecting any page, + * because they're all assumed to be dirty. + */ + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + return; if (kvm_x86_ops.cpu_dirty_log_size) { - /* - * Clear all dirty bits, unless pages are treated as - * dirty from the get-go. - */ - if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) - kvm_mmu_slot_leaf_clear_dirty(kvm, new); - - /* - * Write-protect large pages on write so that dirty - * logging happens at 4k granularity. No need to - * write-protect small SPTEs since write accesses are - * logged by the CPU via dirty bits. - */ - level = PG_LEVEL_2M; - } else if (kvm_dirty_log_manual_protect_and_init_set(kvm)) { - /* - * If we're with initial-all-set, we don't need - * to write protect any small page because - * they're reported as dirty already. However - * we still need to write-protect huge pages - * so that the page split can happen lazily on - * the first write to the huge page. - */ - level = PG_LEVEL_2M; + kvm_mmu_slot_leaf_clear_dirty(kvm, new); + kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_2M); + } else { + kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K); } - kvm_mmu_slot_remove_write_access(kvm, new, level); } } @@ -11428,7 +11923,8 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) void kvm_arch_start_assignment(struct kvm *kvm) { - atomic_inc(&kvm->arch.assigned_device_count); + if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1) + static_call_cond(kvm_x86_start_assignment)(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); @@ -11608,8 +12104,6 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) { bool pcid_enabled; struct x86_exception e; - unsigned i; - unsigned long roots_to_free = 0; struct { u64 pcid; u64 gla; @@ -11643,23 +12137,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) return 1; } - if (kvm_get_active_pcid(vcpu) == operand.pcid) { - kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } - - for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) - if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].pgd) - == operand.pcid) - roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); - - kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free); - /* - * If neither the current cr3 nor any of the prev_roots use the - * given PCID, then nothing needs to be done here because a - * resync will happen anyway before switching to any other CR3. - */ - + kvm_invalidate_pcid(vcpu, operand.pcid); return kvm_skip_emulated_instruction(vcpu); case INVPCID_TYPE_ALL_NON_GLOBAL: @@ -11672,7 +12150,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) fallthrough; case INVPCID_TYPE_ALL_INCL_GLOBAL: - kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return kvm_skip_emulated_instruction(vcpu); default: diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 521f74e5bbf2..44ae10312740 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -157,16 +157,6 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu) return cs_l; } -static inline bool is_la57_mode(struct kvm_vcpu *vcpu) -{ -#ifdef CONFIG_X86_64 - return (vcpu->arch.efer & EFER_LMA) && - kvm_read_cr4_bits(vcpu, X86_CR4_LA57); -#else - return 0; -#endif -} - static inline bool x86_exception_has_error_code(unsigned int vector) { static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) | diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index b93d6cd08a7f..121921b2927c 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -5,7 +5,7 @@ #include <xen/xen.h> #include <asm/fpu/internal.h> -#include <asm/sev-es.h> +#include <asm/sev.h> #include <asm/traps.h> #include <asm/kdebug.h> diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 04aba7e80a36..a9639f663d25 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -529,7 +529,7 @@ void __init sme_enable(struct boot_params *bp) /* * No SME if Hypervisor bit is set. This check is here to * prevent a guest from trying to enable SME. For running as a - * KVM guest the MSR_K8_SYSCFG will be sufficient, but there + * KVM guest the MSR_AMD64_SYSCFG will be sufficient, but there * might be other hypervisors which emulate that MSR as non-zero * or even pass it through to the guest. * A malicious hypervisor can still trick a guest into this @@ -542,8 +542,8 @@ void __init sme_enable(struct boot_params *bp) return; /* For SME, check the SYSCFG MSR */ - msr = __rdmsr(MSR_K8_SYSCFG); - if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + msr = __rdmsr(MSR_AMD64_SYSCFG); + if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT)) return; } else { /* SEV state cannot be controlled by a command line option */ diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index ae744b6a0785..dd40d3fea74e 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -284,7 +284,7 @@ static int __init early_root_info_init(void) /* need to take out [4G, TOM2) for RAM*/ /* SYS_CFG */ - address = MSR_K8_SYSCFG; + address = MSR_AMD64_SYSCFG; rdmsrl(address, val); /* TOP_MEM2 is enabled? */ if (val & (1<<21)) { diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index df7b5477fc4f..7515e78ef898 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -47,7 +47,7 @@ #include <asm/realmode.h> #include <asm/time.h> #include <asm/pgalloc.h> -#include <asm/sev-es.h> +#include <asm/sev.h> /* * We allocate runtime services regions top-down, starting from -4G, i.e. diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 1be71ef5e4c4..2e1c1bec0f9e 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -9,7 +9,7 @@ #include <asm/realmode.h> #include <asm/tlbflush.h> #include <asm/crash.h> -#include <asm/sev-es.h> +#include <asm/sev.h> struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index 84c5d1b33d10..cc8391f86cdb 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -123,9 +123,9 @@ SYM_CODE_START(startup_32) */ btl $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags jnc .Ldone - movl $MSR_K8_SYSCFG, %ecx + movl $MSR_AMD64_SYSCFG, %ecx rdmsr - bts $MSR_K8_SYSCFG_MEM_ENCRYPT_BIT, %eax + bts $MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT, %eax jc .Ldone /* diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 0270cd7ca165..acd1f881273e 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -372,9 +372,38 @@ struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync) return bic->bfqq[is_sync]; } +static void bfq_put_stable_ref(struct bfq_queue *bfqq); + void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync) { + /* + * If bfqq != NULL, then a non-stable queue merge between + * bic->bfqq and bfqq is happening here. This causes troubles + * in the following case: bic->bfqq has also been scheduled + * for a possible stable merge with bic->stable_merge_bfqq, + * and bic->stable_merge_bfqq == bfqq happens to + * hold. Troubles occur because bfqq may then undergo a split, + * thereby becoming eligible for a stable merge. Yet, if + * bic->stable_merge_bfqq points exactly to bfqq, then bfqq + * would be stably merged with itself. To avoid this anomaly, + * we cancel the stable merge if + * bic->stable_merge_bfqq == bfqq. + */ bic->bfqq[is_sync] = bfqq; + + if (bfqq && bic->stable_merge_bfqq == bfqq) { + /* + * Actually, these same instructions are executed also + * in bfq_setup_cooperator, in case of abort or actual + * execution of a stable merge. We could avoid + * repeating these instructions there too, but if we + * did so, we would nest even more complexity in this + * function. + */ + bfq_put_stable_ref(bic->stable_merge_bfqq); + + bic->stable_merge_bfqq = NULL; + } } struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic) @@ -2263,10 +2292,9 @@ static void bfq_remove_request(struct request_queue *q, } -static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio, +static bool bfq_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { - struct request_queue *q = hctx->queue; struct bfq_data *bfqd = q->elevator->elevator_data; struct request *free = NULL; /* @@ -2631,8 +2659,6 @@ static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq, static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd, struct bfq_queue *bfqq); -static void bfq_put_stable_ref(struct bfq_queue *bfqq); - /* * Attempt to schedule a merge of bfqq with the currently in-service * queue or with a close queue among the scheduled queues. Return diff --git a/block/blk-iocost.c b/block/blk-iocost.c index e0c4baa01857..c2d6bc88d3f1 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1069,7 +1069,17 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, lockdep_assert_held(&ioc->lock); - inuse = clamp_t(u32, inuse, 1, active); + /* + * For an active leaf node, its inuse shouldn't be zero or exceed + * @active. An active internal node's inuse is solely determined by the + * inuse to active ratio of its children regardless of @inuse. + */ + if (list_empty(&iocg->active_list) && iocg->child_active_sum) { + inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum, + iocg->child_active_sum); + } else { + inuse = clamp_t(u32, inuse, 1, active); + } iocg->last_inuse = iocg->inuse; if (save) @@ -1086,7 +1096,7 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, /* update the level sums */ parent->child_active_sum += (s32)(active - child->active); parent->child_inuse_sum += (s32)(inuse - child->inuse); - /* apply the udpates */ + /* apply the updates */ child->active = active; child->inuse = inuse; diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 42a365b1b9c0..996a4b2f73aa 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -358,14 +358,16 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { struct elevator_queue *e = q->elevator; - struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); - struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, bio->bi_opf, ctx); + struct blk_mq_ctx *ctx; + struct blk_mq_hw_ctx *hctx; bool ret = false; enum hctx_type type; if (e && e->type->ops.bio_merge) - return e->type->ops.bio_merge(hctx, bio, nr_segs); + return e->type->ops.bio_merge(q, bio, nr_segs); + ctx = blk_mq_get_ctx(q); + hctx = blk_mq_map_queue(q, bio->bi_opf, ctx); type = hctx->type; if (!(hctx->flags & BLK_MQ_F_SHOULD_MERGE) || list_empty_careful(&ctx->rq_lists[type])) diff --git a/block/blk-mq.c b/block/blk-mq.c index 466676bc2f0b..c86c01bfecdb 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2232,8 +2232,9 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) /* Bypass scheduler for flush requests */ blk_insert_flush(rq); blk_mq_run_hw_queue(data.hctx, true); - } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs || - !blk_queue_nonrot(q))) { + } else if (plug && (q->nr_hw_queues == 1 || + blk_mq_is_sbitmap_shared(rq->mq_hctx->flags) || + q->mq_ops->commit_rqs || !blk_queue_nonrot(q))) { /* * Use plugging if we have a ->commit_rqs() hook as well, as * we know the driver uses bd->last in a smart fashion. @@ -3285,10 +3286,12 @@ EXPORT_SYMBOL(blk_mq_init_allocated_queue); /* tags can _not_ be used after returning from blk_mq_exit_queue */ void blk_mq_exit_queue(struct request_queue *q) { - struct blk_mq_tag_set *set = q->tag_set; + struct blk_mq_tag_set *set = q->tag_set; - blk_mq_del_queue_tag_set(q); + /* Checks hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED. */ blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); + /* May clear BLK_MQ_F_TAG_QUEUE_SHARED in hctx->flags. */ + blk_mq_del_queue_tag_set(q); } static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 8969e122f081..81e3279ecd57 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -561,11 +561,12 @@ static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) } } -static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio, +static bool kyber_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { + struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); + struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, bio->bi_opf, ctx); struct kyber_hctx_data *khd = hctx->sched_data; - struct blk_mq_ctx *ctx = blk_mq_get_ctx(hctx->queue); struct kyber_ctx_queue *kcq = &khd->kcqs[ctx->index_hw[hctx->type]]; unsigned int sched_domain = kyber_sched_domain(bio->bi_opf); struct list_head *rq_list = &kcq->rq_list[sched_domain]; diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 04aded71ead2..8eea2cbf2bf4 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -461,10 +461,9 @@ static int dd_request_merge(struct request_queue *q, struct request **rq, return ELEVATOR_NO_MERGE; } -static bool dd_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio, +static bool dd_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { - struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; struct request *free = NULL; bool ret; diff --git a/block/partitions/efi.c b/block/partitions/efi.c index b64bfdd4326c..e2716792ecc1 100644 --- a/block/partitions/efi.c +++ b/block/partitions/efi.c @@ -682,7 +682,7 @@ static void utf16_le_to_7bit(const __le16 *in, unsigned int size, u8 *out) } /** - * efi_partition(struct parsed_partitions *state) + * efi_partition - scan for GPT partitions * @state: disk parsed partitions * * Description: called from check.c, if the disk contains GPT diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 16c0fe8a72a7..d260bc1f3e6e 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -1313,6 +1313,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on) {"PNP0C0B", }, /* Generic ACPI fan */ {"INT3404", }, /* Fan */ {"INTC1044", }, /* Fan for Tiger Lake generation */ + {"INTC1048", }, /* Fan for Alder Lake generation */ {} }; struct acpi_device *adev = ACPI_COMPANION(dev); diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index b852cff80287..f973bbe90e5e 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -142,6 +142,7 @@ int acpi_device_sleep_wake(struct acpi_device *dev, int acpi_power_get_inferred_state(struct acpi_device *device, int *state); int acpi_power_on_resources(struct acpi_device *device, int state); int acpi_power_transition(struct acpi_device *device, int state); +void acpi_turn_off_unused_power_resources(void); /* -------------------------------------------------------------------------- Device Power Management diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 958aaac869e8..23d9a09d7060 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -686,6 +686,13 @@ int nfit_spa_type(struct acpi_nfit_system_address *spa) return -1; } +static size_t sizeof_spa(struct acpi_nfit_system_address *spa) +{ + if (spa->flags & ACPI_NFIT_LOCATION_COOKIE_VALID) + return sizeof(*spa); + return sizeof(*spa) - 8; +} + static bool add_spa(struct acpi_nfit_desc *acpi_desc, struct nfit_table_prev *prev, struct acpi_nfit_system_address *spa) @@ -693,22 +700,22 @@ static bool add_spa(struct acpi_nfit_desc *acpi_desc, struct device *dev = acpi_desc->dev; struct nfit_spa *nfit_spa; - if (spa->header.length != sizeof(*spa)) + if (spa->header.length != sizeof_spa(spa)) return false; list_for_each_entry(nfit_spa, &prev->spas, list) { - if (memcmp(nfit_spa->spa, spa, sizeof(*spa)) == 0) { + if (memcmp(nfit_spa->spa, spa, sizeof_spa(spa)) == 0) { list_move_tail(&nfit_spa->list, &acpi_desc->spas); return true; } } - nfit_spa = devm_kzalloc(dev, sizeof(*nfit_spa) + sizeof(*spa), + nfit_spa = devm_kzalloc(dev, sizeof(*nfit_spa) + sizeof_spa(spa), GFP_KERNEL); if (!nfit_spa) return false; INIT_LIST_HEAD(&nfit_spa->list); - memcpy(nfit_spa->spa, spa, sizeof(*spa)); + memcpy(nfit_spa->spa, spa, sizeof_spa(spa)); list_add_tail(&nfit_spa->list, &acpi_desc->spas); dev_dbg(dev, "spa index: %d type: %s\n", spa->range_index, diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 32974b575e46..56102eaaa2da 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -995,6 +995,7 @@ void acpi_resume_power_resources(void) mutex_unlock(&power_resource_list_lock); } +#endif void acpi_turn_off_unused_power_resources(void) { @@ -1015,4 +1016,3 @@ void acpi_turn_off_unused_power_resources(void) mutex_unlock(&power_resource_list_lock); } -#endif diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index a22778e880c2..453eff8ec8c3 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -700,6 +700,7 @@ int acpi_device_add(struct acpi_device *device, result = acpi_device_set_name(device, acpi_device_bus_id); if (result) { + kfree_const(acpi_device_bus_id->bus_id); kfree(acpi_device_bus_id); goto err_unlock; } @@ -2359,6 +2360,8 @@ int __init acpi_scan_init(void) } } + acpi_turn_off_unused_power_resources(); + acpi_scan_initialized = true; out: diff --git a/drivers/acpi/sleep.h b/drivers/acpi/sleep.h index 1856f76ac83f..7fe41ee489d6 100644 --- a/drivers/acpi/sleep.h +++ b/drivers/acpi/sleep.h @@ -8,7 +8,6 @@ extern struct list_head acpi_wakeup_device_list; extern struct mutex acpi_device_lock; extern void acpi_resume_power_resources(void); -extern void acpi_turn_off_unused_power_resources(void); static inline acpi_status acpi_set_waking_vector(u32 wakeup_address) { diff --git a/drivers/base/core.c b/drivers/base/core.c index 4a8bf8cda52b..628e33939aca 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -150,7 +150,7 @@ void fwnode_links_purge(struct fwnode_handle *fwnode) fwnode_links_purge_consumers(fwnode); } -static void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode) +void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode) { struct fwnode_handle *child; @@ -164,6 +164,7 @@ static void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode) fwnode_for_each_available_child_node(fwnode, child) fw_devlink_purge_absent_suppliers(child); } +EXPORT_SYMBOL_GPL(fw_devlink_purge_absent_suppliers); #ifdef CONFIG_SRCU static DEFINE_MUTEX(device_links_lock); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 1fc1a992f90c..b570848d23e0 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1637,6 +1637,7 @@ void pm_runtime_init(struct device *dev) dev->power.request_pending = false; dev->power.request = RPM_REQ_NONE; dev->power.deferred_resume = false; + dev->power.needs_force_resume = 0; INIT_WORK(&dev->power.work, pm_runtime_work); dev->power.timer_expires = 0; @@ -1804,10 +1805,12 @@ int pm_runtime_force_suspend(struct device *dev) * its parent, but set its status to RPM_SUSPENDED anyway in case this * function will be called again for it in the meantime. */ - if (pm_runtime_need_not_resume(dev)) + if (pm_runtime_need_not_resume(dev)) { pm_runtime_set_suspended(dev); - else + } else { __update_runtime_status(dev, RPM_SUSPENDED); + dev->power.needs_force_resume = 1; + } return 0; @@ -1834,7 +1837,7 @@ int pm_runtime_force_resume(struct device *dev) int (*callback)(struct device *); int ret = 0; - if (!pm_runtime_status_suspended(dev) || pm_runtime_need_not_resume(dev)) + if (!pm_runtime_status_suspended(dev) || !dev->power.needs_force_resume) goto out; /* @@ -1853,6 +1856,7 @@ int pm_runtime_force_resume(struct device *dev) pm_runtime_mark_last_busy(dev); out: + dev->power.needs_force_resume = 0; pm_runtime_enable(dev); return ret; } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 4ff71b579cfc..45d2c28c8fc8 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1980,7 +1980,8 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd) * config ref and try to destroy the workqueue from inside the work * queue. */ - flush_workqueue(nbd->recv_workq); + if (nbd->recv_workq) + flush_workqueue(nbd->recv_workq); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); @@ -2014,12 +2015,11 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } mutex_unlock(&nbd_index_mutex); - if (!refcount_inc_not_zero(&nbd->config_refs)) { - nbd_put(nbd); - return 0; - } + if (!refcount_inc_not_zero(&nbd->config_refs)) + goto put_nbd; nbd_disconnect_and_put(nbd); nbd_config_put(nbd); +put_nbd: nbd_put(nbd); return 0; } diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index eff1f12d981a..c84d23951219 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -656,6 +656,7 @@ int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip) if (nr_commands != be32_to_cpup((__be32 *)&buf.data[TPM_HEADER_SIZE + 5])) { + rc = -EFAULT; tpm_buf_destroy(&buf); goto out; } diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index a2e0395cbe61..55b9d3965ae1 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -709,16 +709,14 @@ static int tpm_tis_gen_interrupt(struct tpm_chip *chip) cap_t cap; int ret; - /* TPM 2.0 */ - if (chip->flags & TPM_CHIP_FLAG_TPM2) - return tpm2_get_tpm_pt(chip, 0x100, &cap2, desc); - - /* TPM 1.2 */ ret = request_locality(chip, 0); if (ret < 0) return ret; - ret = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, desc, 0); + if (chip->flags & TPM_CHIP_FLAG_TPM2) + ret = tpm2_get_tpm_pt(chip, 0x100, &cap2, desc); + else + ret = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, desc, 0); release_locality(chip, 0); @@ -1127,12 +1125,20 @@ int tpm_tis_resume(struct device *dev) if (ret) return ret; - /* TPM 1.2 requires self-test on resume. This function actually returns + /* + * TPM 1.2 requires self-test on resume. This function actually returns * an error code but for unknown reason it isn't handled. */ - if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) + if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) { + ret = request_locality(chip, 0); + if (ret < 0) + return ret; + tpm1_do_selftest(chip); + release_locality(chip, 0); + } + return 0; } EXPORT_SYMBOL_GPL(tpm_tis_resume); diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index e2ec1b745243..65508eb89ec9 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -4540,6 +4540,9 @@ int of_clk_add_provider(struct device_node *np, struct of_clk_provider *cp; int ret; + if (!np) + return 0; + cp = kzalloc(sizeof(*cp), GFP_KERNEL); if (!cp) return -ENOMEM; @@ -4579,6 +4582,9 @@ int of_clk_add_hw_provider(struct device_node *np, struct of_clk_provider *cp; int ret; + if (!np) + return 0; + cp = kzalloc(sizeof(*cp), GFP_KERNEL); if (!cp) return -ENOMEM; @@ -4676,6 +4682,9 @@ void of_clk_del_provider(struct device_node *np) { struct of_clk_provider *cp; + if (!np) + return; + mutex_lock(&of_clk_mutex); list_for_each_entry(cp, &of_clk_providers, link) { if (cp->node == np) { diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 977fd05ac35f..d6ece7bbce89 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -419,7 +419,7 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr); } -#ifdef VDSO_CLOCKMODE_HVCLOCK +#ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { vclocks_set_used(VDSO_CLOCKMODE_HVCLOCK); @@ -435,7 +435,7 @@ static struct clocksource hyperv_cs_tsc = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, .suspend= suspend_hv_clock_tsc, .resume = resume_hv_clock_tsc, -#ifdef VDSO_CLOCKMODE_HVCLOCK +#ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK .enable = hv_cs_enable, .vdso_clock_mode = VDSO_CLOCKMODE_HVCLOCK, #else diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index d1bbc16fba4b..7e7450453714 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -646,7 +646,11 @@ static u64 get_max_boost_ratio(unsigned int cpu) return 0; } - highest_perf = perf_caps.highest_perf; + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + highest_perf = amd_get_highest_perf(); + else + highest_perf = perf_caps.highest_perf; + nominal_perf = perf_caps.nominal_perf; if (!highest_perf || !nominal_perf) { diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index f0401064d7aa..0e69dffd5a76 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -3033,6 +3033,14 @@ static const struct x86_cpu_id hwp_support_ids[] __initconst = { {} }; +static bool intel_pstate_hwp_is_enabled(void) +{ + u64 value; + + rdmsrl(MSR_PM_ENABLE, value); + return !!(value & 0x1); +} + static int __init intel_pstate_init(void) { const struct x86_cpu_id *id; @@ -3051,8 +3059,12 @@ static int __init intel_pstate_init(void) * Avoid enabling HWP for processors without EPP support, * because that means incomplete HWP implementation which is a * corner case and supporting it is generally problematic. + * + * If HWP is enabled already, though, there is no choice but to + * deal with it. */ - if (!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) { + if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) || + intel_pstate_hwp_is_enabled()) { hwp_active++; hwp_mode_bdw = id->driver_data; intel_pstate.attr = hwp_cpufreq_attrs; diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 9fa4dfc6ebee..f0d8f60acee1 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -3083,7 +3083,7 @@ static void read_mc_regs(struct amd64_pvt *pvt) edac_dbg(0, " TOP_MEM: 0x%016llx\n", pvt->top_mem); /* Check first whether TOP_MEM2 is enabled: */ - rdmsrl(MSR_K8_SYSCFG, msr_val); + rdmsrl(MSR_AMD64_SYSCFG, msr_val); if (msr_val & BIT(21)) { rdmsrl(MSR_K8_TOP_MEM2, pvt->top_mem2); edac_dbg(0, " TOP_MEM2: 0x%016llx\n", pvt->top_mem2); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index dc3a69296321..264176a01e16 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1006,6 +1006,7 @@ struct amdgpu_device { struct amdgpu_df df; struct amdgpu_ip_block ip_blocks[AMDGPU_MAX_IP_NUM]; + uint32_t harvest_ip_mask; int num_ip_blocks; struct mutex mn_lock; DECLARE_HASHTABLE(mn_hash, 7); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 7d3b54615147..8b2a37bf2adf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1683,6 +1683,19 @@ int amdgpu_device_ip_block_add(struct amdgpu_device *adev, if (!ip_block_version) return -EINVAL; + switch (ip_block_version->type) { + case AMD_IP_BLOCK_TYPE_VCN: + if (adev->harvest_ip_mask & AMD_HARVEST_IP_VCN_MASK) + return 0; + break; + case AMD_IP_BLOCK_TYPE_JPEG: + if (adev->harvest_ip_mask & AMD_HARVEST_IP_JPEG_MASK) + return 0; + break; + default: + break; + } + DRM_INFO("add ip block number %d <%s>\n", adev->num_ip_blocks, ip_block_version->funcs->name); @@ -3111,7 +3124,6 @@ bool amdgpu_device_has_dc_support(struct amdgpu_device *adev) return amdgpu_device_asic_has_dc_support(adev->asic_type); } - static void amdgpu_device_xgmi_reset_func(struct work_struct *__work) { struct amdgpu_device *adev = @@ -3276,6 +3288,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, adev->vm_manager.vm_pte_funcs = NULL; adev->vm_manager.vm_pte_num_scheds = 0; adev->gmc.gmc_funcs = NULL; + adev->harvest_ip_mask = 0x0; adev->fence_context = dma_fence_context_alloc(AMDGPU_MAX_RINGS); bitmap_zero(adev->gfx.pipe_reserve_bitmap, AMDGPU_MAX_COMPUTE_QUEUES); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index b2dbcb4df020..e1b6f5891759 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -373,6 +373,34 @@ int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, return -EINVAL; } +void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) +{ + struct binary_header *bhdr; + struct harvest_table *harvest_info; + int i; + + bhdr = (struct binary_header *)adev->mman.discovery_bin; + harvest_info = (struct harvest_table *)(adev->mman.discovery_bin + + le16_to_cpu(bhdr->table_list[HARVEST_INFO].offset)); + + for (i = 0; i < 32; i++) { + if (le32_to_cpu(harvest_info->list[i].hw_id) == 0) + break; + + switch (le32_to_cpu(harvest_info->list[i].hw_id)) { + case VCN_HWID: + adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK; + adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK; + break; + case DMU_HWID: + adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK; + break; + default: + break; + } + } +} + int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev) { struct binary_header *bhdr; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h index 8f6183801cb3..1b1ae21b1037 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h @@ -29,6 +29,7 @@ void amdgpu_discovery_fini(struct amdgpu_device *adev); int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev); +void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev); int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, int *major, int *minor, int *revision); int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index d54af7f8801b..d290ca0b06da 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -623,6 +623,16 @@ static const struct amdgpu_ip_block_version nv_common_ip_block = .funcs = &nv_common_ip_funcs, }; +static bool nv_is_headless_sku(struct pci_dev *pdev) +{ + if ((pdev->device == 0x731E && + (pdev->revision == 0xC6 || pdev->revision == 0xC7)) || + (pdev->device == 0x7340 && pdev->revision == 0xC9) || + (pdev->device == 0x7360 && pdev->revision == 0xC7)) + return true; + return false; +} + static int nv_reg_base_init(struct amdgpu_device *adev) { int r; @@ -635,6 +645,12 @@ static int nv_reg_base_init(struct amdgpu_device *adev) goto legacy_init; } + amdgpu_discovery_harvest_ip(adev); + if (nv_is_headless_sku(adev->pdev)) { + adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK; + adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK; + } + return 0; } @@ -671,16 +687,6 @@ void nv_set_virt_ops(struct amdgpu_device *adev) adev->virt.ops = &xgpu_nv_virt_ops; } -static bool nv_is_headless_sku(struct pci_dev *pdev) -{ - if ((pdev->device == 0x731E && - (pdev->revision == 0xC6 || pdev->revision == 0xC7)) || - (pdev->device == 0x7340 && pdev->revision == 0xC9) || - (pdev->device == 0x7360 && pdev->revision == 0xC7)) - return true; - return false; -} - int nv_set_ip_blocks(struct amdgpu_device *adev) { int r; @@ -728,8 +734,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT && !amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - if (!nv_is_headless_sku(adev->pdev)) - amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); + amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); if (adev->enable_mes) amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block); @@ -752,8 +757,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT && !amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - if (!nv_is_headless_sku(adev->pdev)) - amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); + amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); if (!amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); break; @@ -777,7 +781,6 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block); if (!amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block); - if (adev->enable_mes) amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block); break; @@ -1149,6 +1152,11 @@ static int nv_common_early_init(void *handle) return -EINVAL; } + if (adev->harvest_ip_mask & AMD_HARVEST_IP_VCN_MASK) + adev->pg_flags &= ~(AMD_PG_SUPPORT_VCN | + AMD_PG_SUPPORT_VCN_DPG | + AMD_PG_SUPPORT_JPEG); + if (amdgpu_sriov_vf(adev)) { amdgpu_virt_init_setting(adev); xgpu_nv_mailbox_set_irq_funcs(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index d80e12b80c7e..8e1b9a40839f 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1401,7 +1401,8 @@ static int soc15_common_early_init(void *handle) AMD_CG_SUPPORT_MC_MGCG | AMD_CG_SUPPORT_MC_LS | AMD_CG_SUPPORT_SDMA_MGCG | - AMD_CG_SUPPORT_SDMA_LS; + AMD_CG_SUPPORT_SDMA_LS | + AMD_CG_SUPPORT_VCN_MGCG; adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_MMHUB | diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 51a773a37a35..0c1beefa3e49 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -1119,10 +1119,10 @@ static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev) UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_LMI_STATUS, tmp, tmp); - /* put VCPU into reset */ - WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET), - UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK, - ~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK); + /* stall UMC channel */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_CTRL2), + UVD_LMI_CTRL2__STALL_ARB_UMC_MASK, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; @@ -1141,6 +1141,11 @@ static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev) UVD_SOFT_RESET__LMI_SOFT_RESET_MASK, ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK); + /* put VCPU into reset */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET), + UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK, + ~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK); + WREG32_SOC15(UVD, 0, mmUVD_STATUS, 0); vcn_v1_0_enable_clock_gating(adev); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 616f5b1ea3a8..666796a0067c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -650,6 +650,7 @@ struct hdcp_workqueue *hdcp_create_workqueue(struct amdgpu_device *adev, struct /* File created at /sys/class/drm/card0/device/hdcp_srm*/ hdcp_work[0].attr = data_attr; + sysfs_bin_attr_init(&hdcp_work[0].attr); if (sysfs_create_bin_file(&adev->dev->kobj, &hdcp_work[0].attr)) DRM_WARN("Failed to create device file hdcp_srm"); diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 43ed6291b2b8..9ab706cd07ff 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -216,6 +216,12 @@ enum PP_FEATURE_MASK { PP_GFX_DCS_MASK = 0x80000, }; +enum amd_harvest_ip_mask { + AMD_HARVEST_IP_VCN_MASK = 0x1, + AMD_HARVEST_IP_JPEG_MASK = 0x2, + AMD_HARVEST_IP_DMU_MASK = 0x4, +}; + enum DC_FEATURE_MASK { DC_FBC_MASK = 0x1, DC_MULTI_MON_PP_MCLK_SWITCH_MASK = 0x2, diff --git a/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c index 26a5321e621b..15c0b8af376f 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c @@ -4817,70 +4817,70 @@ static int si_populate_smc_initial_state(struct amdgpu_device *adev, u32 reg; int ret; - table->initialState.levels[0].mclk.vDLL_CNTL = + table->initialState.level.mclk.vDLL_CNTL = cpu_to_be32(si_pi->clock_registers.dll_cntl); - table->initialState.levels[0].mclk.vMCLK_PWRMGT_CNTL = + table->initialState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(si_pi->clock_registers.mclk_pwrmgt_cntl); - table->initialState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_ad_func_cntl); - table->initialState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_dq_func_cntl); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL_1 = + table->initialState.level.mclk.vMPLL_FUNC_CNTL_1 = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl_1); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL_2 = + table->initialState.level.mclk.vMPLL_FUNC_CNTL_2 = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl_2); - table->initialState.levels[0].mclk.vMPLL_SS = + table->initialState.level.mclk.vMPLL_SS = cpu_to_be32(si_pi->clock_registers.mpll_ss1); - table->initialState.levels[0].mclk.vMPLL_SS2 = + table->initialState.level.mclk.vMPLL_SS2 = cpu_to_be32(si_pi->clock_registers.mpll_ss2); - table->initialState.levels[0].mclk.mclk_value = + table->initialState.level.mclk.mclk_value = cpu_to_be32(initial_state->performance_levels[0].mclk); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_2); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_3); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_4); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM = cpu_to_be32(si_pi->clock_registers.cg_spll_spread_spectrum); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = cpu_to_be32(si_pi->clock_registers.cg_spll_spread_spectrum_2); - table->initialState.levels[0].sclk.sclk_value = + table->initialState.level.sclk.sclk_value = cpu_to_be32(initial_state->performance_levels[0].sclk); - table->initialState.levels[0].arbRefreshState = + table->initialState.level.arbRefreshState = SISLANDS_INITIAL_STATE_ARB_INDEX; - table->initialState.levels[0].ACIndex = 0; + table->initialState.level.ACIndex = 0; ret = si_populate_voltage_value(adev, &eg_pi->vddc_voltage_table, initial_state->performance_levels[0].vddc, - &table->initialState.levels[0].vddc); + &table->initialState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(adev, - &table->initialState.levels[0].vddc, + &table->initialState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(adev, std_vddc, - table->initialState.levels[0].vddc.index, - &table->initialState.levels[0].std_vddc); + table->initialState.level.vddc.index, + &table->initialState.level.std_vddc); } if (eg_pi->vddci_control) si_populate_voltage_value(adev, &eg_pi->vddci_voltage_table, initial_state->performance_levels[0].vddci, - &table->initialState.levels[0].vddci); + &table->initialState.level.vddci); if (si_pi->vddc_phase_shed_control) si_populate_phase_shedding_value(adev, @@ -4888,41 +4888,41 @@ static int si_populate_smc_initial_state(struct amdgpu_device *adev, initial_state->performance_levels[0].vddc, initial_state->performance_levels[0].sclk, initial_state->performance_levels[0].mclk, - &table->initialState.levels[0].vddc); + &table->initialState.level.vddc); - si_populate_initial_mvdd_value(adev, &table->initialState.levels[0].mvdd); + si_populate_initial_mvdd_value(adev, &table->initialState.level.mvdd); reg = CG_R(0xffff) | CG_L(0); - table->initialState.levels[0].aT = cpu_to_be32(reg); - table->initialState.levels[0].bSP = cpu_to_be32(pi->dsp); - table->initialState.levels[0].gen2PCIE = (u8)si_pi->boot_pcie_gen; + table->initialState.level.aT = cpu_to_be32(reg); + table->initialState.level.bSP = cpu_to_be32(pi->dsp); + table->initialState.level.gen2PCIE = (u8)si_pi->boot_pcie_gen; if (adev->gmc.vram_type == AMDGPU_VRAM_TYPE_GDDR5) { - table->initialState.levels[0].strobeMode = + table->initialState.level.strobeMode = si_get_strobe_mode_settings(adev, initial_state->performance_levels[0].mclk); if (initial_state->performance_levels[0].mclk > pi->mclk_edc_enable_threshold) - table->initialState.levels[0].mcFlags = SISLANDS_SMC_MC_EDC_RD_FLAG | SISLANDS_SMC_MC_EDC_WR_FLAG; + table->initialState.level.mcFlags = SISLANDS_SMC_MC_EDC_RD_FLAG | SISLANDS_SMC_MC_EDC_WR_FLAG; else - table->initialState.levels[0].mcFlags = 0; + table->initialState.level.mcFlags = 0; } table->initialState.levelCount = 1; table->initialState.flags |= PPSMC_SWSTATE_FLAG_DC; - table->initialState.levels[0].dpm2.MaxPS = 0; - table->initialState.levels[0].dpm2.NearTDPDec = 0; - table->initialState.levels[0].dpm2.AboveSafeInc = 0; - table->initialState.levels[0].dpm2.BelowSafeInc = 0; - table->initialState.levels[0].dpm2.PwrEfficiencyRatio = 0; + table->initialState.level.dpm2.MaxPS = 0; + table->initialState.level.dpm2.NearTDPDec = 0; + table->initialState.level.dpm2.AboveSafeInc = 0; + table->initialState.level.dpm2.BelowSafeInc = 0; + table->initialState.level.dpm2.PwrEfficiencyRatio = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->initialState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->initialState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } @@ -4953,18 +4953,18 @@ static int si_populate_smc_acpi_state(struct amdgpu_device *adev, if (pi->acpi_vddc) { ret = si_populate_voltage_value(adev, &eg_pi->vddc_voltage_table, - pi->acpi_vddc, &table->ACPIState.levels[0].vddc); + pi->acpi_vddc, &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(adev, - &table->ACPIState.levels[0].vddc, &std_vddc); + &table->ACPIState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(adev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } - table->ACPIState.levels[0].gen2PCIE = si_pi->acpi_pcie_gen; + table->ACPIState.level.gen2PCIE = si_pi->acpi_pcie_gen; if (si_pi->vddc_phase_shed_control) { si_populate_phase_shedding_value(adev, @@ -4972,23 +4972,23 @@ static int si_populate_smc_acpi_state(struct amdgpu_device *adev, pi->acpi_vddc, 0, 0, - &table->ACPIState.levels[0].vddc); + &table->ACPIState.level.vddc); } } else { ret = si_populate_voltage_value(adev, &eg_pi->vddc_voltage_table, - pi->min_vddc_in_table, &table->ACPIState.levels[0].vddc); + pi->min_vddc_in_table, &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(adev, - &table->ACPIState.levels[0].vddc, &std_vddc); + &table->ACPIState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(adev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } - table->ACPIState.levels[0].gen2PCIE = + table->ACPIState.level.gen2PCIE = (u8)amdgpu_get_pcie_gen_support(adev, si_pi->sys_pcie_mask, si_pi->boot_pcie_gen, @@ -5000,14 +5000,14 @@ static int si_populate_smc_acpi_state(struct amdgpu_device *adev, pi->min_vddc_in_table, 0, 0, - &table->ACPIState.levels[0].vddc); + &table->ACPIState.level.vddc); } if (pi->acpi_vddc) { if (eg_pi->acpi_vddci) si_populate_voltage_value(adev, &eg_pi->vddci_voltage_table, eg_pi->acpi_vddci, - &table->ACPIState.levels[0].vddci); + &table->ACPIState.level.vddci); } mclk_pwrmgt_cntl |= MRDCK0_RESET | MRDCK1_RESET; @@ -5018,59 +5018,59 @@ static int si_populate_smc_acpi_state(struct amdgpu_device *adev, spll_func_cntl_2 &= ~SCLK_MUX_SEL_MASK; spll_func_cntl_2 |= SCLK_MUX_SEL(4); - table->ACPIState.levels[0].mclk.vDLL_CNTL = + table->ACPIState.level.mclk.vDLL_CNTL = cpu_to_be32(dll_cntl); - table->ACPIState.levels[0].mclk.vMCLK_PWRMGT_CNTL = + table->ACPIState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(mclk_pwrmgt_cntl); - table->ACPIState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(mpll_ad_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(mpll_dq_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL = cpu_to_be32(mpll_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL_1 = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL_1 = cpu_to_be32(mpll_func_cntl_1); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL_2 = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL_2 = cpu_to_be32(mpll_func_cntl_2); - table->ACPIState.levels[0].mclk.vMPLL_SS = + table->ACPIState.level.mclk.vMPLL_SS = cpu_to_be32(si_pi->clock_registers.mpll_ss1); - table->ACPIState.levels[0].mclk.vMPLL_SS2 = + table->ACPIState.level.mclk.vMPLL_SS2 = cpu_to_be32(si_pi->clock_registers.mpll_ss2); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(spll_func_cntl); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(spll_func_cntl_2); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(spll_func_cntl_3); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(spll_func_cntl_4); - table->ACPIState.levels[0].mclk.mclk_value = 0; - table->ACPIState.levels[0].sclk.sclk_value = 0; + table->ACPIState.level.mclk.mclk_value = 0; + table->ACPIState.level.sclk.sclk_value = 0; - si_populate_mvdd_value(adev, 0, &table->ACPIState.levels[0].mvdd); + si_populate_mvdd_value(adev, 0, &table->ACPIState.level.mvdd); if (eg_pi->dynamic_ac_timing) - table->ACPIState.levels[0].ACIndex = 0; + table->ACPIState.level.ACIndex = 0; - table->ACPIState.levels[0].dpm2.MaxPS = 0; - table->ACPIState.levels[0].dpm2.NearTDPDec = 0; - table->ACPIState.levels[0].dpm2.AboveSafeInc = 0; - table->ACPIState.levels[0].dpm2.BelowSafeInc = 0; - table->ACPIState.levels[0].dpm2.PwrEfficiencyRatio = 0; + table->ACPIState.level.dpm2.MaxPS = 0; + table->ACPIState.level.dpm2.NearTDPDec = 0; + table->ACPIState.level.dpm2.AboveSafeInc = 0; + table->ACPIState.level.dpm2.BelowSafeInc = 0; + table->ACPIState.level.dpm2.PwrEfficiencyRatio = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->ACPIState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->ACPIState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } static int si_populate_ulv_state(struct amdgpu_device *adev, - SISLANDS_SMC_SWSTATE *state) + struct SISLANDS_SMC_SWSTATE_SINGLE *state) { struct evergreen_power_info *eg_pi = evergreen_get_pi(adev); struct si_power_info *si_pi = si_get_pi(adev); @@ -5079,19 +5079,19 @@ static int si_populate_ulv_state(struct amdgpu_device *adev, int ret; ret = si_convert_power_level_to_smc(adev, &ulv->pl, - &state->levels[0]); + &state->level); if (!ret) { if (eg_pi->sclk_deep_sleep) { if (sclk_in_sr <= SCLK_MIN_DEEPSLEEP_FREQ) - state->levels[0].stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_BYPASS; + state->level.stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_BYPASS; else - state->levels[0].stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_THROTTLE; + state->level.stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_THROTTLE; } if (ulv->one_pcie_lane_in_ulv) state->flags |= PPSMC_SWSTATE_FLAG_PCIE_X1; - state->levels[0].arbRefreshState = (u8)(SISLANDS_ULV_STATE_ARB_INDEX); - state->levels[0].ACIndex = 1; - state->levels[0].std_vddc = state->levels[0].vddc; + state->level.arbRefreshState = (u8)(SISLANDS_ULV_STATE_ARB_INDEX); + state->level.ACIndex = 1; + state->level.std_vddc = state->level.vddc; state->levelCount = 1; state->flags |= PPSMC_SWSTATE_FLAG_DC; @@ -5190,7 +5190,9 @@ static int si_init_smc_table(struct amdgpu_device *adev) if (ret) return ret; - table->driverState = table->initialState; + table->driverState.flags = table->initialState.flags; + table->driverState.levelCount = table->initialState.levelCount; + table->driverState.levels[0] = table->initialState.level; ret = si_do_program_memory_timing_parameters(adev, amdgpu_boot_state, SISLANDS_INITIAL_STATE_ARB_INDEX); @@ -5737,8 +5739,8 @@ static int si_upload_ulv_state(struct amdgpu_device *adev) if (ulv->supported && ulv->pl.vddc) { u32 address = si_pi->state_table_start + offsetof(SISLANDS_SMC_STATETABLE, ULVState); - SISLANDS_SMC_SWSTATE *smc_state = &si_pi->smc_statetable.ULVState; - u32 state_size = sizeof(SISLANDS_SMC_SWSTATE); + struct SISLANDS_SMC_SWSTATE_SINGLE *smc_state = &si_pi->smc_statetable.ULVState; + u32 state_size = sizeof(struct SISLANDS_SMC_SWSTATE_SINGLE); memset(smc_state, 0, state_size); diff --git a/drivers/gpu/drm/amd/pm/powerplay/sislands_smc.h b/drivers/gpu/drm/amd/pm/powerplay/sislands_smc.h index 0f7554052c90..c7dc117a688c 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/sislands_smc.h +++ b/drivers/gpu/drm/amd/pm/powerplay/sislands_smc.h @@ -191,6 +191,14 @@ struct SISLANDS_SMC_SWSTATE typedef struct SISLANDS_SMC_SWSTATE SISLANDS_SMC_SWSTATE; +struct SISLANDS_SMC_SWSTATE_SINGLE { + uint8_t flags; + uint8_t levelCount; + uint8_t padding2; + uint8_t padding3; + SISLANDS_SMC_HW_PERFORMANCE_LEVEL level; +}; + #define SISLANDS_SMC_VOLTAGEMASK_VDDC 0 #define SISLANDS_SMC_VOLTAGEMASK_MVDD 1 #define SISLANDS_SMC_VOLTAGEMASK_VDDCI 2 @@ -208,19 +216,19 @@ typedef struct SISLANDS_SMC_VOLTAGEMASKTABLE SISLANDS_SMC_VOLTAGEMASKTABLE; struct SISLANDS_SMC_STATETABLE { - uint8_t thermalProtectType; - uint8_t systemFlags; - uint8_t maxVDDCIndexInPPTable; - uint8_t extraFlags; - uint32_t lowSMIO[SISLANDS_MAX_NO_VREG_STEPS]; - SISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; - SISLANDS_SMC_VOLTAGEMASKTABLE phaseMaskTable; - PP_SIslands_DPM2Parameters dpm2Params; - SISLANDS_SMC_SWSTATE initialState; - SISLANDS_SMC_SWSTATE ACPIState; - SISLANDS_SMC_SWSTATE ULVState; - SISLANDS_SMC_SWSTATE driverState; - SISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE - 1]; + uint8_t thermalProtectType; + uint8_t systemFlags; + uint8_t maxVDDCIndexInPPTable; + uint8_t extraFlags; + uint32_t lowSMIO[SISLANDS_MAX_NO_VREG_STEPS]; + SISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; + SISLANDS_SMC_VOLTAGEMASKTABLE phaseMaskTable; + PP_SIslands_DPM2Parameters dpm2Params; + struct SISLANDS_SMC_SWSTATE_SINGLE initialState; + struct SISLANDS_SMC_SWSTATE_SINGLE ACPIState; + struct SISLANDS_SMC_SWSTATE_SINGLE ULVState; + SISLANDS_SMC_SWSTATE driverState; + SISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE]; }; typedef struct SISLANDS_SMC_STATETABLE SISLANDS_SMC_STATETABLE; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 6a2dee8cef1f..642c60f3d9b1 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1095,44 +1095,6 @@ intel_dp_compute_link_config_wide(struct intel_dp *intel_dp, return -EINVAL; } -/* Optimize link config in order: max bpp, min lanes, min clock */ -static int -intel_dp_compute_link_config_fast(struct intel_dp *intel_dp, - struct intel_crtc_state *pipe_config, - const struct link_config_limits *limits) -{ - const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; - int bpp, clock, lane_count; - int mode_rate, link_clock, link_avail; - - for (bpp = limits->max_bpp; bpp >= limits->min_bpp; bpp -= 2 * 3) { - int output_bpp = intel_dp_output_bpp(pipe_config->output_format, bpp); - - mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock, - output_bpp); - - for (lane_count = limits->min_lane_count; - lane_count <= limits->max_lane_count; - lane_count <<= 1) { - for (clock = limits->min_clock; clock <= limits->max_clock; clock++) { - link_clock = intel_dp->common_rates[clock]; - link_avail = intel_dp_max_data_rate(link_clock, - lane_count); - - if (mode_rate <= link_avail) { - pipe_config->lane_count = lane_count; - pipe_config->pipe_bpp = bpp; - pipe_config->port_clock = link_clock; - - return 0; - } - } - } - } - - return -EINVAL; -} - static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc) { int i, num_bpc; @@ -1382,22 +1344,11 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, intel_dp_can_bigjoiner(intel_dp)) pipe_config->bigjoiner = true; - if (intel_dp_is_edp(intel_dp)) - /* - * Optimize for fast and narrow. eDP 1.3 section 3.3 and eDP 1.4 - * section A.1: "It is recommended that the minimum number of - * lanes be used, using the minimum link rate allowed for that - * lane configuration." - * - * Note that we fall back to the max clock and lane count for eDP - * panels that fail with the fast optimal settings (see - * intel_dp->use_max_params), in which case the fast vs. wide - * choice doesn't matter. - */ - ret = intel_dp_compute_link_config_fast(intel_dp, pipe_config, &limits); - else - /* Optimize for slow and wide. */ - ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits); + /* + * Optimize for slow and wide for everything, because there are some + * eDP 1.3 and 1.4 panels don't work well with fast and narrow. + */ + ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits); /* enable compression if the mode doesn't fit available BW */ drm_dbg_kms(&i915->drm, "Force DSC en = %d\n", intel_dp->force_dsc_en); @@ -2160,7 +2111,7 @@ void intel_dp_check_frl_training(struct intel_dp *intel_dp) * -PCON supports SRC_CTL_MODE (VESA DP2.0-HDMI2.1 PCON Spec Draft-1 Sec-7) * -sink is HDMI2.1 */ - if (!(intel_dp->dpcd[2] & DP_PCON_SOURCE_CTL_MODE) || + if (!(intel_dp->downstream_ports[2] & DP_PCON_SOURCE_CTL_MODE) || !intel_dp_is_hdmi_2_1_sink(intel_dp) || intel_dp->frl.is_trained) return; diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index e5dadde422f7..bbaf05515e88 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -383,7 +383,7 @@ static void intel_overlay_off_tail(struct intel_overlay *overlay) i830_overlay_clock_gating(dev_priv, true); } -static void +__i915_active_call static void intel_overlay_last_flip_retire(struct i915_active *active) { struct intel_overlay *overlay = diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 23f6b00e08e2..f6fe5cb01438 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -189,7 +189,7 @@ compute_partial_view(const struct drm_i915_gem_object *obj, struct i915_ggtt_view view; if (i915_gem_object_is_tiled(obj)) - chunk = roundup(chunk, tile_row_pages(obj)); + chunk = roundup(chunk, tile_row_pages(obj) ?: 1); view.type = I915_GGTT_VIEW_PARTIAL; view.partial.offset = rounddown(page_offset, chunk); diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 176c19633412..74bf6fc8461f 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -641,7 +641,6 @@ static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt) err = pin_pt_dma(vm, pde->pt.base); if (err) { - i915_gem_object_put(pde->pt.base); free_pd(vm, pde); return err; } diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index e72b7a0dc316..8a322594210c 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -653,8 +653,8 @@ static void detect_bit_6_swizzle(struct i915_ggtt *ggtt) * banks of memory are paired and unswizzled on the * uneven portion, so leave that as unknown. */ - if (intel_uncore_read(uncore, C0DRB3) == - intel_uncore_read(uncore, C1DRB3)) { + if (intel_uncore_read16(uncore, C0DRB3) == + intel_uncore_read16(uncore, C1DRB3)) { swizzle_x = I915_BIT_6_SWIZZLE_9_10; swizzle_y = I915_BIT_6_SWIZZLE_9; } diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index cf9a3d384971..aa573b078ae7 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -1156,7 +1156,8 @@ static int auto_active(struct i915_active *ref) return 0; } -static void auto_retire(struct i915_active *ref) +__i915_active_call static void +auto_retire(struct i915_active *ref) { i915_active_put(ref); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index d553f62f4eeb..b4d8e1b01ee4 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1153,10 +1153,6 @@ static void a6xx_llc_slices_init(struct platform_device *pdev, { struct device_node *phandle; - a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem", "gpu_cx"); - if (IS_ERR(a6xx_gpu->llc_mmio)) - return; - /* * There is a different programming path for targets with an mmu500 * attached, so detect if that is the case @@ -1166,6 +1162,11 @@ static void a6xx_llc_slices_init(struct platform_device *pdev, of_device_is_compatible(phandle, "arm,mmu-500")); of_node_put(phandle); + if (a6xx_gpu->have_mmu500) + a6xx_gpu->llc_mmio = NULL; + else + a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem", "gpu_cx"); + a6xx_gpu->llc_slice = llcc_slice_getd(LLCC_GPU); a6xx_gpu->htw_llc_slice = llcc_slice_getd(LLCC_GPUHTW); diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c index 82a8673ab8da..d7e4a39a904e 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.c +++ b/drivers/gpu/drm/msm/dp/dp_audio.c @@ -527,6 +527,7 @@ int dp_audio_hw_params(struct device *dev, dp_audio_setup_acr(audio); dp_audio_safe_to_exit_level(audio); dp_audio_enable(audio, true); + dp_display_signal_audio_start(dp_display); dp_display->audio_enabled = true; end: diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 5a39da6e1eaf..1784e119269b 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -178,6 +178,15 @@ static int dp_del_event(struct dp_display_private *dp_priv, u32 event) return 0; } +void dp_display_signal_audio_start(struct msm_dp *dp_display) +{ + struct dp_display_private *dp; + + dp = container_of(dp_display, struct dp_display_private, dp_display); + + reinit_completion(&dp->audio_comp); +} + void dp_display_signal_audio_complete(struct msm_dp *dp_display) { struct dp_display_private *dp; @@ -586,10 +595,8 @@ static int dp_connect_pending_timeout(struct dp_display_private *dp, u32 data) mutex_lock(&dp->event_mutex); state = dp->hpd_state; - if (state == ST_CONNECT_PENDING) { - dp_display_enable(dp, 0); + if (state == ST_CONNECT_PENDING) dp->hpd_state = ST_CONNECTED; - } mutex_unlock(&dp->event_mutex); @@ -651,7 +658,6 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) dp_add_event(dp, EV_DISCONNECT_PENDING_TIMEOUT, 0, DP_TIMEOUT_5_SECOND); /* signal the disconnect event early to ensure proper teardown */ - reinit_completion(&dp->audio_comp); dp_display_handle_plugged_change(g_dp_display, false); dp_catalog_hpd_config_intr(dp->catalog, DP_DP_HPD_PLUG_INT_MASK | @@ -669,10 +675,8 @@ static int dp_disconnect_pending_timeout(struct dp_display_private *dp, u32 data mutex_lock(&dp->event_mutex); state = dp->hpd_state; - if (state == ST_DISCONNECT_PENDING) { - dp_display_disable(dp, 0); + if (state == ST_DISCONNECT_PENDING) dp->hpd_state = ST_DISCONNECTED; - } mutex_unlock(&dp->event_mutex); @@ -898,7 +902,6 @@ static int dp_display_disable(struct dp_display_private *dp, u32 data) /* wait only if audio was enabled */ if (dp_display->audio_enabled) { /* signal the disconnect event */ - reinit_completion(&dp->audio_comp); dp_display_handle_plugged_change(dp_display, false); if (!wait_for_completion_timeout(&dp->audio_comp, HZ * 5)) @@ -1272,7 +1275,12 @@ static int dp_pm_resume(struct device *dev) status = dp_catalog_link_is_connected(dp->catalog); - if (status) + /* + * can not declared display is connected unless + * HDMI cable is plugged in and sink_count of + * dongle become 1 + */ + if (status && dp->link->sink_count) dp->dp_display.is_connected = true; else dp->dp_display.is_connected = false; diff --git a/drivers/gpu/drm/msm/dp/dp_display.h b/drivers/gpu/drm/msm/dp/dp_display.h index 6092ba1ed85e..5173c89eedf7 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.h +++ b/drivers/gpu/drm/msm/dp/dp_display.h @@ -34,6 +34,7 @@ int dp_display_get_modes(struct msm_dp *dp_display, int dp_display_request_irq(struct msm_dp *dp_display); bool dp_display_check_video_test(struct msm_dp *dp_display); int dp_display_get_test_bpp(struct msm_dp *dp_display); +void dp_display_signal_audio_start(struct msm_dp *dp_display); void dp_display_signal_audio_complete(struct msm_dp *dp_display); #endif /* _DP_DISPLAY_H_ */ diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index f0a2ddf96a4b..ff7f2ec42030 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -843,7 +843,7 @@ int msm_dsi_phy_get_clk_provider(struct msm_dsi_phy *phy, if (pixel_clk_provider) *pixel_clk_provider = phy->provided_clocks->hws[DSI_PIXEL_PLL_CLK]->clk; - return -EINVAL; + return 0; } void msm_dsi_phy_pll_save_state(struct msm_dsi_phy *phy) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c index 582b1428f971..86e40a0d41a3 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c @@ -405,6 +405,10 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov if (!vco_name) return -ENOMEM; + parent_name = devm_kzalloc(dev, 32, GFP_KERNEL); + if (!parent_name) + return -ENOMEM; + clk_name = devm_kzalloc(dev, 32, GFP_KERNEL); if (!clk_name) return -ENOMEM; diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index e1104d2454e2..fe7d17cd35ec 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -42,7 +42,7 @@ * - 1.7.0 - Add MSM_PARAM_SUSPENDS to access suspend count */ #define MSM_VERSION_MAJOR 1 -#define MSM_VERSION_MINOR 6 +#define MSM_VERSION_MINOR 7 #define MSM_VERSION_PATCHLEVEL 0 static const struct drm_mode_config_funcs mode_config_funcs = { diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index b199942266a2..56df86e5f740 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -190,13 +190,25 @@ struct page **msm_gem_get_pages(struct drm_gem_object *obj) } p = get_pages(obj); + + if (!IS_ERR(p)) { + msm_obj->pin_count++; + update_inactive(msm_obj); + } + msm_gem_unlock(obj); return p; } void msm_gem_put_pages(struct drm_gem_object *obj) { - /* when we start tracking the pin count, then do something here */ + struct msm_gem_object *msm_obj = to_msm_bo(obj); + + msm_gem_lock(obj); + msm_obj->pin_count--; + GEM_WARN_ON(msm_obj->pin_count < 0); + update_inactive(msm_obj); + msm_gem_unlock(obj); } int msm_gem_mmap_obj(struct drm_gem_object *obj, @@ -646,6 +658,8 @@ static void *get_vaddr(struct drm_gem_object *obj, unsigned madv) ret = -ENOMEM; goto fail; } + + update_inactive(msm_obj); } return msm_obj->vaddr; diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index a6480d2c81b2..03e2cc2a2ce1 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -221,7 +221,7 @@ static inline bool is_active(struct msm_gem_object *msm_obj) /* imported/exported objects are not purgeable: */ static inline bool is_unpurgeable(struct msm_gem_object *msm_obj) { - return msm_obj->base.dma_buf && msm_obj->base.import_attach; + return msm_obj->base.import_attach || msm_obj->pin_count; } static inline bool is_purgeable(struct msm_gem_object *msm_obj) @@ -271,7 +271,7 @@ static inline void mark_unpurgeable(struct msm_gem_object *msm_obj) static inline bool is_unevictable(struct msm_gem_object *msm_obj) { - return is_unpurgeable(msm_obj) || msm_obj->pin_count || msm_obj->vaddr; + return is_unpurgeable(msm_obj) || msm_obj->vaddr; } static inline void mark_evictable(struct msm_gem_object *msm_obj) diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c index dd5ef6493723..769f666335ac 100644 --- a/drivers/gpu/drm/radeon/ni_dpm.c +++ b/drivers/gpu/drm/radeon/ni_dpm.c @@ -1687,102 +1687,102 @@ static int ni_populate_smc_initial_state(struct radeon_device *rdev, u32 reg; int ret; - table->initialState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(ni_pi->clock_registers.mpll_ad_func_cntl); - table->initialState.levels[0].mclk.vMPLL_AD_FUNC_CNTL_2 = + table->initialState.level.mclk.vMPLL_AD_FUNC_CNTL_2 = cpu_to_be32(ni_pi->clock_registers.mpll_ad_func_cntl_2); - table->initialState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(ni_pi->clock_registers.mpll_dq_func_cntl); - table->initialState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL_2 = + table->initialState.level.mclk.vMPLL_DQ_FUNC_CNTL_2 = cpu_to_be32(ni_pi->clock_registers.mpll_dq_func_cntl_2); - table->initialState.levels[0].mclk.vMCLK_PWRMGT_CNTL = + table->initialState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(ni_pi->clock_registers.mclk_pwrmgt_cntl); - table->initialState.levels[0].mclk.vDLL_CNTL = + table->initialState.level.mclk.vDLL_CNTL = cpu_to_be32(ni_pi->clock_registers.dll_cntl); - table->initialState.levels[0].mclk.vMPLL_SS = + table->initialState.level.mclk.vMPLL_SS = cpu_to_be32(ni_pi->clock_registers.mpll_ss1); - table->initialState.levels[0].mclk.vMPLL_SS2 = + table->initialState.level.mclk.vMPLL_SS2 = cpu_to_be32(ni_pi->clock_registers.mpll_ss2); - table->initialState.levels[0].mclk.mclk_value = + table->initialState.level.mclk.mclk_value = cpu_to_be32(initial_state->performance_levels[0].mclk); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(ni_pi->clock_registers.cg_spll_func_cntl); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(ni_pi->clock_registers.cg_spll_func_cntl_2); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(ni_pi->clock_registers.cg_spll_func_cntl_3); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(ni_pi->clock_registers.cg_spll_func_cntl_4); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM = cpu_to_be32(ni_pi->clock_registers.cg_spll_spread_spectrum); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = cpu_to_be32(ni_pi->clock_registers.cg_spll_spread_spectrum_2); - table->initialState.levels[0].sclk.sclk_value = + table->initialState.level.sclk.sclk_value = cpu_to_be32(initial_state->performance_levels[0].sclk); - table->initialState.levels[0].arbRefreshState = + table->initialState.level.arbRefreshState = NISLANDS_INITIAL_STATE_ARB_INDEX; - table->initialState.levels[0].ACIndex = 0; + table->initialState.level.ACIndex = 0; ret = ni_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, initial_state->performance_levels[0].vddc, - &table->initialState.levels[0].vddc); + &table->initialState.level.vddc); if (!ret) { u16 std_vddc; ret = ni_get_std_voltage_value(rdev, - &table->initialState.levels[0].vddc, + &table->initialState.level.vddc, &std_vddc); if (!ret) ni_populate_std_voltage_value(rdev, std_vddc, - table->initialState.levels[0].vddc.index, - &table->initialState.levels[0].std_vddc); + table->initialState.level.vddc.index, + &table->initialState.level.std_vddc); } if (eg_pi->vddci_control) ni_populate_voltage_value(rdev, &eg_pi->vddci_voltage_table, initial_state->performance_levels[0].vddci, - &table->initialState.levels[0].vddci); + &table->initialState.level.vddci); - ni_populate_initial_mvdd_value(rdev, &table->initialState.levels[0].mvdd); + ni_populate_initial_mvdd_value(rdev, &table->initialState.level.mvdd); reg = CG_R(0xffff) | CG_L(0); - table->initialState.levels[0].aT = cpu_to_be32(reg); + table->initialState.level.aT = cpu_to_be32(reg); - table->initialState.levels[0].bSP = cpu_to_be32(pi->dsp); + table->initialState.level.bSP = cpu_to_be32(pi->dsp); if (pi->boot_in_gen2) - table->initialState.levels[0].gen2PCIE = 1; + table->initialState.level.gen2PCIE = 1; else - table->initialState.levels[0].gen2PCIE = 0; + table->initialState.level.gen2PCIE = 0; if (pi->mem_gddr5) { - table->initialState.levels[0].strobeMode = + table->initialState.level.strobeMode = cypress_get_strobe_mode_settings(rdev, initial_state->performance_levels[0].mclk); if (initial_state->performance_levels[0].mclk > pi->mclk_edc_enable_threshold) - table->initialState.levels[0].mcFlags = NISLANDS_SMC_MC_EDC_RD_FLAG | NISLANDS_SMC_MC_EDC_WR_FLAG; + table->initialState.level.mcFlags = NISLANDS_SMC_MC_EDC_RD_FLAG | NISLANDS_SMC_MC_EDC_WR_FLAG; else - table->initialState.levels[0].mcFlags = 0; + table->initialState.level.mcFlags = 0; } table->initialState.levelCount = 1; table->initialState.flags |= PPSMC_SWSTATE_FLAG_DC; - table->initialState.levels[0].dpm2.MaxPS = 0; - table->initialState.levels[0].dpm2.NearTDPDec = 0; - table->initialState.levels[0].dpm2.AboveSafeInc = 0; - table->initialState.levels[0].dpm2.BelowSafeInc = 0; + table->initialState.level.dpm2.MaxPS = 0; + table->initialState.level.dpm2.NearTDPDec = 0; + table->initialState.level.dpm2.AboveSafeInc = 0; + table->initialState.level.dpm2.BelowSafeInc = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->initialState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->initialState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } @@ -1813,43 +1813,43 @@ static int ni_populate_smc_acpi_state(struct radeon_device *rdev, if (pi->acpi_vddc) { ret = ni_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, - pi->acpi_vddc, &table->ACPIState.levels[0].vddc); + pi->acpi_vddc, &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = ni_get_std_voltage_value(rdev, - &table->ACPIState.levels[0].vddc, &std_vddc); + &table->ACPIState.level.vddc, &std_vddc); if (!ret) ni_populate_std_voltage_value(rdev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } if (pi->pcie_gen2) { if (pi->acpi_pcie_gen2) - table->ACPIState.levels[0].gen2PCIE = 1; + table->ACPIState.level.gen2PCIE = 1; else - table->ACPIState.levels[0].gen2PCIE = 0; + table->ACPIState.level.gen2PCIE = 0; } else { - table->ACPIState.levels[0].gen2PCIE = 0; + table->ACPIState.level.gen2PCIE = 0; } } else { ret = ni_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, pi->min_vddc_in_table, - &table->ACPIState.levels[0].vddc); + &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = ni_get_std_voltage_value(rdev, - &table->ACPIState.levels[0].vddc, + &table->ACPIState.level.vddc, &std_vddc); if (!ret) ni_populate_std_voltage_value(rdev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } - table->ACPIState.levels[0].gen2PCIE = 0; + table->ACPIState.level.gen2PCIE = 0; } if (eg_pi->acpi_vddci) { @@ -1857,7 +1857,7 @@ static int ni_populate_smc_acpi_state(struct radeon_device *rdev, ni_populate_voltage_value(rdev, &eg_pi->vddci_voltage_table, eg_pi->acpi_vddci, - &table->ACPIState.levels[0].vddci); + &table->ACPIState.level.vddci); } @@ -1900,37 +1900,37 @@ static int ni_populate_smc_acpi_state(struct radeon_device *rdev, spll_func_cntl_2 &= ~SCLK_MUX_SEL_MASK; spll_func_cntl_2 |= SCLK_MUX_SEL(4); - table->ACPIState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(mpll_ad_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_AD_FUNC_CNTL_2 = cpu_to_be32(mpll_ad_func_cntl_2); - table->ACPIState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(mpll_dq_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL_2 = cpu_to_be32(mpll_dq_func_cntl_2); - table->ACPIState.levels[0].mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(mclk_pwrmgt_cntl); - table->ACPIState.levels[0].mclk.vDLL_CNTL = cpu_to_be32(dll_cntl); + table->ACPIState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(mpll_ad_func_cntl); + table->ACPIState.level.mclk.vMPLL_AD_FUNC_CNTL_2 = cpu_to_be32(mpll_ad_func_cntl_2); + table->ACPIState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(mpll_dq_func_cntl); + table->ACPIState.level.mclk.vMPLL_DQ_FUNC_CNTL_2 = cpu_to_be32(mpll_dq_func_cntl_2); + table->ACPIState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(mclk_pwrmgt_cntl); + table->ACPIState.level.mclk.vDLL_CNTL = cpu_to_be32(dll_cntl); - table->ACPIState.levels[0].mclk.mclk_value = 0; + table->ACPIState.level.mclk.mclk_value = 0; - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(spll_func_cntl); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(spll_func_cntl_2); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(spll_func_cntl_3); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(spll_func_cntl_4); + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(spll_func_cntl); + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(spll_func_cntl_2); + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(spll_func_cntl_3); + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(spll_func_cntl_4); - table->ACPIState.levels[0].sclk.sclk_value = 0; + table->ACPIState.level.sclk.sclk_value = 0; - ni_populate_mvdd_value(rdev, 0, &table->ACPIState.levels[0].mvdd); + ni_populate_mvdd_value(rdev, 0, &table->ACPIState.level.mvdd); if (eg_pi->dynamic_ac_timing) - table->ACPIState.levels[0].ACIndex = 1; + table->ACPIState.level.ACIndex = 1; - table->ACPIState.levels[0].dpm2.MaxPS = 0; - table->ACPIState.levels[0].dpm2.NearTDPDec = 0; - table->ACPIState.levels[0].dpm2.AboveSafeInc = 0; - table->ACPIState.levels[0].dpm2.BelowSafeInc = 0; + table->ACPIState.level.dpm2.MaxPS = 0; + table->ACPIState.level.dpm2.NearTDPDec = 0; + table->ACPIState.level.dpm2.AboveSafeInc = 0; + table->ACPIState.level.dpm2.BelowSafeInc = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->ACPIState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->ACPIState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } @@ -1980,7 +1980,9 @@ static int ni_init_smc_table(struct radeon_device *rdev) if (ret) return ret; - table->driverState = table->initialState; + table->driverState.flags = table->initialState.flags; + table->driverState.levelCount = table->initialState.levelCount; + table->driverState.levels[0] = table->initialState.level; table->ULVState = table->initialState; diff --git a/drivers/gpu/drm/radeon/nislands_smc.h b/drivers/gpu/drm/radeon/nislands_smc.h index 7395cb6b3cac..42f3bab0f9ee 100644 --- a/drivers/gpu/drm/radeon/nislands_smc.h +++ b/drivers/gpu/drm/radeon/nislands_smc.h @@ -143,6 +143,14 @@ struct NISLANDS_SMC_SWSTATE typedef struct NISLANDS_SMC_SWSTATE NISLANDS_SMC_SWSTATE; +struct NISLANDS_SMC_SWSTATE_SINGLE { + uint8_t flags; + uint8_t levelCount; + uint8_t padding2; + uint8_t padding3; + NISLANDS_SMC_HW_PERFORMANCE_LEVEL level; +}; + #define NISLANDS_SMC_VOLTAGEMASK_VDDC 0 #define NISLANDS_SMC_VOLTAGEMASK_MVDD 1 #define NISLANDS_SMC_VOLTAGEMASK_VDDCI 2 @@ -160,19 +168,19 @@ typedef struct NISLANDS_SMC_VOLTAGEMASKTABLE NISLANDS_SMC_VOLTAGEMASKTABLE; struct NISLANDS_SMC_STATETABLE { - uint8_t thermalProtectType; - uint8_t systemFlags; - uint8_t maxVDDCIndexInPPTable; - uint8_t extraFlags; - uint8_t highSMIO[NISLANDS_MAX_NO_VREG_STEPS]; - uint32_t lowSMIO[NISLANDS_MAX_NO_VREG_STEPS]; - NISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; - PP_NIslands_DPM2Parameters dpm2Params; - NISLANDS_SMC_SWSTATE initialState; - NISLANDS_SMC_SWSTATE ACPIState; - NISLANDS_SMC_SWSTATE ULVState; - NISLANDS_SMC_SWSTATE driverState; - NISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[NISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE - 1]; + uint8_t thermalProtectType; + uint8_t systemFlags; + uint8_t maxVDDCIndexInPPTable; + uint8_t extraFlags; + uint8_t highSMIO[NISLANDS_MAX_NO_VREG_STEPS]; + uint32_t lowSMIO[NISLANDS_MAX_NO_VREG_STEPS]; + NISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; + PP_NIslands_DPM2Parameters dpm2Params; + struct NISLANDS_SMC_SWSTATE_SINGLE initialState; + struct NISLANDS_SMC_SWSTATE_SINGLE ACPIState; + struct NISLANDS_SMC_SWSTATE_SINGLE ULVState; + NISLANDS_SMC_SWSTATE driverState; + NISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[NISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE]; }; typedef struct NISLANDS_SMC_STATETABLE NISLANDS_SMC_STATETABLE; diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 42281fce552e..56ed5634cebe 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -1549,6 +1549,7 @@ struct radeon_dpm { void *priv; u32 new_active_crtcs; int new_active_crtc_count; + int high_pixelclock_count; u32 current_active_crtcs; int current_active_crtc_count; bool single_display; diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 0c1950f4e146..3861c0b98fcf 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1767,6 +1767,7 @@ static void radeon_pm_compute_clocks_dpm(struct radeon_device *rdev) struct drm_device *ddev = rdev->ddev; struct drm_crtc *crtc; struct radeon_crtc *radeon_crtc; + struct radeon_connector *radeon_connector; if (!rdev->pm.dpm_enabled) return; @@ -1776,6 +1777,7 @@ static void radeon_pm_compute_clocks_dpm(struct radeon_device *rdev) /* update active crtc counts */ rdev->pm.dpm.new_active_crtcs = 0; rdev->pm.dpm.new_active_crtc_count = 0; + rdev->pm.dpm.high_pixelclock_count = 0; if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) { list_for_each_entry(crtc, &ddev->mode_config.crtc_list, head) { @@ -1783,6 +1785,12 @@ static void radeon_pm_compute_clocks_dpm(struct radeon_device *rdev) if (crtc->enabled) { rdev->pm.dpm.new_active_crtcs |= (1 << radeon_crtc->crtc_id); rdev->pm.dpm.new_active_crtc_count++; + if (!radeon_crtc->connector) + continue; + + radeon_connector = to_radeon_connector(radeon_crtc->connector); + if (radeon_connector->pixelclock_for_modeset > 297000) + rdev->pm.dpm.high_pixelclock_count++; } } } diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 918609551804..3add39c1a689 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2979,6 +2979,9 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, (rdev->pdev->device == 0x6605)) { max_sclk = 75000; } + + if (rdev->pm.dpm.high_pixelclock_count > 1) + disable_sclk_switching = true; } if (rps->vce_active) { @@ -4350,70 +4353,70 @@ static int si_populate_smc_initial_state(struct radeon_device *rdev, u32 reg; int ret; - table->initialState.levels[0].mclk.vDLL_CNTL = + table->initialState.level.mclk.vDLL_CNTL = cpu_to_be32(si_pi->clock_registers.dll_cntl); - table->initialState.levels[0].mclk.vMCLK_PWRMGT_CNTL = + table->initialState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(si_pi->clock_registers.mclk_pwrmgt_cntl); - table->initialState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_ad_func_cntl); - table->initialState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_dq_func_cntl); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL_1 = + table->initialState.level.mclk.vMPLL_FUNC_CNTL_1 = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl_1); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL_2 = + table->initialState.level.mclk.vMPLL_FUNC_CNTL_2 = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl_2); - table->initialState.levels[0].mclk.vMPLL_SS = + table->initialState.level.mclk.vMPLL_SS = cpu_to_be32(si_pi->clock_registers.mpll_ss1); - table->initialState.levels[0].mclk.vMPLL_SS2 = + table->initialState.level.mclk.vMPLL_SS2 = cpu_to_be32(si_pi->clock_registers.mpll_ss2); - table->initialState.levels[0].mclk.mclk_value = + table->initialState.level.mclk.mclk_value = cpu_to_be32(initial_state->performance_levels[0].mclk); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_2); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_3); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_4); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM = cpu_to_be32(si_pi->clock_registers.cg_spll_spread_spectrum); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = cpu_to_be32(si_pi->clock_registers.cg_spll_spread_spectrum_2); - table->initialState.levels[0].sclk.sclk_value = + table->initialState.level.sclk.sclk_value = cpu_to_be32(initial_state->performance_levels[0].sclk); - table->initialState.levels[0].arbRefreshState = + table->initialState.level.arbRefreshState = SISLANDS_INITIAL_STATE_ARB_INDEX; - table->initialState.levels[0].ACIndex = 0; + table->initialState.level.ACIndex = 0; ret = si_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, initial_state->performance_levels[0].vddc, - &table->initialState.levels[0].vddc); + &table->initialState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(rdev, - &table->initialState.levels[0].vddc, + &table->initialState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(rdev, std_vddc, - table->initialState.levels[0].vddc.index, - &table->initialState.levels[0].std_vddc); + table->initialState.level.vddc.index, + &table->initialState.level.std_vddc); } if (eg_pi->vddci_control) si_populate_voltage_value(rdev, &eg_pi->vddci_voltage_table, initial_state->performance_levels[0].vddci, - &table->initialState.levels[0].vddci); + &table->initialState.level.vddci); if (si_pi->vddc_phase_shed_control) si_populate_phase_shedding_value(rdev, @@ -4421,43 +4424,43 @@ static int si_populate_smc_initial_state(struct radeon_device *rdev, initial_state->performance_levels[0].vddc, initial_state->performance_levels[0].sclk, initial_state->performance_levels[0].mclk, - &table->initialState.levels[0].vddc); + &table->initialState.level.vddc); - si_populate_initial_mvdd_value(rdev, &table->initialState.levels[0].mvdd); + si_populate_initial_mvdd_value(rdev, &table->initialState.level.mvdd); reg = CG_R(0xffff) | CG_L(0); - table->initialState.levels[0].aT = cpu_to_be32(reg); + table->initialState.level.aT = cpu_to_be32(reg); - table->initialState.levels[0].bSP = cpu_to_be32(pi->dsp); + table->initialState.level.bSP = cpu_to_be32(pi->dsp); - table->initialState.levels[0].gen2PCIE = (u8)si_pi->boot_pcie_gen; + table->initialState.level.gen2PCIE = (u8)si_pi->boot_pcie_gen; if (pi->mem_gddr5) { - table->initialState.levels[0].strobeMode = + table->initialState.level.strobeMode = si_get_strobe_mode_settings(rdev, initial_state->performance_levels[0].mclk); if (initial_state->performance_levels[0].mclk > pi->mclk_edc_enable_threshold) - table->initialState.levels[0].mcFlags = SISLANDS_SMC_MC_EDC_RD_FLAG | SISLANDS_SMC_MC_EDC_WR_FLAG; + table->initialState.level.mcFlags = SISLANDS_SMC_MC_EDC_RD_FLAG | SISLANDS_SMC_MC_EDC_WR_FLAG; else - table->initialState.levels[0].mcFlags = 0; + table->initialState.level.mcFlags = 0; } table->initialState.levelCount = 1; table->initialState.flags |= PPSMC_SWSTATE_FLAG_DC; - table->initialState.levels[0].dpm2.MaxPS = 0; - table->initialState.levels[0].dpm2.NearTDPDec = 0; - table->initialState.levels[0].dpm2.AboveSafeInc = 0; - table->initialState.levels[0].dpm2.BelowSafeInc = 0; - table->initialState.levels[0].dpm2.PwrEfficiencyRatio = 0; + table->initialState.level.dpm2.MaxPS = 0; + table->initialState.level.dpm2.NearTDPDec = 0; + table->initialState.level.dpm2.AboveSafeInc = 0; + table->initialState.level.dpm2.BelowSafeInc = 0; + table->initialState.level.dpm2.PwrEfficiencyRatio = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->initialState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->initialState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } @@ -4488,18 +4491,18 @@ static int si_populate_smc_acpi_state(struct radeon_device *rdev, if (pi->acpi_vddc) { ret = si_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, - pi->acpi_vddc, &table->ACPIState.levels[0].vddc); + pi->acpi_vddc, &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(rdev, - &table->ACPIState.levels[0].vddc, &std_vddc); + &table->ACPIState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(rdev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } - table->ACPIState.levels[0].gen2PCIE = si_pi->acpi_pcie_gen; + table->ACPIState.level.gen2PCIE = si_pi->acpi_pcie_gen; if (si_pi->vddc_phase_shed_control) { si_populate_phase_shedding_value(rdev, @@ -4507,23 +4510,23 @@ static int si_populate_smc_acpi_state(struct radeon_device *rdev, pi->acpi_vddc, 0, 0, - &table->ACPIState.levels[0].vddc); + &table->ACPIState.level.vddc); } } else { ret = si_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, - pi->min_vddc_in_table, &table->ACPIState.levels[0].vddc); + pi->min_vddc_in_table, &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(rdev, - &table->ACPIState.levels[0].vddc, &std_vddc); + &table->ACPIState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(rdev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } - table->ACPIState.levels[0].gen2PCIE = (u8)r600_get_pcie_gen_support(rdev, + table->ACPIState.level.gen2PCIE = (u8)r600_get_pcie_gen_support(rdev, si_pi->sys_pcie_mask, si_pi->boot_pcie_gen, RADEON_PCIE_GEN1); @@ -4534,14 +4537,14 @@ static int si_populate_smc_acpi_state(struct radeon_device *rdev, pi->min_vddc_in_table, 0, 0, - &table->ACPIState.levels[0].vddc); + &table->ACPIState.level.vddc); } if (pi->acpi_vddc) { if (eg_pi->acpi_vddci) si_populate_voltage_value(rdev, &eg_pi->vddci_voltage_table, eg_pi->acpi_vddci, - &table->ACPIState.levels[0].vddci); + &table->ACPIState.level.vddci); } mclk_pwrmgt_cntl |= MRDCK0_RESET | MRDCK1_RESET; @@ -4552,59 +4555,59 @@ static int si_populate_smc_acpi_state(struct radeon_device *rdev, spll_func_cntl_2 &= ~SCLK_MUX_SEL_MASK; spll_func_cntl_2 |= SCLK_MUX_SEL(4); - table->ACPIState.levels[0].mclk.vDLL_CNTL = + table->ACPIState.level.mclk.vDLL_CNTL = cpu_to_be32(dll_cntl); - table->ACPIState.levels[0].mclk.vMCLK_PWRMGT_CNTL = + table->ACPIState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(mclk_pwrmgt_cntl); - table->ACPIState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(mpll_ad_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(mpll_dq_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL = cpu_to_be32(mpll_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL_1 = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL_1 = cpu_to_be32(mpll_func_cntl_1); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL_2 = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL_2 = cpu_to_be32(mpll_func_cntl_2); - table->ACPIState.levels[0].mclk.vMPLL_SS = + table->ACPIState.level.mclk.vMPLL_SS = cpu_to_be32(si_pi->clock_registers.mpll_ss1); - table->ACPIState.levels[0].mclk.vMPLL_SS2 = + table->ACPIState.level.mclk.vMPLL_SS2 = cpu_to_be32(si_pi->clock_registers.mpll_ss2); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(spll_func_cntl); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(spll_func_cntl_2); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(spll_func_cntl_3); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(spll_func_cntl_4); - table->ACPIState.levels[0].mclk.mclk_value = 0; - table->ACPIState.levels[0].sclk.sclk_value = 0; + table->ACPIState.level.mclk.mclk_value = 0; + table->ACPIState.level.sclk.sclk_value = 0; - si_populate_mvdd_value(rdev, 0, &table->ACPIState.levels[0].mvdd); + si_populate_mvdd_value(rdev, 0, &table->ACPIState.level.mvdd); if (eg_pi->dynamic_ac_timing) - table->ACPIState.levels[0].ACIndex = 0; + table->ACPIState.level.ACIndex = 0; - table->ACPIState.levels[0].dpm2.MaxPS = 0; - table->ACPIState.levels[0].dpm2.NearTDPDec = 0; - table->ACPIState.levels[0].dpm2.AboveSafeInc = 0; - table->ACPIState.levels[0].dpm2.BelowSafeInc = 0; - table->ACPIState.levels[0].dpm2.PwrEfficiencyRatio = 0; + table->ACPIState.level.dpm2.MaxPS = 0; + table->ACPIState.level.dpm2.NearTDPDec = 0; + table->ACPIState.level.dpm2.AboveSafeInc = 0; + table->ACPIState.level.dpm2.BelowSafeInc = 0; + table->ACPIState.level.dpm2.PwrEfficiencyRatio = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->ACPIState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->ACPIState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } static int si_populate_ulv_state(struct radeon_device *rdev, - SISLANDS_SMC_SWSTATE *state) + struct SISLANDS_SMC_SWSTATE_SINGLE *state) { struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev); struct si_power_info *si_pi = si_get_pi(rdev); @@ -4613,19 +4616,19 @@ static int si_populate_ulv_state(struct radeon_device *rdev, int ret; ret = si_convert_power_level_to_smc(rdev, &ulv->pl, - &state->levels[0]); + &state->level); if (!ret) { if (eg_pi->sclk_deep_sleep) { if (sclk_in_sr <= SCLK_MIN_DEEPSLEEP_FREQ) - state->levels[0].stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_BYPASS; + state->level.stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_BYPASS; else - state->levels[0].stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_THROTTLE; + state->level.stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_THROTTLE; } if (ulv->one_pcie_lane_in_ulv) state->flags |= PPSMC_SWSTATE_FLAG_PCIE_X1; - state->levels[0].arbRefreshState = (u8)(SISLANDS_ULV_STATE_ARB_INDEX); - state->levels[0].ACIndex = 1; - state->levels[0].std_vddc = state->levels[0].vddc; + state->level.arbRefreshState = (u8)(SISLANDS_ULV_STATE_ARB_INDEX); + state->level.ACIndex = 1; + state->level.std_vddc = state->level.vddc; state->levelCount = 1; state->flags |= PPSMC_SWSTATE_FLAG_DC; @@ -4725,7 +4728,9 @@ static int si_init_smc_table(struct radeon_device *rdev) if (ret) return ret; - table->driverState = table->initialState; + table->driverState.flags = table->initialState.flags; + table->driverState.levelCount = table->initialState.levelCount; + table->driverState.levels[0] = table->initialState.level; ret = si_do_program_memory_timing_parameters(rdev, radeon_boot_state, SISLANDS_INITIAL_STATE_ARB_INDEX); @@ -5275,8 +5280,8 @@ static int si_upload_ulv_state(struct radeon_device *rdev) if (ulv->supported && ulv->pl.vddc) { u32 address = si_pi->state_table_start + offsetof(SISLANDS_SMC_STATETABLE, ULVState); - SISLANDS_SMC_SWSTATE *smc_state = &si_pi->smc_statetable.ULVState; - u32 state_size = sizeof(SISLANDS_SMC_SWSTATE); + struct SISLANDS_SMC_SWSTATE_SINGLE *smc_state = &si_pi->smc_statetable.ULVState; + u32 state_size = sizeof(struct SISLANDS_SMC_SWSTATE_SINGLE); memset(smc_state, 0, state_size); diff --git a/drivers/gpu/drm/radeon/sislands_smc.h b/drivers/gpu/drm/radeon/sislands_smc.h index fbd6589bdab9..4ea1cb2e45a3 100644 --- a/drivers/gpu/drm/radeon/sislands_smc.h +++ b/drivers/gpu/drm/radeon/sislands_smc.h @@ -191,6 +191,14 @@ struct SISLANDS_SMC_SWSTATE typedef struct SISLANDS_SMC_SWSTATE SISLANDS_SMC_SWSTATE; +struct SISLANDS_SMC_SWSTATE_SINGLE { + uint8_t flags; + uint8_t levelCount; + uint8_t padding2; + uint8_t padding3; + SISLANDS_SMC_HW_PERFORMANCE_LEVEL level; +}; + #define SISLANDS_SMC_VOLTAGEMASK_VDDC 0 #define SISLANDS_SMC_VOLTAGEMASK_MVDD 1 #define SISLANDS_SMC_VOLTAGEMASK_VDDCI 2 @@ -208,19 +216,19 @@ typedef struct SISLANDS_SMC_VOLTAGEMASKTABLE SISLANDS_SMC_VOLTAGEMASKTABLE; struct SISLANDS_SMC_STATETABLE { - uint8_t thermalProtectType; - uint8_t systemFlags; - uint8_t maxVDDCIndexInPPTable; - uint8_t extraFlags; - uint32_t lowSMIO[SISLANDS_MAX_NO_VREG_STEPS]; - SISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; - SISLANDS_SMC_VOLTAGEMASKTABLE phaseMaskTable; - PP_SIslands_DPM2Parameters dpm2Params; - SISLANDS_SMC_SWSTATE initialState; - SISLANDS_SMC_SWSTATE ACPIState; - SISLANDS_SMC_SWSTATE ULVState; - SISLANDS_SMC_SWSTATE driverState; - SISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE - 1]; + uint8_t thermalProtectType; + uint8_t systemFlags; + uint8_t maxVDDCIndexInPPTable; + uint8_t extraFlags; + uint32_t lowSMIO[SISLANDS_MAX_NO_VREG_STEPS]; + SISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; + SISLANDS_SMC_VOLTAGEMASKTABLE phaseMaskTable; + PP_SIslands_DPM2Parameters dpm2Params; + struct SISLANDS_SMC_SWSTATE_SINGLE initialState; + struct SISLANDS_SMC_SWSTATE_SINGLE ACPIState; + struct SISLANDS_SMC_SWSTATE_SINGLE ULVState; + SISLANDS_SMC_SWSTATE driverState; + SISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE]; }; typedef struct SISLANDS_SMC_STATETABLE SISLANDS_SMC_STATETABLE; diff --git a/drivers/gpu/drm/vc4/vc4_vec.c b/drivers/gpu/drm/vc4/vc4_vec.c index bd5b8eb58b18..090529d0d5dc 100644 --- a/drivers/gpu/drm/vc4/vc4_vec.c +++ b/drivers/gpu/drm/vc4/vc4_vec.c @@ -197,12 +197,6 @@ struct vc4_vec_connector { struct drm_encoder *encoder; }; -static inline struct vc4_vec_connector * -to_vc4_vec_connector(struct drm_connector *connector) -{ - return container_of(connector, struct vc4_vec_connector, base); -} - enum vc4_vec_tv_mode_id { VC4_VEC_TV_MODE_NTSC, VC4_VEC_TV_MODE_NTSC_J, diff --git a/drivers/hwmon/adm9240.c b/drivers/hwmon/adm9240.c index 5677263bcf0d..483cd757abd3 100644 --- a/drivers/hwmon/adm9240.c +++ b/drivers/hwmon/adm9240.c @@ -485,7 +485,7 @@ static int adm9240_in_write(struct device *dev, u32 attr, int channel, long val) reg = ADM9240_REG_IN_MIN(channel); break; case hwmon_in_max: - reg = ADM9240_REG_IN(channel); + reg = ADM9240_REG_IN_MAX(channel); break; default: return -EOPNOTSUPP; diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c index 3a5807e4a2ef..02298b86b57b 100644 --- a/drivers/hwmon/corsair-psu.c +++ b/drivers/hwmon/corsair-psu.c @@ -355,7 +355,7 @@ static umode_t corsairpsu_hwmon_power_is_visible(const struct corsairpsu_data *p return 0444; default: return 0; - }; + } } static umode_t corsairpsu_hwmon_in_is_visible(const struct corsairpsu_data *priv, u32 attr, @@ -376,7 +376,7 @@ static umode_t corsairpsu_hwmon_in_is_visible(const struct corsairpsu_data *priv break; default: break; - }; + } return res; } diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c index 4382105bf142..2a4bed0ab226 100644 --- a/drivers/hwmon/ltc2992.c +++ b/drivers/hwmon/ltc2992.c @@ -900,11 +900,15 @@ static int ltc2992_parse_dt(struct ltc2992_state *st) fwnode_for_each_available_child_node(fwnode, child) { ret = fwnode_property_read_u32(child, "reg", &addr); - if (ret < 0) + if (ret < 0) { + fwnode_handle_put(child); return ret; + } - if (addr > 1) + if (addr > 1) { + fwnode_handle_put(child); return -EINVAL; + } ret = fwnode_property_read_u32(child, "shunt-resistor-micro-ohms", &val); if (!ret) diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index f1ac153d0b56..967532afb1c0 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -217,9 +217,9 @@ int occ_update_response(struct occ *occ) return rc; /* limit the maximum rate of polling the OCC */ - if (time_after(jiffies, occ->last_update + OCC_UPDATE_FREQUENCY)) { + if (time_after(jiffies, occ->next_update)) { rc = occ_poll(occ); - occ->last_update = jiffies; + occ->next_update = jiffies + OCC_UPDATE_FREQUENCY; } else { rc = occ->last_error; } @@ -1165,6 +1165,7 @@ int occ_setup(struct occ *occ, const char *name) return rc; } + occ->next_update = jiffies + OCC_UPDATE_FREQUENCY; occ_parse_poll_response(occ); rc = occ_setup_sensor_attrs(occ); diff --git a/drivers/hwmon/occ/common.h b/drivers/hwmon/occ/common.h index 67e6968b8978..e6df719770e8 100644 --- a/drivers/hwmon/occ/common.h +++ b/drivers/hwmon/occ/common.h @@ -99,7 +99,7 @@ struct occ { u8 poll_cmd_data; /* to perform OCC poll command */ int (*send_cmd)(struct occ *occ, u8 *cmd); - unsigned long last_update; + unsigned long next_update; struct mutex lock; /* lock OCC access */ struct device *hwmon; diff --git a/drivers/hwmon/pmbus/fsp-3y.c b/drivers/hwmon/pmbus/fsp-3y.c index b177987286ae..e24842475254 100644 --- a/drivers/hwmon/pmbus/fsp-3y.c +++ b/drivers/hwmon/pmbus/fsp-3y.c @@ -57,7 +57,7 @@ static int page_log_to_page_real(int page_log, enum chips chip) case YH5151E_PAGE_12V_LOG: return YH5151E_PAGE_12V_REAL; case YH5151E_PAGE_5V_LOG: - return YH5151E_PAGE_5V_LOG; + return YH5151E_PAGE_5V_REAL; case YH5151E_PAGE_3V3_LOG: return YH5151E_PAGE_3V3_REAL; } @@ -103,8 +103,18 @@ static int set_page(struct i2c_client *client, int page_log) static int fsp3y_read_byte_data(struct i2c_client *client, int page, int reg) { + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct fsp3y_data *data = to_fsp3y_data(info); int rv; + /* + * YH5151-E outputs vout in linear11. The conversion is done when + * reading. Here, we have to inject pmbus_core with the correct + * exponent (it is -6). + */ + if (data->chip == yh5151e && reg == PMBUS_VOUT_MODE) + return 0x1A; + rv = set_page(client, page); if (rv < 0) return rv; @@ -114,6 +124,8 @@ static int fsp3y_read_byte_data(struct i2c_client *client, int page, int reg) static int fsp3y_read_word_data(struct i2c_client *client, int page, int phase, int reg) { + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct fsp3y_data *data = to_fsp3y_data(info); int rv; /* @@ -144,7 +156,18 @@ static int fsp3y_read_word_data(struct i2c_client *client, int page, int phase, if (rv < 0) return rv; - return i2c_smbus_read_word_data(client, reg); + rv = i2c_smbus_read_word_data(client, reg); + if (rv < 0) + return rv; + + /* + * YH-5151E is non-compliant and outputs output voltages in linear11 + * instead of linear16. + */ + if (data->chip == yh5151e && reg == PMBUS_READ_VOUT) + rv = sign_extend32(rv, 10) & 0xffff; + + return rv; } static struct pmbus_driver_info fsp3y_info[] = { diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index cceda3cecbcf..8b1723635cce 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -229,7 +229,6 @@ config DMARD10 config HID_SENSOR_ACCEL_3D depends on HID_SENSOR_HUB select IIO_BUFFER - select IIO_TRIGGERED_BUFFER select HID_SENSOR_IIO_COMMON select HID_SENSOR_IIO_TRIGGER tristate "HID Accelerometers 3D" diff --git a/drivers/iio/common/hid-sensors/Kconfig b/drivers/iio/common/hid-sensors/Kconfig index 24d492567336..2a3dd3b907be 100644 --- a/drivers/iio/common/hid-sensors/Kconfig +++ b/drivers/iio/common/hid-sensors/Kconfig @@ -19,6 +19,7 @@ config HID_SENSOR_IIO_TRIGGER tristate "Common module (trigger) for all HID Sensor IIO drivers" depends on HID_SENSOR_HUB && HID_SENSOR_IIO_COMMON && IIO_BUFFER select IIO_TRIGGER + select IIO_TRIGGERED_BUFFER help Say yes here to build trigger support for HID sensors. Triggers will be send if all requested attributes were read. diff --git a/drivers/iio/gyro/Kconfig b/drivers/iio/gyro/Kconfig index 5824f2edf975..20b5ac7ab66a 100644 --- a/drivers/iio/gyro/Kconfig +++ b/drivers/iio/gyro/Kconfig @@ -111,7 +111,6 @@ config FXAS21002C_SPI config HID_SENSOR_GYRO_3D depends on HID_SENSOR_HUB select IIO_BUFFER - select IIO_TRIGGERED_BUFFER select HID_SENSOR_IIO_COMMON select HID_SENSOR_IIO_TRIGGER tristate "HID Gyroscope 3D" diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c index ac90be03332a..f17a93519535 100644 --- a/drivers/iio/gyro/mpu3050-core.c +++ b/drivers/iio/gyro/mpu3050-core.c @@ -272,7 +272,16 @@ static int mpu3050_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_OFFSET: switch (chan->type) { case IIO_TEMP: - /* The temperature scaling is (x+23000)/280 Celsius */ + /* + * The temperature scaling is (x+23000)/280 Celsius + * for the "best fit straight line" temperature range + * of -30C..85C. The 23000 includes room temperature + * offset of +35C, 280 is the precision scale and x is + * the 16-bit signed integer reported by hardware. + * + * Temperature value itself represents temperature of + * the sensor die. + */ *val = 23000; return IIO_VAL_INT; default: @@ -329,7 +338,7 @@ static int mpu3050_read_raw(struct iio_dev *indio_dev, goto out_read_raw_unlock; } - *val = be16_to_cpu(raw_val); + *val = (s16)be16_to_cpu(raw_val); ret = IIO_VAL_INT; goto out_read_raw_unlock; diff --git a/drivers/iio/humidity/Kconfig b/drivers/iio/humidity/Kconfig index 6549fcf6db69..2de5494e7c22 100644 --- a/drivers/iio/humidity/Kconfig +++ b/drivers/iio/humidity/Kconfig @@ -52,7 +52,6 @@ config HID_SENSOR_HUMIDITY tristate "HID Environmental humidity sensor" depends on HID_SENSOR_HUB select IIO_BUFFER - select IIO_TRIGGERED_BUFFER select HID_SENSOR_IIO_COMMON select HID_SENSOR_IIO_TRIGGER help diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index d92c58a94fe4..59efb36db2c7 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1778,7 +1778,6 @@ static long iio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (!indio_dev->info) goto out_unlock; - ret = -EINVAL; list_for_each_entry(h, &iio_dev_opaque->ioctl_handlers, entry) { ret = h->ioctl(indio_dev, filp, cmd, arg); if (ret != IIO_IOCTL_UNHANDLED) @@ -1786,7 +1785,7 @@ static long iio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) } if (ret == IIO_IOCTL_UNHANDLED) - ret = -EINVAL; + ret = -ENODEV; out_unlock: mutex_unlock(&indio_dev->info_exist_lock); @@ -1926,9 +1925,6 @@ EXPORT_SYMBOL(__iio_device_register); **/ void iio_device_unregister(struct iio_dev *indio_dev) { - struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev); - struct iio_ioctl_handler *h, *t; - cdev_device_del(&indio_dev->chrdev, &indio_dev->dev); mutex_lock(&indio_dev->info_exist_lock); @@ -1939,9 +1935,6 @@ void iio_device_unregister(struct iio_dev *indio_dev) indio_dev->info = NULL; - list_for_each_entry_safe(h, t, &iio_dev_opaque->ioctl_handlers, entry) - list_del(&h->entry); - iio_device_wakeup_eventset(indio_dev); iio_buffer_wakeup_poll(indio_dev); diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index 33ad4dd0b5c7..917f9becf9c7 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -256,7 +256,6 @@ config ISL29125 config HID_SENSOR_ALS depends on HID_SENSOR_HUB select IIO_BUFFER - select IIO_TRIGGERED_BUFFER select HID_SENSOR_IIO_COMMON select HID_SENSOR_IIO_TRIGGER tristate "HID ALS" @@ -270,7 +269,6 @@ config HID_SENSOR_ALS config HID_SENSOR_PROX depends on HID_SENSOR_HUB select IIO_BUFFER - select IIO_TRIGGERED_BUFFER select HID_SENSOR_IIO_COMMON select HID_SENSOR_IIO_TRIGGER tristate "HID PROX" diff --git a/drivers/iio/light/gp2ap002.c b/drivers/iio/light/gp2ap002.c index d048ae257c51..f960be7d4001 100644 --- a/drivers/iio/light/gp2ap002.c +++ b/drivers/iio/light/gp2ap002.c @@ -582,7 +582,7 @@ static int gp2ap002_probe(struct i2c_client *client, "gp2ap002", indio_dev); if (ret) { dev_err(dev, "unable to request IRQ\n"); - goto out_disable_vio; + goto out_put_pm; } gp2ap002->irq = client->irq; @@ -612,8 +612,9 @@ static int gp2ap002_probe(struct i2c_client *client, return 0; -out_disable_pm: +out_put_pm: pm_runtime_put_noidle(dev); +out_disable_pm: pm_runtime_disable(dev); out_disable_vio: regulator_disable(gp2ap002->vio); diff --git a/drivers/iio/light/tsl2583.c b/drivers/iio/light/tsl2583.c index 0f787bfc88fc..c9d8f07a6fcd 100644 --- a/drivers/iio/light/tsl2583.c +++ b/drivers/iio/light/tsl2583.c @@ -341,6 +341,14 @@ static int tsl2583_als_calibrate(struct iio_dev *indio_dev) return lux_val; } + /* Avoid division by zero of lux_value later on */ + if (lux_val == 0) { + dev_err(&chip->client->dev, + "%s: lux_val of 0 will produce out of range trim_value\n", + __func__); + return -ENODATA; + } + gain_trim_val = (unsigned int)(((chip->als_settings.als_cal_target) * chip->als_settings.als_gain_trim) / lux_val); if ((gain_trim_val < 250) || (gain_trim_val > 4000)) { diff --git a/drivers/iio/magnetometer/Kconfig b/drivers/iio/magnetometer/Kconfig index 5d4ffd66032e..74ad5701c6c2 100644 --- a/drivers/iio/magnetometer/Kconfig +++ b/drivers/iio/magnetometer/Kconfig @@ -95,7 +95,6 @@ config MAG3110 config HID_SENSOR_MAGNETOMETER_3D depends on HID_SENSOR_HUB select IIO_BUFFER - select IIO_TRIGGERED_BUFFER select HID_SENSOR_IIO_COMMON select HID_SENSOR_IIO_TRIGGER tristate "HID Magenetometer 3D" diff --git a/drivers/iio/orientation/Kconfig b/drivers/iio/orientation/Kconfig index a505583cc2fd..396cbbb867f4 100644 --- a/drivers/iio/orientation/Kconfig +++ b/drivers/iio/orientation/Kconfig @@ -9,7 +9,6 @@ menu "Inclinometer sensors" config HID_SENSOR_INCLINOMETER_3D depends on HID_SENSOR_HUB select IIO_BUFFER - select IIO_TRIGGERED_BUFFER select HID_SENSOR_IIO_COMMON select HID_SENSOR_IIO_TRIGGER tristate "HID Inclinometer 3D" @@ -20,7 +19,6 @@ config HID_SENSOR_INCLINOMETER_3D config HID_SENSOR_DEVICE_ROTATION depends on HID_SENSOR_HUB select IIO_BUFFER - select IIO_TRIGGERED_BUFFER select HID_SENSOR_IIO_COMMON select HID_SENSOR_IIO_TRIGGER tristate "HID Device Rotation" diff --git a/drivers/iio/pressure/Kconfig b/drivers/iio/pressure/Kconfig index 689b978db4f9..fc0d3cfca418 100644 --- a/drivers/iio/pressure/Kconfig +++ b/drivers/iio/pressure/Kconfig @@ -79,7 +79,6 @@ config DPS310 config HID_SENSOR_PRESS depends on HID_SENSOR_HUB select IIO_BUFFER - select IIO_TRIGGERED_BUFFER select HID_SENSOR_IIO_COMMON select HID_SENSOR_IIO_TRIGGER tristate "HID PRESS" diff --git a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c index c685f10b5ae4..cc206bfa09c7 100644 --- a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c +++ b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c @@ -160,6 +160,7 @@ static int lidar_get_measurement(struct lidar_data *data, u16 *reg) ret = lidar_write_control(data, LIDAR_REG_CONTROL_ACQUIRE); if (ret < 0) { dev_err(&client->dev, "cannot send start measurement command"); + pm_runtime_put_noidle(&client->dev); return ret; } diff --git a/drivers/iio/temperature/Kconfig b/drivers/iio/temperature/Kconfig index f1f2a1499c9e..4df60082c1fa 100644 --- a/drivers/iio/temperature/Kconfig +++ b/drivers/iio/temperature/Kconfig @@ -45,7 +45,6 @@ config HID_SENSOR_TEMP tristate "HID Environmental temperature sensor" depends on HID_SENSOR_HUB select IIO_BUFFER - select IIO_TRIGGERED_BUFFER select HID_SENSOR_IIO_COMMON select HID_SENSOR_IIO_TRIGGER help diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 522c9b229f80..762125f2905f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2901,7 +2901,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->hmmaxd = le16_to_cpu(id->hmmaxd); } - ret = nvme_mpath_init(ctrl, id); + ret = nvme_mpath_init_identify(ctrl, id); if (ret < 0) goto out_free; @@ -4364,6 +4364,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, min(default_ps_max_latency_us, (unsigned long)S32_MAX)); nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device)); + nvme_mpath_init_ctrl(ctrl); return 0; out_free_name: diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 0551796517e6..f81871c7128a 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -781,9 +781,18 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) put_disk(head->disk); } -int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl) { - int error; + mutex_init(&ctrl->ana_lock); + timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0); + INIT_WORK(&ctrl->ana_work, nvme_ana_work); +} + +int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +{ + size_t max_transfer_size = ctrl->max_hw_sectors << SECTOR_SHIFT; + size_t ana_log_size; + int error = 0; /* check if multipath is enabled and we have the capability */ if (!multipath || !ctrl->subsys || @@ -795,37 +804,31 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) ctrl->nanagrpid = le32_to_cpu(id->nanagrpid); ctrl->anagrpmax = le32_to_cpu(id->anagrpmax); - mutex_init(&ctrl->ana_lock); - timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0); - ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) + - ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc); - ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32); - - if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) { + ana_log_size = sizeof(struct nvme_ana_rsp_hdr) + + ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc) + + ctrl->max_namespaces * sizeof(__le32); + if (ana_log_size > max_transfer_size) { dev_err(ctrl->device, - "ANA log page size (%zd) larger than MDTS (%d).\n", - ctrl->ana_log_size, - ctrl->max_hw_sectors << SECTOR_SHIFT); + "ANA log page size (%zd) larger than MDTS (%zd).\n", + ana_log_size, max_transfer_size); dev_err(ctrl->device, "disabling ANA support.\n"); - return 0; + goto out_uninit; } - - INIT_WORK(&ctrl->ana_work, nvme_ana_work); - kfree(ctrl->ana_log_buf); - ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL); - if (!ctrl->ana_log_buf) { - error = -ENOMEM; - goto out; + if (ana_log_size > ctrl->ana_log_size) { + nvme_mpath_stop(ctrl); + kfree(ctrl->ana_log_buf); + ctrl->ana_log_buf = kmalloc(ana_log_size, GFP_KERNEL); + if (!ctrl->ana_log_buf) + return -ENOMEM; } - + ctrl->ana_log_size = ana_log_size; error = nvme_read_ana_log(ctrl); if (error) - goto out_free_ana_log_buf; + goto out_uninit; return 0; -out_free_ana_log_buf: - kfree(ctrl->ana_log_buf); - ctrl->ana_log_buf = NULL; -out: + +out_uninit: + nvme_mpath_uninit(ctrl); return error; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 05f31a2c64bb..0015860ec12b 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -712,7 +712,8 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id); void nvme_mpath_remove_disk(struct nvme_ns_head *head); -int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id); +int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id); +void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl); void nvme_mpath_uninit(struct nvme_ctrl *ctrl); void nvme_mpath_stop(struct nvme_ctrl *ctrl); bool nvme_mpath_clear_current_path(struct nvme_ns *ns); @@ -780,7 +781,10 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns) static inline void nvme_trace_bio_complete(struct request *req) { } -static inline int nvme_mpath_init(struct nvme_ctrl *ctrl, +static inline void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl) +{ +} +static inline int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) { if (ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index e7a367cf6d36..dcd49a72f2f3 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -975,10 +975,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) case nvme_admin_keep_alive: req->execute = nvmet_execute_keep_alive; return 0; + default: + return nvmet_report_invalid_opcode(req); } - - pr_debug("unhandled cmd %d on qid %d\n", cmd->common.opcode, - req->sq->qid); - req->error_loc = offsetof(struct nvme_common_command, opcode); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 4845d12e374a..fc3645fc2c24 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -379,7 +379,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) req->execute = nvmet_execute_disc_identify; return 0; default: - pr_err("unhandled cmd %d\n", cmd->common.opcode); + pr_debug("unhandled cmd %d\n", cmd->common.opcode); req->error_loc = offsetof(struct nvme_common_command, opcode); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 1420a8e3e0b1..7d0f3523fdab 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -94,7 +94,7 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req) req->execute = nvmet_execute_prop_get; break; default: - pr_err("received unknown capsule type 0x%x\n", + pr_debug("received unknown capsule type 0x%x\n", cmd->fabrics.fctype); req->error_loc = offsetof(struct nvmf_common_command, fctype); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; @@ -284,13 +284,13 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req) struct nvme_command *cmd = req->cmd; if (!nvme_is_fabrics(cmd)) { - pr_err("invalid command 0x%x on unconnected queue.\n", + pr_debug("invalid command 0x%x on unconnected queue.\n", cmd->fabrics.opcode); req->error_loc = offsetof(struct nvme_common_command, opcode); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } if (cmd->fabrics.fctype != nvme_fabrics_type_connect) { - pr_err("invalid capsule type 0x%x on unconnected queue.\n", + pr_debug("invalid capsule type 0x%x on unconnected queue.\n", cmd->fabrics.fctype); req->error_loc = offsetof(struct nvmf_common_command, fctype); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 9a8b3726a37c..429263ca9b97 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -258,7 +258,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) sector = nvmet_lba_to_sect(req->ns, req->cmd->rw.slba); - if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) { + if (nvmet_use_inline_bvec(req)) { bio = &req->b.inline_bio; bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); } else { diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 715d4376c997..7fdbdc496597 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -49,9 +49,11 @@ int nvmet_file_ns_enable(struct nvmet_ns *ns) ns->file = filp_open(ns->device_path, flags, 0); if (IS_ERR(ns->file)) { - pr_err("failed to open file %s: (%ld)\n", - ns->device_path, PTR_ERR(ns->file)); - return PTR_ERR(ns->file); + ret = PTR_ERR(ns->file); + pr_err("failed to open file %s: (%d)\n", + ns->device_path, ret); + ns->file = NULL; + return ret; } ret = nvmet_file_ns_revalidate(ns); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 5566ed403576..d69a409515d6 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -616,4 +616,10 @@ static inline sector_t nvmet_lba_to_sect(struct nvmet_ns *ns, __le64 lba) return le64_to_cpu(lba) << (ns->blksize_shift - SECTOR_SHIFT); } +static inline bool nvmet_use_inline_bvec(struct nvmet_req *req) +{ + return req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN && + req->sg_cnt <= NVMET_MAX_INLINE_BIOVEC; +} + #endif /* _NVMET_H */ diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 2798944899b7..39b1473f7204 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -194,7 +194,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq) if (req->sg_cnt > BIO_MAX_VECS) return -EINVAL; - if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) { + if (nvmet_use_inline_bvec(req)) { bio = &req->p.inline_bio; bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); } else { diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 6c1f3ab7649c..7d607f435e36 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -700,7 +700,7 @@ static void nvmet_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc) { struct nvmet_rdma_rsp *rsp = container_of(wc->wr_cqe, struct nvmet_rdma_rsp, send_cqe); - struct nvmet_rdma_queue *queue = cq->cq_context; + struct nvmet_rdma_queue *queue = wc->qp->qp_context; nvmet_rdma_release_rsp(rsp); @@ -786,7 +786,7 @@ static void nvmet_rdma_write_data_done(struct ib_cq *cq, struct ib_wc *wc) { struct nvmet_rdma_rsp *rsp = container_of(wc->wr_cqe, struct nvmet_rdma_rsp, write_cqe); - struct nvmet_rdma_queue *queue = cq->cq_context; + struct nvmet_rdma_queue *queue = wc->qp->qp_context; struct rdma_cm_id *cm_id = rsp->queue->cm_id; u16 status; diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index c1dac6eec59f..a6d731e959a2 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -527,6 +527,9 @@ static int rtw_cfg80211_ap_set_encryption(struct net_device *dev, struct ieee_pa struct mlme_priv *pmlmepriv = &padapter->mlmepriv; struct security_priv *psecuritypriv = &(padapter->securitypriv); struct sta_priv *pstapriv = &padapter->stapriv; + char *grpkey = padapter->securitypriv.dot118021XGrpKey[param->u.crypt.idx].skey; + char *txkey = padapter->securitypriv.dot118021XGrptxmickey[param->u.crypt.idx].skey; + char *rxkey = padapter->securitypriv.dot118021XGrprxmickey[param->u.crypt.idx].skey; param->u.crypt.err = 0; param->u.crypt.alg[IEEE_CRYPT_ALG_NAME_LEN - 1] = '\0'; @@ -609,7 +612,7 @@ static int rtw_cfg80211_ap_set_encryption(struct net_device *dev, struct ieee_pa { if (strcmp(param->u.crypt.alg, "WEP") == 0) { - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); psecuritypriv->dot118021XGrpPrivacy = _WEP40_; if (param->u.crypt.key_len == 13) @@ -622,12 +625,12 @@ static int rtw_cfg80211_ap_set_encryption(struct net_device *dev, struct ieee_pa { psecuritypriv->dot118021XGrpPrivacy = _TKIP_; - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); /* DEBUG_ERR("set key length :param->u.crypt.key_len =%d\n", param->u.crypt.key_len); */ /* set mic key */ - memcpy(psecuritypriv->dot118021XGrptxmickey[param->u.crypt.idx].skey, &(param->u.crypt.key[16]), 8); - memcpy(psecuritypriv->dot118021XGrprxmickey[param->u.crypt.idx].skey, &(param->u.crypt.key[24]), 8); + memcpy(txkey, &(param->u.crypt.key[16]), 8); + memcpy(rxkey, &(param->u.crypt.key[24]), 8); psecuritypriv->busetkipkey = true; @@ -636,7 +639,7 @@ static int rtw_cfg80211_ap_set_encryption(struct net_device *dev, struct ieee_pa { psecuritypriv->dot118021XGrpPrivacy = _AES_; - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); } else { @@ -713,7 +716,7 @@ static int rtw_cfg80211_ap_set_encryption(struct net_device *dev, struct ieee_pa { if (strcmp(param->u.crypt.alg, "WEP") == 0) { - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); psecuritypriv->dot118021XGrpPrivacy = _WEP40_; if (param->u.crypt.key_len == 13) @@ -725,12 +728,12 @@ static int rtw_cfg80211_ap_set_encryption(struct net_device *dev, struct ieee_pa { psecuritypriv->dot118021XGrpPrivacy = _TKIP_; - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); /* DEBUG_ERR("set key length :param->u.crypt.key_len =%d\n", param->u.crypt.key_len); */ /* set mic key */ - memcpy(psecuritypriv->dot118021XGrptxmickey[param->u.crypt.idx].skey, &(param->u.crypt.key[16]), 8); - memcpy(psecuritypriv->dot118021XGrprxmickey[param->u.crypt.idx].skey, &(param->u.crypt.key[24]), 8); + memcpy(txkey, &(param->u.crypt.key[16]), 8); + memcpy(rxkey, &(param->u.crypt.key[24]), 8); psecuritypriv->busetkipkey = true; @@ -739,7 +742,7 @@ static int rtw_cfg80211_ap_set_encryption(struct net_device *dev, struct ieee_pa { psecuritypriv->dot118021XGrpPrivacy = _AES_; - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); } else { diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c index e98e5388d5c7..5088c3731b6d 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c @@ -2963,6 +2963,9 @@ static int rtw_set_encryption(struct net_device *dev, struct ieee_param *param, struct mlme_priv *pmlmepriv = &padapter->mlmepriv; struct security_priv *psecuritypriv = &(padapter->securitypriv); struct sta_priv *pstapriv = &padapter->stapriv; + char *txkey = padapter->securitypriv.dot118021XGrptxmickey[param->u.crypt.idx].skey; + char *rxkey = padapter->securitypriv.dot118021XGrprxmickey[param->u.crypt.idx].skey; + char *grpkey = psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey; param->u.crypt.err = 0; param->u.crypt.alg[IEEE_CRYPT_ALG_NAME_LEN - 1] = '\0'; @@ -3064,7 +3067,7 @@ static int rtw_set_encryption(struct net_device *dev, struct ieee_param *param, if (!psta && check_fwstate(pmlmepriv, WIFI_AP_STATE)) { /* group key */ if (param->u.crypt.set_tx == 1) { if (strcmp(param->u.crypt.alg, "WEP") == 0) { - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); psecuritypriv->dot118021XGrpPrivacy = _WEP40_; if (param->u.crypt.key_len == 13) @@ -3073,11 +3076,11 @@ static int rtw_set_encryption(struct net_device *dev, struct ieee_param *param, } else if (strcmp(param->u.crypt.alg, "TKIP") == 0) { psecuritypriv->dot118021XGrpPrivacy = _TKIP_; - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); /* DEBUG_ERR("set key length :param->u.crypt.key_len =%d\n", param->u.crypt.key_len); */ /* set mic key */ - memcpy(psecuritypriv->dot118021XGrptxmickey[param->u.crypt.idx].skey, &(param->u.crypt.key[16]), 8); + memcpy(txkey, &(param->u.crypt.key[16]), 8); memcpy(psecuritypriv->dot118021XGrprxmickey[param->u.crypt.idx].skey, &(param->u.crypt.key[24]), 8); psecuritypriv->busetkipkey = true; @@ -3086,7 +3089,7 @@ static int rtw_set_encryption(struct net_device *dev, struct ieee_param *param, else if (strcmp(param->u.crypt.alg, "CCMP") == 0) { psecuritypriv->dot118021XGrpPrivacy = _AES_; - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); } else { psecuritypriv->dot118021XGrpPrivacy = _NO_PRIVACY_; } @@ -3142,7 +3145,7 @@ static int rtw_set_encryption(struct net_device *dev, struct ieee_param *param, } else { /* group key??? */ if (strcmp(param->u.crypt.alg, "WEP") == 0) { - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); psecuritypriv->dot118021XGrpPrivacy = _WEP40_; if (param->u.crypt.key_len == 13) @@ -3150,19 +3153,19 @@ static int rtw_set_encryption(struct net_device *dev, struct ieee_param *param, } else if (strcmp(param->u.crypt.alg, "TKIP") == 0) { psecuritypriv->dot118021XGrpPrivacy = _TKIP_; - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); /* DEBUG_ERR("set key length :param->u.crypt.key_len =%d\n", param->u.crypt.key_len); */ /* set mic key */ - memcpy(psecuritypriv->dot118021XGrptxmickey[param->u.crypt.idx].skey, &(param->u.crypt.key[16]), 8); - memcpy(psecuritypriv->dot118021XGrprxmickey[param->u.crypt.idx].skey, &(param->u.crypt.key[24]), 8); + memcpy(txkey, &(param->u.crypt.key[16]), 8); + memcpy(rxkey, &(param->u.crypt.key[24]), 8); psecuritypriv->busetkipkey = true; } else if (strcmp(param->u.crypt.alg, "CCMP") == 0) { psecuritypriv->dot118021XGrpPrivacy = _AES_; - memcpy(psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); + memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); } else { psecuritypriv->dot118021XGrpPrivacy = _NO_PRIVACY_; } diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 01645e87b3d5..fa1548d4f94b 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1171,7 +1171,7 @@ static inline int resize_screen(struct vc_data *vc, int width, int height, /* Resizes the resolution of the display adapater */ int err = 0; - if (vc->vc_mode != KD_GRAPHICS && vc->vc_sw->con_resize) + if (vc->vc_sw->con_resize) err = vc->vc_sw->con_resize(vc, width, height, user); return err; diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 89aeaf3c1bca..0e0cd9e9e589 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -671,21 +671,58 @@ static int vt_resizex(struct vc_data *vc, struct vt_consize __user *cs) if (copy_from_user(&v, cs, sizeof(struct vt_consize))) return -EFAULT; - if (v.v_vlin) - pr_info_once("\"struct vt_consize\"->v_vlin is ignored. Please report if you need this.\n"); - if (v.v_clin) - pr_info_once("\"struct vt_consize\"->v_clin is ignored. Please report if you need this.\n"); + /* FIXME: Should check the copies properly */ + if (!v.v_vlin) + v.v_vlin = vc->vc_scan_lines; + + if (v.v_clin) { + int rows = v.v_vlin / v.v_clin; + if (v.v_rows != rows) { + if (v.v_rows) /* Parameters don't add up */ + return -EINVAL; + v.v_rows = rows; + } + } + + if (v.v_vcol && v.v_ccol) { + int cols = v.v_vcol / v.v_ccol; + if (v.v_cols != cols) { + if (v.v_cols) + return -EINVAL; + v.v_cols = cols; + } + } + + if (v.v_clin > 32) + return -EINVAL; - console_lock(); for (i = 0; i < MAX_NR_CONSOLES; i++) { - vc = vc_cons[i].d; + struct vc_data *vcp; - if (vc) { - vc->vc_resize_user = 1; - vc_resize(vc, v.v_cols, v.v_rows); + if (!vc_cons[i].d) + continue; + console_lock(); + vcp = vc_cons[i].d; + if (vcp) { + int ret; + int save_scan_lines = vcp->vc_scan_lines; + int save_cell_height = vcp->vc_cell_height; + + if (v.v_vlin) + vcp->vc_scan_lines = v.v_vlin; + if (v.v_clin) + vcp->vc_cell_height = v.v_clin; + vcp->vc_resize_user = 1; + ret = vc_resize(vcp, v.v_cols, v.v_rows); + if (ret) { + vcp->vc_scan_lines = save_scan_lines; + vcp->vc_cell_height = save_cell_height; + console_unlock(); + return ret; + } } + console_unlock(); } - console_unlock(); return 0; } diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 508b1c3f8b73..d1e4a7379beb 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -321,12 +321,23 @@ exit: } -static void kill_urbs(struct wdm_device *desc) +static void poison_urbs(struct wdm_device *desc) { /* the order here is essential */ - usb_kill_urb(desc->command); - usb_kill_urb(desc->validity); - usb_kill_urb(desc->response); + usb_poison_urb(desc->command); + usb_poison_urb(desc->validity); + usb_poison_urb(desc->response); +} + +static void unpoison_urbs(struct wdm_device *desc) +{ + /* + * the order here is not essential + * it is symmetrical just to be nice + */ + usb_unpoison_urb(desc->response); + usb_unpoison_urb(desc->validity); + usb_unpoison_urb(desc->command); } static void free_urbs(struct wdm_device *desc) @@ -741,11 +752,12 @@ static int wdm_release(struct inode *inode, struct file *file) if (!desc->count) { if (!test_bit(WDM_DISCONNECTING, &desc->flags)) { dev_dbg(&desc->intf->dev, "wdm_release: cleanup\n"); - kill_urbs(desc); + poison_urbs(desc); spin_lock_irq(&desc->iuspin); desc->resp_count = 0; spin_unlock_irq(&desc->iuspin); desc->manage_power(desc->intf, 0); + unpoison_urbs(desc); } else { /* must avoid dev_printk here as desc->intf is invalid */ pr_debug(KBUILD_MODNAME " %s: device gone - cleaning up\n", __func__); @@ -1037,9 +1049,9 @@ static void wdm_disconnect(struct usb_interface *intf) wake_up_all(&desc->wait); mutex_lock(&desc->rlock); mutex_lock(&desc->wlock); + poison_urbs(desc); cancel_work_sync(&desc->rxwork); cancel_work_sync(&desc->service_outs_intr); - kill_urbs(desc); mutex_unlock(&desc->wlock); mutex_unlock(&desc->rlock); @@ -1080,9 +1092,10 @@ static int wdm_suspend(struct usb_interface *intf, pm_message_t message) set_bit(WDM_SUSPENDING, &desc->flags); spin_unlock_irq(&desc->iuspin); /* callback submits work - order is essential */ - kill_urbs(desc); + poison_urbs(desc); cancel_work_sync(&desc->rxwork); cancel_work_sync(&desc->service_outs_intr); + unpoison_urbs(desc); } if (!PMSG_IS_AUTO(message)) { mutex_unlock(&desc->wlock); @@ -1140,7 +1153,7 @@ static int wdm_pre_reset(struct usb_interface *intf) wake_up_all(&desc->wait); mutex_lock(&desc->rlock); mutex_lock(&desc->wlock); - kill_urbs(desc); + poison_urbs(desc); cancel_work_sync(&desc->rxwork); cancel_work_sync(&desc->service_outs_intr); return 0; @@ -1151,6 +1164,7 @@ static int wdm_post_reset(struct usb_interface *intf) struct wdm_device *desc = wdm_find_device(intf); int rv; + unpoison_urbs(desc); clear_bit(WDM_OVERFLOW, &desc->flags); clear_bit(WDM_RESETTING, &desc->flags); rv = recover_from_urb_loss(desc); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index b2bc4b7c4289..fc7d6cdacf16 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -3642,9 +3642,6 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg) * sequence. */ status = hub_port_status(hub, port1, &portstatus, &portchange); - - /* TRSMRCY = 10 msec */ - msleep(10); } SuspendCleared: @@ -3659,6 +3656,9 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg) usb_clear_port_feature(hub->hdev, port1, USB_PORT_FEAT_C_SUSPEND); } + + /* TRSMRCY = 10 msec */ + msleep(10); } if (udev->persist_enabled) diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h index da5ac4a4595b..ab6b815e0089 100644 --- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -113,6 +113,7 @@ struct dwc2_hsotg_req; * @debugfs: File entry for debugfs file for this endpoint. * @dir_in: Set to true if this endpoint is of the IN direction, which * means that it is sending data to the Host. + * @map_dir: Set to the value of dir_in when the DMA buffer is mapped. * @index: The index for the endpoint registers. * @mc: Multi Count - number of transactions per microframe * @interval: Interval for periodic endpoints, in frames or microframes. @@ -162,6 +163,7 @@ struct dwc2_hsotg_ep { unsigned short fifo_index; unsigned char dir_in; + unsigned char map_dir; unsigned char index; unsigned char mc; u16 interval; diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index e6bb1bdb2760..184964174dc0 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -422,7 +422,7 @@ static void dwc2_hsotg_unmap_dma(struct dwc2_hsotg *hsotg, { struct usb_request *req = &hs_req->req; - usb_gadget_unmap_request(&hsotg->gadget, req, hs_ep->dir_in); + usb_gadget_unmap_request(&hsotg->gadget, req, hs_ep->map_dir); } /* @@ -1242,6 +1242,7 @@ static int dwc2_hsotg_map_dma(struct dwc2_hsotg *hsotg, { int ret; + hs_ep->map_dir = hs_ep->dir_in; ret = usb_gadget_map_request(&hsotg->gadget, req, hs_ep->dir_in); if (ret) goto dma_error; diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index 3024785d84cb..520a0beef77c 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -776,7 +776,3 @@ static struct platform_driver dwc2_platform_driver = { }; module_platform_driver(dwc2_platform_driver); - -MODULE_DESCRIPTION("DESIGNWARE HS OTG Platform Glue"); -MODULE_AUTHOR("Matthijs Kooijman <matthijs@stdin.nl>"); -MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index b1e875c58f20..c5d5760cdf53 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -57,7 +57,7 @@ #define DWC3_DEVICE_EVENT_LINK_STATUS_CHANGE 3 #define DWC3_DEVICE_EVENT_WAKEUP 4 #define DWC3_DEVICE_EVENT_HIBER_REQ 5 -#define DWC3_DEVICE_EVENT_EOPF 6 +#define DWC3_DEVICE_EVENT_SUSPEND 6 #define DWC3_DEVICE_EVENT_SOF 7 #define DWC3_DEVICE_EVENT_ERRATIC_ERROR 9 #define DWC3_DEVICE_EVENT_CMD_CMPL 10 @@ -460,7 +460,7 @@ #define DWC3_DEVTEN_CMDCMPLTEN BIT(10) #define DWC3_DEVTEN_ERRTICERREN BIT(9) #define DWC3_DEVTEN_SOFEN BIT(7) -#define DWC3_DEVTEN_EOPFEN BIT(6) +#define DWC3_DEVTEN_U3L2L1SUSPEN BIT(6) #define DWC3_DEVTEN_HIBERNATIONREQEVTEN BIT(5) #define DWC3_DEVTEN_WKUPEVTEN BIT(4) #define DWC3_DEVTEN_ULSTCNGEN BIT(3) @@ -850,6 +850,7 @@ struct dwc3_trb { * @hwparams6: GHWPARAMS6 * @hwparams7: GHWPARAMS7 * @hwparams8: GHWPARAMS8 + * @hwparams9: GHWPARAMS9 */ struct dwc3_hwparams { u32 hwparams0; @@ -1374,7 +1375,7 @@ struct dwc3_event_depevt { * 3 - ULStChng * 4 - WkUpEvt * 5 - Reserved - * 6 - EOPF + * 6 - Suspend (EOPF on revisions 2.10a and prior) * 7 - SOF * 8 - Reserved * 9 - ErrticErr diff --git a/drivers/usb/dwc3/debug.h b/drivers/usb/dwc3/debug.h index db231de46bb3..d0ac89c5b317 100644 --- a/drivers/usb/dwc3/debug.h +++ b/drivers/usb/dwc3/debug.h @@ -221,8 +221,8 @@ static inline const char *dwc3_gadget_event_string(char *str, size_t size, snprintf(str, size, "WakeUp [%s]", dwc3_gadget_link_string(state)); break; - case DWC3_DEVICE_EVENT_EOPF: - snprintf(str, size, "End-Of-Frame [%s]", + case DWC3_DEVICE_EVENT_SUSPEND: + snprintf(str, size, "Suspend [%s]", dwc3_gadget_link_string(state)); break; case DWC3_DEVICE_EVENT_SOF: @@ -353,8 +353,8 @@ static inline const char *dwc3_gadget_event_type_string(u8 event) return "Wake-Up"; case DWC3_DEVICE_EVENT_HIBER_REQ: return "Hibernation"; - case DWC3_DEVICE_EVENT_EOPF: - return "End of Periodic Frame"; + case DWC3_DEVICE_EVENT_SUSPEND: + return "Suspend"; case DWC3_DEVICE_EVENT_SOF: return "Start of Frame"; case DWC3_DEVICE_EVENT_ERRATIC_ERROR: diff --git a/drivers/usb/dwc3/dwc3-imx8mp.c b/drivers/usb/dwc3/dwc3-imx8mp.c index b13cfab89d53..756faa46d33a 100644 --- a/drivers/usb/dwc3/dwc3-imx8mp.c +++ b/drivers/usb/dwc3/dwc3-imx8mp.c @@ -165,8 +165,9 @@ static int dwc3_imx8mp_probe(struct platform_device *pdev) if (err < 0) goto disable_rpm; - dwc3_np = of_get_child_by_name(node, "dwc3"); + dwc3_np = of_get_compatible_child(node, "snps,dwc3"); if (!dwc3_np) { + err = -ENODEV; dev_err(dev, "failed to find dwc3 core child\n"); goto disable_rpm; } diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c index 3db17806e92e..e196673f5c64 100644 --- a/drivers/usb/dwc3/dwc3-omap.c +++ b/drivers/usb/dwc3/dwc3-omap.c @@ -437,8 +437,13 @@ static int dwc3_omap_extcon_register(struct dwc3_omap *omap) if (extcon_get_state(edev, EXTCON_USB) == true) dwc3_omap_set_mailbox(omap, OMAP_DWC3_VBUS_VALID); + else + dwc3_omap_set_mailbox(omap, OMAP_DWC3_VBUS_OFF); + if (extcon_get_state(edev, EXTCON_USB_HOST) == true) dwc3_omap_set_mailbox(omap, OMAP_DWC3_ID_GROUND); + else + dwc3_omap_set_mailbox(omap, OMAP_DWC3_ID_FLOAT); omap->edev = edev; } diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index e7b932dcbf82..1e51460938b8 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -123,6 +123,7 @@ static const struct property_entry dwc3_pci_mrfld_properties[] = { PROPERTY_ENTRY_STRING("linux,extcon-name", "mrfld_bcove_pwrsrc"), PROPERTY_ENTRY_BOOL("snps,dis_u3_susphy_quirk"), PROPERTY_ENTRY_BOOL("snps,dis_u2_susphy_quirk"), + PROPERTY_ENTRY_BOOL("snps,usb2-gadget-lpm-disable"), PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"), {} }; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index dd80e5ca8c78..49ca5da5e279 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1684,7 +1684,9 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req) } } - return __dwc3_gadget_kick_transfer(dep); + __dwc3_gadget_kick_transfer(dep); + + return 0; } static int dwc3_gadget_ep_queue(struct usb_ep *ep, struct usb_request *request, @@ -2323,6 +2325,10 @@ static void dwc3_gadget_enable_irq(struct dwc3 *dwc) if (DWC3_VER_IS_PRIOR(DWC3, 250A)) reg |= DWC3_DEVTEN_ULSTCNGEN; + /* On 2.30a and above this bit enables U3/L2-L1 Suspend Events */ + if (!DWC3_VER_IS_PRIOR(DWC3, 230A)) + reg |= DWC3_DEVTEN_U3L2L1SUSPEN; + dwc3_writel(dwc->regs, DWC3_DEVTEN, reg); } @@ -3740,7 +3746,7 @@ static void dwc3_gadget_interrupt(struct dwc3 *dwc, case DWC3_DEVICE_EVENT_LINK_STATUS_CHANGE: dwc3_gadget_linksts_change_interrupt(dwc, event->event_info); break; - case DWC3_DEVICE_EVENT_EOPF: + case DWC3_DEVICE_EVENT_SUSPEND: /* It changed to be suspend event for version 2.30a and above */ if (!DWC3_VER_IS_PRIOR(DWC3, 230A)) { /* @@ -4058,8 +4064,9 @@ err0: void dwc3_gadget_exit(struct dwc3 *dwc) { - usb_del_gadget_udc(dwc->gadget); + usb_del_gadget(dwc->gadget); dwc3_gadget_free_endpoints(dwc); + usb_put_gadget(dwc->gadget); dma_free_coherent(dwc->sysdev, DWC3_BOUNCE_SIZE, dwc->bounce, dwc->bounce_addr); kfree(dwc->setup_buf); diff --git a/drivers/usb/host/fotg210-hcd.c b/drivers/usb/host/fotg210-hcd.c index 6cac642520fc..9c2eda0918e1 100644 --- a/drivers/usb/host/fotg210-hcd.c +++ b/drivers/usb/host/fotg210-hcd.c @@ -5568,7 +5568,7 @@ static int fotg210_hcd_probe(struct platform_device *pdev) struct usb_hcd *hcd; struct resource *res; int irq; - int retval = -ENODEV; + int retval; struct fotg210_hcd *fotg210; if (usb_disabled()) @@ -5588,7 +5588,7 @@ static int fotg210_hcd_probe(struct platform_device *pdev) hcd = usb_create_hcd(&fotg210_fotg210_hc_driver, dev, dev_name(dev)); if (!hcd) { - dev_err(dev, "failed to create hcd with err %d\n", retval); + dev_err(dev, "failed to create hcd\n"); retval = -ENOMEM; goto fail_create_hcd; } diff --git a/drivers/usb/host/xhci-ext-caps.h b/drivers/usb/host/xhci-ext-caps.h index fa59b242cd51..e8af0a125f84 100644 --- a/drivers/usb/host/xhci-ext-caps.h +++ b/drivers/usb/host/xhci-ext-caps.h @@ -7,8 +7,9 @@ * Author: Sarah Sharp * Some code borrowed from the Linux EHCI driver. */ -/* Up to 16 ms to halt an HC */ -#define XHCI_MAX_HALT_USEC (16*1000) + +/* HC should halt within 16 ms, but use 32 ms as some hosts take longer */ +#define XHCI_MAX_HALT_USEC (32 * 1000) /* HC not running - set to 1 when run/stop bit is cleared. */ #define XHCI_STS_HALT (1<<0) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 5bbccc9a0179..7bc18cf8042c 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -57,6 +57,7 @@ #define PCI_DEVICE_ID_INTEL_CML_XHCI 0xa3af #define PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI 0x9a13 #define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI 0x1138 +#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI 0x461e #define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba @@ -166,8 +167,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) (pdev->device == 0x15e0 || pdev->device == 0x15e1)) xhci->quirks |= XHCI_SNPS_BROKEN_SUSPEND; - if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == 0x15e5) + if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == 0x15e5) { xhci->quirks |= XHCI_DISABLE_SPARSE; + xhci->quirks |= XHCI_RESET_ON_RESUME; + } if (pdev->vendor == PCI_VENDOR_ID_AMD) xhci->quirks |= XHCI_TRUST_TX_LENGTH; @@ -243,7 +246,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI)) + pdev->device == PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI)) xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW; if (pdev->vendor == PCI_VENDOR_ID_ETRON && diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 05c38dd3ee36..a8e4189277da 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -862,7 +862,7 @@ done: return ret; } -static void xhci_handle_halted_endpoint(struct xhci_hcd *xhci, +static int xhci_handle_halted_endpoint(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, unsigned int stream_id, struct xhci_td *td, enum xhci_ep_reset_type reset_type) @@ -875,7 +875,7 @@ static void xhci_handle_halted_endpoint(struct xhci_hcd *xhci, * Device will be reset soon to recover the link so don't do anything */ if (ep->vdev->flags & VDEV_PORT_ERROR) - return; + return -ENODEV; /* add td to cancelled list and let reset ep handler take care of it */ if (reset_type == EP_HARD_RESET) { @@ -888,16 +888,18 @@ static void xhci_handle_halted_endpoint(struct xhci_hcd *xhci, if (ep->ep_state & EP_HALTED) { xhci_dbg(xhci, "Reset ep command already pending\n"); - return; + return 0; } err = xhci_reset_halted_ep(xhci, slot_id, ep->ep_index, reset_type); if (err) - return; + return err; ep->ep_state |= EP_HALTED; xhci_ring_cmd_db(xhci); + + return 0; } /* @@ -1014,6 +1016,7 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id, struct xhci_td *td = NULL; enum xhci_ep_reset_type reset_type; struct xhci_command *command; + int err; if (unlikely(TRB_TO_SUSPEND_PORT(le32_to_cpu(trb->generic.field[3])))) { if (!xhci->devs[slot_id]) @@ -1058,7 +1061,10 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id, td->status = -EPROTO; } /* reset ep, reset handler cleans up cancelled tds */ - xhci_handle_halted_endpoint(xhci, ep, 0, td, reset_type); + err = xhci_handle_halted_endpoint(xhci, ep, 0, td, + reset_type); + if (err) + break; xhci_stop_watchdog_timer_in_irq(xhci, ep); return; case EP_STATE_RUNNING: diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index ca9385d22f68..27283654ca08 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1514,7 +1514,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci, * we need to issue an evaluate context command and wait on it. */ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id, - unsigned int ep_index, struct urb *urb) + unsigned int ep_index, struct urb *urb, gfp_t mem_flags) { struct xhci_container_ctx *out_ctx; struct xhci_input_control_ctx *ctrl_ctx; @@ -1545,7 +1545,7 @@ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id, * changes max packet sizes. */ - command = xhci_alloc_command(xhci, true, GFP_KERNEL); + command = xhci_alloc_command(xhci, true, mem_flags); if (!command) return -ENOMEM; @@ -1639,7 +1639,7 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag */ if (urb->dev->speed == USB_SPEED_FULL) { ret = xhci_check_maxpacket(xhci, slot_id, - ep_index, urb); + ep_index, urb, mem_flags); if (ret < 0) { xhci_urb_free_priv(urb_priv); urb->hcpriv = NULL; diff --git a/drivers/usb/musb/mediatek.c b/drivers/usb/musb/mediatek.c index eebeadd26946..6b92d037d8fc 100644 --- a/drivers/usb/musb/mediatek.c +++ b/drivers/usb/musb/mediatek.c @@ -518,8 +518,8 @@ static int mtk_musb_probe(struct platform_device *pdev) glue->xceiv = devm_usb_get_phy(dev, USB_PHY_TYPE_USB2); if (IS_ERR(glue->xceiv)) { - dev_err(dev, "fail to getting usb-phy %d\n", ret); ret = PTR_ERR(glue->xceiv); + dev_err(dev, "fail to getting usb-phy %d\n", ret); goto err_unregister_usb_phy; } diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index c4fdc00a3bc8..64133e586c64 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -259,6 +259,7 @@ enum frs_typec_current { #define ALTMODE_DISCOVERY_MAX (SVID_DISCOVERY_MAX * MODE_DISCOVERY_MAX) #define GET_SINK_CAP_RETRY_MS 100 +#define SEND_DISCOVER_RETRY_MS 100 struct pd_mode_data { int svid_index; /* current SVID index */ @@ -366,6 +367,8 @@ struct tcpm_port { struct kthread_work vdm_state_machine; struct hrtimer enable_frs_timer; struct kthread_work enable_frs; + struct hrtimer send_discover_timer; + struct kthread_work send_discover_work; bool state_machine_running; bool vdm_sm_running; @@ -1178,6 +1181,16 @@ static void mod_enable_frs_delayed_work(struct tcpm_port *port, unsigned int del } } +static void mod_send_discover_delayed_work(struct tcpm_port *port, unsigned int delay_ms) +{ + if (delay_ms) { + hrtimer_start(&port->send_discover_timer, ms_to_ktime(delay_ms), HRTIMER_MODE_REL); + } else { + hrtimer_cancel(&port->send_discover_timer); + kthread_queue_work(port->wq, &port->send_discover_work); + } +} + static void tcpm_set_state(struct tcpm_port *port, enum tcpm_state state, unsigned int delay_ms) { @@ -1855,6 +1868,9 @@ static void vdm_run_state_machine(struct tcpm_port *port) res = tcpm_ams_start(port, DISCOVER_IDENTITY); if (res == 0) port->send_discover = false; + else if (res == -EAGAIN) + mod_send_discover_delayed_work(port, + SEND_DISCOVER_RETRY_MS); break; case CMD_DISCOVER_SVID: res = tcpm_ams_start(port, DISCOVER_SVIDS); @@ -1880,7 +1896,7 @@ static void vdm_run_state_machine(struct tcpm_port *port) } if (res < 0) { - port->vdm_sm_running = false; + port->vdm_state = VDM_STATE_ERR_BUSY; return; } } @@ -1896,6 +1912,7 @@ static void vdm_run_state_machine(struct tcpm_port *port) port->vdo_data[0] = port->vdo_retry; port->vdo_count = 1; port->vdm_state = VDM_STATE_READY; + tcpm_ams_finish(port); break; case VDM_STATE_BUSY: port->vdm_state = VDM_STATE_ERR_TMOUT; @@ -1961,7 +1978,7 @@ static void vdm_state_machine_work(struct kthread_work *work) port->vdm_state != VDM_STATE_BUSY && port->vdm_state != VDM_STATE_SEND_MESSAGE); - if (port->vdm_state == VDM_STATE_ERR_TMOUT) + if (port->vdm_state < VDM_STATE_READY) port->vdm_sm_running = false; mutex_unlock(&port->lock); @@ -2390,7 +2407,7 @@ static void tcpm_pd_data_request(struct tcpm_port *port, port->nr_sink_caps = cnt; port->sink_cap_done = true; if (port->ams == GET_SINK_CAPABILITIES) - tcpm_pd_handle_state(port, ready_state(port), NONE_AMS, 0); + tcpm_set_state(port, ready_state(port), 0); /* Unexpected Sink Capabilities */ else tcpm_pd_handle_msg(port, @@ -2552,6 +2569,16 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port, port->sink_cap_done = true; tcpm_set_state(port, ready_state(port), 0); break; + case SRC_READY: + case SNK_READY: + if (port->vdm_state > VDM_STATE_READY) { + port->vdm_state = VDM_STATE_DONE; + if (tcpm_vdm_ams(port)) + tcpm_ams_finish(port); + mod_vdm_delayed_work(port, 0); + break; + } + fallthrough; default: tcpm_pd_handle_state(port, port->pwr_role == TYPEC_SOURCE ? @@ -3682,14 +3709,6 @@ static inline enum tcpm_state unattached_state(struct tcpm_port *port) return SNK_UNATTACHED; } -static void tcpm_check_send_discover(struct tcpm_port *port) -{ - if ((port->data_role == TYPEC_HOST || port->negotiated_rev > PD_REV20) && - port->send_discover && port->pd_capable) - tcpm_send_vdm(port, USB_SID_PD, CMD_DISCOVER_IDENT, NULL, 0); - port->send_discover = false; -} - static void tcpm_swap_complete(struct tcpm_port *port, int result) { if (port->swap_pending) { @@ -3926,7 +3945,18 @@ static void run_state_machine(struct tcpm_port *port) break; } - tcpm_check_send_discover(port); + /* + * 6.4.4.3.1 Discover Identity + * "The Discover Identity Command Shall only be sent to SOP when there is an + * Explicit Contract." + * For now, this driver only supports SOP for DISCOVER_IDENTITY, thus using + * port->explicit_contract to decide whether to send the command. + */ + if (port->explicit_contract) + mod_send_discover_delayed_work(port, 0); + else + port->send_discover = false; + /* * 6.3.5 * Sending ping messages is not necessary if @@ -4055,7 +4085,7 @@ static void run_state_machine(struct tcpm_port *port) if (port->vbus_present) { u32 current_lim = tcpm_get_current_limit(port); - if (port->slow_charger_loop || (current_lim > PD_P_SNK_STDBY_MW / 5)) + if (port->slow_charger_loop && (current_lim > PD_P_SNK_STDBY_MW / 5)) current_lim = PD_P_SNK_STDBY_MW / 5; tcpm_set_current_limit(port, current_lim, 5000); tcpm_set_charge(port, true); @@ -4194,7 +4224,18 @@ static void run_state_machine(struct tcpm_port *port) break; } - tcpm_check_send_discover(port); + /* + * 6.4.4.3.1 Discover Identity + * "The Discover Identity Command Shall only be sent to SOP when there is an + * Explicit Contract." + * For now, this driver only supports SOP for DISCOVER_IDENTITY, thus using + * port->explicit_contract. + */ + if (port->explicit_contract) + mod_send_discover_delayed_work(port, 0); + else + port->send_discover = false; + power_supply_changed(port->psy); break; @@ -5288,6 +5329,29 @@ unlock: mutex_unlock(&port->lock); } +static void tcpm_send_discover_work(struct kthread_work *work) +{ + struct tcpm_port *port = container_of(work, struct tcpm_port, send_discover_work); + + mutex_lock(&port->lock); + /* No need to send DISCOVER_IDENTITY anymore */ + if (!port->send_discover) + goto unlock; + + /* Retry if the port is not idle */ + if ((port->state != SRC_READY && port->state != SNK_READY) || port->vdm_sm_running) { + mod_send_discover_delayed_work(port, SEND_DISCOVER_RETRY_MS); + goto unlock; + } + + /* Only send the Message if the port is host for PD rev2.0 */ + if (port->data_role == TYPEC_HOST || port->negotiated_rev > PD_REV20) + tcpm_send_vdm(port, USB_SID_PD, CMD_DISCOVER_IDENT, NULL, 0); + +unlock: + mutex_unlock(&port->lock); +} + static int tcpm_dr_set(struct typec_port *p, enum typec_data_role data) { struct tcpm_port *port = typec_get_drvdata(p); @@ -5754,6 +5818,15 @@ static int tcpm_fw_get_caps(struct tcpm_port *port, if (!fwnode) return -EINVAL; + /* + * This fwnode has a "compatible" property, but is never populated as a + * struct device. Instead we simply parse it to read the properties. + * This it breaks fw_devlink=on. To maintain backward compatibility + * with existing DT files, we work around this by deleting any + * fwnode_links to/from this fwnode. + */ + fw_devlink_purge_absent_suppliers(fwnode); + /* USB data support is optional */ ret = fwnode_property_read_string(fwnode, "data-role", &cap_str); if (ret == 0) { @@ -6093,6 +6166,14 @@ static enum hrtimer_restart enable_frs_timer_handler(struct hrtimer *timer) return HRTIMER_NORESTART; } +static enum hrtimer_restart send_discover_timer_handler(struct hrtimer *timer) +{ + struct tcpm_port *port = container_of(timer, struct tcpm_port, send_discover_timer); + + kthread_queue_work(port->wq, &port->send_discover_work); + return HRTIMER_NORESTART; +} + struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) { struct tcpm_port *port; @@ -6123,12 +6204,15 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) kthread_init_work(&port->vdm_state_machine, vdm_state_machine_work); kthread_init_work(&port->event_work, tcpm_pd_event_handler); kthread_init_work(&port->enable_frs, tcpm_enable_frs_work); + kthread_init_work(&port->send_discover_work, tcpm_send_discover_work); hrtimer_init(&port->state_machine_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); port->state_machine_timer.function = state_machine_timer_handler; hrtimer_init(&port->vdm_state_machine_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); port->vdm_state_machine_timer.function = vdm_state_machine_timer_handler; hrtimer_init(&port->enable_frs_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); port->enable_frs_timer.function = enable_frs_timer_handler; + hrtimer_init(&port->send_discover_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + port->send_discover_timer.function = send_discover_timer_handler; spin_lock_init(&port->pd_event_lock); diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 282c3c825c13..1d8b7df59ff4 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -495,7 +495,8 @@ static void ucsi_unregister_altmodes(struct ucsi_connector *con, u8 recipient) } } -static void ucsi_get_pdos(struct ucsi_connector *con, int is_partner) +static int ucsi_get_pdos(struct ucsi_connector *con, int is_partner, + u32 *pdos, int offset, int num_pdos) { struct ucsi *ucsi = con->ucsi; u64 command; @@ -503,17 +504,39 @@ static void ucsi_get_pdos(struct ucsi_connector *con, int is_partner) command = UCSI_COMMAND(UCSI_GET_PDOS) | UCSI_CONNECTOR_NUMBER(con->num); command |= UCSI_GET_PDOS_PARTNER_PDO(is_partner); - command |= UCSI_GET_PDOS_NUM_PDOS(UCSI_MAX_PDOS - 1); + command |= UCSI_GET_PDOS_PDO_OFFSET(offset); + command |= UCSI_GET_PDOS_NUM_PDOS(num_pdos - 1); command |= UCSI_GET_PDOS_SRC_PDOS; - ret = ucsi_send_command(ucsi, command, con->src_pdos, - sizeof(con->src_pdos)); - if (ret < 0) { + ret = ucsi_send_command(ucsi, command, pdos + offset, + num_pdos * sizeof(u32)); + if (ret < 0) dev_err(ucsi->dev, "UCSI_GET_PDOS failed (%d)\n", ret); + if (ret == 0 && offset == 0) + dev_warn(ucsi->dev, "UCSI_GET_PDOS returned 0 bytes\n"); + + return ret; +} + +static void ucsi_get_src_pdos(struct ucsi_connector *con, int is_partner) +{ + int ret; + + /* UCSI max payload means only getting at most 4 PDOs at a time */ + ret = ucsi_get_pdos(con, 1, con->src_pdos, 0, UCSI_MAX_PDOS); + if (ret < 0) return; - } + con->num_pdos = ret / sizeof(u32); /* number of bytes to 32-bit PDOs */ - if (ret == 0) - dev_warn(ucsi->dev, "UCSI_GET_PDOS returned 0 bytes\n"); + if (con->num_pdos < UCSI_MAX_PDOS) + return; + + /* get the remaining PDOs, if any */ + ret = ucsi_get_pdos(con, 1, con->src_pdos, UCSI_MAX_PDOS, + PDO_MAX_OBJECTS - UCSI_MAX_PDOS); + if (ret < 0) + return; + + con->num_pdos += ret / sizeof(u32); } static void ucsi_pwr_opmode_change(struct ucsi_connector *con) @@ -522,7 +545,7 @@ static void ucsi_pwr_opmode_change(struct ucsi_connector *con) case UCSI_CONSTAT_PWR_OPMODE_PD: con->rdo = con->status.request_data_obj; typec_set_pwr_opmode(con->port, TYPEC_PWR_MODE_PD); - ucsi_get_pdos(con, 1); + ucsi_get_src_pdos(con, 1); break; case UCSI_CONSTAT_PWR_OPMODE_TYPEC1_5: con->rdo = 0; @@ -999,6 +1022,7 @@ static const struct typec_operations ucsi_ops = { .pr_set = ucsi_pr_swap }; +/* Caller must call fwnode_handle_put() after use */ static struct fwnode_handle *ucsi_find_fwnode(struct ucsi_connector *con) { struct fwnode_handle *fwnode; @@ -1033,7 +1057,7 @@ static int ucsi_register_port(struct ucsi *ucsi, int index) command |= UCSI_CONNECTOR_NUMBER(con->num); ret = ucsi_send_command(ucsi, command, &con->cap, sizeof(con->cap)); if (ret < 0) - goto out; + goto out_unlock; if (con->cap.op_mode & UCSI_CONCAP_OPMODE_DRP) cap->data = TYPEC_PORT_DRD; @@ -1151,6 +1175,8 @@ static int ucsi_register_port(struct ucsi *ucsi, int index) trace_ucsi_register_port(con->num, &con->status); out: + fwnode_handle_put(cap->fwnode); +out_unlock: mutex_unlock(&con->lock); return ret; } diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index 3920e20a9e9e..cee666790907 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -8,6 +8,7 @@ #include <linux/power_supply.h> #include <linux/types.h> #include <linux/usb/typec.h> +#include <linux/usb/pd.h> #include <linux/usb/role.h> /* -------------------------------------------------------------------------- */ @@ -134,7 +135,9 @@ void ucsi_connector_change(struct ucsi *ucsi, u8 num); /* GET_PDOS command bits */ #define UCSI_GET_PDOS_PARTNER_PDO(_r_) ((u64)(_r_) << 23) +#define UCSI_GET_PDOS_PDO_OFFSET(_r_) ((u64)(_r_) << 24) #define UCSI_GET_PDOS_NUM_PDOS(_r_) ((u64)(_r_) << 32) +#define UCSI_MAX_PDOS (4) #define UCSI_GET_PDOS_SRC_PDOS ((u64)1 << 34) /* -------------------------------------------------------------------------- */ @@ -302,7 +305,6 @@ struct ucsi { #define UCSI_MAX_SVID 5 #define UCSI_MAX_ALTMODES (UCSI_MAX_SVID * 6) -#define UCSI_MAX_PDOS (4) #define UCSI_TYPEC_VSAFE5V 5000 #define UCSI_TYPEC_1_5_CURRENT 1500 @@ -330,7 +332,7 @@ struct ucsi_connector { struct power_supply *psy; struct power_supply_desc psy_desc; u32 rdo; - u32 src_pdos[UCSI_MAX_PDOS]; + u32 src_pdos[PDO_MAX_OBJECTS]; int num_pdos; struct usb_role_switch *usb_role_sw; diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index 39258f9d36a0..ef9c57ce0906 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -380,7 +380,7 @@ static void vgacon_init(struct vc_data *c, int init) vc_resize(c, vga_video_num_columns, vga_video_num_lines); c->vc_scan_lines = vga_scan_lines; - c->vc_font.height = vga_video_font_height; + c->vc_font.height = c->vc_cell_height = vga_video_font_height; c->vc_complement_mask = 0x7700; if (vga_512_chars) c->vc_hi_font_mask = 0x0800; @@ -515,32 +515,32 @@ static void vgacon_cursor(struct vc_data *c, int mode) switch (CUR_SIZE(c->vc_cursor_type)) { case CUR_UNDERLINE: vgacon_set_cursor_size(c->state.x, - c->vc_font.height - - (c->vc_font.height < + c->vc_cell_height - + (c->vc_cell_height < 10 ? 2 : 3), - c->vc_font.height - - (c->vc_font.height < + c->vc_cell_height - + (c->vc_cell_height < 10 ? 1 : 2)); break; case CUR_TWO_THIRDS: vgacon_set_cursor_size(c->state.x, - c->vc_font.height / 3, - c->vc_font.height - - (c->vc_font.height < + c->vc_cell_height / 3, + c->vc_cell_height - + (c->vc_cell_height < 10 ? 1 : 2)); break; case CUR_LOWER_THIRD: vgacon_set_cursor_size(c->state.x, - (c->vc_font.height * 2) / 3, - c->vc_font.height - - (c->vc_font.height < + (c->vc_cell_height * 2) / 3, + c->vc_cell_height - + (c->vc_cell_height < 10 ? 1 : 2)); break; case CUR_LOWER_HALF: vgacon_set_cursor_size(c->state.x, - c->vc_font.height / 2, - c->vc_font.height - - (c->vc_font.height < + c->vc_cell_height / 2, + c->vc_cell_height - + (c->vc_cell_height < 10 ? 1 : 2)); break; case CUR_NONE: @@ -551,7 +551,7 @@ static void vgacon_cursor(struct vc_data *c, int mode) break; default: vgacon_set_cursor_size(c->state.x, 1, - c->vc_font.height); + c->vc_cell_height); break; } break; @@ -562,13 +562,13 @@ static int vgacon_doresize(struct vc_data *c, unsigned int width, unsigned int height) { unsigned long flags; - unsigned int scanlines = height * c->vc_font.height; + unsigned int scanlines = height * c->vc_cell_height; u8 scanlines_lo = 0, r7 = 0, vsync_end = 0, mode, max_scan; raw_spin_lock_irqsave(&vga_lock, flags); vgacon_xres = width * VGA_FONTWIDTH; - vgacon_yres = height * c->vc_font.height; + vgacon_yres = height * c->vc_cell_height; if (vga_video_type >= VIDEO_TYPE_VGAC) { outb_p(VGA_CRTC_MAX_SCAN, vga_video_port_reg); max_scan = inb_p(vga_video_port_val); @@ -623,9 +623,9 @@ static int vgacon_doresize(struct vc_data *c, static int vgacon_switch(struct vc_data *c) { int x = c->vc_cols * VGA_FONTWIDTH; - int y = c->vc_rows * c->vc_font.height; + int y = c->vc_rows * c->vc_cell_height; int rows = screen_info.orig_video_lines * vga_default_font_height/ - c->vc_font.height; + c->vc_cell_height; /* * We need to save screen size here as it's the only way * we can spot the screen has been resized and we need to @@ -1038,7 +1038,7 @@ static int vgacon_adjust_height(struct vc_data *vc, unsigned fontheight) cursor_size_lastto = 0; c->vc_sw->con_cursor(c, CM_DRAW); } - c->vc_font.height = fontheight; + c->vc_font.height = c->vc_cell_height = fontheight; vc_resize(c, 0, rows); /* Adjust console size */ } } @@ -1086,12 +1086,20 @@ static int vgacon_resize(struct vc_data *c, unsigned int width, if ((width << 1) * height > vga_vram_size) return -EINVAL; + if (user) { + /* + * Ho ho! Someone (svgatextmode, eh?) may have reprogrammed + * the video mode! Set the new defaults then and go away. + */ + screen_info.orig_video_cols = width; + screen_info.orig_video_lines = height; + vga_default_font_height = c->vc_cell_height; + return 0; + } if (width % 2 || width > screen_info.orig_video_cols || height > (screen_info.orig_video_lines * vga_default_font_height)/ - c->vc_font.height) - /* let svgatextmode tinker with video timings and - return success */ - return (user) ? 0 : -EINVAL; + c->vc_cell_height) + return -EINVAL; if (con_is_visible(c) && !vga_is_gfx) /* who knows */ vgacon_doresize(c, width, height); diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 3406067985b1..22bb3892f6bd 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2019,7 +2019,7 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width, return -EINVAL; pr_debug("resize now %ix%i\n", var.xres, var.yres); - if (con_is_visible(vc)) { + if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { var.activate = FB_ACTIVATE_NOW | FB_ACTIVATE_FORCE; fb_set_var(info, &var); diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index f01d58c7a042..a3e7be96527d 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -1017,8 +1017,10 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) err = mmu_interval_notifier_insert_locked( &map->notifier, vma->vm_mm, vma->vm_start, vma->vm_end - vma->vm_start, &gntdev_mmu_ops); - if (err) + if (err) { + map->vma = NULL; goto out_unlock_put; + } } mutex_unlock(&priv->lock); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 4c89afc0df62..24d11861ac7d 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -164,6 +164,11 @@ int __ref xen_swiotlb_init(void) int rc = -ENOMEM; char *start; + if (io_tlb_default_mem != NULL) { + pr_warn("swiotlb buffer already initialized\n"); + return -EEXIST; + } + retry: m_ret = XEN_SWIOTLB_ENOMEM; order = get_order(bytes); diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c index e64e6befc63b..87e6b7db892f 100644 --- a/drivers/xen/unpopulated-alloc.c +++ b/drivers/xen/unpopulated-alloc.c @@ -39,8 +39,10 @@ static int fill_list(unsigned int nr_pages) } pgmap = kzalloc(sizeof(*pgmap), GFP_KERNEL); - if (!pgmap) + if (!pgmap) { + ret = -ENOMEM; goto err_pgmap; + } pgmap->type = MEMORY_DEVICE_GENERIC; pgmap->range = (struct range) { diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f83fd3cbf243..9fb76829a281 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3127,7 +3127,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, u64 new_size, u32 min_type); -int btrfs_start_delalloc_snapshot(struct btrfs_root *root); +int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context); int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, bool in_reclaim_context); int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 7a28314189b4..f1d15b68994a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1340,12 +1340,16 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, stripe = bbio->stripes; for (i = 0; i < bbio->num_stripes; i++, stripe++) { u64 bytes; + struct btrfs_device *device = stripe->dev; - if (!stripe->dev->bdev) { + if (!device->bdev) { ASSERT(btrfs_test_opt(fs_info, DEGRADED)); continue; } + if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) + continue; + ret = do_discard_extent(stripe, &bytes); if (!ret) { discarded_bytes += bytes; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 864c08d08a35..3b10d98b4ebb 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2067,6 +2067,30 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end) return ret; } +static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx) +{ + struct btrfs_inode *inode = BTRFS_I(ctx->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + + if (btrfs_inode_in_log(inode, fs_info->generation) && + list_empty(&ctx->ordered_extents)) + return true; + + /* + * If we are doing a fast fsync we can not bail out if the inode's + * last_trans is <= then the last committed transaction, because we only + * update the last_trans of the inode during ordered extent completion, + * and for a fast fsync we don't wait for that, we only wait for the + * writeback to complete. + */ + if (inode->last_trans <= fs_info->last_trans_committed && + (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) || + list_empty(&ctx->ordered_extents))) + return true; + + return false; +} + /* * fsync call for both files and directories. This logs the inode into * the tree log instead of forcing full commits whenever possible. @@ -2185,17 +2209,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); - /* - * If we are doing a fast fsync we can not bail out if the inode's - * last_trans is <= then the last committed transaction, because we only - * update the last_trans of the inode during ordered extent completion, - * and for a fast fsync we don't wait for that, we only wait for the - * writeback to complete. - */ smp_mb(); - if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) || - (BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed && - (full_sync || list_empty(&ctx.ordered_extents)))) { + if (skip_inode_logging(&ctx)) { /* * We've had everything committed since the last time we were * modified so clear this flag in case it was set for whatever diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index e54466fc101f..4806295116d8 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -3949,7 +3949,7 @@ static int cleanup_free_space_cache_v1(struct btrfs_fs_info *fs_info, { struct btrfs_block_group *block_group; struct rb_node *node; - int ret; + int ret = 0; btrfs_info(fs_info, "cleaning free space cache v1"); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4af336008b12..eb6fddf40841 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9678,7 +9678,7 @@ out: return ret; } -int btrfs_start_delalloc_snapshot(struct btrfs_root *root) +int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, @@ -9691,7 +9691,7 @@ int btrfs_start_delalloc_snapshot(struct btrfs_root *root) if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) return -EROFS; - return start_delalloc_inodes(root, &wbc, true, false); + return start_delalloc_inodes(root, &wbc, true, in_reclaim_context); } int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ee1dbabb5d3c..5dc2fd843ae3 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -259,6 +259,8 @@ int btrfs_fileattr_set(struct user_namespace *mnt_userns, if (!fa->flags_valid) { /* 1 item for the inode */ trans = btrfs_start_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); goto update_flags; } @@ -907,7 +909,7 @@ static noinline int btrfs_mksnapshot(const struct path *parent, */ btrfs_drew_read_lock(&root->snapshot_lock); - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, false); if (ret) goto out; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 07b0b4218791..6c413bb451a3 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -984,7 +984,7 @@ int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre, if (pre) ret = clone_ordered_extent(ordered, 0, pre); - if (post) + if (ret == 0 && post) ret = clone_ordered_extent(ordered, pre + ordered->disk_num_bytes, post); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 2319c923c9e6..3ded812f522c 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3545,11 +3545,15 @@ static int try_flush_qgroup(struct btrfs_root *root) struct btrfs_trans_handle *trans; int ret; - /* Can't hold an open transaction or we run the risk of deadlocking */ - ASSERT(current->journal_info == NULL || - current->journal_info == BTRFS_SEND_TRANS_STUB); - if (WARN_ON(current->journal_info && - current->journal_info != BTRFS_SEND_TRANS_STUB)) + /* + * Can't hold an open transaction or we run the risk of deadlocking, + * and can't either be under the context of a send operation (where + * current->journal_info is set to BTRFS_SEND_TRANS_STUB), as that + * would result in a crash when starting a transaction and does not + * make sense either (send is a read-only operation). + */ + ASSERT(current->journal_info == NULL); + if (WARN_ON(current->journal_info)) return 0; /* @@ -3562,7 +3566,7 @@ static int try_flush_qgroup(struct btrfs_root *root) return 0; } - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, true); if (ret < 0) goto out; btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 55741adf9071..bd69db72acc5 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -7170,7 +7170,7 @@ static int flush_delalloc_roots(struct send_ctx *sctx) int i; if (root) { - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, false); if (ret) return ret; btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); @@ -7178,7 +7178,7 @@ static int flush_delalloc_roots(struct send_ctx *sctx) for (i = 0; i < sctx->clone_roots_cnt; i++) { root = sctx->clone_roots[i].root; - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, false); if (ret) return ret; btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index f67721d82e5d..95a600034d61 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6061,7 +6061,8 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, * (since logging them is pointless, a link count of 0 means they * will never be accessible). */ - if (btrfs_inode_in_log(inode, trans->transid) || + if ((btrfs_inode_in_log(inode, trans->transid) && + list_empty(&ctx->ordered_extents)) || inode->vfs_inode.i_nlink == 0) { ret = BTRFS_NO_LOG_SYNC; goto end_no_trans; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 70b23a0d03b1..304ce64c70a4 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1126,6 +1126,11 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) goto out; } + if (zone.type == BLK_ZONE_TYPE_CONVENTIONAL) { + ret = -EIO; + goto out; + } + switch (zone.cond) { case BLK_ZONE_COND_OFFLINE: case BLK_ZONE_COND_READONLY: @@ -144,6 +144,16 @@ struct wait_exceptional_entry_queue { struct exceptional_entry_key key; }; +/** + * enum dax_wake_mode: waitqueue wakeup behaviour + * @WAKE_ALL: wake all waiters in the waitqueue + * @WAKE_NEXT: wake only the first waiter in the waitqueue + */ +enum dax_wake_mode { + WAKE_ALL, + WAKE_NEXT, +}; + static wait_queue_head_t *dax_entry_waitqueue(struct xa_state *xas, void *entry, struct exceptional_entry_key *key) { @@ -182,7 +192,8 @@ static int wake_exceptional_entry_func(wait_queue_entry_t *wait, * The important information it's conveying is whether the entry at * this index used to be a PMD entry. */ -static void dax_wake_entry(struct xa_state *xas, void *entry, bool wake_all) +static void dax_wake_entry(struct xa_state *xas, void *entry, + enum dax_wake_mode mode) { struct exceptional_entry_key key; wait_queue_head_t *wq; @@ -196,7 +207,7 @@ static void dax_wake_entry(struct xa_state *xas, void *entry, bool wake_all) * must be in the waitqueue and the following check will see them. */ if (waitqueue_active(wq)) - __wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key); + __wake_up(wq, TASK_NORMAL, mode == WAKE_ALL ? 0 : 1, &key); } /* @@ -264,11 +275,11 @@ static void wait_entry_unlocked(struct xa_state *xas, void *entry) finish_wait(wq, &ewait.wait); } -static void put_unlocked_entry(struct xa_state *xas, void *entry) +static void put_unlocked_entry(struct xa_state *xas, void *entry, + enum dax_wake_mode mode) { - /* If we were the only waiter woken, wake the next one */ if (entry && !dax_is_conflict(entry)) - dax_wake_entry(xas, entry, false); + dax_wake_entry(xas, entry, mode); } /* @@ -286,7 +297,7 @@ static void dax_unlock_entry(struct xa_state *xas, void *entry) old = xas_store(xas, entry); xas_unlock_irq(xas); BUG_ON(!dax_is_locked(old)); - dax_wake_entry(xas, entry, false); + dax_wake_entry(xas, entry, WAKE_NEXT); } /* @@ -524,7 +535,7 @@ retry: dax_disassociate_entry(entry, mapping, false); xas_store(xas, NULL); /* undo the PMD join */ - dax_wake_entry(xas, entry, true); + dax_wake_entry(xas, entry, WAKE_ALL); mapping->nrpages -= PG_PMD_NR; entry = NULL; xas_set(xas, index); @@ -622,7 +633,7 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, entry = get_unlocked_entry(&xas, 0); if (entry) page = dax_busy_page(entry); - put_unlocked_entry(&xas, entry); + put_unlocked_entry(&xas, entry, WAKE_NEXT); if (page) break; if (++scanned % XA_CHECK_SCHED) @@ -664,7 +675,7 @@ static int __dax_invalidate_entry(struct address_space *mapping, mapping->nrpages -= 1UL << dax_entry_order(entry); ret = 1; out: - put_unlocked_entry(&xas, entry); + put_unlocked_entry(&xas, entry, WAKE_ALL); xas_unlock_irq(&xas); return ret; } @@ -937,13 +948,13 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev, xas_lock_irq(xas); xas_store(xas, entry); xas_clear_mark(xas, PAGECACHE_TAG_DIRTY); - dax_wake_entry(xas, entry, false); + dax_wake_entry(xas, entry, WAKE_NEXT); trace_dax_writeback_one(mapping->host, index, count); return ret; put_unlocked: - put_unlocked_entry(xas, entry); + put_unlocked_entry(xas, entry, WAKE_NEXT); return ret; } @@ -1684,7 +1695,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order) /* Did we race with someone splitting entry or so? */ if (!entry || dax_is_conflict(entry) || (order == 0 && !dax_is_pte_entry(entry))) { - put_unlocked_entry(&xas, entry); + put_unlocked_entry(&xas, entry, WAKE_NEXT); xas_unlock_irq(&xas); trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf, VM_FAULT_NOPAGE); diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index e62d813756f2..efaf32596b97 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -450,14 +450,31 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, lcn = m->lcn + 1; if (m->compressedlcs) goto out; - if (lcn == initial_lcn) - goto err_bonus_cblkcnt; err = z_erofs_load_cluster_from_disk(m, lcn); if (err) return err; + /* + * If the 1st NONHEAD lcluster has already been handled initially w/o + * valid compressedlcs, which means at least it mustn't be CBLKCNT, or + * an internal implemenatation error is detected. + * + * The following code can also handle it properly anyway, but let's + * BUG_ON in the debugging mode only for developers to notice that. + */ + DBG_BUGON(lcn == initial_lcn && + m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD); + switch (m->type) { + case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: + case Z_EROFS_VLE_CLUSTER_TYPE_HEAD: + /* + * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type + * rather than CBLKCNT, it's a 1 lcluster-sized pcluster. + */ + m->compressedlcs = 1; + break; case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: if (m->delta[0] != 1) goto err_bonus_cblkcnt; diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 53b13787eb2c..925a5ca3744a 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -117,19 +117,6 @@ static void f2fs_unlock_rpages(struct compress_ctx *cc, int len) f2fs_drop_rpages(cc, len, true); } -static void f2fs_put_rpages_mapping(struct address_space *mapping, - pgoff_t start, int len) -{ - int i; - - for (i = 0; i < len; i++) { - struct page *page = find_get_page(mapping, start + i); - - put_page(page); - put_page(page); - } -} - static void f2fs_put_rpages_wbc(struct compress_ctx *cc, struct writeback_control *wbc, bool redirty, int unlock) { @@ -158,13 +145,14 @@ int f2fs_init_compress_ctx(struct compress_ctx *cc) return cc->rpages ? 0 : -ENOMEM; } -void f2fs_destroy_compress_ctx(struct compress_ctx *cc) +void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse) { page_array_free(cc->inode, cc->rpages, cc->cluster_size); cc->rpages = NULL; cc->nr_rpages = 0; cc->nr_cpages = 0; - cc->cluster_idx = NULL_CLUSTER; + if (!reuse) + cc->cluster_idx = NULL_CLUSTER; } void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page) @@ -1036,7 +1024,7 @@ retry: } if (PageUptodate(page)) - unlock_page(page); + f2fs_put_page(page, 1); else f2fs_compress_ctx_add_page(cc, page); } @@ -1046,33 +1034,35 @@ retry: ret = f2fs_read_multi_pages(cc, &bio, cc->cluster_size, &last_block_in_bio, false, true); - f2fs_destroy_compress_ctx(cc); + f2fs_put_rpages(cc); + f2fs_destroy_compress_ctx(cc, true); if (ret) - goto release_pages; + goto out; if (bio) f2fs_submit_bio(sbi, bio, DATA); ret = f2fs_init_compress_ctx(cc); if (ret) - goto release_pages; + goto out; } for (i = 0; i < cc->cluster_size; i++) { f2fs_bug_on(sbi, cc->rpages[i]); page = find_lock_page(mapping, start_idx + i); - f2fs_bug_on(sbi, !page); + if (!page) { + /* page can be truncated */ + goto release_and_retry; + } f2fs_wait_on_page_writeback(page, DATA, true, true); - f2fs_compress_ctx_add_page(cc, page); - f2fs_put_page(page, 0); if (!PageUptodate(page)) { +release_and_retry: + f2fs_put_rpages(cc); f2fs_unlock_rpages(cc, i + 1); - f2fs_put_rpages_mapping(mapping, start_idx, - cc->cluster_size); - f2fs_destroy_compress_ctx(cc); + f2fs_destroy_compress_ctx(cc, true); goto retry; } } @@ -1103,10 +1093,10 @@ retry: } unlock_pages: + f2fs_put_rpages(cc); f2fs_unlock_rpages(cc, i); -release_pages: - f2fs_put_rpages_mapping(mapping, start_idx, i); - f2fs_destroy_compress_ctx(cc); + f2fs_destroy_compress_ctx(cc, true); +out: return ret; } @@ -1141,7 +1131,7 @@ bool f2fs_compress_write_end(struct inode *inode, void *fsdata, set_cluster_dirty(&cc); f2fs_put_rpages_wbc(&cc, NULL, false, 1); - f2fs_destroy_compress_ctx(&cc); + f2fs_destroy_compress_ctx(&cc, false); return first_index; } @@ -1361,7 +1351,7 @@ unlock_continue: f2fs_put_rpages(cc); page_array_free(cc->inode, cc->cpages, cc->nr_cpages); cc->cpages = NULL; - f2fs_destroy_compress_ctx(cc); + f2fs_destroy_compress_ctx(cc, false); return 0; out_destroy_crypt: @@ -1372,7 +1362,8 @@ out_destroy_crypt: for (i = 0; i < cc->nr_cpages; i++) { if (!cc->cpages[i]) continue; - f2fs_put_page(cc->cpages[i], 1); + f2fs_compress_free_page(cc->cpages[i]); + cc->cpages[i] = NULL; } out_put_cic: kmem_cache_free(cic_entry_slab, cic); @@ -1522,7 +1513,7 @@ write: err = f2fs_write_raw_pages(cc, submitted, wbc, io_type); f2fs_put_rpages_wbc(cc, wbc, false, 0); destroy_out: - f2fs_destroy_compress_ctx(cc); + f2fs_destroy_compress_ctx(cc, false); return err; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 96f1a354f89f..009a09fb9d88 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2287,7 +2287,7 @@ static int f2fs_mpage_readpages(struct inode *inode, max_nr_pages, &last_block_in_bio, rac != NULL, false); - f2fs_destroy_compress_ctx(&cc); + f2fs_destroy_compress_ctx(&cc, false); if (ret) goto set_error_page; } @@ -2332,7 +2332,7 @@ next_page: max_nr_pages, &last_block_in_bio, rac != NULL, false); - f2fs_destroy_compress_ctx(&cc); + f2fs_destroy_compress_ctx(&cc, false); } } #endif @@ -3033,7 +3033,7 @@ next: } } if (f2fs_compressed_file(inode)) - f2fs_destroy_compress_ctx(&cc); + f2fs_destroy_compress_ctx(&cc, false); #endif if (retry) { index = 0; @@ -3801,6 +3801,7 @@ static int f2fs_is_file_aligned(struct inode *inode) block_t pblock; unsigned long nr_pblocks; unsigned int blocks_per_sec = BLKS_PER_SEC(sbi); + unsigned int not_aligned = 0; int ret = 0; cur_lblock = 0; @@ -3833,13 +3834,20 @@ static int f2fs_is_file_aligned(struct inode *inode) if ((pblock - main_blkaddr) & (blocks_per_sec - 1) || nr_pblocks & (blocks_per_sec - 1)) { - f2fs_err(sbi, "Swapfile does not align to section"); - ret = -EINVAL; - goto out; + if (f2fs_is_pinned_file(inode)) { + f2fs_err(sbi, "Swapfile does not align to section"); + ret = -EINVAL; + goto out; + } + not_aligned++; } cur_lblock += nr_pblocks; } + if (not_aligned) + f2fs_warn(sbi, "Swapfile (%u) is not align to section: \n" + "\t1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate()", + not_aligned); out: return ret; } @@ -3858,6 +3866,7 @@ static int check_swap_activate_fast(struct swap_info_struct *sis, int nr_extents = 0; unsigned long nr_pblocks; unsigned int blocks_per_sec = BLKS_PER_SEC(sbi); + unsigned int not_aligned = 0; int ret = 0; /* @@ -3887,7 +3896,7 @@ static int check_swap_activate_fast(struct swap_info_struct *sis, /* hole */ if (!(map.m_flags & F2FS_MAP_FLAGS)) { f2fs_err(sbi, "Swapfile has holes\n"); - ret = -ENOENT; + ret = -EINVAL; goto out; } @@ -3896,9 +3905,12 @@ static int check_swap_activate_fast(struct swap_info_struct *sis, if ((pblock - SM_I(sbi)->main_blkaddr) & (blocks_per_sec - 1) || nr_pblocks & (blocks_per_sec - 1)) { - f2fs_err(sbi, "Swapfile does not align to section"); - ret = -EINVAL; - goto out; + if (f2fs_is_pinned_file(inode)) { + f2fs_err(sbi, "Swapfile does not align to section"); + ret = -EINVAL; + goto out; + } + not_aligned++; } if (cur_lblock + nr_pblocks >= sis->max) @@ -3927,6 +3939,11 @@ static int check_swap_activate_fast(struct swap_info_struct *sis, sis->max = cur_lblock; sis->pages = cur_lblock - 1; sis->highest_bit = cur_lblock - 1; + + if (not_aligned) + f2fs_warn(sbi, "Swapfile (%u) is not align to section: \n" + "\t1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate()", + not_aligned); out: return ret; } @@ -4035,7 +4052,7 @@ out: return ret; bad_bmap: f2fs_err(sbi, "Swapfile has holes\n"); - return -ENOENT; + return -EINVAL; } static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 044878866ca3..c83d90125ebd 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3956,7 +3956,7 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed); void f2fs_put_page_dic(struct page *page); int f2fs_init_compress_ctx(struct compress_ctx *cc); -void f2fs_destroy_compress_ctx(struct compress_ctx *cc); +void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse); void f2fs_init_compress_info(struct f2fs_sb_info *sbi); int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi); void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 44a4650aea7b..ceb575f99048 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1817,7 +1817,8 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) struct f2fs_inode_info *fi = F2FS_I(inode); u32 masked_flags = fi->i_flags & mask; - f2fs_bug_on(F2FS_I_SB(inode), (iflags & ~mask)); + /* mask can be shrunk by flags_valid selector */ + iflags &= mask; /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index c605415840b5..51dc79fad4fe 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -3574,12 +3574,12 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) return err; drop_bio: - if (fio->bio) { + if (fio->bio && *(fio->bio)) { struct bio *bio = *(fio->bio); bio->bi_status = BLK_STS_IOERR; bio_endio(bio); - fio->bio = NULL; + *(fio->bio) = NULL; } return err; } diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index a930ddd15681..7054a542689f 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -598,13 +598,15 @@ void hfsplus_file_truncate(struct inode *inode) res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt); if (res) break; - hfs_brec_remove(&fd); - mutex_unlock(&fd.tree->tree_lock); start = hip->cached_start; + if (blk_cnt <= start) + hfs_brec_remove(&fd); + mutex_unlock(&fd.tree->tree_lock); hfsplus_free_extents(sb, hip->cached_extents, alloc_cnt - start, alloc_cnt - blk_cnt); hfsplus_dump_extent(hip->cached_extents); + mutex_lock(&fd.tree->tree_lock); if (blk_cnt > start) { hip->extent_state |= HFSPLUS_EXT_DIRTY; break; @@ -612,7 +614,6 @@ void hfsplus_file_truncate(struct inode *inode) alloc_cnt = start; hip->cached_start = hip->cached_blocks = 0; hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); - mutex_lock(&fd.tree->tree_lock); } hfs_find_exit(&fd); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a2a42335e8fd..9d9e0097c1d3 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -131,6 +131,7 @@ static void huge_pagevec_release(struct pagevec *pvec) static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); + struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); @@ -146,6 +147,10 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND; vma->vm_ops = &hugetlb_vm_ops; + ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret; + /* * page based offset in vm_pgoff could be sufficiently large to * overflow a loff_t when converted to byte offset. This can diff --git a/fs/io_uring.c b/fs/io_uring.c index f46acbbeed57..e481ac8a757a 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -100,6 +100,8 @@ #define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ IORING_REGISTER_LAST + IORING_OP_LAST) +#define IORING_MAX_REG_BUFFERS (1U << 14) + #define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ IOSQE_BUFFER_SELECT) @@ -4035,7 +4037,7 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, #if defined(CONFIG_EPOLL) if (sqe->ioprio || sqe->buf_index) return -EINVAL; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; req->epoll.epfd = READ_ONCE(sqe->fd); @@ -4150,7 +4152,7 @@ static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags) static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->buf_index) return -EINVAL; @@ -5827,8 +5829,6 @@ done: static int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & IORING_SETUP_SQPOLL)) - return -EINVAL; if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; if (sqe->ioprio || sqe->rw_flags) @@ -6354,19 +6354,20 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) * We don't expect the list to be empty, that will only happen if we * race with the completion of the linked work. */ - if (prev && req_ref_inc_not_zero(prev)) + if (prev) { io_remove_next_linked(prev); - else - prev = NULL; + if (!req_ref_inc_not_zero(prev)) + prev = NULL; + } spin_unlock_irqrestore(&ctx->completion_lock, flags); if (prev) { io_async_find_and_cancel(ctx, req, prev->user_data, -ETIME); io_put_req_deferred(prev, 1); + io_put_req_deferred(req, 1); } else { io_req_complete_post(req, -ETIME, 0); } - io_put_req_deferred(req, 1); return HRTIMER_NORESTART; } @@ -8390,7 +8391,7 @@ static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, if (ctx->user_bufs) return -EBUSY; - if (!nr_args || nr_args > UIO_MAXIOV) + if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS) return -EINVAL; ret = io_rsrc_node_switch_start(ctx); if (ret) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index f2cd2034a87b..9023717c5188 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -394,7 +394,7 @@ void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops) { struct inode *inode = rac->mapping->host; loff_t pos = readahead_pos(rac); - loff_t length = readahead_length(rac); + size_t length = readahead_length(rac); struct iomap_readpage_ctx ctx = { .rac = rac, }; @@ -402,7 +402,7 @@ void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops) trace_iomap_readahead(inode, readahead_count(rac)); while (length > 0) { - loff_t ret = iomap_apply(inode, pos, length, 0, ops, + ssize_t ret = iomap_apply(inode, pos, length, 0, ops, &ctx, iomap_readahead_actor); if (ret <= 0) { WARN_ON_ONCE(ret == 0); diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 7b1128398976..89d492916dea 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -211,11 +211,11 @@ failure: * If the skip factor is limited in this way then the file will use multiple * slots. */ -static inline int calculate_skip(int blocks) +static inline int calculate_skip(u64 blocks) { - int skip = blocks / ((SQUASHFS_META_ENTRIES + 1) + u64 skip = blocks / ((SQUASHFS_META_ENTRIES + 1) * SQUASHFS_META_INDEXES); - return min(SQUASHFS_CACHED_BLKS - 1, skip + 1); + return min((u64) SQUASHFS_CACHED_BLKS - 1, skip + 1); } diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index 515c3fb06ab3..56348a541c50 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -194,6 +194,7 @@ enum HV_GENERIC_SET_FORMAT { #define HV_STATUS_INVALID_HYPERCALL_INPUT 3 #define HV_STATUS_INVALID_ALIGNMENT 4 #define HV_STATUS_INVALID_PARAMETER 5 +#define HV_STATUS_ACCESS_DENIED 6 #define HV_STATUS_OPERATION_DENIED 8 #define HV_STATUS_INSUFFICIENT_MEMORY 11 #define HV_STATUS_INVALID_PORT_ID 17 diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1255823b2bc0..f69c75bd6d27 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -676,11 +676,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); -static inline bool blk_account_rq(struct request *rq) -{ - return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); -} - #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 153734816b49..d5b9c8d40c18 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -101,6 +101,7 @@ struct vc_data { unsigned int vc_rows; unsigned int vc_size_row; /* Bytes per row */ unsigned int vc_scan_lines; /* # of scan lines */ + unsigned int vc_cell_height; /* CRTC character cell height */ unsigned long vc_origin; /* [!] Start of real screen */ unsigned long vc_scr_end; /* [!] End of real screen */ unsigned long vc_visible_origin; /* [!] Top of visible window */ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 1fe8e105b83b..dcb2f9022c1d 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -34,7 +34,7 @@ struct elevator_mq_ops { void (*depth_updated)(struct blk_mq_hw_ctx *); bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); - bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *, unsigned int); + bool (*bio_merge)(struct request_queue *, struct bio *, unsigned int); int (*request_merge)(struct request_queue *q, struct request **, struct bio *); void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); void (*requests_merged)(struct request_queue *, struct request *, struct request *); diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index ed4e67a7ff1c..59828516ebaf 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -187,5 +187,6 @@ extern u32 fw_devlink_get_flags(void); extern bool fw_devlink_is_strict(void); int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup); void fwnode_links_purge(struct fwnode_handle *fwnode); +void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode); #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2f34487e21f2..ae7735b490b4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -10,6 +10,7 @@ #include <linux/spinlock.h> #include <linux/signal.h> #include <linux/sched.h> +#include <linux/sched/stat.h> #include <linux/bug.h> #include <linux/minmax.h> #include <linux/mm.h> @@ -27,6 +28,7 @@ #include <linux/rcuwait.h> #include <linux/refcount.h> #include <linux/nospec.h> +#include <linux/notifier.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -146,7 +148,7 @@ static inline bool is_error_page(struct page *page) */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_PENDING_TIMER 2 +#define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 #define KVM_REQUEST_ARCH_BASE 8 @@ -265,6 +267,11 @@ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) return !!map->hva; } +static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) +{ + return single_task_running() && !need_resched() && ktime_before(cur, stop); +} + /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. @@ -298,7 +305,6 @@ struct kvm_vcpu { struct pid __rcu *pid; int sigset_active; sigset_t sigset; - struct kvm_vcpu_stat stat; unsigned int halt_poll_ns; bool valid_wakeup; @@ -335,6 +341,8 @@ struct kvm_vcpu { bool preempted; bool ready; struct kvm_vcpu_arch arch; + struct kvm_vcpu_stat stat; + char stats_id[KVM_STATS_NAME_SIZE]; struct kvm_dirty_ring dirty_ring; }; @@ -517,6 +525,15 @@ struct kvm { #endif /* KVM_HAVE_MMU_RWLOCK */ struct mutex slots_lock; + + /* + * Protects the arch-specific fields of struct kvm_memory_slots in + * use by the VM. To be used under the slots_lock (above) or in a + * kvm->srcu critical section where acquiring the slots_lock would + * lead to deadlock with the synchronize_srcu in + * install_new_memslots. + */ + struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; @@ -579,6 +596,11 @@ struct kvm { pid_t userspace_pid; unsigned int max_halt_poll_ns; u32 dirty_ring_size; + +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER + struct notifier_block pm_notifier; +#endif + char stats_id[KVM_STATS_NAME_SIZE]; }; #define kvm_err(fmt, ...) \ @@ -992,6 +1014,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state); +#endif + #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); #endif @@ -1179,7 +1205,15 @@ __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { - return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE; + /* + * The index was checked originally in search_memslots. To avoid + * that a malicious guest builds a Spectre gadget out of e.g. page + * table walks, do not let the processor speculate loads outside + * the guest's registered memslots. + */ + unsigned long offset = gfn - slot->base_gfn; + offset = array_index_nospec(offset, slot->npages); + return slot->userspace_addr + offset * PAGE_SIZE; } static inline int memslot_id(struct kvm *kvm, gfn_t gfn) @@ -1230,26 +1264,104 @@ enum kvm_stat_kind { struct kvm_stat_data { struct kvm *kvm; - struct kvm_stats_debugfs_item *dbgfs_item; -}; - -struct kvm_stats_debugfs_item { - const char *name; - int offset; + const struct _kvm_stats_desc *desc; enum kvm_stat_kind kind; - int mode; }; -#define KVM_DBGFS_GET_MODE(dbgfs_item) \ - ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) +struct _kvm_stats_desc { + struct kvm_stats_desc desc; + char name[KVM_STATS_NAME_SIZE]; +}; -#define VM_STAT(n, x, ...) \ - { n, offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ } -#define VCPU_STAT(n, x, ...) \ - { n, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ } +#define STATS_DESC_COMMON(type, unit, base, exp) \ + .flags = type | unit | base | \ + BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ + BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ + BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ + .exponent = exp, \ + .size = 1 + +#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vm_stat, generic.stat) \ + }, \ + .name = #stat, \ + } +#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ + }, \ + .name = #stat, \ + } +#define VM_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vm_stat, stat) \ + }, \ + .name = #stat, \ + } +#define VCPU_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vcpu_stat, stat) \ + }, \ + .name = #stat, \ + } +/* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ +#define STATS_DESC(SCOPE, stat, type, unit, base, exp) \ + SCOPE##_STATS_DESC(stat, type, unit, base, exp) + +#define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, unit, base, exponent) +#define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, unit, base, exponent) +#define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, unit, base, exponent) + +/* Cumulative counter, read/write */ +#define STATS_DESC_COUNTER(SCOPE, name) \ + STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) +/* Instantaneous counter, read only */ +#define STATS_DESC_ICOUNTER(SCOPE, name) \ + STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) +/* Peak counter, read/write */ +#define STATS_DESC_PCOUNTER(SCOPE, name) \ + STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) + +/* Cumulative time in nanosecond */ +#define STATS_DESC_TIME_NSEC(SCOPE, name) \ + STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ + KVM_STATS_BASE_POW10, -9) + +#define KVM_GENERIC_VM_STATS() \ + STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush) + +#define KVM_GENERIC_VCPU_STATS() \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_successful_poll), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_attempted_poll), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_poll_invalid), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup), \ + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \ + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns) -extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; +ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, + const struct _kvm_stats_desc *desc, + void *stats, size_t size_stats, + char __user *user_buffer, size_t size, loff_t *offset); +extern const struct kvm_stats_header kvm_vm_stats_header; +extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; +extern const struct kvm_stats_header kvm_vcpu_stats_header; +extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index a7580f69dda0..ed6a985c5680 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -76,5 +76,19 @@ struct kvm_mmu_memory_cache { }; #endif +struct kvm_vm_stat_generic { + u64 remote_tlb_flush; +}; + +struct kvm_vcpu_stat_generic { + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 halt_poll_success_ns; + u64 halt_poll_fail_ns; +}; + +#define KVM_STATS_NAME_SIZE 48 #endif /* __KVM_TYPES_H__ */ diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 01f251b6e36c..89b69e645ac7 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -141,7 +141,6 @@ static inline void __iomem *devm_nvdimm_ioremap(struct device *dev, struct nvdimm_bus; struct module; -struct device; struct nd_blk_region; struct nd_blk_region_desc { int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); diff --git a/include/linux/math64.h b/include/linux/math64.h index 66deb1fdc2ef..2928f03d6d46 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -3,6 +3,7 @@ #define _LINUX_MATH64_H #include <linux/types.h> +#include <linux/math.h> #include <vdso/math64.h> #include <asm/div64.h> @@ -234,6 +235,24 @@ static inline u64 mul_u64_u64_shr(u64 a, u64 b, unsigned int shift) #endif +#ifndef mul_s64_u64_shr +static inline u64 mul_s64_u64_shr(s64 a, u64 b, unsigned int shift) +{ + u64 ret; + + /* + * Extract the sign before the multiplication and put it back + * afterwards if needed. + */ + ret = mul_u64_u64_shr(abs(a), b, shift); + + if (a < 0) + ret = -((s64) ret); + + return ret; +} +#endif /* mul_s64_u64_shr */ + #ifndef mul_u64_u32_div static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) { diff --git a/include/linux/mm.h b/include/linux/mm.h index 322ec61d0da7..c274f75efcf9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3216,5 +3216,37 @@ void mem_dump_obj(void *object); static inline void mem_dump_obj(void *object) {} #endif +/** + * seal_check_future_write - Check for F_SEAL_FUTURE_WRITE flag and handle it + * @seals: the seals to check + * @vma: the vma to operate on + * + * Check whether F_SEAL_FUTURE_WRITE is set; if so, do proper check/handling on + * the vma flags. Return 0 if check pass, or <0 for errors. + */ +static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) +{ + if (seals & F_SEAL_FUTURE_WRITE) { + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * "future write" seal active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; + + /* + * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (vma->vm_flags & VM_SHARED) + vma->vm_flags &= ~(VM_MAYWRITE); + } + + return 0; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6613b26a8894..5aacc1c10a45 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -97,10 +97,10 @@ struct page { }; struct { /* page_pool used by netstack */ /** - * @dma_addr: might require a 64-bit value even on + * @dma_addr: might require a 64-bit value on * 32-bit architectures. */ - dma_addr_t dma_addr; + unsigned long dma_addr[2]; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a4bd41128bf3..e89df447fae3 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -997,9 +997,9 @@ static inline loff_t readahead_pos(struct readahead_control *rac) * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ -static inline loff_t readahead_length(struct readahead_control *rac) +static inline size_t readahead_length(struct readahead_control *rac) { - return (loff_t)rac->_nr_pages * PAGE_SIZE; + return rac->_nr_pages * PAGE_SIZE; } /** @@ -1024,7 +1024,7 @@ static inline unsigned int readahead_count(struct readahead_control *rac) * readahead_batch_length - The number of bytes in the current batch. * @rac: The readahead request. */ -static inline loff_t readahead_batch_length(struct readahead_control *rac) +static inline size_t readahead_batch_length(struct readahead_control *rac) { return rac->_batch_count * PAGE_SIZE; } diff --git a/include/linux/pm.h b/include/linux/pm.h index c9657408fee1..1d8209c09686 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -601,6 +601,7 @@ struct dev_pm_info { unsigned int idle_notification:1; unsigned int request_pending:1; unsigned int deferred_resume:1; + unsigned int needs_force_resume:1; unsigned int runtime_auto:1; bool ignore_children:1; unsigned int no_callbacks:1; diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index fd80fab663a9..bebc911161b6 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -38,7 +38,7 @@ void *__builtin_alloca(size_t size); u32 offset = raw_cpu_read(kstack_offset); \ u8 *ptr = __builtin_alloca(KSTACK_OFFSET_MAX(offset)); \ /* Keep allocation even after "ptr" loses scope. */ \ - asm volatile("" : "=o"(*ptr) :: "memory"); \ + asm volatile("" :: "r"(ptr) : "memory"); \ } \ } while (0) diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 6d517a37c18b..b4b6de909c93 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -198,7 +198,17 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - return page->dma_addr; + dma_addr_t ret = page->dma_addr[0]; + if (sizeof(dma_addr_t) > sizeof(unsigned long)) + ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16; + return ret; +} + +static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) +{ + page->dma_addr[0] = addr; + if (sizeof(dma_addr_t) > sizeof(unsigned long)) + page->dma_addr[1] = upper_32_bits(addr); } static inline bool is_page_pool_compiled_in(void) diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index f44eb0a04afd..4c32e97dcdf0 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -185,7 +185,7 @@ struct fsxattr { #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) /* - * A jump here: 130-131 are reserved for zoned block devices + * A jump here: 130-136 are reserved for zoned block devices * (see uapi/linux/blkzoned.h) */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 3fd9a7e9d90c..68c9e6d8bbda 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include <linux/const.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/ioctl.h> @@ -279,6 +280,9 @@ struct kvm_xen_exit { /* Encounter unexpected vm-exit reason */ #define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON 4 +/* Flags that describe what fields in emulation_failure hold valid data. */ +#define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) + /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { /* in */ @@ -382,6 +386,25 @@ struct kvm_run { __u32 ndata; __u64 data[16]; } internal; + /* + * KVM_INTERNAL_ERROR_EMULATION + * + * "struct emulation_failure" is an overlay of "struct internal" + * that is used for the KVM_INTERNAL_ERROR_EMULATION sub-type of + * KVM_EXIT_INTERNAL_ERROR. Note, unlike other internal error + * sub-types, this struct is ABI! It also needs to be backwards + * compatible with "struct internal". Take special care that + * "ndata" is correct, that new fields are enumerated in "flags", + * and that each flag enumerates fields that are 64-bit aligned + * and sized (so that ndata+internal.data[] is valid/accurate). + */ + struct { + __u32 suberror; + __u32 ndata; + __u64 flags; + __u8 insn_size; + __u8 insn_bytes[15]; + } emulation_failure; /* KVM_EXIT_OSI */ struct { __u64 gprs[32]; @@ -1082,6 +1105,12 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SGX_ATTRIBUTE 196 #define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197 #define KVM_CAP_PTP_KVM 198 +#define KVM_CAP_HYPERV_ENFORCE_CPUID 199 +#define KVM_CAP_SREGS2 200 +#define KVM_CAP_EXIT_HYPERCALL 201 +#define KVM_CAP_PPC_RPT_INVALIDATE 202 +#define KVM_CAP_BINARY_STATS_FD 203 +#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204 #ifdef KVM_CAP_IRQ_ROUTING @@ -1620,6 +1649,9 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) +#define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) +#define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) + struct kvm_xen_vcpu_attr { __u16 type; __u16 pad[3]; @@ -1879,8 +1911,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* @@ -1898,4 +1930,76 @@ struct kvm_dirty_gfn { #define KVM_BUS_LOCK_DETECTION_OFF (1 << 0) #define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1) +/** + * struct kvm_stats_header - Header of per vm/vcpu binary statistics data. + * @flags: Some extra information for header, always 0 for now. + * @name_size: The size in bytes of the memory which contains statistics + * name string including trailing '\0'. The memory is allocated + * at the send of statistics descriptor. + * @num_desc: The number of statistics the vm or vcpu has. + * @id_offset: The offset of the vm/vcpu stats' id string in the file pointed + * by vm/vcpu stats fd. + * @desc_offset: The offset of the vm/vcpu stats' descriptor block in the file + * pointd by vm/vcpu stats fd. + * @data_offset: The offset of the vm/vcpu stats' data block in the file + * pointed by vm/vcpu stats fd. + * + * This is the header userspace needs to read from stats fd before any other + * readings. It is used by userspace to discover all the information about the + * vm/vcpu's binary statistics. + * Userspace reads this header from the start of the vm/vcpu's stats fd. + */ +struct kvm_stats_header { + __u32 flags; + __u32 name_size; + __u32 num_desc; + __u32 id_offset; + __u32 desc_offset; + __u32 data_offset; +}; + +#define KVM_STATS_TYPE_SHIFT 0 +#define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_PEAK + +#define KVM_STATS_UNIT_SHIFT 4 +#define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES + +#define KVM_STATS_BASE_SHIFT 8 +#define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_MAX KVM_STATS_BASE_POW2 + +/** + * struct kvm_stats_desc - Descriptor of a KVM statistics. + * @flags: Annotations of the stats, like type, unit, etc. + * @exponent: Used together with @flags to determine the unit. + * @size: The number of data items for this stats. + * Every data item is of type __u64. + * @offset: The offset of the stats to the start of stat structure in + * struture kvm or kvm_vcpu. + * @unused: Unused field for future usage. Always 0 for now. + * @name: The name string for the stats. Its size is indicated by the + * &kvm_stats_header->name_size. + */ +struct kvm_stats_desc { + __u32 flags; + __s16 exponent; + __u16 size; + __u32 offset; + __u32 unused; + char name[]; +}; + +#define KVM_GET_STATS_FD _IO(KVMIO, 0xce) + #endif /* __LINUX_KVM_H */ diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h index 8b86609849b9..960c7e93d1a9 100644 --- a/include/uapi/linux/kvm_para.h +++ b/include/uapi/linux/kvm_para.h @@ -29,6 +29,7 @@ #define KVM_HC_CLOCK_PAIRING 9 #define KVM_HC_SEND_IPI 10 #define KVM_HC_SCHED_YIELD 11 +#define KVM_HC_MAP_GPA_RANGE 12 /* * hypercalls use architecture specific diff --git a/include/xen/arm/swiotlb-xen.h b/include/xen/arm/swiotlb-xen.h index 2994fe6031a0..33336ab58afc 100644 --- a/include/xen/arm/swiotlb-xen.h +++ b/include/xen/arm/swiotlb-xen.h @@ -2,6 +2,19 @@ #ifndef _ASM_ARM_SWIOTLB_XEN_H #define _ASM_ARM_SWIOTLB_XEN_H -extern int xen_swiotlb_detect(void); +#include <xen/features.h> +#include <xen/xen.h> + +static inline int xen_swiotlb_detect(void) +{ + if (!xen_domain()) + return 0; + if (xen_feature(XENFEAT_direct_mapped)) + return 1; + /* legacy case */ + if (!xen_feature(XENFEAT_not_direct_mapped) && xen_initial_domain()) + return 1; + return 0; +} #endif /* _ASM_ARM_SWIOTLB_XEN_H */ diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 76f09456ec4b..2997ca600d18 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -170,6 +170,21 @@ void __ptrace_unlink(struct task_struct *child) spin_unlock(&child->sighand->siglock); } +static bool looks_like_a_spurious_pid(struct task_struct *task) +{ + if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) + return false; + + if (task_pid_vnr(task) == task->ptrace_message) + return false; + /* + * The tracee changed its pid but the PTRACE_EVENT_EXEC event + * was not wait()'ed, most probably debugger targets the old + * leader which was destroyed in de_thread(). + */ + return true; +} + /* Ensure that nothing can wake it up, even SIGKILL */ static bool ptrace_freeze_traced(struct task_struct *task) { @@ -180,7 +195,8 @@ static bool ptrace_freeze_traced(struct task_struct *task) return ret; spin_lock_irq(&task->sighand->siglock); - if (task_is_traced(task) && !__fatal_signal_pending(task)) { + if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && + !__fatal_signal_pending(task)) { task->state = __TASK_TRACED; ret = true; } diff --git a/kernel/resource.c b/kernel/resource.c index 028a5ab18818..ca9f5198a01f 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1805,7 +1805,7 @@ static struct resource *__request_free_mem_region(struct device *dev, REGION_DISJOINT) continue; - if (!__request_region_locked(res, &iomem_resource, addr, size, + if (__request_region_locked(res, &iomem_resource, addr, size, name, 0)) break; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 20aa234ffe04..3248e24a90b0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6217,7 +6217,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool } if (has_idle_core) - set_idle_cores(this, false); + set_idle_cores(target, false); if (sched_feat(SIS_PROP) && !has_idle_core) { time = cpu_clock(this) - time; diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index bea9d08b1698..5897828b9d7e 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -92,7 +92,7 @@ static int alarmtimer_rtc_add_device(struct device *dev, if (rtcdev) return -EBUSY; - if (!rtc->ops->set_alarm) + if (!test_bit(RTC_FEATURE_ALARM, rtc->features)) return -1; if (!device_may_wakeup(rtc->dev.parent)) return -1; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 560e4c8d3825..a21ef9cd2aae 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3704,6 +3704,9 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, goto print; while (*p) { + bool star = false; + int len = 0; + j = 0; /* We only care about %s and variants */ @@ -3725,13 +3728,17 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, /* Need to test cases like %08.*s */ for (j = 1; p[i+j]; j++) { if (isdigit(p[i+j]) || - p[i+j] == '*' || p[i+j] == '.') continue; + if (p[i+j] == '*') { + star = true; + continue; + } break; } if (p[i+j] == 's') break; + star = false; } j = 0; } @@ -3744,6 +3751,9 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, iter->fmt[i] = '\0'; trace_seq_vprintf(&iter->seq, iter->fmt, ap); + if (star) + len = va_arg(ap, int); + /* The ap now points to the string data of the %s */ str = va_arg(ap, const char *); @@ -3762,8 +3772,18 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, int ret; /* Try to safely read the string */ - ret = strncpy_from_kernel_nofault(iter->fmt, str, - iter->fmt_size); + if (star) { + if (len + 1 > iter->fmt_size) + len = iter->fmt_size - 1; + if (len < 0) + len = 0; + ret = copy_from_kernel_nofault(iter->fmt, str, len); + iter->fmt[len] = 0; + star = false; + } else { + ret = strncpy_from_kernel_nofault(iter->fmt, str, + iter->fmt_size); + } if (ret < 0) trace_seq_printf(&iter->seq, "(0x%px)", str); else @@ -3775,7 +3795,10 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, strncpy(iter->fmt, p + i, j + 1); iter->fmt[j+1] = '\0'; } - trace_seq_printf(&iter->seq, iter->fmt, str); + if (star) + trace_seq_printf(&iter->seq, iter->fmt, len, str); + else + trace_seq_printf(&iter->seq, iter->fmt, str); p += i + j + 1; } diff --git a/lib/test_kasan.c b/lib/test_kasan.c index dc05cfc2d12f..cacbbbdef768 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -654,8 +654,20 @@ static char global_array[10]; static void kasan_global_oob(struct kunit *test) { - volatile int i = 3; - char *p = &global_array[ARRAY_SIZE(global_array) + i]; + /* + * Deliberate out-of-bounds access. To prevent CONFIG_UBSAN_LOCAL_BOUNDS + * from failing here and panicing the kernel, access the array via a + * volatile pointer, which will prevent the compiler from being able to + * determine the array bounds. + * + * This access uses a volatile pointer to char (char *volatile) rather + * than the more conventional pointer to volatile char (volatile char *) + * because we want to prevent the compiler from making inferences about + * the pointer itself (i.e. its array bounds), not the data that it + * refers to. + */ + char *volatile array = global_array; + char *p = &array[ARRAY_SIZE(global_array) + 3]; /* Only generic mode instruments globals. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); @@ -703,8 +715,9 @@ static void ksize_uaf(struct kunit *test) static void kasan_stack_oob(struct kunit *test) { char stack_array[10]; - volatile int i = OOB_TAG_OFF; - char *p = &stack_array[ARRAY_SIZE(stack_array) + i]; + /* See comment in kasan_global_oob. */ + char *volatile array = stack_array; + char *p = &array[ARRAY_SIZE(stack_array) + OOB_TAG_OFF]; KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_STACK); @@ -715,7 +728,9 @@ static void kasan_alloca_oob_left(struct kunit *test) { volatile int i = 10; char alloca_array[i]; - char *p = alloca_array - 1; + /* See comment in kasan_global_oob. */ + char *volatile array = alloca_array; + char *p = array - 1; /* Only generic mode instruments dynamic allocas. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); @@ -728,7 +743,9 @@ static void kasan_alloca_oob_right(struct kunit *test) { volatile int i = 10; char alloca_array[i]; - char *p = alloca_array + i; + /* See comment in kasan_global_oob. */ + char *volatile array = alloca_array; + char *p = array + i; /* Only generic mode instruments dynamic allocas. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3db405dea3dc..95918f410c0f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4056,6 +4056,7 @@ again: * See Documentation/vm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); + entry = huge_pte_wrprotect(entry); } page_dup_rmap(ptepage, true); diff --git a/mm/ioremap.c b/mm/ioremap.c index d1dcc7e744ac..8ee0136f8cb0 100644 --- a/mm/ioremap.c +++ b/mm/ioremap.c @@ -16,16 +16,16 @@ #include "pgalloc-track.h" #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP -static bool __ro_after_init iomap_max_page_shift = PAGE_SHIFT; +static unsigned int __ro_after_init iomap_max_page_shift = BITS_PER_LONG - 1; static int __init set_nohugeiomap(char *str) { - iomap_max_page_shift = P4D_SHIFT; + iomap_max_page_shift = PAGE_SHIFT; return 0; } early_param("nohugeiomap", set_nohugeiomap); #else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ -static const bool iomap_max_page_shift = PAGE_SHIFT; +static const unsigned int iomap_max_page_shift = PAGE_SHIFT; #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ int ioremap_page_range(unsigned long addr, @@ -776,11 +776,12 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) struct page *page; stable_node = rmap_item->head; - page = get_ksm_page(stable_node, GET_KSM_PAGE_NOLOCK); + page = get_ksm_page(stable_node, GET_KSM_PAGE_LOCK); if (!page) goto out; hlist_del(&rmap_item->hlist); + unlock_page(page); put_page(page); if (!hlist_empty(&stable_node->hlist)) diff --git a/mm/shmem.c b/mm/shmem.c index a08cedefbfaa..5d46611cba8d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2258,25 +2258,11 @@ out_nomem: static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { struct shmem_inode_info *info = SHMEM_I(file_inode(file)); + int ret; - if (info->seals & F_SEAL_FUTURE_WRITE) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * "future write" seal active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vma->vm_flags &= ~(VM_MAYWRITE); - } + ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret; /* arm64 - allow memory tagging on RAM-based files */ vma->vm_flags |= VM_MTE_ALLOWED; @@ -2375,8 +2361,18 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pgoff_t offset, max_off; ret = -ENOMEM; - if (!shmem_inode_acct_block(inode, 1)) + if (!shmem_inode_acct_block(inode, 1)) { + /* + * We may have got a page, returned -ENOENT triggering a retry, + * and now we find ourselves with -ENOMEM. Release the page, to + * avoid a BUG_ON in our caller. + */ + if (unlikely(*pagep)) { + put_page(*pagep); + *pagep = NULL; + } goto out; + } if (!*pagep) { page = shmem_alloc_page(gfp, info, pgoff); diff --git a/mm/slab_common.c b/mm/slab_common.c index f8833d3e5d47..a4a571428c51 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -318,6 +318,16 @@ kmem_cache_create_usercopy(const char *name, const char *cache_name; int err; +#ifdef CONFIG_SLUB_DEBUG + /* + * If no slub_debug was enabled globally, the static key is not yet + * enabled by setup_slub_debug(). Enable it if the cache is being + * created with any of the debugging flags passed explicitly. + */ + if (flags & SLAB_DEBUG_FLAGS) + static_branch_enable(&slub_debug_enabled); +#endif + mutex_lock(&slab_mutex); err = kmem_cache_sanity_check(name, size); diff --git a/mm/slub.c b/mm/slub.c index feda53ae62ba..438fa8d4c970 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3828,15 +3828,6 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags) { -#ifdef CONFIG_SLUB_DEBUG - /* - * If no slub_debug was enabled globally, the static key is not yet - * enabled by setup_slub_debug(). Enable it if the cache is being - * created with any of the debugging flags passed explicitly. - */ - if (flags & SLAB_DEBUG_FLAGS) - static_branch_enable(&slub_debug_enabled); -#endif s->flags = kmem_cache_flags(s->size, flags, s->name); #ifdef CONFIG_SLAB_FREELIST_HARDENED s->random = get_random_long(); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9ec1aa9640ad..3c4c4c7a0402 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool, struct page *page, unsigned int dma_sync_size) { + dma_addr_t dma_addr = page_pool_get_dma_addr(page); + dma_sync_size = min(dma_sync_size, pool->p.max_len); - dma_sync_single_range_for_device(pool->p.dev, page->dma_addr, + dma_sync_single_range_for_device(pool->p.dev, dma_addr, pool->p.offset, dma_sync_size, pool->p.dma_dir); } @@ -195,7 +197,7 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) if (dma_mapping_error(pool->p.dev, dma)) return false; - page->dma_addr = dma; + page_pool_set_dma_addr(page, dma); if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) page_pool_dma_sync_for_device(pool, page, pool->p.max_len); @@ -331,13 +333,13 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) */ goto skip_dma_unmap; - dma = page->dma_addr; + dma = page_pool_get_dma_addr(page); - /* When page is unmapped, it cannot be returned our pool */ + /* When page is unmapped, it cannot be returned to our pool */ dma_unmap_page_attrs(pool->p.dev, dma, PAGE_SIZE << pool->p.order, pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC); - page->dma_addr = 0; + page_pool_set_dma_addr(page, 0); skip_dma_unmap: /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. diff --git a/security/keys/trusted-keys/trusted_tpm1.c b/security/keys/trusted-keys/trusted_tpm1.c index 469394550801..aa108bea6739 100644 --- a/security/keys/trusted-keys/trusted_tpm1.c +++ b/security/keys/trusted-keys/trusted_tpm1.c @@ -493,10 +493,12 @@ static int tpm_seal(struct tpm_buf *tb, uint16_t keytype, ret = tpm_get_random(chip, td->nonceodd, TPM_NONCE_SIZE); if (ret < 0) - return ret; + goto out; - if (ret != TPM_NONCE_SIZE) - return -EIO; + if (ret != TPM_NONCE_SIZE) { + ret = -EIO; + goto out; + } ordinal = htonl(TPM_ORD_SEAL); datsize = htonl(datalen); diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index 617fabd4d913..0165da386289 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -336,9 +336,9 @@ out: rc = -EPERM; } if (blob_len < 0) - return blob_len; - - payload->blob_len = blob_len; + rc = blob_len; + else + payload->blob_len = blob_len; tpm_put_ops(chip); return rc; diff --git a/tools/arch/powerpc/include/uapi/asm/errno.h b/tools/arch/powerpc/include/uapi/asm/errno.h index cc79856896a1..4ba87de32be0 100644 --- a/tools/arch/powerpc/include/uapi/asm/errno.h +++ b/tools/arch/powerpc/include/uapi/asm/errno.h @@ -2,6 +2,7 @@ #ifndef _ASM_POWERPC_ERRNO_H #define _ASM_POWERPC_ERRNO_H +#undef EDEADLOCK #include <asm-generic/errno.h> #undef EDEADLOCK diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index cc96e26d69f7..ac37830ae941 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -84,7 +84,7 @@ /* CPU types for specific tunings: */ #define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ +/* FREE, was #define X86_FEATURE_K7 ( 3*32+ 5) "" Athlon */ #define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ #define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ @@ -236,6 +236,8 @@ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ +#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ +#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -290,6 +292,8 @@ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ #define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ +#define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ +#define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ @@ -336,6 +340,7 @@ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ +#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -354,6 +359,7 @@ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ #define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ +#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* Bus Lock detect */ #define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ #define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ #define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ @@ -374,6 +380,7 @@ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */ +#define X86_FEATURE_HYBRID_CPU (18*32+15) /* "" This part has CPUs of more than one type */ #define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 45029354e0a8..211ba3375ee9 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -185,6 +185,9 @@ #define MSR_PEBS_DATA_CFG 0x000003f2 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 +#define PERF_CAP_METRICS_IDX 15 +#define PERF_CAP_PT_IDX 16 + #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 #define MSR_IA32_RTIT_CTL 0x00000570 @@ -265,6 +268,7 @@ #define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ #define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ +#define DEBUGCTLMSR_BUS_LOCK_DETECT (1UL << 2) #define DEBUGCTLMSR_TR (1UL << 6) #define DEBUGCTLMSR_BTS (1UL << 7) #define DEBUGCTLMSR_BTINT (1UL << 8) @@ -533,9 +537,9 @@ /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d -#define MSR_K8_SYSCFG 0xc0010010 -#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT 23 -#define MSR_K8_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG 0xc0010010 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index b8e650a985e3..946d761adbd3 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -27,6 +27,7 @@ #define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000 +#define VMX_EXIT_REASONS_SGX_ENCLAVE_MODE 0x08000000 #define EXIT_REASON_EXCEPTION_NMI 0 #define EXIT_REASON_EXTERNAL_INTERRUPT 1 diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 1e299ac73c86..1cc9da6e29c7 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -4,7 +4,7 @@ #include <linux/linkage.h> #include <asm/errno.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h> .pushsection .noinstr.text, "ax" diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 0bfd26e4ca9e..9827ae267f96 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -3,7 +3,7 @@ #include <linux/linkage.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h> /* diff --git a/tools/include/asm/alternative-asm.h b/tools/include/asm/alternative.h index b54bd860dff6..b54bd860dff6 100644 --- a/tools/include/asm/alternative-asm.h +++ b/tools/include/asm/alternative.h diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index ce58cff99b66..6de5a7fc066b 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -863,9 +863,18 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise) __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) #define __NR_mount_setattr 442 __SYSCALL(__NR_mount_setattr, sys_mount_setattr) +#define __NR_quotactl_path 443 +__SYSCALL(__NR_quotactl_path, sys_quotactl_path) + +#define __NR_landlock_create_ruleset 444 +__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) +#define __NR_landlock_add_rule 445 +__SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule) +#define __NR_landlock_restrict_self 446 +__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) #undef __NR_syscalls -#define __NR_syscalls 443 +#define __NR_syscalls 447 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 0827037c5484..67b94bc3c885 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -625,30 +625,147 @@ struct drm_gem_open { __u64 size; }; +/** + * DRM_CAP_DUMB_BUFFER + * + * If set to 1, the driver supports creating dumb buffers via the + * &DRM_IOCTL_MODE_CREATE_DUMB ioctl. + */ #define DRM_CAP_DUMB_BUFFER 0x1 +/** + * DRM_CAP_VBLANK_HIGH_CRTC + * + * If set to 1, the kernel supports specifying a CRTC index in the high bits of + * &drm_wait_vblank_request.type. + * + * Starting kernel version 2.6.39, this capability is always set to 1. + */ #define DRM_CAP_VBLANK_HIGH_CRTC 0x2 +/** + * DRM_CAP_DUMB_PREFERRED_DEPTH + * + * The preferred bit depth for dumb buffers. + * + * The bit depth is the number of bits used to indicate the color of a single + * pixel excluding any padding. This is different from the number of bits per + * pixel. For instance, XRGB8888 has a bit depth of 24 but has 32 bits per + * pixel. + * + * Note that this preference only applies to dumb buffers, it's irrelevant for + * other types of buffers. + */ #define DRM_CAP_DUMB_PREFERRED_DEPTH 0x3 +/** + * DRM_CAP_DUMB_PREFER_SHADOW + * + * If set to 1, the driver prefers userspace to render to a shadow buffer + * instead of directly rendering to a dumb buffer. For best speed, userspace + * should do streaming ordered memory copies into the dumb buffer and never + * read from it. + * + * Note that this preference only applies to dumb buffers, it's irrelevant for + * other types of buffers. + */ #define DRM_CAP_DUMB_PREFER_SHADOW 0x4 +/** + * DRM_CAP_PRIME + * + * Bitfield of supported PRIME sharing capabilities. See &DRM_PRIME_CAP_IMPORT + * and &DRM_PRIME_CAP_EXPORT. + * + * PRIME buffers are exposed as dma-buf file descriptors. See + * Documentation/gpu/drm-mm.rst, section "PRIME Buffer Sharing". + */ #define DRM_CAP_PRIME 0x5 +/** + * DRM_PRIME_CAP_IMPORT + * + * If this bit is set in &DRM_CAP_PRIME, the driver supports importing PRIME + * buffers via the &DRM_IOCTL_PRIME_FD_TO_HANDLE ioctl. + */ #define DRM_PRIME_CAP_IMPORT 0x1 +/** + * DRM_PRIME_CAP_EXPORT + * + * If this bit is set in &DRM_CAP_PRIME, the driver supports exporting PRIME + * buffers via the &DRM_IOCTL_PRIME_HANDLE_TO_FD ioctl. + */ #define DRM_PRIME_CAP_EXPORT 0x2 +/** + * DRM_CAP_TIMESTAMP_MONOTONIC + * + * If set to 0, the kernel will report timestamps with ``CLOCK_REALTIME`` in + * struct drm_event_vblank. If set to 1, the kernel will report timestamps with + * ``CLOCK_MONOTONIC``. See ``clock_gettime(2)`` for the definition of these + * clocks. + * + * Starting from kernel version 2.6.39, the default value for this capability + * is 1. Starting kernel version 4.15, this capability is always set to 1. + */ #define DRM_CAP_TIMESTAMP_MONOTONIC 0x6 +/** + * DRM_CAP_ASYNC_PAGE_FLIP + * + * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC. + */ #define DRM_CAP_ASYNC_PAGE_FLIP 0x7 -/* - * The CURSOR_WIDTH and CURSOR_HEIGHT capabilities return a valid widthxheight - * combination for the hardware cursor. The intention is that a hardware - * agnostic userspace can query a cursor plane size to use. +/** + * DRM_CAP_CURSOR_WIDTH + * + * The ``CURSOR_WIDTH`` and ``CURSOR_HEIGHT`` capabilities return a valid + * width x height combination for the hardware cursor. The intention is that a + * hardware agnostic userspace can query a cursor plane size to use. * * Note that the cross-driver contract is to merely return a valid size; * drivers are free to attach another meaning on top, eg. i915 returns the * maximum plane size. */ #define DRM_CAP_CURSOR_WIDTH 0x8 +/** + * DRM_CAP_CURSOR_HEIGHT + * + * See &DRM_CAP_CURSOR_WIDTH. + */ #define DRM_CAP_CURSOR_HEIGHT 0x9 +/** + * DRM_CAP_ADDFB2_MODIFIERS + * + * If set to 1, the driver supports supplying modifiers in the + * &DRM_IOCTL_MODE_ADDFB2 ioctl. + */ #define DRM_CAP_ADDFB2_MODIFIERS 0x10 +/** + * DRM_CAP_PAGE_FLIP_TARGET + * + * If set to 1, the driver supports the &DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE and + * &DRM_MODE_PAGE_FLIP_TARGET_RELATIVE flags in + * &drm_mode_crtc_page_flip_target.flags for the &DRM_IOCTL_MODE_PAGE_FLIP + * ioctl. + */ #define DRM_CAP_PAGE_FLIP_TARGET 0x11 +/** + * DRM_CAP_CRTC_IN_VBLANK_EVENT + * + * If set to 1, the kernel supports reporting the CRTC ID in + * &drm_event_vblank.crtc_id for the &DRM_EVENT_VBLANK and + * &DRM_EVENT_FLIP_COMPLETE events. + * + * Starting kernel version 4.12, this capability is always set to 1. + */ #define DRM_CAP_CRTC_IN_VBLANK_EVENT 0x12 +/** + * DRM_CAP_SYNCOBJ + * + * If set to 1, the driver supports sync objects. See + * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + */ #define DRM_CAP_SYNCOBJ 0x13 +/** + * DRM_CAP_SYNCOBJ_TIMELINE + * + * If set to 1, the driver supports timeline operations on sync objects. See + * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + */ #define DRM_CAP_SYNCOBJ_TIMELINE 0x14 /* DRM_IOCTL_GET_CAP ioctl argument type */ diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 1987e2ea79a3..ddc47bbf48b6 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -943,6 +943,7 @@ struct drm_i915_gem_exec_object { __u64 offset; }; +/* DRM_IOCTL_I915_GEM_EXECBUFFER was removed in Linux 5.13 */ struct drm_i915_gem_execbuffer { /** * List of buffers to be validated with their relocations to be diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index f6afee209620..79d9c44d1ad7 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include <linux/const.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/ioctl.h> @@ -1078,6 +1079,10 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DIRTY_LOG_RING 192 #define KVM_CAP_X86_BUS_LOCK_EXIT 193 #define KVM_CAP_PPC_DAWR1 194 +#define KVM_CAP_SET_GUEST_DEBUG2 195 +#define KVM_CAP_SGX_ATTRIBUTE 196 +#define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197 +#define KVM_CAP_PTP_KVM 198 #ifdef KVM_CAP_IRQ_ROUTING @@ -1671,6 +1676,8 @@ enum sev_cmd_id { KVM_SEV_CERT_EXPORT, /* Attestation report */ KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, KVM_SEV_NR_MAX, }; @@ -1729,6 +1736,45 @@ struct kvm_sev_attestation_report { __u32 len; }; +struct kvm_sev_send_start { + __u32 policy; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) #define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) @@ -1834,8 +1880,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 14332f4cf816..bf8143505c49 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -127,6 +127,7 @@ enum perf_sw_ids { PERF_COUNT_SW_EMULATION_FAULTS = 8, PERF_COUNT_SW_DUMMY = 9, PERF_COUNT_SW_BPF_OUTPUT = 10, + PERF_COUNT_SW_CGROUP_SWITCHES = 11, PERF_COUNT_SW_MAX, /* non-ABI */ }; @@ -326,6 +327,7 @@ enum perf_event_read_format { #define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */ #define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ #define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ +#define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -404,7 +406,10 @@ struct perf_event_attr { cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ build_id : 1, /* use build id in mmap2 events */ - __reserved_1 : 29; + inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ + remove_on_exec : 1, /* event is removed from task on exec */ + sigtrap : 1, /* send synchronous SIGTRAP on event */ + __reserved_1 : 26; union { __u32 wakeup_events; /* wakeup every n events */ @@ -456,6 +461,12 @@ struct perf_event_attr { __u16 __reserved_2; __u32 aux_sample_size; __u32 __reserved_3; + + /* + * User provided data if sigtrap=1, passed back to user via + * siginfo_t::si_perf, e.g. to permit user to identify the event. + */ + __u64 sig_data; }; /* @@ -1171,10 +1182,15 @@ enum perf_callchain_context { /** * PERF_RECORD_AUX::flags bits */ -#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ -#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ -#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ -#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ +#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ +#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ +#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK 0xff00 /* PMU specific trace format type */ + +/* CoreSight PMU AUX buffer formats */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ #define PERF_FLAG_FD_NO_GROUP (1UL << 0) #define PERF_FLAG_FD_OUTPUT (1UL << 1) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 667f1aed091c..18a9f59dc067 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -255,4 +255,8 @@ struct prctl_mm_map { # define SYSCALL_DISPATCH_FILTER_ALLOW 0 # define SYSCALL_DISPATCH_FILTER_BLOCK 1 +/* Set/get enabled arm64 pointer authentication keys */ +#define PR_PAC_SET_ENABLED_KEYS 60 +#define PR_PAC_GET_ENABLED_KEYS 61 + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index feaf46451e83..3a9f2037bd23 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -111,7 +111,7 @@ OPTIONS --tracepoints:: retrieve statistics from tracepoints -*z*:: +-z:: --skip-zero-records:: omit records with all zeros in logging mode diff --git a/tools/lib/traceevent/plugins/plugin_kvm.c b/tools/lib/traceevent/plugins/plugin_kvm.c index 51ceeb9147eb..9ce7b4b68e3f 100644 --- a/tools/lib/traceevent/plugins/plugin_kvm.c +++ b/tools/lib/traceevent/plugins/plugin_kvm.c @@ -366,7 +366,7 @@ union kvm_mmu_page_role { unsigned direct:1; unsigned access:3; unsigned invalid:1; - unsigned nxe:1; + unsigned efer_nx:1; unsigned cr0_wp:1; unsigned smep_and_not_wp:1; unsigned smap_and_not_wp:1; @@ -403,7 +403,7 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record, access_str[role.access], role.invalid ? " invalid" : "", role.cr4_pae ? "" : "!", - role.nxe ? "" : "!", + role.efer_nx ? "" : "!", role.cr0_wp ? "" : "!", role.smep_and_not_wp ? " smep" : "", role.smap_and_not_wp ? " smap" : "", diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index cedf3ede7545..24295d39713b 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -19,6 +19,7 @@ #include <objtool/elf.h> #include <objtool/arch.h> #include <objtool/warn.h> +#include <objtool/endianness.h> #include <arch/elf.h> static int is_x86_64(const struct elf *elf) @@ -725,7 +726,7 @@ static int elf_add_alternative(struct elf *elf, return -1; } - alt->cpuid = cpuid; + alt->cpuid = bswap_if_needed(cpuid); alt->instrlen = orig_len; alt->replacementlen = repl_len; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index d08f5f3670f8..743c2e9d0f56 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -762,6 +762,7 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) data->d_buf = &sym->sym; data->d_size = sizeof(sym->sym); data->d_align = 1; + data->d_type = ELF_T_SYM; sym->idx = symtab->len / sizeof(sym->sym); diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0d6619064a83..406a9519145e 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -540,6 +540,7 @@ ifndef NO_LIBELF ifdef LIBBPF_DYNAMIC ifeq ($(feature-libbpf), 1) EXTLIBS += -lbpf + $(call detected,CONFIG_LIBBPF_DYNAMIC) else dummy := $(error Error: No libbpf devel library found, please install libbpf-devel); endif diff --git a/tools/perf/arch/arm64/util/kvm-stat.c b/tools/perf/arch/arm64/util/kvm-stat.c index 2303256b7d05..73d18e0ed6f6 100644 --- a/tools/perf/arch/arm64/util/kvm-stat.c +++ b/tools/perf/arch/arm64/util/kvm-stat.c @@ -71,7 +71,7 @@ struct kvm_reg_events_ops kvm_reg_events_ops[] = { .name = "vmexit", .ops = &exit_events, }, - { NULL }, + { NULL, NULL }, }; const char * const kvm_skip_events[] = { diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 91649690b52f..9974f5f8e49b 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -356,3 +356,8 @@ 439 n64 faccessat2 sys_faccessat2 440 n64 process_madvise sys_process_madvise 441 n64 epoll_pwait2 sys_epoll_pwait2 +442 n64 mount_setattr sys_mount_setattr +443 n64 quotactl_path sys_quotactl_path +444 n64 landlock_create_ruleset sys_landlock_create_ruleset +445 n64 landlock_add_rule sys_landlock_add_rule +446 n64 landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 0b2480cf3e47..2e68fbb57cc6 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -522,3 +522,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr +443 common quotactl_path sys_quotactl_path +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 3abef2144dac..7e4a2aba366d 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -445,3 +445,7 @@ 440 common process_madvise sys_process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr sys_mount_setattr +443 common quotactl_path sys_quotactl_path sys_quotactl_path +444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 7bf01cbe582f..ecd551b08d05 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -364,6 +364,10 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr +443 common quotactl_path sys_quotactl_path +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index ed4f0bd72e5a..7422b0ea8790 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -1123,8 +1123,10 @@ static int process_one_file(const char *fpath, const struct stat *sb, mapfile = strdup(fpath); return 0; } - - pr_info("%s: Ignoring file %s\n", prog, fpath); + if (is_json_file(bname)) + pr_debug("%s: ArchStd json is preprocessed %s\n", prog, fpath); + else + pr_info("%s: Ignoring file %s\n", prog, fpath); return 0; } diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 645009c08b3c..4a7b8deef3fd 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0|1 -size=120 +size=128 config=0 sample_period=* sample_type=263 diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index b0f42c34882e..408164456530 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0 -size=120 +size=128 config=0 sample_period=0 sample_type=65536 diff --git a/tools/perf/tests/attr/system-wide-dummy b/tools/perf/tests/attr/system-wide-dummy index eba723cc0d38..86a15dd359d9 100644 --- a/tools/perf/tests/attr/system-wide-dummy +++ b/tools/perf/tests/attr/system-wide-dummy @@ -7,7 +7,7 @@ cpu=* pid=-1 flags=8 type=1 -size=120 +size=128 config=9 sample_period=4000 sample_type=455 diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 8c0d9f368ebc..b64bdc1a7026 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -145,7 +145,14 @@ perf-$(CONFIG_LIBELF) += symbol-elf.o perf-$(CONFIG_LIBELF) += probe-file.o perf-$(CONFIG_LIBELF) += probe-event.o +ifdef CONFIG_LIBBPF_DYNAMIC + hashmap := 1 +endif ifndef CONFIG_LIBBPF + hashmap := 1 +endif + +ifdef hashmap perf-y += hashmap.o endif diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index f99852d54b14..43e5b563dee8 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -157,9 +157,15 @@ static int get_max_rate(unsigned int *rate) static int record_opts__config_freq(struct record_opts *opts) { bool user_freq = opts->user_freq != UINT_MAX; + bool user_interval = opts->user_interval != ULLONG_MAX; unsigned int max_rate; - if (opts->user_interval != ULLONG_MAX) + if (user_interval && user_freq) { + pr_err("cannot set frequency and period at the same time\n"); + return -1; + } + + if (user_interval) opts->default_interval = opts->user_interval; if (user_freq) opts->freq = opts->user_freq; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index a12cf4f0e97a..106b3d60881a 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -904,7 +904,7 @@ static void perf_event__cpu_map_swap(union perf_event *event, struct perf_record_record_cpu_map *mask; unsigned i; - data->type = bswap_64(data->type); + data->type = bswap_16(data->type); switch (data->type) { case PERF_CPU_MAP__CPUS: @@ -937,7 +937,7 @@ static void perf_event__stat_config_swap(union perf_event *event, { u64 size; - size = event->stat_config.nr * sizeof(event->stat_config.data[0]); + size = bswap_64(event->stat_config.nr) * sizeof(event->stat_config.data[0]); size += 1; /* nr item itself */ mem_bswap_64(&event->stat_config.nr, size); } diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index c62d372d426f..ed563bdd88f3 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -62,7 +62,7 @@ struct nfit_test_resource *get_nfit_res(resource_size_t resource) } EXPORT_SYMBOL(get_nfit_res); -void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size, +static void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size, void __iomem *(*fallback_fn)(resource_size_t, unsigned long)) { struct nfit_test_resource *nfit_res = get_nfit_res(offset); diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 9b185bf82da8..54f367cbadae 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1871,9 +1871,16 @@ static void smart_init(struct nfit_test *t) } } +static size_t sizeof_spa(struct acpi_nfit_system_address *spa) +{ + /* until spa location cookie support is added... */ + return sizeof(*spa) - 8; +} + static int nfit_test0_alloc(struct nfit_test *t) { - size_t nfit_size = sizeof(struct acpi_nfit_system_address) * NUM_SPA + struct acpi_nfit_system_address *spa = NULL; + size_t nfit_size = sizeof_spa(spa) * NUM_SPA + sizeof(struct acpi_nfit_memory_map) * NUM_MEM + sizeof(struct acpi_nfit_control_region) * NUM_DCR + offsetof(struct acpi_nfit_control_region, @@ -1937,7 +1944,8 @@ static int nfit_test0_alloc(struct nfit_test *t) static int nfit_test1_alloc(struct nfit_test *t) { - size_t nfit_size = sizeof(struct acpi_nfit_system_address) * 2 + struct acpi_nfit_system_address *spa = NULL; + size_t nfit_size = sizeof_spa(spa) * 2 + sizeof(struct acpi_nfit_memory_map) * 2 + offsetof(struct acpi_nfit_control_region, window_size) * 2; int i; @@ -2000,7 +2008,7 @@ static void nfit_test0_setup(struct nfit_test *t) */ spa = nfit_buf; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16); spa->range_index = 0+1; spa->address = t->spa_set_dma[0]; @@ -2014,7 +2022,7 @@ static void nfit_test0_setup(struct nfit_test *t) */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16); spa->range_index = 1+1; spa->address = t->spa_set_dma[1]; @@ -2024,7 +2032,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa2 (dcr0) dimm0 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); spa->range_index = 2+1; spa->address = t->dcr_dma[0]; @@ -2034,7 +2042,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa3 (dcr1) dimm1 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); spa->range_index = 3+1; spa->address = t->dcr_dma[1]; @@ -2044,7 +2052,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa4 (dcr2) dimm2 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); spa->range_index = 4+1; spa->address = t->dcr_dma[2]; @@ -2054,7 +2062,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa5 (dcr3) dimm3 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); spa->range_index = 5+1; spa->address = t->dcr_dma[3]; @@ -2064,7 +2072,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa6 (bdw for dcr0) dimm0 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); spa->range_index = 6+1; spa->address = t->dimm_dma[0]; @@ -2074,7 +2082,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa7 (bdw for dcr1) dimm1 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); spa->range_index = 7+1; spa->address = t->dimm_dma[1]; @@ -2084,7 +2092,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa8 (bdw for dcr2) dimm2 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); spa->range_index = 8+1; spa->address = t->dimm_dma[2]; @@ -2094,7 +2102,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa9 (bdw for dcr3) dimm3 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); spa->range_index = 9+1; spa->address = t->dimm_dma[3]; @@ -2581,7 +2589,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa10 (dcr4) dimm4 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); spa->range_index = 10+1; spa->address = t->dcr_dma[4]; @@ -2595,7 +2603,7 @@ static void nfit_test0_setup(struct nfit_test *t) */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16); spa->range_index = 11+1; spa->address = t->spa_set_dma[2]; @@ -2605,7 +2613,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa12 (bdw for dcr4) dimm4 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); spa->range_index = 12+1; spa->address = t->dimm_dma[4]; @@ -2739,7 +2747,7 @@ static void nfit_test1_setup(struct nfit_test *t) /* spa0 (flat range with no bdw aliasing) */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16); spa->range_index = 0+1; spa->address = t->spa_set_dma[0]; @@ -2749,7 +2757,7 @@ static void nfit_test1_setup(struct nfit_test *t) /* virtual cd region */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_VCD), 16); spa->range_index = 0; spa->address = t->spa_set_dma[1]; diff --git a/tools/testing/selftests/arm64/bti/test.c b/tools/testing/selftests/arm64/bti/test.c index 656b04976ccc..67b77ab83c20 100644 --- a/tools/testing/selftests/arm64/bti/test.c +++ b/tools/testing/selftests/arm64/bti/test.c @@ -6,6 +6,7 @@ #include "system.h" +#include <stddef.h> #include <linux/errno.h> #include <linux/auxvec.h> #include <linux/signal.h> diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index bd83158e0e0b..d5bc9bf3b528 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -8,12 +8,15 @@ /x86_64/cr4_cpuid_sync_test /x86_64/debug_regs /x86_64/evmcs_test +/x86_64/emulator_error_test /x86_64/get_cpuid_test /x86_64/get_msr_index_features /x86_64/kvm_pv_test /x86_64/hyperv_clock /x86_64/hyperv_cpuid +/x86_64/hyperv_features /x86_64/mmio_warning_test +/x86_64/mmu_role_test /x86_64/platform_info_test /x86_64/set_boot_cpu_id /x86_64/set_sregs_test @@ -29,6 +32,7 @@ /x86_64/vmx_preemption_timer_test /x86_64/vmx_set_nested_state_test /x86_64/vmx_tsc_adjust_test +/x86_64/vmx_nested_tsc_scaling_test /x86_64/xapic_ipi_test /x86_64/xen_shinfo_test /x86_64/xen_vmcall_test @@ -41,5 +45,7 @@ /kvm_create_max_vcpus /kvm_page_table_test /memslot_modification_stress_test +/memslot_perf_test /set_memory_region_test /steal_time +/kvm_binary_stats_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index e439d027939d..bc65c57ae40d 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -33,19 +33,22 @@ ifeq ($(ARCH),s390) UNAME_M := s390x endif -LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c -LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S +LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c +LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test +TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid +TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test +TEST_GEN_PROGS_x86_64 += x86_64/mmu_role_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test @@ -60,6 +63,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test +TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs @@ -74,8 +78,10 @@ TEST_GEN_PROGS_x86_64 += hardware_disable_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += kvm_page_table_test TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test +TEST_GEN_PROGS_x86_64 += memslot_perf_test TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time +TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve @@ -87,6 +93,7 @@ TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus TEST_GEN_PROGS_aarch64 += kvm_page_table_test TEST_GEN_PROGS_aarch64 += set_memory_region_test TEST_GEN_PROGS_aarch64 += steal_time +TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test TEST_GEN_PROGS_s390x = s390x/memop TEST_GEN_PROGS_s390x += s390x/resets @@ -96,6 +103,7 @@ TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += kvm_create_max_vcpus TEST_GEN_PROGS_s390x += kvm_page_table_test TEST_GEN_PROGS_s390x += set_memory_region_test +TEST_GEN_PROGS_s390x += kvm_binary_stats_test TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M)) LIBKVM += $(LIBKVM_$(UNAME_M)) diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 5f7a229c3af1..b74704305835 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -9,6 +9,7 @@ #define _GNU_SOURCE /* for pipe2 */ +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <time.h> @@ -38,6 +39,7 @@ static int nr_vcpus = 1; static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; +static size_t demand_paging_size; static char *guest_data_prototype; static void *vcpu_worker(void *data) @@ -71,36 +73,51 @@ static void *vcpu_worker(void *data) return NULL; } -static int handle_uffd_page_request(int uffd, uint64_t addr) +static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr) { - pid_t tid; + pid_t tid = syscall(__NR_gettid); struct timespec start; struct timespec ts_diff; - struct uffdio_copy copy; int r; - tid = syscall(__NR_gettid); + clock_gettime(CLOCK_MONOTONIC, &start); - copy.src = (uint64_t)guest_data_prototype; - copy.dst = addr; - copy.len = perf_test_args.host_page_size; - copy.mode = 0; + if (uffd_mode == UFFDIO_REGISTER_MODE_MISSING) { + struct uffdio_copy copy; - clock_gettime(CLOCK_MONOTONIC, &start); + copy.src = (uint64_t)guest_data_prototype; + copy.dst = addr; + copy.len = demand_paging_size; + copy.mode = 0; - r = ioctl(uffd, UFFDIO_COPY, ©); - if (r == -1) { - pr_info("Failed Paged in 0x%lx from thread %d with errno: %d\n", - addr, tid, errno); - return r; + r = ioctl(uffd, UFFDIO_COPY, ©); + if (r == -1) { + pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d with errno: %d\n", + addr, tid, errno); + return r; + } + } else if (uffd_mode == UFFDIO_REGISTER_MODE_MINOR) { + struct uffdio_continue cont = {0}; + + cont.range.start = addr; + cont.range.len = demand_paging_size; + + r = ioctl(uffd, UFFDIO_CONTINUE, &cont); + if (r == -1) { + pr_info("Failed UFFDIO_CONTINUE in 0x%lx from thread %d with errno: %d\n", + addr, tid, errno); + return r; + } + } else { + TEST_FAIL("Invalid uffd mode %d", uffd_mode); } ts_diff = timespec_elapsed(start); - PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid, + PER_PAGE_DEBUG("UFFD page-in %d \t%ld ns\n", tid, timespec_to_ns(ts_diff)); PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n", - perf_test_args.host_page_size, addr, tid); + demand_paging_size, addr, tid); return 0; } @@ -108,6 +125,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) bool quit_uffd_thread; struct uffd_handler_args { + int uffd_mode; int uffd; int pipefd; useconds_t delay; @@ -169,7 +187,7 @@ static void *uffd_handler_thread_fn(void *arg) if (r == -1) { if (errno == EAGAIN) continue; - pr_info("Read of uffd gor errno %d", errno); + pr_info("Read of uffd got errno %d\n", errno); return NULL; } @@ -184,7 +202,7 @@ static void *uffd_handler_thread_fn(void *arg) if (delay) usleep(delay); addr = msg.arg.pagefault.address; - r = handle_uffd_page_request(uffd, addr); + r = handle_uffd_page_request(uffd_args->uffd_mode, uffd, addr); if (r < 0) return NULL; pages++; @@ -198,43 +216,53 @@ static void *uffd_handler_thread_fn(void *arg) return NULL; } -static int setup_demand_paging(struct kvm_vm *vm, - pthread_t *uffd_handler_thread, int pipefd, - useconds_t uffd_delay, - struct uffd_handler_args *uffd_args, - void *hva, uint64_t len) +static void setup_demand_paging(struct kvm_vm *vm, + pthread_t *uffd_handler_thread, int pipefd, + int uffd_mode, useconds_t uffd_delay, + struct uffd_handler_args *uffd_args, + void *hva, void *alias, uint64_t len) { + bool is_minor = (uffd_mode == UFFDIO_REGISTER_MODE_MINOR); int uffd; struct uffdio_api uffdio_api; struct uffdio_register uffdio_register; + uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY; - uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); - if (uffd == -1) { - pr_info("uffd creation failed\n"); - return -1; + PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n", + is_minor ? "MINOR" : "MISSING", + is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY"); + + /* In order to get minor faults, prefault via the alias. */ + if (is_minor) { + size_t p; + + expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE; + + TEST_ASSERT(alias != NULL, "Alias required for minor faults"); + for (p = 0; p < (len / demand_paging_size); ++p) { + memcpy(alias + (p * demand_paging_size), + guest_data_prototype, demand_paging_size); + } } + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno); + uffdio_api.api = UFFD_API; uffdio_api.features = 0; - if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) { - pr_info("ioctl uffdio_api failed\n"); - return -1; - } + TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1, + "ioctl UFFDIO_API failed: %" PRIu64, + (uint64_t)uffdio_api.api); uffdio_register.range.start = (uint64_t)hva; uffdio_register.range.len = len; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) { - pr_info("ioctl uffdio_register failed\n"); - return -1; - } - - if ((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) != - UFFD_API_RANGE_IOCTLS) { - pr_info("unexpected userfaultfd ioctl set\n"); - return -1; - } + uffdio_register.mode = uffd_mode; + TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1, + "ioctl UFFDIO_REGISTER failed"); + TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) == + expected_ioctls, "missing userfaultfd ioctls"); + uffd_args->uffd_mode = uffd_mode; uffd_args->uffd = uffd; uffd_args->pipefd = pipefd; uffd_args->delay = uffd_delay; @@ -243,13 +271,12 @@ static int setup_demand_paging(struct kvm_vm *vm, PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n", hva, hva + len); - - return 0; } struct test_params { - bool use_uffd; + int uffd_mode; useconds_t uffd_delay; + enum vm_mem_backing_src_type src_type; bool partition_vcpu_memory_access; }; @@ -267,14 +294,16 @@ static void run_test(enum vm_guest_mode mode, void *arg) int r; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, - VM_MEM_SRC_ANONYMOUS); + p->src_type); perf_test_args.wr_fract = 1; - guest_data_prototype = malloc(perf_test_args.host_page_size); + demand_paging_size = get_backing_src_pagesz(p->src_type); + + guest_data_prototype = malloc(demand_paging_size); TEST_ASSERT(guest_data_prototype, "Failed to allocate buffer for guest data pattern"); - memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size); + memset(guest_data_prototype, 0xAB, demand_paging_size); vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); TEST_ASSERT(vcpu_threads, "Memory allocation failed"); @@ -282,7 +311,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, p->partition_vcpu_memory_access); - if (p->use_uffd) { + if (p->uffd_mode) { uffd_handler_threads = malloc(nr_vcpus * sizeof(*uffd_handler_threads)); TEST_ASSERT(uffd_handler_threads, "Memory allocation failed"); @@ -296,6 +325,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { vm_paddr_t vcpu_gpa; void *vcpu_hva; + void *vcpu_alias; uint64_t vcpu_mem_size; @@ -310,8 +340,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size); - /* Cache the HVA pointer of the region */ + /* Cache the host addresses of the region */ vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); + vcpu_alias = addr_gpa2alias(vm, vcpu_gpa); /* * Set up user fault fd to handle demand paging @@ -321,13 +352,11 @@ static void run_test(enum vm_guest_mode mode, void *arg) O_CLOEXEC | O_NONBLOCK); TEST_ASSERT(!r, "Failed to set up pipefd"); - r = setup_demand_paging(vm, - &uffd_handler_threads[vcpu_id], - pipefds[vcpu_id * 2], - p->uffd_delay, &uffd_args[vcpu_id], - vcpu_hva, vcpu_mem_size); - if (r < 0) - exit(-r); + setup_demand_paging(vm, &uffd_handler_threads[vcpu_id], + pipefds[vcpu_id * 2], p->uffd_mode, + p->uffd_delay, &uffd_args[vcpu_id], + vcpu_hva, vcpu_alias, + vcpu_mem_size); } } @@ -355,7 +384,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("All vCPU threads joined\n"); - if (p->use_uffd) { + if (p->uffd_mode) { char c; /* Tell the user fault fd handler threads to quit */ @@ -377,7 +406,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) free(guest_data_prototype); free(vcpu_threads); - if (p->use_uffd) { + if (p->uffd_mode) { free(uffd_handler_threads); free(uffd_args); free(pipefds); @@ -387,17 +416,19 @@ static void run_test(enum vm_guest_mode mode, void *arg) static void help(char *name) { puts(""); - printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n" - " [-b memory] [-v vcpus] [-o]\n", name); + printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n" + " [-b memory] [-t type] [-v vcpus] [-o]\n", name); guest_modes_help(); - printf(" -u: use User Fault FD to handle vCPU page\n" - " faults.\n"); + printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n" + " UFFD registration mode: 'MISSING' or 'MINOR'.\n"); printf(" -d: add a delay in usec to the User Fault\n" " FD handler to simulate demand paging\n" " overheads. Ignored without -u.\n"); printf(" -b: specify the size of the memory region which should be\n" " demand paged by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); + printf(" -t: The type of backing memory to use. Default: anonymous\n"); + backing_src_help(); printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); @@ -409,19 +440,24 @@ int main(int argc, char *argv[]) { int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { + .src_type = VM_MEM_SRC_ANONYMOUS, .partition_vcpu_memory_access = true, }; int opt; guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:ud:b:v:o")) != -1) { + while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); break; case 'u': - p.use_uffd = true; + if (!strcmp("MISSING", optarg)) + p.uffd_mode = UFFDIO_REGISTER_MODE_MISSING; + else if (!strcmp("MINOR", optarg)) + p.uffd_mode = UFFDIO_REGISTER_MODE_MINOR; + TEST_ASSERT(p.uffd_mode, "UFFD mode must be 'MISSING' or 'MINOR'."); break; case 'd': p.uffd_delay = strtoul(optarg, NULL, 0); @@ -430,6 +466,9 @@ int main(int argc, char *argv[]) case 'b': guest_percpu_mem_size = parse_size(optarg); break; + case 't': + p.src_type = parse_backing_src_type(optarg); + break; case 'v': nr_vcpus = atoi(optarg); TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, @@ -445,6 +484,11 @@ int main(int argc, char *argv[]) } } + if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR && + !backing_src_is_shared(p.src_type)) { + TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t"); + } + for_each_guest_mode(run_test, &p); return 0; diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 81edbd23d371..5fe0140e407e 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -16,7 +16,6 @@ #include <errno.h> #include <linux/bitmap.h> #include <linux/bitops.h> -#include <asm/barrier.h> #include <linux/atomic.h> #include "kvm_util.h" @@ -681,7 +680,7 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); + kvm_vm_elf_load(vm, program_invocation_name); #ifdef __x86_64__ vm_create_irqchip(vm); #endif @@ -761,7 +760,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) KVM_MEM_LOG_DIRTY_PAGES); /* Do mapping for the dirty track memory slot */ - virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages); /* Cache the HVA pointer of the region */ host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem); diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index 5aadf84c91c0..b21c69a56daa 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -105,7 +105,7 @@ static void run_test(uint32_t run) CPU_SET(i, &cpu_set); vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); + kvm_vm_elf_load(vm, program_invocation_name); vm_create_irqchip(vm); pr_debug("%s: [%d] start vcpus\n", __func__, run); @@ -132,6 +132,36 @@ static void run_test(uint32_t run) TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run); } +void wait_for_child_setup(pid_t pid) +{ + /* + * Wait for the child to post to the semaphore, but wake up periodically + * to check if the child exited prematurely. + */ + for (;;) { + const struct timespec wait_period = { .tv_sec = 1 }; + int status; + + if (!sem_timedwait(sem, &wait_period)) + return; + + /* Child is still running, keep waiting. */ + if (pid != waitpid(pid, &status, WNOHANG)) + continue; + + /* + * Child is no longer running, which is not expected. + * + * If it exited with a non-zero status, we explicitly forward + * the child's status in case it exited with KSFT_SKIP. + */ + if (WIFEXITED(status)) + exit(WEXITSTATUS(status)); + else + TEST_ASSERT(false, "Child exited unexpectedly"); + } +} + int main(int argc, char **argv) { uint32_t i; @@ -148,7 +178,7 @@ int main(int argc, char **argv) run_test(i); /* This function always exits */ pr_debug("%s: [%d] waiting semaphore\n", __func__, i); - sem_wait(sem); + wait_for_child_setup(pid); r = (rand() % DELAY_US_MAX) + 1; pr_debug("%s: [%d] waiting %dus\n", __func__, i, r); usleep(r); diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index a8f022794ce3..45678a2566dd 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -30,6 +30,7 @@ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ /* Minimum allocated guest virtual and physical addresses */ #define KVM_UTIL_MIN_VADDR 0x2000 +#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 #define DEFAULT_GUEST_PHY_PAGES 512 #define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000 @@ -43,6 +44,7 @@ enum vm_guest_mode { VM_MODE_P40V48_4K, VM_MODE_P40V48_64K, VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ + VM_MODE_P47V64_4K, NUM_VM_MODES, }; @@ -60,7 +62,7 @@ enum vm_guest_mode { #elif defined(__s390x__) -#define VM_MODE_DEFAULT VM_MODE_P52V48_4K +#define VM_MODE_DEFAULT VM_MODE_P47V64_4K #define MIN_PAGE_SHIFT 12U #define ptes_per_page(page_size) ((page_size) / 16) @@ -77,6 +79,7 @@ struct vm_guest_mode_params { }; extern const struct vm_guest_mode_params vm_guest_mode_params[]; +int open_kvm_dev_path_or_exit(void); int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, @@ -96,8 +99,7 @@ uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm); int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, size_t len); -void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename, - uint32_t data_memslot, uint32_t pgd_memslot); +void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); @@ -139,13 +141,16 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid); -vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, - uint32_t data_memslot, uint32_t pgd_memslot); +vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); +vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); +vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm); + void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - unsigned int npages, uint32_t pgd_memslot); + unsigned int npages); void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); /* * Address Guest Virtual to Guest Physical @@ -234,7 +239,7 @@ int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, const char *exit_reason_str(unsigned int exit_reason); -void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot); +void virt_pgd_alloc(struct kvm_vm *vm); /* * VM Virtual Page Map @@ -252,13 +257,13 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot); * Within @vm, creates a virtual translation for the page starting * at @vaddr to the page starting at @paddr. */ -void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - uint32_t memslot); +void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr); vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, uint32_t memslot); vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, vm_paddr_t paddr_min, uint32_t memslot); +vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); /* * Create a VM with reasonable defaults @@ -283,10 +288,11 @@ struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_me uint32_t num_percpu_pages, void *guest_code, uint32_t vcpuids[]); -/* Like vm_create_default_with_vcpus, but accepts mode as a parameter */ +/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t extra_mem_pages, uint32_t num_percpu_pages, - void *guest_code, uint32_t vcpuids[]); + uint64_t slot0_mem_pages, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]); /* * Adds a vCPU with reasonable defaults (e.g. a stack) @@ -302,7 +308,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm); unsigned int vm_get_page_size(struct kvm_vm *vm); unsigned int vm_get_page_shift(struct kvm_vm *vm); -unsigned int vm_get_max_gfn(struct kvm_vm *vm); +uint64_t vm_get_max_gfn(struct kvm_vm *vm); int vm_get_fd(struct kvm_vm *vm); unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); @@ -387,4 +393,7 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc); #define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \ __GUEST_ASSERT((_condition), 4, (arg1), (arg2), (arg3), (arg4)) +int vm_get_stats_fd(struct kvm_vm *vm); +int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid); + #endif /* SELFTEST_KVM_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index fade3130eb01..d79be15dd3d2 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -17,6 +17,7 @@ #include <errno.h> #include <unistd.h> #include <fcntl.h> +#include <sys/mman.h> #include "kselftest.h" static inline int _no_printf(const char *format, ...) { return 0; } @@ -84,6 +85,8 @@ enum vm_mem_backing_src_type { VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB, + VM_MEM_SRC_SHMEM, + VM_MEM_SRC_SHARED_HUGETLB, NUM_SRC_TYPES, }; @@ -100,4 +103,13 @@ size_t get_backing_src_pagesz(uint32_t i); void backing_src_help(void); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); +/* + * Whether or not the given source type is shared memory (as opposed to + * anonymous). + */ +static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t) +{ + return vm_mem_backing_src_alias(t)->flag & MAP_SHARED; +} + #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h new file mode 100644 index 000000000000..0be4757f1f20 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/apic.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * tools/testing/selftests/kvm/include/x86_64/apic.h + * + * Copyright (C) 2021, Google LLC. + */ + +#ifndef SELFTEST_KVM_APIC_H +#define SELFTEST_KVM_APIC_H + +#include <stdint.h> + +#include "processor.h" + +#define APIC_DEFAULT_GPA 0xfee00000ULL + +/* APIC base address MSR and fields */ +#define MSR_IA32_APICBASE 0x0000001b +#define MSR_IA32_APICBASE_BSP (1<<8) +#define MSR_IA32_APICBASE_EXTD (1<<10) +#define MSR_IA32_APICBASE_ENABLE (1<<11) +#define MSR_IA32_APICBASE_BASE (0xfffff<<12) +#define GET_APIC_BASE(x) (((x) >> 12) << 12) + +#define APIC_BASE_MSR 0x800 +#define X2APIC_ENABLE (1UL << 10) +#define APIC_ID 0x20 +#define APIC_LVR 0x30 +#define GET_APIC_ID_FIELD(x) (((x) >> 24) & 0xFF) +#define APIC_TASKPRI 0x80 +#define APIC_PROCPRI 0xA0 +#define APIC_EOI 0xB0 +#define APIC_SPIV 0xF0 +#define APIC_SPIV_FOCUS_DISABLED (1 << 9) +#define APIC_SPIV_APIC_ENABLED (1 << 8) +#define APIC_ICR 0x300 +#define APIC_DEST_SELF 0x40000 +#define APIC_DEST_ALLINC 0x80000 +#define APIC_DEST_ALLBUT 0xC0000 +#define APIC_ICR_RR_MASK 0x30000 +#define APIC_ICR_RR_INVALID 0x00000 +#define APIC_ICR_RR_INPROG 0x10000 +#define APIC_ICR_RR_VALID 0x20000 +#define APIC_INT_LEVELTRIG 0x08000 +#define APIC_INT_ASSERT 0x04000 +#define APIC_ICR_BUSY 0x01000 +#define APIC_DEST_LOGICAL 0x00800 +#define APIC_DEST_PHYSICAL 0x00000 +#define APIC_DM_FIXED 0x00000 +#define APIC_DM_FIXED_MASK 0x00700 +#define APIC_DM_LOWEST 0x00100 +#define APIC_DM_SMI 0x00200 +#define APIC_DM_REMRD 0x00300 +#define APIC_DM_NMI 0x00400 +#define APIC_DM_INIT 0x00500 +#define APIC_DM_STARTUP 0x00600 +#define APIC_DM_EXTINT 0x00700 +#define APIC_VECTOR_MASK 0x000FF +#define APIC_ICR2 0x310 +#define SET_APIC_DEST_FIELD(x) ((x) << 24) + +void apic_disable(void); +void xapic_enable(void); +void x2apic_enable(void); + +static inline uint32_t get_bsp_flag(void) +{ + return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP; +} + +static inline uint32_t xapic_read_reg(unsigned int reg) +{ + return ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2]; +} + +static inline void xapic_write_reg(unsigned int reg, uint32_t val) +{ + ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2] = val; +} + +static inline uint64_t x2apic_read_reg(unsigned int reg) +{ + return rdmsr(APIC_BASE_MSR + (reg >> 4)); +} + +static inline void x2apic_write_reg(unsigned int reg, uint64_t value) +{ + wrmsr(APIC_BASE_MSR + (reg >> 4), value); +} + +#endif /* SELFTEST_KVM_APIC_H */ diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/x86_64/evmcs.h index a034438b6266..c9af97abd622 100644 --- a/tools/testing/selftests/kvm/include/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86_64/evmcs.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * tools/testing/selftests/kvm/include/vmx.h + * tools/testing/selftests/kvm/include/x86_64/evmcs.h * * Copyright (C) 2018, Red Hat, Inc. * diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h new file mode 100644 index 000000000000..412eaee7884a --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h @@ -0,0 +1,185 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * tools/testing/selftests/kvm/include/x86_64/hyperv.h + * + * Copyright (C) 2021, Red Hat, Inc. + * + */ + +#ifndef SELFTEST_KVM_HYPERV_H +#define SELFTEST_KVM_HYPERV_H + +#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 0x40000000 +#define HYPERV_CPUID_INTERFACE 0x40000001 +#define HYPERV_CPUID_VERSION 0x40000002 +#define HYPERV_CPUID_FEATURES 0x40000003 +#define HYPERV_CPUID_ENLIGHTMENT_INFO 0x40000004 +#define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005 +#define HYPERV_CPUID_CPU_MANAGEMENT_FEATURES 0x40000007 +#define HYPERV_CPUID_NESTED_FEATURES 0x4000000A +#define HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS 0x40000080 +#define HYPERV_CPUID_SYNDBG_INTERFACE 0x40000081 +#define HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES 0x40000082 + +#define HV_X64_MSR_GUEST_OS_ID 0x40000000 +#define HV_X64_MSR_HYPERCALL 0x40000001 +#define HV_X64_MSR_VP_INDEX 0x40000002 +#define HV_X64_MSR_RESET 0x40000003 +#define HV_X64_MSR_VP_RUNTIME 0x40000010 +#define HV_X64_MSR_TIME_REF_COUNT 0x40000020 +#define HV_X64_MSR_REFERENCE_TSC 0x40000021 +#define HV_X64_MSR_TSC_FREQUENCY 0x40000022 +#define HV_X64_MSR_APIC_FREQUENCY 0x40000023 +#define HV_X64_MSR_EOI 0x40000070 +#define HV_X64_MSR_ICR 0x40000071 +#define HV_X64_MSR_TPR 0x40000072 +#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 +#define HV_X64_MSR_SCONTROL 0x40000080 +#define HV_X64_MSR_SVERSION 0x40000081 +#define HV_X64_MSR_SIEFP 0x40000082 +#define HV_X64_MSR_SIMP 0x40000083 +#define HV_X64_MSR_EOM 0x40000084 +#define HV_X64_MSR_SINT0 0x40000090 +#define HV_X64_MSR_SINT1 0x40000091 +#define HV_X64_MSR_SINT2 0x40000092 +#define HV_X64_MSR_SINT3 0x40000093 +#define HV_X64_MSR_SINT4 0x40000094 +#define HV_X64_MSR_SINT5 0x40000095 +#define HV_X64_MSR_SINT6 0x40000096 +#define HV_X64_MSR_SINT7 0x40000097 +#define HV_X64_MSR_SINT8 0x40000098 +#define HV_X64_MSR_SINT9 0x40000099 +#define HV_X64_MSR_SINT10 0x4000009A +#define HV_X64_MSR_SINT11 0x4000009B +#define HV_X64_MSR_SINT12 0x4000009C +#define HV_X64_MSR_SINT13 0x4000009D +#define HV_X64_MSR_SINT14 0x4000009E +#define HV_X64_MSR_SINT15 0x4000009F +#define HV_X64_MSR_STIMER0_CONFIG 0x400000B0 +#define HV_X64_MSR_STIMER0_COUNT 0x400000B1 +#define HV_X64_MSR_STIMER1_CONFIG 0x400000B2 +#define HV_X64_MSR_STIMER1_COUNT 0x400000B3 +#define HV_X64_MSR_STIMER2_CONFIG 0x400000B4 +#define HV_X64_MSR_STIMER2_COUNT 0x400000B5 +#define HV_X64_MSR_STIMER3_CONFIG 0x400000B6 +#define HV_X64_MSR_STIMER3_COUNT 0x400000B7 +#define HV_X64_MSR_GUEST_IDLE 0x400000F0 +#define HV_X64_MSR_CRASH_P0 0x40000100 +#define HV_X64_MSR_CRASH_P1 0x40000101 +#define HV_X64_MSR_CRASH_P2 0x40000102 +#define HV_X64_MSR_CRASH_P3 0x40000103 +#define HV_X64_MSR_CRASH_P4 0x40000104 +#define HV_X64_MSR_CRASH_CTL 0x40000105 +#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 +#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 +#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 +#define HV_X64_MSR_TSC_INVARIANT_CONTROL 0x40000118 + +#define HV_X64_MSR_SYNDBG_CONTROL 0x400000F1 +#define HV_X64_MSR_SYNDBG_STATUS 0x400000F2 +#define HV_X64_MSR_SYNDBG_SEND_BUFFER 0x400000F3 +#define HV_X64_MSR_SYNDBG_RECV_BUFFER 0x400000F4 +#define HV_X64_MSR_SYNDBG_PENDING_BUFFER 0x400000F5 +#define HV_X64_MSR_SYNDBG_OPTIONS 0x400000FF + +/* HYPERV_CPUID_FEATURES.EAX */ +#define HV_MSR_VP_RUNTIME_AVAILABLE BIT(0) +#define HV_MSR_TIME_REF_COUNT_AVAILABLE BIT(1) +#define HV_MSR_SYNIC_AVAILABLE BIT(2) +#define HV_MSR_SYNTIMER_AVAILABLE BIT(3) +#define HV_MSR_APIC_ACCESS_AVAILABLE BIT(4) +#define HV_MSR_HYPERCALL_AVAILABLE BIT(5) +#define HV_MSR_VP_INDEX_AVAILABLE BIT(6) +#define HV_MSR_RESET_AVAILABLE BIT(7) +#define HV_MSR_STAT_PAGES_AVAILABLE BIT(8) +#define HV_MSR_REFERENCE_TSC_AVAILABLE BIT(9) +#define HV_MSR_GUEST_IDLE_AVAILABLE BIT(10) +#define HV_ACCESS_FREQUENCY_MSRS BIT(11) +#define HV_ACCESS_REENLIGHTENMENT BIT(13) +#define HV_ACCESS_TSC_INVARIANT BIT(15) + +/* HYPERV_CPUID_FEATURES.EBX */ +#define HV_CREATE_PARTITIONS BIT(0) +#define HV_ACCESS_PARTITION_ID BIT(1) +#define HV_ACCESS_MEMORY_POOL BIT(2) +#define HV_ADJUST_MESSAGE_BUFFERS BIT(3) +#define HV_POST_MESSAGES BIT(4) +#define HV_SIGNAL_EVENTS BIT(5) +#define HV_CREATE_PORT BIT(6) +#define HV_CONNECT_PORT BIT(7) +#define HV_ACCESS_STATS BIT(8) +#define HV_DEBUGGING BIT(11) +#define HV_CPU_MANAGEMENT BIT(12) +#define HV_ISOLATION BIT(22) + +/* HYPERV_CPUID_FEATURES.EDX */ +#define HV_X64_MWAIT_AVAILABLE BIT(0) +#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) +#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) +#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) +#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE BIT(4) +#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) +#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) +#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) +#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) + +/* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ +#define HV_X64_AS_SWITCH_RECOMMENDED BIT(0) +#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED BIT(1) +#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED BIT(2) +#define HV_X64_APIC_ACCESS_RECOMMENDED BIT(3) +#define HV_X64_SYSTEM_RESET_RECOMMENDED BIT(4) +#define HV_X64_RELAXED_TIMING_RECOMMENDED BIT(5) +#define HV_DEPRECATING_AEOI_RECOMMENDED BIT(9) +#define HV_X64_CLUSTER_IPI_RECOMMENDED BIT(10) +#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11) +#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) + +/* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ +#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING BIT(1) + +/* Hypercalls */ +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002 +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003 +#define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008 +#define HVCALL_SEND_IPI 0x000b +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013 +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX 0x0014 +#define HVCALL_SEND_IPI_EX 0x0015 +#define HVCALL_GET_PARTITION_ID 0x0046 +#define HVCALL_DEPOSIT_MEMORY 0x0048 +#define HVCALL_CREATE_VP 0x004e +#define HVCALL_GET_VP_REGISTERS 0x0050 +#define HVCALL_SET_VP_REGISTERS 0x0051 +#define HVCALL_POST_MESSAGE 0x005c +#define HVCALL_SIGNAL_EVENT 0x005d +#define HVCALL_POST_DEBUG_DATA 0x0069 +#define HVCALL_RETRIEVE_DEBUG_DATA 0x006a +#define HVCALL_RESET_DEBUG_SESSION 0x006b +#define HVCALL_ADD_LOGICAL_PROCESSOR 0x0076 +#define HVCALL_MAP_DEVICE_INTERRUPT 0x007c +#define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d +#define HVCALL_RETARGET_INTERRUPT 0x007e +#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af +#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 + +#define HV_FLUSH_ALL_PROCESSORS BIT(0) +#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1) +#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2) +#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT BIT(3) + +/* hypercall status code */ +#define HV_STATUS_SUCCESS 0 +#define HV_STATUS_INVALID_HYPERCALL_CODE 2 +#define HV_STATUS_INVALID_HYPERCALL_INPUT 3 +#define HV_STATUS_INVALID_ALIGNMENT 4 +#define HV_STATUS_INVALID_PARAMETER 5 +#define HV_STATUS_ACCESS_DENIED 6 +#define HV_STATUS_OPERATION_DENIED 8 +#define HV_STATUS_INSUFFICIENT_MEMORY 11 +#define HV_STATUS_INVALID_PORT_ID 17 +#define HV_STATUS_INVALID_CONNECTION_ID 18 +#define HV_STATUS_INSUFFICIENT_BUFFERS 19 + +#endif /* !SELFTEST_KVM_HYPERV_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 0b30b4e15c38..6d27a5435971 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -13,6 +13,8 @@ #include <asm/msr-index.h> +#include "../kvm_util.h" + #define X86_EFLAGS_FIXED (1u << 1) #define X86_CR4_VME (1ul << 0) @@ -53,6 +55,9 @@ #define CPUID_PKU (1ul << 3) #define CPUID_LA57 (1ul << 16) +/* CPUID.0x8000_0001.EDX */ +#define CPUID_GBPAGES (1ul << 26) + #define UNEXPECTED_VECTOR_PORT 0xfff0u /* General Registers in 64-Bit Mode */ @@ -394,6 +399,10 @@ void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid); void vm_handle_exception(struct kvm_vm *vm, int vector, void (*handler)(struct ex_regs *)); +uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr); +void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr, + uint64_t pte); + /* * set_cpuid() - overwrites a matching cpuid entry with the provided value. * matches based on ent->function && ent->index. returns true @@ -410,6 +419,14 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid); struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid); +enum x86_page_size { + X86_PAGE_SIZE_4K = 0, + X86_PAGE_SIZE_2M, + X86_PAGE_SIZE_1G, +}; +void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + enum x86_page_size page_size); + /* * Basic CPU control in CR0 */ @@ -425,53 +442,6 @@ struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpui #define X86_CR0_CD (1UL<<30) /* Cache Disable */ #define X86_CR0_PG (1UL<<31) /* Paging */ -#define APIC_DEFAULT_GPA 0xfee00000ULL - -/* APIC base address MSR and fields */ -#define MSR_IA32_APICBASE 0x0000001b -#define MSR_IA32_APICBASE_BSP (1<<8) -#define MSR_IA32_APICBASE_EXTD (1<<10) -#define MSR_IA32_APICBASE_ENABLE (1<<11) -#define MSR_IA32_APICBASE_BASE (0xfffff<<12) -#define GET_APIC_BASE(x) (((x) >> 12) << 12) - -#define APIC_BASE_MSR 0x800 -#define X2APIC_ENABLE (1UL << 10) -#define APIC_ID 0x20 -#define APIC_LVR 0x30 -#define GET_APIC_ID_FIELD(x) (((x) >> 24) & 0xFF) -#define APIC_TASKPRI 0x80 -#define APIC_PROCPRI 0xA0 -#define APIC_EOI 0xB0 -#define APIC_SPIV 0xF0 -#define APIC_SPIV_FOCUS_DISABLED (1 << 9) -#define APIC_SPIV_APIC_ENABLED (1 << 8) -#define APIC_ICR 0x300 -#define APIC_DEST_SELF 0x40000 -#define APIC_DEST_ALLINC 0x80000 -#define APIC_DEST_ALLBUT 0xC0000 -#define APIC_ICR_RR_MASK 0x30000 -#define APIC_ICR_RR_INVALID 0x00000 -#define APIC_ICR_RR_INPROG 0x10000 -#define APIC_ICR_RR_VALID 0x20000 -#define APIC_INT_LEVELTRIG 0x08000 -#define APIC_INT_ASSERT 0x04000 -#define APIC_ICR_BUSY 0x01000 -#define APIC_DEST_LOGICAL 0x00800 -#define APIC_DEST_PHYSICAL 0x00000 -#define APIC_DM_FIXED 0x00000 -#define APIC_DM_FIXED_MASK 0x00700 -#define APIC_DM_LOWEST 0x00100 -#define APIC_DM_SMI 0x00200 -#define APIC_DM_REMRD 0x00300 -#define APIC_DM_NMI 0x00400 -#define APIC_DM_INIT 0x00500 -#define APIC_DM_STARTUP 0x00600 -#define APIC_DM_EXTINT 0x00700 -#define APIC_VECTOR_MASK 0x000FF -#define APIC_ICR2 0x310 -#define SET_APIC_DEST_FIELD(x) ((x) << 24) - /* VMX_EPT_VPID_CAP bits */ #define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21) diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index 65eb1079a161..583ceb0d1457 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -10,6 +10,7 @@ #include <stdint.h> #include "processor.h" +#include "apic.h" /* * Definitions of Primary Processor-Based VM-Execution Controls. @@ -607,15 +608,13 @@ bool nested_vmx_supported(void); void nested_vmx_check_supported(void); void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, - uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot); + uint64_t nested_paddr, uint64_t paddr); void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm, - uint64_t nested_paddr, uint64_t paddr, uint64_t size, - uint32_t eptp_memslot); + uint64_t nested_paddr, uint64_t paddr, uint64_t size); void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm, - uint32_t memslot, uint32_t eptp_memslot); + uint32_t memslot); void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, uint32_t eptp_memslot); -void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm, - uint32_t eptp_memslot); +void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm); #endif /* SELFTEST_KVM_VMX_H */ diff --git a/tools/testing/selftests/kvm/kvm_binary_stats_test.c b/tools/testing/selftests/kvm/kvm_binary_stats_test.c new file mode 100644 index 000000000000..5906bbc08483 --- /dev/null +++ b/tools/testing/selftests/kvm/kvm_binary_stats_test.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * kvm_binary_stats_test + * + * Copyright (C) 2021, Google LLC. + * + * Test the fd-based interface for KVM statistics. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "asm/kvm.h" +#include "linux/kvm.h" + +static void stats_test(int stats_fd) +{ + ssize_t ret; + int i; + size_t size_desc; + size_t size_data = 0; + struct kvm_stats_header *header; + char *id; + struct kvm_stats_desc *stats_desc; + u64 *stats_data; + struct kvm_stats_desc *pdesc; + + /* Read kvm stats header */ + header = malloc(sizeof(*header)); + TEST_ASSERT(header, "Allocate memory for stats header"); + + ret = read(stats_fd, header, sizeof(*header)); + TEST_ASSERT(ret == sizeof(*header), "Read stats header"); + size_desc = sizeof(*stats_desc) + header->name_size; + + /* Read kvm stats id string */ + id = malloc(header->name_size); + TEST_ASSERT(id, "Allocate memory for id string"); + ret = read(stats_fd, id, header->name_size); + TEST_ASSERT(ret == header->name_size, "Read id string"); + + /* Check id string, that should start with "kvm" */ + TEST_ASSERT(!strncmp(id, "kvm", 3) && strlen(id) < header->name_size, + "Invalid KVM stats type, id: %s", id); + + /* Sanity check for other fields in header */ + if (header->num_desc == 0) { + printf("No KVM stats defined!"); + return; + } + /* Check overlap */ + TEST_ASSERT(header->desc_offset > 0 && header->data_offset > 0 + && header->desc_offset >= sizeof(*header) + && header->data_offset >= sizeof(*header), + "Invalid offset fields in header"); + TEST_ASSERT(header->desc_offset > header->data_offset || + (header->desc_offset + size_desc * header->num_desc <= + header->data_offset), + "Descriptor block is overlapped with data block"); + + /* Allocate memory for stats descriptors */ + stats_desc = calloc(header->num_desc, size_desc); + TEST_ASSERT(stats_desc, "Allocate memory for stats descriptors"); + /* Read kvm stats descriptors */ + ret = pread(stats_fd, stats_desc, + size_desc * header->num_desc, header->desc_offset); + TEST_ASSERT(ret == size_desc * header->num_desc, + "Read KVM stats descriptors"); + + /* Sanity check for fields in descriptors */ + for (i = 0; i < header->num_desc; ++i) { + pdesc = (void *)stats_desc + i * size_desc; + /* Check type,unit,base boundaries */ + TEST_ASSERT((pdesc->flags & KVM_STATS_TYPE_MASK) + <= KVM_STATS_TYPE_MAX, "Unknown KVM stats type"); + TEST_ASSERT((pdesc->flags & KVM_STATS_UNIT_MASK) + <= KVM_STATS_UNIT_MAX, "Unknown KVM stats unit"); + TEST_ASSERT((pdesc->flags & KVM_STATS_BASE_MASK) + <= KVM_STATS_BASE_MAX, "Unknown KVM stats base"); + /* Check exponent for stats unit + * Exponent for counter should be greater than or equal to 0 + * Exponent for unit bytes should be greater than or equal to 0 + * Exponent for unit seconds should be less than or equal to 0 + * Exponent for unit clock cycles should be greater than or + * equal to 0 + */ + switch (pdesc->flags & KVM_STATS_UNIT_MASK) { + case KVM_STATS_UNIT_NONE: + case KVM_STATS_UNIT_BYTES: + case KVM_STATS_UNIT_CYCLES: + TEST_ASSERT(pdesc->exponent >= 0, + "Unsupported KVM stats unit"); + break; + case KVM_STATS_UNIT_SECONDS: + TEST_ASSERT(pdesc->exponent <= 0, + "Unsupported KVM stats unit"); + break; + } + /* Check name string */ + TEST_ASSERT(strlen(pdesc->name) < header->name_size, + "KVM stats name(%s) too long", pdesc->name); + /* Check size field, which should not be zero */ + TEST_ASSERT(pdesc->size, "KVM descriptor(%s) with size of 0", + pdesc->name); + size_data += pdesc->size * sizeof(*stats_data); + } + /* Check overlap */ + TEST_ASSERT(header->data_offset >= header->desc_offset + || header->data_offset + size_data <= header->desc_offset, + "Data block is overlapped with Descriptor block"); + /* Check validity of all stats data size */ + TEST_ASSERT(size_data >= header->num_desc * sizeof(*stats_data), + "Data size is not correct"); + /* Check stats offset */ + for (i = 0; i < header->num_desc; ++i) { + pdesc = (void *)stats_desc + i * size_desc; + TEST_ASSERT(pdesc->offset < size_data, + "Invalid offset (%u) for stats: %s", + pdesc->offset, pdesc->name); + } + + /* Allocate memory for stats data */ + stats_data = malloc(size_data); + TEST_ASSERT(stats_data, "Allocate memory for stats data"); + /* Read kvm stats data as a bulk */ + ret = pread(stats_fd, stats_data, size_data, header->data_offset); + TEST_ASSERT(ret == size_data, "Read KVM stats data"); + /* Read kvm stats data one by one */ + size_data = 0; + for (i = 0; i < header->num_desc; ++i) { + pdesc = (void *)stats_desc + i * size_desc; + ret = pread(stats_fd, stats_data, + pdesc->size * sizeof(*stats_data), + header->data_offset + size_data); + TEST_ASSERT(ret == pdesc->size * sizeof(*stats_data), + "Read data of KVM stats: %s", pdesc->name); + size_data += pdesc->size * sizeof(*stats_data); + } + + free(stats_data); + free(stats_desc); + free(id); + free(header); +} + + +static void vm_stats_test(struct kvm_vm *vm) +{ + int stats_fd; + + /* Get fd for VM stats */ + stats_fd = vm_get_stats_fd(vm); + TEST_ASSERT(stats_fd >= 0, "Get VM stats fd"); + + stats_test(stats_fd); + close(stats_fd); + TEST_ASSERT(fcntl(stats_fd, F_GETFD) == -1, "Stats fd not freed"); +} + +static void vcpu_stats_test(struct kvm_vm *vm, int vcpu_id) +{ + int stats_fd; + + /* Get fd for VCPU stats */ + stats_fd = vcpu_get_stats_fd(vm, vcpu_id); + TEST_ASSERT(stats_fd >= 0, "Get VCPU stats fd"); + + stats_test(stats_fd); + close(stats_fd); + TEST_ASSERT(fcntl(stats_fd, F_GETFD) == -1, "Stats fd not freed"); +} + +#define DEFAULT_NUM_VM 4 +#define DEFAULT_NUM_VCPU 4 + +/* + * Usage: kvm_bin_form_stats [#vm] [#vcpu] + * The first parameter #vm set the number of VMs being created. + * The second parameter #vcpu set the number of VCPUs being created. + * By default, DEFAULT_NUM_VM VM and DEFAULT_NUM_VCPU VCPU for the VM would be + * created for testing. + */ + +int main(int argc, char *argv[]) +{ + int i, j; + struct kvm_vm **vms; + int max_vm = DEFAULT_NUM_VM; + int max_vcpu = DEFAULT_NUM_VCPU; + + /* Get the number of VMs and VCPUs that would be created for testing. */ + if (argc > 1) { + max_vm = strtol(argv[1], NULL, 0); + if (max_vm <= 0) + max_vm = DEFAULT_NUM_VM; + } + if (argc > 2) { + max_vcpu = strtol(argv[2], NULL, 0); + if (max_vcpu <= 0) + max_vcpu = DEFAULT_NUM_VCPU; + } + + /* Check the extension for binary stats */ + if (kvm_check_cap(KVM_CAP_BINARY_STATS_FD) <= 0) { + print_skip("Binary form statistics interface is not supported"); + exit(KSFT_SKIP); + } + + /* Create VMs and VCPUs */ + vms = malloc(sizeof(vms[0]) * max_vm); + TEST_ASSERT(vms, "Allocate memory for storing VM pointers"); + for (i = 0; i < max_vm; ++i) { + vms[i] = vm_create(VM_MODE_DEFAULT, + DEFAULT_GUEST_PHY_PAGES, O_RDWR); + for (j = 0; j < max_vcpu; ++j) + vm_vcpu_add(vms[i], j); + } + + /* Check stats read for every VM and VCPU */ + for (i = 0; i < max_vm; ++i) { + vm_stats_test(vms[i]); + for (j = 0; j < max_vcpu; ++j) + vcpu_stats_test(vms[i], j); + } + + for (i = 0; i < max_vm; ++i) + kvm_vm_free(vms[i]); + free(vms); + return 0; +} diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 1c4753fff19e..0d04a7db7f24 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -268,7 +268,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) /* Create a VM with enough guest pages */ guest_num_pages = test_mem_size / guest_page_size; - vm = vm_create_with_vcpus(mode, nr_vcpus, + vm = vm_create_with_vcpus(mode, nr_vcpus, DEFAULT_GUEST_PHY_PAGES, guest_num_pages, 0, guest_code, NULL); /* Align down GPA of the testing memslot */ @@ -303,7 +303,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) TEST_MEM_SLOT_INDEX, guest_num_pages, 0); /* Do mapping(GVA->GPA) for the testing memory slot */ - virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages); /* Cache the HVA pointer of the region */ host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem); diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index cee92d477dc0..ad465ca16237 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -11,7 +11,6 @@ #include "../kvm_util_internal.h" #include "processor.h" -#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 #define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN 0xac0000 static uint64_t page_align(struct kvm_vm *vm, uint64_t v) @@ -72,19 +71,19 @@ static uint64_t __maybe_unused ptrs_per_pte(struct kvm_vm *vm) return 1 << (vm->page_shift - 3); } -void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot) +void virt_pgd_alloc(struct kvm_vm *vm) { if (!vm->pgd_created) { vm_paddr_t paddr = vm_phy_pages_alloc(vm, page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size, - KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot); + KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0); vm->pgd = paddr; vm->pgd_created = true; } } -void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - uint32_t pgd_memslot, uint64_t flags) +static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + uint64_t flags) { uint8_t attr_idx = flags & 7; uint64_t *ptep; @@ -104,25 +103,19 @@ void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, paddr, vm->max_gfn, vm->page_size); ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8; - if (!*ptep) { - *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot); - *ptep |= 3; - } + if (!*ptep) + *ptep = vm_alloc_page_table(vm) | 3; switch (vm->pgtable_levels) { case 4: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8; - if (!*ptep) { - *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot); - *ptep |= 3; - } + if (!*ptep) + *ptep = vm_alloc_page_table(vm) | 3; /* fall through */ case 3: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8; - if (!*ptep) { - *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot); - *ptep |= 3; - } + if (!*ptep) + *ptep = vm_alloc_page_table(vm) | 3; /* fall through */ case 2: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8; @@ -135,12 +128,11 @@ void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, *ptep |= (attr_idx << 2) | (1 << 10) /* Access Flag */; } -void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - uint32_t pgd_memslot) +void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) { uint64_t attr_idx = 4; /* NORMAL (See DEFAULT_MAIR_EL1) */ - _virt_pg_map(vm, vaddr, paddr, pgd_memslot, attr_idx); + _virt_pg_map(vm, vaddr, paddr, attr_idx); } vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) @@ -302,7 +294,7 @@ void aarch64_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, DEFAULT_STACK_PGS * vm->page_size : vm->page_size; uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size, - DEFAULT_ARM64_GUEST_STACK_VADDR_MIN, 0, 0); + DEFAULT_ARM64_GUEST_STACK_VADDR_MIN); vm_vcpu_add(vm, vcpuid); aarch64_vcpu_setup(vm, vcpuid, init); diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index 2f37b90ee1a9..e0b0164e9af8 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -14,7 +14,7 @@ static bool ucall_mmio_init(struct kvm_vm *vm, vm_paddr_t gpa) if (kvm_userspace_memory_region_find(vm, gpa, gpa + 1)) return false; - virt_pg_map(vm, gpa, gpa, 0); + virt_pg_map(vm, gpa, gpa); ucall_exit_mmio_addr = (vm_vaddr_t *)gpa; sync_global_to_guest(vm, ucall_exit_mmio_addr); diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c index bc75a91e00a6..eac44f5d0db0 100644 --- a/tools/testing/selftests/kvm/lib/elf.c +++ b/tools/testing/selftests/kvm/lib/elf.c @@ -111,8 +111,7 @@ static void elfhdr_get(const char *filename, Elf64_Ehdr *hdrp) * by the image and it needs to have sufficient available physical pages, to * back the virtual pages used to load the image. */ -void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename, - uint32_t data_memslot, uint32_t pgd_memslot) +void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename) { off_t offset, offset_rv; Elf64_Ehdr hdr; @@ -164,8 +163,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename, seg_vend |= vm->page_size - 1; size_t seg_size = seg_vend - seg_vstart + 1; - vm_vaddr_t vaddr = vm_vaddr_alloc(vm, seg_size, seg_vstart, - data_memslot, pgd_memslot); + vm_vaddr_t vaddr = vm_vaddr_alloc(vm, seg_size, seg_vstart); TEST_ASSERT(vaddr == seg_vstart, "Unable to allocate " "virtual memory for segment at requested min addr,\n" " segment idx: %u\n" diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index fc83f6c5902d..5b56b57b3c20 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -32,6 +32,34 @@ static void *align(void *x, size_t size) } /* + * Open KVM_DEV_PATH if available, otherwise exit the entire program. + * + * Input Args: + * flags - The flags to pass when opening KVM_DEV_PATH. + * + * Return: + * The opened file descriptor of /dev/kvm. + */ +static int _open_kvm_dev_path_or_exit(int flags) +{ + int fd; + + fd = open(KVM_DEV_PATH, flags); + if (fd < 0) { + print_skip("%s not available, is KVM loaded? (errno: %d)", + KVM_DEV_PATH, errno); + exit(KSFT_SKIP); + } + + return fd; +} + +int open_kvm_dev_path_or_exit(void) +{ + return _open_kvm_dev_path_or_exit(O_RDONLY); +} + +/* * Capability * * Input Args: @@ -52,12 +80,9 @@ int kvm_check_cap(long cap) int ret; int kvm_fd; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); - + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); - TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n" + TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n" " rc: %i errno: %i", ret, errno); close(kvm_fd); @@ -128,9 +153,7 @@ void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size) static void vm_open(struct kvm_vm *vm, int perm) { - vm->kvm_fd = open(KVM_DEV_PATH, perm); - if (vm->kvm_fd < 0) - exit(KSFT_SKIP); + vm->kvm_fd = _open_kvm_dev_path_or_exit(perm); if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { print_skip("immediate_exit not available"); @@ -152,6 +175,7 @@ const char *vm_guest_mode_string(uint32_t i) [VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages", [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages", [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages", + [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages", }; _Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES, "Missing new mode strings?"); @@ -169,6 +193,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { { 40, 48, 0x1000, 12 }, { 40, 48, 0x10000, 16 }, { 0, 0, 0x1000, 12 }, + { 47, 64, 0x1000, 12 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); @@ -203,7 +228,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_ASSERT(vm != NULL, "Insufficient Memory"); INIT_LIST_HEAD(&vm->vcpus); - INIT_LIST_HEAD(&vm->userspace_mem_regions); + vm->regions.gpa_tree = RB_ROOT; + vm->regions.hva_tree = RB_ROOT; + hash_init(vm->regions.slot_hash); vm->mode = mode; vm->type = 0; @@ -252,6 +279,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms"); #endif break; + case VM_MODE_P47V64_4K: + vm->pgtable_levels = 5; + break; default: TEST_FAIL("Unknown guest mode, mode: 0x%x", mode); } @@ -283,21 +313,50 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } +/* + * VM Create with customized parameters + * + * Input Args: + * mode - VM Mode (e.g. VM_MODE_P52V48_4K) + * nr_vcpus - VCPU count + * slot0_mem_pages - Slot0 physical memory size + * extra_mem_pages - Non-slot0 physical memory total size + * num_percpu_pages - Per-cpu physical memory pages + * guest_code - Guest entry point + * vcpuids - VCPU IDs + * + * Output Args: None + * + * Return: + * Pointer to opaque structure that describes the created VM. + * + * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K), + * with customized slot0 memory size, at least 512 pages currently. + * extra_mem_pages is only used to calculate the maximum page table size, + * no real memory allocation for non-slot0 memory in this function. + */ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t extra_mem_pages, uint32_t num_percpu_pages, - void *guest_code, uint32_t vcpuids[]) + uint64_t slot0_mem_pages, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]) { + uint64_t vcpu_pages, extra_pg_pages, pages; + struct kvm_vm *vm; + int i; + + /* Force slot0 memory size not small than DEFAULT_GUEST_PHY_PAGES */ + if (slot0_mem_pages < DEFAULT_GUEST_PHY_PAGES) + slot0_mem_pages = DEFAULT_GUEST_PHY_PAGES; + /* The maximum page table size for a memory region will be when the * smallest pages are used. Considering each page contains x page * table descriptors, the total extra size for page tables (for extra * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller * than N/x*2. */ - uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; - uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages; - struct kvm_vm *vm; - int i; + vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; + extra_pg_pages = (slot0_mem_pages + extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; + pages = slot0_mem_pages + vcpu_pages + extra_pg_pages; TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS), "nr_vcpus = %d too large for host, max-vcpus = %d", @@ -306,7 +365,7 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, pages = vm_adjust_num_guest_pages(mode, pages); vm = vm_create(mode, pages, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); + kvm_vm_elf_load(vm, program_invocation_name); #ifdef __x86_64__ vm_create_irqchip(vm); @@ -316,10 +375,6 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, uint32_t vcpuid = vcpuids ? vcpuids[i] : i; vm_vcpu_add_default(vm, vcpuid, guest_code); - -#ifdef __x86_64__ - vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid()); -#endif } return vm; @@ -329,8 +384,8 @@ struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_me uint32_t num_percpu_pages, void *guest_code, uint32_t vcpuids[]) { - return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, extra_mem_pages, - num_percpu_pages, guest_code, vcpuids); + return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, DEFAULT_GUEST_PHY_PAGES, + extra_mem_pages, num_percpu_pages, guest_code, vcpuids); } struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, @@ -355,13 +410,14 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, */ void kvm_vm_restart(struct kvm_vm *vmp, int perm) { + int ctr; struct userspace_mem_region *region; vm_open(vmp, perm); if (vmp->has_irqchip) vm_create_irqchip(vmp); - list_for_each_entry(region, &vmp->userspace_mem_regions, list) { + hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) { int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" @@ -424,14 +480,21 @@ uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) static struct userspace_mem_region * userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + for (node = vm->regions.gpa_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, gpa_node); uint64_t existing_start = region->region.guest_phys_addr; uint64_t existing_end = region->region.guest_phys_addr + region->region.memory_size - 1; if (start <= existing_end && end >= existing_start) return region; + + if (start < existing_start) + node = node->rb_left; + else + node = node->rb_right; } return NULL; @@ -546,11 +609,16 @@ void kvm_vm_release(struct kvm_vm *vmp) } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region) + struct userspace_mem_region *region, + bool unlink) { int ret; - list_del(®ion->list); + if (unlink) { + rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); + rb_erase(®ion->hva_node, &vm->regions.hva_tree); + hash_del(®ion->slot_node); + } region->region.memory_size = 0; ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); @@ -569,14 +637,16 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, */ void kvm_vm_free(struct kvm_vm *vmp) { - struct userspace_mem_region *region, *tmp; + int ctr; + struct hlist_node *node; + struct userspace_mem_region *region; if (vmp == NULL) return; /* Free userspace_mem_regions. */ - list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list) - __vm_mem_region_delete(vmp, region); + hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) + __vm_mem_region_delete(vmp, region, false); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -658,13 +728,64 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) return 0; } +static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &gpa_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), gpa_node); + parent = *cur; + if (region->region.guest_phys_addr < + cregion->region.guest_phys_addr) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->region.guest_phys_addr != + cregion->region.guest_phys_addr, + "Duplicate GPA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(®ion->gpa_node, parent, cur); + rb_insert_color(®ion->gpa_node, gpa_tree); +} + +static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &hva_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), hva_node); + parent = *cur; + if (region->host_mem < cregion->host_mem) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->host_mem != + cregion->host_mem, + "Duplicate HVA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(®ion->hva_node, parent, cur); + rb_insert_color(®ion->hva_node, hva_tree); +} + /* * VM Userspace Memory Region Add * * Input Args: * vm - Virtual Machine - * backing_src - Storage source for this region. - * NULL to use anonymous memory. + * src_type - Storage source for this region. + * NULL to use anonymous memory. * guest_paddr - Starting guest physical address * slot - KVM region slot * npages - Number of physical pages @@ -722,7 +843,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, (uint64_t) region->region.memory_size); /* Confirm no region with the requested slot already exists. */ - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + slot) { if (region->region.slot != slot) continue; @@ -755,11 +877,30 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, if (alignment > 1) region->mmap_size += alignment; + region->fd = -1; + if (backing_src_is_shared(src_type)) { + int memfd_flags = MFD_CLOEXEC; + + if (src_type == VM_MEM_SRC_SHARED_HUGETLB) + memfd_flags |= MFD_HUGETLB; + + region->fd = memfd_create("kvm_selftest", memfd_flags); + TEST_ASSERT(region->fd != -1, + "memfd_create failed, errno: %i", errno); + + ret = ftruncate(region->fd, region->mmap_size); + TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno); + + ret = fallocate(region->fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, + region->mmap_size); + TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno); + } + region->mmap_start = mmap(NULL, region->mmap_size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS - | vm_mem_backing_src_alias(src_type)->flag, - -1, 0); + vm_mem_backing_src_alias(src_type)->flag, + region->fd, 0); TEST_ASSERT(region->mmap_start != MAP_FAILED, "test_malloc failed, mmap_start: %p errno: %i", region->mmap_start, errno); @@ -793,8 +934,23 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, ret, errno, slot, flags, guest_paddr, (uint64_t) region->region.memory_size); - /* Add to linked-list of memory regions. */ - list_add(®ion->list, &vm->userspace_mem_regions); + /* Add to quick lookup data structures */ + vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); + vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region); + hash_add(vm->regions.slot_hash, ®ion->slot_node, slot); + + /* If shared memory, create an alias. */ + if (region->fd >= 0) { + region->mmap_alias = mmap(NULL, region->mmap_size, + PROT_READ | PROT_WRITE, + vm_mem_backing_src_alias(src_type)->flag, + region->fd, 0); + TEST_ASSERT(region->mmap_alias != MAP_FAILED, + "mmap of alias failed, errno: %i", errno); + + /* Align host alias address */ + region->host_alias = align(region->mmap_alias, alignment); + } } /* @@ -817,10 +973,10 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + memslot) if (region->region.slot == memslot) return region; - } fprintf(stderr, "No mem region with the requested slot found,\n" " requested slot: %u\n", memslot); @@ -905,7 +1061,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) */ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) { - __vm_mem_region_delete(vm, memslot2region(vm, slot)); + __vm_mem_region_delete(vm, memslot2region(vm, slot), true); } /* @@ -925,9 +1081,7 @@ static int vcpu_mmap_sz(void) { int dev_fd, ret; - dev_fd = open(KVM_DEV_PATH, O_RDONLY); - if (dev_fd < 0) - exit(KSFT_SKIP); + dev_fd = open_kvm_dev_path_or_exit(); ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); TEST_ASSERT(ret >= sizeof(struct kvm_run), @@ -1093,12 +1247,13 @@ va_found: * a unique set of pages, with the minimum real allocation being at least * a page. */ -vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, - uint32_t data_memslot, uint32_t pgd_memslot) +vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min) { uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); - virt_pgd_alloc(vm, pgd_memslot); + virt_pgd_alloc(vm); + vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages, + KVM_UTIL_MIN_PFN * vm->page_size, 0); /* * Find an unused range of virtual page addresses of at least @@ -1108,13 +1263,9 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, /* Map the virtual pages. */ for (vm_vaddr_t vaddr = vaddr_start; pages > 0; - pages--, vaddr += vm->page_size) { - vm_paddr_t paddr; - - paddr = vm_phy_page_alloc(vm, - KVM_UTIL_MIN_PFN * vm->page_size, data_memslot); + pages--, vaddr += vm->page_size, paddr += vm->page_size) { - virt_pg_map(vm, vaddr, paddr, pgd_memslot); + virt_pg_map(vm, vaddr, paddr); sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift); @@ -1124,6 +1275,44 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, } /* + * VM Virtual Address Allocate Pages + * + * Input Args: + * vm - Virtual Machine + * + * Output Args: None + * + * Return: + * Starting guest virtual address + * + * Allocates at least N system pages worth of bytes within the virtual address + * space of the vm. + */ +vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages) +{ + return vm_vaddr_alloc(vm, nr_pages * getpagesize(), KVM_UTIL_MIN_VADDR); +} + +/* + * VM Virtual Address Allocate Page + * + * Input Args: + * vm - Virtual Machine + * + * Output Args: None + * + * Return: + * Starting guest virtual address + * + * Allocates at least one system page worth of bytes within the virtual address + * space of the vm. + */ +vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm) +{ + return vm_vaddr_alloc_pages(vm, 1); +} + +/* * Map a range of VM virtual address to the VM's physical address * * Input Args: @@ -1141,7 +1330,7 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, * @npages starting at @vaddr to the page range starting at @paddr. */ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - unsigned int npages, uint32_t pgd_memslot) + unsigned int npages) { size_t page_size = vm->page_size; size_t size = npages * page_size; @@ -1150,7 +1339,7 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, TEST_ASSERT(paddr + size > paddr, "Paddr overflow"); while (npages--) { - virt_pg_map(vm, vaddr, paddr, pgd_memslot); + virt_pg_map(vm, vaddr, paddr); vaddr += page_size; paddr += page_size; } @@ -1177,16 +1366,14 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((gpa >= region->region.guest_phys_addr) - && (gpa <= (region->region.guest_phys_addr - + region->region.memory_size - 1))) - return (void *) ((uintptr_t) region->host_mem - + (gpa - region->region.guest_phys_addr)); + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) { + TEST_FAIL("No vm physical memory at 0x%lx", gpa); + return NULL; } - TEST_FAIL("No vm physical memory at 0x%lx", gpa); - return NULL; + return (void *)((uintptr_t)region->host_mem + + (gpa - region->region.guest_phys_addr)); } /* @@ -1208,15 +1395,22 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) */ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) { - struct userspace_mem_region *region; + struct rb_node *node; + + for (node = vm->regions.hva_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, hva_node); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((hva >= region->host_mem) - && (hva <= (region->host_mem - + region->region.memory_size - 1))) - return (vm_paddr_t) ((uintptr_t) - region->region.guest_phys_addr - + (hva - (uintptr_t) region->host_mem)); + if (hva >= region->host_mem) { + if (hva <= (region->host_mem + + region->region.memory_size - 1)) + return (vm_paddr_t)((uintptr_t) + region->region.guest_phys_addr + + (hva - (uintptr_t)region->host_mem)); + + node = node->rb_right; + } else + node = node->rb_left; } TEST_FAIL("No mapping to a guest physical address, hva: %p", hva); @@ -1224,6 +1418,42 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) } /* + * Address VM physical to Host Virtual *alias*. + * + * Input Args: + * vm - Virtual Machine + * gpa - VM physical address + * + * Output Args: None + * + * Return: + * Equivalent address within the host virtual *alias* area, or NULL + * (without failing the test) if the guest memory is not shared (so + * no alias exists). + * + * When vm_create() and related functions are called with a shared memory + * src_type, we also create a writable, shared alias mapping of the + * underlying guest memory. This allows the host to manipulate guest memory + * without mapping that memory in the guest's address space. And, for + * userfaultfd-based demand paging, we can do so without triggering userfaults. + */ +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) +{ + struct userspace_mem_region *region; + uintptr_t offset; + + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) + return NULL; + + if (!region->host_alias) + return NULL; + + offset = gpa - region->region.guest_phys_addr; + return (void *) ((uintptr_t) region->host_alias + offset); +} + +/* * VM Create IRQ Chip * * Input Args: @@ -1822,6 +2052,7 @@ int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, */ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { + int ctr; struct userspace_mem_region *region; struct vcpu *vcpu; @@ -1829,7 +2060,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd); fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size); fprintf(stream, "%*sMem Regions:\n", indent, ""); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) { fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx " "host_virt: %p\n", indent + 2, "", (uint64_t) region->region.guest_phys_addr, @@ -1978,6 +2209,14 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, return vm_phy_pages_alloc(vm, 1, paddr_min, memslot); } +/* Arbitrary minimum physical address used for virtual translation tables. */ +#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 + +vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm) +{ + return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0); +} + /* * Address Guest Virtual to Host Virtual * @@ -2015,10 +2254,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm) if (vm == NULL) { /* Ensure that the KVM vendor-specific module is loaded. */ - f = fopen(KVM_DEV_PATH, "r"); - TEST_ASSERT(f != NULL, "Error in opening KVM dev file: %d", - errno); - fclose(f); + close(open_kvm_dev_path_or_exit()); } f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r"); @@ -2041,7 +2277,7 @@ unsigned int vm_get_page_shift(struct kvm_vm *vm) return vm->page_shift; } -unsigned int vm_get_max_gfn(struct kvm_vm *vm) +uint64_t vm_get_max_gfn(struct kvm_vm *vm) { return vm->max_gfn; } @@ -2090,3 +2326,15 @@ unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size) n = DIV_ROUND_UP(size, vm_guest_mode_params[mode].page_size); return vm_adjust_num_guest_pages(mode, n); } + +int vm_get_stats_fd(struct kvm_vm *vm) +{ + return ioctl(vm->fd, KVM_GET_STATS_FD, NULL); +} + +int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + + return ioctl(vcpu->fd, KVM_GET_STATS_FD, NULL); +} diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 91ce1b5d480b..a03febc24ba6 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -8,6 +8,9 @@ #ifndef SELFTEST_KVM_UTIL_INTERNAL_H #define SELFTEST_KVM_UTIL_INTERNAL_H +#include "linux/hashtable.h" +#include "linux/rbtree.h" + #include "sparsebit.h" struct userspace_mem_region { @@ -16,9 +19,13 @@ struct userspace_mem_region { int fd; off_t offset; void *host_mem; + void *host_alias; void *mmap_start; + void *mmap_alias; size_t mmap_size; - struct list_head list; + struct rb_node gpa_node; + struct rb_node hva_node; + struct hlist_node slot_node; }; struct vcpu { @@ -31,6 +38,12 @@ struct vcpu { uint32_t dirty_gfns_count; }; +struct userspace_mem_regions { + struct rb_root gpa_tree; + struct rb_root hva_tree; + DECLARE_HASHTABLE(slot_hash, 9); +}; + struct kvm_vm { int mode; unsigned long type; @@ -43,7 +56,7 @@ struct kvm_vm { unsigned int va_bits; uint64_t max_gfn; struct list_head vcpus; - struct list_head userspace_mem_regions; + struct userspace_mem_regions regions; struct sparsebit *vpages_valid; struct sparsebit *vpages_mapped; bool has_irqchip; diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c index 81490b9b4e32..b488f4aefea8 100644 --- a/tools/testing/selftests/kvm/lib/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/perf_test_util.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2020, Google LLC. */ +#include <inttypes.h> #include "kvm_util.h" #include "perf_test_util.h" @@ -68,7 +69,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, "Guest memory size is not guest page size aligned."); - vm = vm_create_with_vcpus(mode, vcpus, + vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES, (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size, 0, guest_code, NULL); @@ -80,7 +81,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, */ TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), "Requested more guest memory than address space allows.\n" - " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", + " guest pages: %" PRIx64 " max gfn: %" PRIx64 + " vcpus: %d wss: %" PRIx64 "]\n", guest_num_pages, vm_get_max_gfn(vm), vcpus, vcpu_memory_bytes); @@ -99,7 +101,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, guest_num_pages, 0); /* Do mapping for the demand paging memory slot */ - virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages); ucall_init(vm, NULL); diff --git a/tools/testing/selftests/kvm/lib/rbtree.c b/tools/testing/selftests/kvm/lib/rbtree.c new file mode 100644 index 000000000000..a703f0194ea3 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/rbtree.c @@ -0,0 +1 @@ +#include "../../../../lib/rbtree.c" diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index 0152f356c099..f87c7137598e 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -9,11 +9,9 @@ #include "kvm_util.h" #include "../kvm_util_internal.h" -#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 - #define PAGES_PER_REGION 4 -void virt_pgd_alloc(struct kvm_vm *vm, uint32_t memslot) +void virt_pgd_alloc(struct kvm_vm *vm) { vm_paddr_t paddr; @@ -24,7 +22,7 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t memslot) return; paddr = vm_phy_pages_alloc(vm, PAGES_PER_REGION, - KVM_GUEST_PAGE_TABLE_MIN_PADDR, memslot); + KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0); memset(addr_gpa2hva(vm, paddr), 0xff, PAGES_PER_REGION * vm->page_size); vm->pgd = paddr; @@ -36,12 +34,12 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t memslot) * a page table (ri == 4). Returns a suitable region/segment table entry * which points to the freshly allocated pages. */ -static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri, uint32_t memslot) +static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri) { uint64_t taddr; taddr = vm_phy_pages_alloc(vm, ri < 4 ? PAGES_PER_REGION : 1, - KVM_GUEST_PAGE_TABLE_MIN_PADDR, memslot); + KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0); memset(addr_gpa2hva(vm, taddr), 0xff, PAGES_PER_REGION * vm->page_size); return (taddr & REGION_ENTRY_ORIGIN) @@ -49,8 +47,7 @@ static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri, uint32_t memslot) | ((ri < 4 ? (PAGES_PER_REGION - 1) : 0) & REGION_ENTRY_LENGTH); } -void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa, - uint32_t memslot) +void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa) { int ri, idx; uint64_t *entry; @@ -77,7 +74,7 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa, for (ri = 1; ri <= 4; ri++) { idx = (gva >> (64 - 11 * ri)) & 0x7ffu; if (entry[idx] & REGION_ENTRY_INVALID) - entry[idx] = virt_alloc_region(vm, ri, memslot); + entry[idx] = virt_alloc_region(vm, ri); entry = addr_gpa2hva(vm, entry[idx] & REGION_ENTRY_ORIGIN); } @@ -170,7 +167,7 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) vm->page_size); stack_vaddr = vm_vaddr_alloc(vm, stack_size, - DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0); + DEFAULT_GUEST_STACK_VADDR_MIN); vm_vcpu_add(vm, vcpuid); diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 63d2bc7d757b..af1031fed97f 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -166,72 +166,89 @@ size_t get_def_hugetlb_pagesz(void) return 0; } +#define ANON_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS) +#define ANON_HUGE_FLAGS (ANON_FLAGS | MAP_HUGETLB) + const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i) { static const struct vm_mem_backing_src_alias aliases[] = { [VM_MEM_SRC_ANONYMOUS] = { .name = "anonymous", - .flag = 0, + .flag = ANON_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_THP] = { .name = "anonymous_thp", - .flag = 0, + .flag = ANON_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB] = { .name = "anonymous_hugetlb", - .flag = MAP_HUGETLB, + .flag = ANON_HUGE_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB] = { .name = "anonymous_hugetlb_16kb", - .flag = MAP_HUGETLB | MAP_HUGE_16KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB] = { .name = "anonymous_hugetlb_64kb", - .flag = MAP_HUGETLB | MAP_HUGE_64KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_64KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB] = { .name = "anonymous_hugetlb_512kb", - .flag = MAP_HUGETLB | MAP_HUGE_512KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_512KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB] = { .name = "anonymous_hugetlb_1mb", - .flag = MAP_HUGETLB | MAP_HUGE_1MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_1MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB] = { .name = "anonymous_hugetlb_2mb", - .flag = MAP_HUGETLB | MAP_HUGE_2MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_2MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB] = { .name = "anonymous_hugetlb_8mb", - .flag = MAP_HUGETLB | MAP_HUGE_8MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_8MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB] = { .name = "anonymous_hugetlb_16mb", - .flag = MAP_HUGETLB | MAP_HUGE_16MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB] = { .name = "anonymous_hugetlb_32mb", - .flag = MAP_HUGETLB | MAP_HUGE_32MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_32MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB] = { .name = "anonymous_hugetlb_256mb", - .flag = MAP_HUGETLB | MAP_HUGE_256MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_256MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB] = { .name = "anonymous_hugetlb_512mb", - .flag = MAP_HUGETLB | MAP_HUGE_512MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_512MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB] = { .name = "anonymous_hugetlb_1gb", - .flag = MAP_HUGETLB | MAP_HUGE_1GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_1GB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB] = { .name = "anonymous_hugetlb_2gb", - .flag = MAP_HUGETLB | MAP_HUGE_2GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_2GB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB] = { .name = "anonymous_hugetlb_16gb", - .flag = MAP_HUGETLB | MAP_HUGE_16GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16GB, + }, + [VM_MEM_SRC_SHMEM] = { + .name = "shmem", + .flag = MAP_SHARED, + }, + [VM_MEM_SRC_SHARED_HUGETLB] = { + .name = "shared_hugetlb", + /* + * No MAP_HUGETLB, we use MFD_HUGETLB instead. Since + * we're using "file backed" memory, we need to specify + * this when the FD is created, not when the area is + * mapped. + */ + .flag = MAP_SHARED, }, }; _Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES, @@ -250,10 +267,12 @@ size_t get_backing_src_pagesz(uint32_t i) switch (i) { case VM_MEM_SRC_ANONYMOUS: + case VM_MEM_SRC_SHMEM: return getpagesize(); case VM_MEM_SRC_ANONYMOUS_THP: return get_trans_hugepagesz(); case VM_MEM_SRC_ANONYMOUS_HUGETLB: + case VM_MEM_SRC_SHARED_HUGETLB: return get_def_hugetlb_pagesz(); default: return MAP_HUGE_PAGE_SIZE(flag); diff --git a/tools/testing/selftests/kvm/lib/x86_64/apic.c b/tools/testing/selftests/kvm/lib/x86_64/apic.c new file mode 100644 index 000000000000..7168e25c194e --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/apic.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * tools/testing/selftests/kvm/lib/x86_64/processor.c + * + * Copyright (C) 2021, Google LLC. + */ + +#include "apic.h" + +void apic_disable(void) +{ + wrmsr(MSR_IA32_APICBASE, + rdmsr(MSR_IA32_APICBASE) & + ~(MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD)); +} + +void xapic_enable(void) +{ + uint64_t val = rdmsr(MSR_IA32_APICBASE); + + /* Per SDM: to enable xAPIC when in x2APIC must first disable APIC */ + if (val & MSR_IA32_APICBASE_EXTD) { + apic_disable(); + wrmsr(MSR_IA32_APICBASE, + rdmsr(MSR_IA32_APICBASE) | MSR_IA32_APICBASE_ENABLE); + } else if (!(val & MSR_IA32_APICBASE_ENABLE)) { + wrmsr(MSR_IA32_APICBASE, val | MSR_IA32_APICBASE_ENABLE); + } + + /* + * Per SDM: reset value of spurious interrupt vector register has the + * APIC software enabled bit=0. It must be enabled in addition to the + * enable bit in the MSR. + */ + val = xapic_read_reg(APIC_SPIV) | APIC_SPIV_APIC_ENABLED; + xapic_write_reg(APIC_SPIV, val); +} + +void x2apic_enable(void) +{ + wrmsr(MSR_IA32_APICBASE, rdmsr(MSR_IA32_APICBASE) | + MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD); + x2apic_write_reg(APIC_SPIV, + x2apic_read_reg(APIC_SPIV) | APIC_SPIV_APIC_ENABLED); +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S index aaf7bc7d2ce1..7629819734af 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/handlers.S +++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S @@ -54,9 +54,9 @@ idt_handlers: .align 8 /* Fetch current address and append it to idt_handlers. */ - current_handler = . +666 : .pushsection .rodata -.quad current_handler + .quad 666b .popsection .if ! \has_error diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index a8906e60a108..3114b18454d5 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -17,43 +17,10 @@ #define DEFAULT_CODE_SELECTOR 0x8 #define DEFAULT_DATA_SELECTOR 0x10 -/* Minimum physical address used for virtual translation tables. */ -#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 - vm_vaddr_t exception_handlers; /* Virtual translation table structure declarations */ -struct pageMapL4Entry { - uint64_t present:1; - uint64_t writable:1; - uint64_t user:1; - uint64_t write_through:1; - uint64_t cache_disable:1; - uint64_t accessed:1; - uint64_t ignored_06:1; - uint64_t page_size:1; - uint64_t ignored_11_08:4; - uint64_t address:40; - uint64_t ignored_62_52:11; - uint64_t execute_disable:1; -}; - -struct pageDirectoryPointerEntry { - uint64_t present:1; - uint64_t writable:1; - uint64_t user:1; - uint64_t write_through:1; - uint64_t cache_disable:1; - uint64_t accessed:1; - uint64_t ignored_06:1; - uint64_t page_size:1; - uint64_t ignored_11_08:4; - uint64_t address:40; - uint64_t ignored_62_52:11; - uint64_t execute_disable:1; -}; - -struct pageDirectoryEntry { +struct pageUpperEntry { uint64_t present:1; uint64_t writable:1; uint64_t user:1; @@ -63,7 +30,7 @@ struct pageDirectoryEntry { uint64_t ignored_06:1; uint64_t page_size:1; uint64_t ignored_11_08:4; - uint64_t address:40; + uint64_t pfn:40; uint64_t ignored_62_52:11; uint64_t execute_disable:1; }; @@ -79,7 +46,7 @@ struct pageTableEntry { uint64_t reserved_07:1; uint64_t global:1; uint64_t ignored_11_09:3; - uint64_t address:40; + uint64_t pfn:40; uint64_t ignored_62_52:11; uint64_t execute_disable:1; }; @@ -207,96 +174,211 @@ void sregs_dump(FILE *stream, struct kvm_sregs *sregs, } } -void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot) +void virt_pgd_alloc(struct kvm_vm *vm) { TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); /* If needed, create page map l4 table. */ if (!vm->pgd_created) { - vm_paddr_t paddr = vm_phy_page_alloc(vm, - KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot); - vm->pgd = paddr; + vm->pgd = vm_alloc_page_table(vm); vm->pgd_created = true; } } -void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - uint32_t pgd_memslot) +static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr, + int level) +{ + uint64_t *page_table = addr_gpa2hva(vm, pt_pfn << vm->page_shift); + int index = vaddr >> (vm->page_shift + level * 9) & 0x1ffu; + + return &page_table[index]; +} + +static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm, + uint64_t pt_pfn, + uint64_t vaddr, + uint64_t paddr, + int level, + enum x86_page_size page_size) +{ + struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, level); + + if (!pte->present) { + pte->writable = true; + pte->present = true; + pte->page_size = (level == page_size); + if (pte->page_size) + pte->pfn = paddr >> vm->page_shift; + else + pte->pfn = vm_alloc_page_table(vm) >> vm->page_shift; + } else { + /* + * Entry already present. Assert that the caller doesn't want + * a hugepage at this level, and that there isn't a hugepage at + * this level. + */ + TEST_ASSERT(level != page_size, + "Cannot create hugepage at level: %u, vaddr: 0x%lx\n", + page_size, vaddr); + TEST_ASSERT(!pte->page_size, + "Cannot create page table at level: %u, vaddr: 0x%lx\n", + level, vaddr); + } + return pte; +} + +void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + enum x86_page_size page_size) +{ + const uint64_t pg_size = 1ull << ((page_size * 9) + 12); + struct pageUpperEntry *pml4e, *pdpe, *pde; + struct pageTableEntry *pte; + + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, + "Unknown or unsupported guest mode, mode: 0x%x", vm->mode); + + TEST_ASSERT((vaddr % pg_size) == 0, + "Virtual address not aligned,\n" + "vaddr: 0x%lx page size: 0x%lx", vaddr, pg_size); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, (vaddr >> vm->page_shift)), + "Invalid virtual address, vaddr: 0x%lx", vaddr); + TEST_ASSERT((paddr % pg_size) == 0, + "Physical address not aligned,\n" + " paddr: 0x%lx page size: 0x%lx", paddr, pg_size); + TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, + "Physical address beyond maximum supported,\n" + " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + paddr, vm->max_gfn, vm->page_size); + + /* + * Allocate upper level page tables, if not already present. Return + * early if a hugepage was created. + */ + pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift, + vaddr, paddr, 3, page_size); + if (pml4e->page_size) + return; + + pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, 2, page_size); + if (pdpe->page_size) + return; + + pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, 1, page_size); + if (pde->page_size) + return; + + /* Fill in page table entry. */ + pte = virt_get_pte(vm, pde->pfn, vaddr, 0); + TEST_ASSERT(!pte->present, + "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr); + pte->pfn = paddr >> vm->page_shift; + pte->writable = true; + pte->present = 1; +} + +void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +{ + __virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K); +} + +static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, + uint64_t vaddr) { uint16_t index[4]; - struct pageMapL4Entry *pml4e; + struct pageUpperEntry *pml4e, *pdpe, *pde; + struct pageTableEntry *pte; + struct kvm_cpuid_entry2 *entry; + struct kvm_sregs sregs; + int max_phy_addr; + /* Set the bottom 52 bits. */ + uint64_t rsvd_mask = 0x000fffffffffffff; + + entry = kvm_get_supported_cpuid_index(0x80000008, 0); + max_phy_addr = entry->eax & 0x000000ff; + /* Clear the bottom bits of the reserved mask. */ + rsvd_mask = (rsvd_mask >> max_phy_addr) << max_phy_addr; + + /* + * SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries + * with 4-Level Paging and 5-Level Paging". + * If IA32_EFER.NXE = 0 and the P flag of a paging-structure entry is 1, + * the XD flag (bit 63) is reserved. + */ + vcpu_sregs_get(vm, vcpuid, &sregs); + if ((sregs.efer & EFER_NX) == 0) { + rsvd_mask |= (1ull << 63); + } TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); - - TEST_ASSERT((vaddr % vm->page_size) == 0, - "Virtual address not on page boundary,\n" - " vaddr: 0x%lx vm->page_size: 0x%x", - vaddr, vm->page_size); TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, (vaddr >> vm->page_shift)), "Invalid virtual address, vaddr: 0x%lx", vaddr); - TEST_ASSERT((paddr % vm->page_size) == 0, - "Physical address not on page boundary,\n" - " paddr: 0x%lx vm->page_size: 0x%x", - paddr, vm->page_size); - TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, - "Physical address beyond beyond maximum supported,\n" - " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", - paddr, vm->max_gfn, vm->page_size); + /* + * Based on the mode check above there are 48 bits in the vaddr, so + * shift 16 to sign extend the last bit (bit-47), + */ + TEST_ASSERT(vaddr == (((int64_t)vaddr << 16) >> 16), + "Canonical check failed. The virtual address is invalid."); index[0] = (vaddr >> 12) & 0x1ffu; index[1] = (vaddr >> 21) & 0x1ffu; index[2] = (vaddr >> 30) & 0x1ffu; index[3] = (vaddr >> 39) & 0x1ffu; - /* Allocate page directory pointer table if not present. */ pml4e = addr_gpa2hva(vm, vm->pgd); - if (!pml4e[index[3]].present) { - pml4e[index[3]].address = vm_phy_page_alloc(vm, - KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot) - >> vm->page_shift; - pml4e[index[3]].writable = true; - pml4e[index[3]].present = true; - } + TEST_ASSERT(pml4e[index[3]].present, + "Expected pml4e to be present for gva: 0x%08lx", vaddr); + TEST_ASSERT((*(uint64_t*)(&pml4e[index[3]]) & + (rsvd_mask | (1ull << 7))) == 0, + "Unexpected reserved bits set."); + + pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size); + TEST_ASSERT(pdpe[index[2]].present, + "Expected pdpe to be present for gva: 0x%08lx", vaddr); + TEST_ASSERT(pdpe[index[2]].page_size == 0, + "Expected pdpe to map a pde not a 1-GByte page."); + TEST_ASSERT((*(uint64_t*)(&pdpe[index[2]]) & rsvd_mask) == 0, + "Unexpected reserved bits set."); + + pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size); + TEST_ASSERT(pde[index[1]].present, + "Expected pde to be present for gva: 0x%08lx", vaddr); + TEST_ASSERT(pde[index[1]].page_size == 0, + "Expected pde to map a pte not a 2-MByte page."); + TEST_ASSERT((*(uint64_t*)(&pde[index[1]]) & rsvd_mask) == 0, + "Unexpected reserved bits set."); + + pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size); + TEST_ASSERT(pte[index[0]].present, + "Expected pte to be present for gva: 0x%08lx", vaddr); + + return &pte[index[0]]; +} - /* Allocate page directory table if not present. */ - struct pageDirectoryPointerEntry *pdpe; - pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size); - if (!pdpe[index[2]].present) { - pdpe[index[2]].address = vm_phy_page_alloc(vm, - KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot) - >> vm->page_shift; - pdpe[index[2]].writable = true; - pdpe[index[2]].present = true; - } +uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr) +{ + struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); - /* Allocate page table if not present. */ - struct pageDirectoryEntry *pde; - pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size); - if (!pde[index[1]].present) { - pde[index[1]].address = vm_phy_page_alloc(vm, - KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot) - >> vm->page_shift; - pde[index[1]].writable = true; - pde[index[1]].present = true; - } + return *(uint64_t *)pte; +} - /* Fill in page table entry. */ - struct pageTableEntry *pte; - pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size); - pte[index[0]].address = paddr >> vm->page_shift; - pte[index[0]].writable = true; - pte[index[0]].present = 1; +void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr, + uint64_t pte) +{ + struct pageTableEntry *new_pte = _vm_get_page_table_entry(vm, vcpuid, + vaddr); + + *(uint64_t *)new_pte = pte; } void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { - struct pageMapL4Entry *pml4e, *pml4e_start; - struct pageDirectoryPointerEntry *pdpe, *pdpe_start; - struct pageDirectoryEntry *pde, *pde_start; + struct pageUpperEntry *pml4e, *pml4e_start; + struct pageUpperEntry *pdpe, *pdpe_start; + struct pageUpperEntry *pde, *pde_start; struct pageTableEntry *pte, *pte_start; if (!vm->pgd_created) @@ -307,8 +389,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*s index hvaddr gpaddr " "addr w exec dirty\n", indent, ""); - pml4e_start = (struct pageMapL4Entry *) addr_gpa2hva(vm, - vm->pgd); + pml4e_start = (struct pageUpperEntry *) addr_gpa2hva(vm, vm->pgd); for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) { pml4e = &pml4e_start[n1]; if (!pml4e->present) @@ -317,11 +398,10 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) " %u\n", indent, "", pml4e - pml4e_start, pml4e, - addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->address, + addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->pfn, pml4e->writable, pml4e->execute_disable); - pdpe_start = addr_gpa2hva(vm, pml4e->address - * vm->page_size); + pdpe_start = addr_gpa2hva(vm, pml4e->pfn * vm->page_size); for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) { pdpe = &pdpe_start[n2]; if (!pdpe->present) @@ -331,11 +411,10 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) indent, "", pdpe - pdpe_start, pdpe, addr_hva2gpa(vm, pdpe), - (uint64_t) pdpe->address, pdpe->writable, + (uint64_t) pdpe->pfn, pdpe->writable, pdpe->execute_disable); - pde_start = addr_gpa2hva(vm, - pdpe->address * vm->page_size); + pde_start = addr_gpa2hva(vm, pdpe->pfn * vm->page_size); for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) { pde = &pde_start[n3]; if (!pde->present) @@ -344,11 +423,10 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) "0x%-12lx 0x%-10lx %u %u\n", indent, "", pde - pde_start, pde, addr_hva2gpa(vm, pde), - (uint64_t) pde->address, pde->writable, + (uint64_t) pde->pfn, pde->writable, pde->execute_disable); - pte_start = addr_gpa2hva(vm, - pde->address * vm->page_size); + pte_start = addr_gpa2hva(vm, pde->pfn * vm->page_size); for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) { pte = &pte_start[n4]; if (!pte->present) @@ -359,7 +437,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) indent, "", pte - pte_start, pte, addr_hva2gpa(vm, pte), - (uint64_t) pte->address, + (uint64_t) pte->pfn, pte->writable, pte->execute_disable, pte->dirty, @@ -480,9 +558,7 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { uint16_t index[4]; - struct pageMapL4Entry *pml4e; - struct pageDirectoryPointerEntry *pdpe; - struct pageDirectoryEntry *pde; + struct pageUpperEntry *pml4e, *pdpe, *pde; struct pageTableEntry *pte; TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " @@ -499,43 +575,39 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) if (!pml4e[index[3]].present) goto unmapped_gva; - pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size); + pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size); if (!pdpe[index[2]].present) goto unmapped_gva; - pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size); + pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size); if (!pde[index[1]].present) goto unmapped_gva; - pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size); + pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size); if (!pte[index[0]].present) goto unmapped_gva; - return (pte[index[0]].address * vm->page_size) + (gva & 0xfffu); + return (pte[index[0]].pfn * vm->page_size) + (gva & 0xfffu); unmapped_gva: TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva); exit(EXIT_FAILURE); } -static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt, int gdt_memslot, - int pgd_memslot) +static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt) { if (!vm->gdt) - vm->gdt = vm_vaddr_alloc(vm, getpagesize(), - KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot); + vm->gdt = vm_vaddr_alloc_page(vm); dt->base = vm->gdt; dt->limit = getpagesize(); } static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp, - int selector, int gdt_memslot, - int pgd_memslot) + int selector) { if (!vm->tss) - vm->tss = vm_vaddr_alloc(vm, getpagesize(), - KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot); + vm->tss = vm_vaddr_alloc_page(vm); memset(segp, 0, sizeof(*segp)); segp->base = vm->tss; @@ -546,7 +618,7 @@ static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp, kvm_seg_fill_gdt_64bit(vm, segp); } -static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot) +static void vcpu_setup(struct kvm_vm *vm, int vcpuid) { struct kvm_sregs sregs; @@ -555,7 +627,7 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m sregs.idt.limit = 0; - kvm_setup_gdt(vm, &sregs.gdt, gdt_memslot, pgd_memslot); + kvm_setup_gdt(vm, &sregs.gdt); switch (vm->mode) { case VM_MODE_PXXV48_4K: @@ -567,7 +639,7 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs); kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds); kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es); - kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot); + kvm_setup_tss_64bit(vm, &sregs.tr, 0x18); break; default: @@ -584,11 +656,11 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) struct kvm_regs regs; vm_vaddr_t stack_vaddr; stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(), - DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0); + DEFAULT_GUEST_STACK_VADDR_MIN); /* Create VCPU */ vm_vcpu_add(vm, vcpuid); - vcpu_setup(vm, vcpuid, 0, 0); + vcpu_setup(vm, vcpuid); /* Setup guest general purpose registers */ vcpu_regs_get(vm, vcpuid, ®s); @@ -600,6 +672,9 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) /* Setup the MP state */ mp_state.mp_state = 0; vcpu_set_mp_state(vm, vcpuid, &mp_state); + + /* Setup supported CPUIDs */ + vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid()); } /* @@ -657,9 +732,7 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void) return cpuid; cpuid = allocate_kvm_cpuid2(); - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n", @@ -691,9 +764,7 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index) buffer.header.nmsrs = 1; buffer.entry.index = msr_index; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); r = ioctl(kvm_fd, KVM_GET_MSRS, &buffer.header); TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n" @@ -986,9 +1057,7 @@ struct kvm_msr_list *kvm_get_msr_index_list(void) struct kvm_msr_list *list; int nmsrs, r, kvm_fd; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); nmsrs = kvm_get_num_msrs_fd(kvm_fd); list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); @@ -1228,8 +1297,8 @@ void vm_init_descriptor_tables(struct kvm_vm *vm) extern void *idt_handlers; int i; - vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0); - vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0); + vm->idt = vm_vaddr_alloc_page(vm); + vm->handlers = vm_vaddr_alloc_page(vm); /* Handlers have the same address in both address spaces.*/ for (i = 0; i < NUM_INTERRUPTS; i++) set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, @@ -1312,9 +1381,7 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) return cpuid; cpuid = allocate_kvm_cpuid2(); - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_HV_CPUID failed %d %d\n", diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c index 827fe6028dd4..2ac98d70d02b 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/svm.c +++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c @@ -30,17 +30,14 @@ u64 rflags; struct svm_test_data * vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva) { - vm_vaddr_t svm_gva = vm_vaddr_alloc(vm, getpagesize(), - 0x10000, 0, 0); + vm_vaddr_t svm_gva = vm_vaddr_alloc_page(vm); struct svm_test_data *svm = addr_gva2hva(vm, svm_gva); - svm->vmcb = (void *)vm_vaddr_alloc(vm, getpagesize(), - 0x10000, 0, 0); + svm->vmcb = (void *)vm_vaddr_alloc_page(vm); svm->vmcb_hva = addr_gva2hva(vm, (uintptr_t)svm->vmcb); svm->vmcb_gpa = addr_gva2gpa(vm, (uintptr_t)svm->vmcb); - svm->save_area = (void *)vm_vaddr_alloc(vm, getpagesize(), - 0x10000, 0, 0); + svm->save_area = (void *)vm_vaddr_alloc_page(vm); svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area); svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area); diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 2448b30e8efa..d089d8b850b5 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -77,50 +77,48 @@ int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id) struct vmx_pages * vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva) { - vm_vaddr_t vmx_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vm_vaddr_t vmx_gva = vm_vaddr_alloc_page(vm); struct vmx_pages *vmx = addr_gva2hva(vm, vmx_gva); /* Setup of a region of guest memory for the vmxon region. */ - vmx->vmxon = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->vmxon = (void *)vm_vaddr_alloc_page(vm); vmx->vmxon_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmxon); vmx->vmxon_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmxon); /* Setup of a region of guest memory for a vmcs. */ - vmx->vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->vmcs = (void *)vm_vaddr_alloc_page(vm); vmx->vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmcs); vmx->vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmcs); /* Setup of a region of guest memory for the MSR bitmap. */ - vmx->msr = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->msr = (void *)vm_vaddr_alloc_page(vm); vmx->msr_hva = addr_gva2hva(vm, (uintptr_t)vmx->msr); vmx->msr_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->msr); memset(vmx->msr_hva, 0, getpagesize()); /* Setup of a region of guest memory for the shadow VMCS. */ - vmx->shadow_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->shadow_vmcs = (void *)vm_vaddr_alloc_page(vm); vmx->shadow_vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->shadow_vmcs); vmx->shadow_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->shadow_vmcs); /* Setup of a region of guest memory for the VMREAD and VMWRITE bitmaps. */ - vmx->vmread = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->vmread = (void *)vm_vaddr_alloc_page(vm); vmx->vmread_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmread); vmx->vmread_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmread); memset(vmx->vmread_hva, 0, getpagesize()); - vmx->vmwrite = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->vmwrite = (void *)vm_vaddr_alloc_page(vm); vmx->vmwrite_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmwrite); vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite); memset(vmx->vmwrite_hva, 0, getpagesize()); /* Setup of a region of guest memory for the VP Assist page. */ - vmx->vp_assist = (void *)vm_vaddr_alloc(vm, getpagesize(), - 0x10000, 0, 0); + vmx->vp_assist = (void *)vm_vaddr_alloc_page(vm); vmx->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)vmx->vp_assist); vmx->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vp_assist); /* Setup of a region of guest memory for the enlightened VMCS. */ - vmx->enlightened_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), - 0x10000, 0, 0); + vmx->enlightened_vmcs = (void *)vm_vaddr_alloc_page(vm); vmx->enlightened_vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->enlightened_vmcs); vmx->enlightened_vmcs_gpa = @@ -395,7 +393,7 @@ void nested_vmx_check_supported(void) } void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, - uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot) + uint64_t nested_paddr, uint64_t paddr) { uint16_t index[4]; struct eptPageTableEntry *pml4e; @@ -428,9 +426,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, /* Allocate page directory pointer table if not present. */ pml4e = vmx->eptp_hva; if (!pml4e[index[3]].readable) { - pml4e[index[3]].address = vm_phy_page_alloc(vm, - KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot) - >> vm->page_shift; + pml4e[index[3]].address = vm_alloc_page_table(vm) >> vm->page_shift; pml4e[index[3]].writable = true; pml4e[index[3]].readable = true; pml4e[index[3]].executable = true; @@ -440,9 +436,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, struct eptPageTableEntry *pdpe; pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size); if (!pdpe[index[2]].readable) { - pdpe[index[2]].address = vm_phy_page_alloc(vm, - KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot) - >> vm->page_shift; + pdpe[index[2]].address = vm_alloc_page_table(vm) >> vm->page_shift; pdpe[index[2]].writable = true; pdpe[index[2]].readable = true; pdpe[index[2]].executable = true; @@ -452,9 +446,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, struct eptPageTableEntry *pde; pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size); if (!pde[index[1]].readable) { - pde[index[1]].address = vm_phy_page_alloc(vm, - KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot) - >> vm->page_shift; + pde[index[1]].address = vm_alloc_page_table(vm) >> vm->page_shift; pde[index[1]].writable = true; pde[index[1]].readable = true; pde[index[1]].executable = true; @@ -494,8 +486,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, * page range starting at nested_paddr to the page range starting at paddr. */ void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm, - uint64_t nested_paddr, uint64_t paddr, uint64_t size, - uint32_t eptp_memslot) + uint64_t nested_paddr, uint64_t paddr, uint64_t size) { size_t page_size = vm->page_size; size_t npages = size / page_size; @@ -504,7 +495,7 @@ void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm, TEST_ASSERT(paddr + size > paddr, "Paddr overflow"); while (npages--) { - nested_pg_map(vmx, vm, nested_paddr, paddr, eptp_memslot); + nested_pg_map(vmx, vm, nested_paddr, paddr); nested_paddr += page_size; paddr += page_size; } @@ -514,7 +505,7 @@ void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm, * physical pages in VM. */ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm, - uint32_t memslot, uint32_t eptp_memslot) + uint32_t memslot) { sparsebit_idx_t i, last; struct userspace_mem_region *region = @@ -530,24 +521,21 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm, nested_map(vmx, vm, (uint64_t)i << vm->page_shift, (uint64_t)i << vm->page_shift, - 1 << vm->page_shift, - eptp_memslot); + 1 << vm->page_shift); } } void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, uint32_t eptp_memslot) { - vmx->eptp = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->eptp = (void *)vm_vaddr_alloc_page(vm); vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp); vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp); } -void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm, - uint32_t eptp_memslot) +void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm) { - vmx->apic_access = (void *)vm_vaddr_alloc(vm, getpagesize(), - 0x10000, 0, 0); + vmx->apic_access = (void *)vm_vaddr_alloc_page(vm); vmx->apic_access_hva = addr_gva2hva(vm, (uintptr_t)vmx->apic_access); vmx->apic_access_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->apic_access); } diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 6096bf0a5b34..98351ba0933c 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -71,14 +71,22 @@ struct memslot_antagonist_args { }; static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, - uint64_t nr_modifications, uint64_t gpa) + uint64_t nr_modifications) { + const uint64_t pages = 1; + uint64_t gpa; int i; + /* + * Add the dummy memslot just below the perf_test_util memslot, which is + * at the top of the guest physical address space. + */ + gpa = guest_test_phys_mem - pages * vm_get_page_size(vm); + for (i = 0; i < nr_modifications; i++) { usleep(delay); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa, - DUMMY_MEMSLOT_INDEX, 1, 0); + DUMMY_MEMSLOT_INDEX, pages, 0); vm_mem_region_delete(vm, DUMMY_MEMSLOT_INDEX); } @@ -120,11 +128,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("Started all vCPUs\n"); add_remove_memslot(vm, p->memslot_modification_delay, - p->nr_memslot_modifications, - guest_test_phys_mem + - (guest_percpu_mem_size * nr_vcpus) + - perf_test_args.host_page_size + - perf_test_args.guest_page_size); + p->nr_memslot_modifications); run_vcpus = false; diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c new file mode 100644 index 000000000000..d6e381e01db7 --- /dev/null +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -0,0 +1,1037 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A memslot-related performance benchmark. + * + * Copyright (C) 2021 Oracle and/or its affiliates. + * + * Basic guest setup / host vCPU thread code lifted from set_memory_region_test. + */ +#include <pthread.h> +#include <sched.h> +#include <semaphore.h> +#include <stdatomic.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <time.h> +#include <unistd.h> + +#include <linux/compiler.h> + +#include <test_util.h> +#include <kvm_util.h> +#include <processor.h> + +#define VCPU_ID 0 + +#define MEM_SIZE ((512U << 20) + 4096) +#define MEM_SIZE_PAGES (MEM_SIZE / 4096) +#define MEM_GPA 0x10000000UL +#define MEM_AUX_GPA MEM_GPA +#define MEM_SYNC_GPA MEM_AUX_GPA +#define MEM_TEST_GPA (MEM_AUX_GPA + 4096) +#define MEM_TEST_SIZE (MEM_SIZE - 4096) +static_assert(MEM_SIZE % 4096 == 0, "invalid mem size"); +static_assert(MEM_TEST_SIZE % 4096 == 0, "invalid mem test size"); + +/* + * 32 MiB is max size that gets well over 100 iterations on 509 slots. + * Considering that each slot needs to have at least one page up to + * 8194 slots in use can then be tested (although with slightly + * limited resolution). + */ +#define MEM_SIZE_MAP ((32U << 20) + 4096) +#define MEM_SIZE_MAP_PAGES (MEM_SIZE_MAP / 4096) +#define MEM_TEST_MAP_SIZE (MEM_SIZE_MAP - 4096) +#define MEM_TEST_MAP_SIZE_PAGES (MEM_TEST_MAP_SIZE / 4096) +static_assert(MEM_SIZE_MAP % 4096 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE % 4096 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE_PAGES % 2 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE_PAGES > 2, "invalid map test region size"); + +/* + * 128 MiB is min size that fills 32k slots with at least one page in each + * while at the same time gets 100+ iterations in such test + */ +#define MEM_TEST_UNMAP_SIZE (128U << 20) +#define MEM_TEST_UNMAP_SIZE_PAGES (MEM_TEST_UNMAP_SIZE / 4096) +/* 2 MiB chunk size like a typical huge page */ +#define MEM_TEST_UNMAP_CHUNK_PAGES (2U << (20 - 12)) +static_assert(MEM_TEST_UNMAP_SIZE <= MEM_TEST_SIZE, + "invalid unmap test region size"); +static_assert(MEM_TEST_UNMAP_SIZE % 4096 == 0, + "invalid unmap test region size"); +static_assert(MEM_TEST_UNMAP_SIZE_PAGES % + (2 * MEM_TEST_UNMAP_CHUNK_PAGES) == 0, + "invalid unmap test region size"); + +/* + * For the move active test the middle of the test area is placed on + * a memslot boundary: half lies in the memslot being moved, half in + * other memslot(s). + * + * When running this test with 32k memslots (32764, really) each memslot + * contains 4 pages. + * The last one additionally contains the remaining 21 pages of memory, + * for the total size of 25 pages. + * Hence, the maximum size here is 50 pages. + */ +#define MEM_TEST_MOVE_SIZE_PAGES (50) +#define MEM_TEST_MOVE_SIZE (MEM_TEST_MOVE_SIZE_PAGES * 4096) +#define MEM_TEST_MOVE_GPA_DEST (MEM_GPA + MEM_SIZE) +static_assert(MEM_TEST_MOVE_SIZE <= MEM_TEST_SIZE, + "invalid move test region size"); + +#define MEM_TEST_VAL_1 0x1122334455667788 +#define MEM_TEST_VAL_2 0x99AABBCCDDEEFF00 + +struct vm_data { + struct kvm_vm *vm; + pthread_t vcpu_thread; + uint32_t nslots; + uint64_t npages; + uint64_t pages_per_slot; + void **hva_slots; + bool mmio_ok; + uint64_t mmio_gpa_min; + uint64_t mmio_gpa_max; +}; + +struct sync_area { + atomic_bool start_flag; + atomic_bool exit_flag; + atomic_bool sync_flag; + void *move_area_ptr; +}; + +/* + * Technically, we need also for the atomic bool to be address-free, which + * is recommended, but not strictly required, by C11 for lockless + * implementations. + * However, in practice both GCC and Clang fulfill this requirement on + * all KVM-supported platforms. + */ +static_assert(ATOMIC_BOOL_LOCK_FREE == 2, "atomic bool is not lockless"); + +static sem_t vcpu_ready; + +static bool map_unmap_verify; + +static bool verbose; +#define pr_info_v(...) \ + do { \ + if (verbose) \ + pr_info(__VA_ARGS__); \ + } while (0) + +static void *vcpu_worker(void *data) +{ + struct vm_data *vm = data; + struct kvm_run *run; + struct ucall uc; + uint64_t cmd; + + run = vcpu_state(vm->vm, VCPU_ID); + while (1) { + vcpu_run(vm->vm, VCPU_ID); + + if (run->exit_reason == KVM_EXIT_IO) { + cmd = get_ucall(vm->vm, VCPU_ID, &uc); + if (cmd != UCALL_SYNC) + break; + + sem_post(&vcpu_ready); + continue; + } + + if (run->exit_reason != KVM_EXIT_MMIO) + break; + + TEST_ASSERT(vm->mmio_ok, "Unexpected mmio exit"); + TEST_ASSERT(run->mmio.is_write, "Unexpected mmio read"); + TEST_ASSERT(run->mmio.len == 8, + "Unexpected exit mmio size = %u", run->mmio.len); + TEST_ASSERT(run->mmio.phys_addr >= vm->mmio_gpa_min && + run->mmio.phys_addr <= vm->mmio_gpa_max, + "Unexpected exit mmio address = 0x%llx", + run->mmio.phys_addr); + } + + if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT) + TEST_FAIL("%s at %s:%ld, val = %lu", (const char *)uc.args[0], + __FILE__, uc.args[1], uc.args[2]); + + return NULL; +} + +static void wait_for_vcpu(void) +{ + struct timespec ts; + + TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts), + "clock_gettime() failed: %d\n", errno); + + ts.tv_sec += 2; + TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts), + "sem_timedwait() failed: %d\n", errno); +} + +static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages) +{ + uint64_t gpage, pgoffs; + uint32_t slot, slotoffs; + void *base; + + TEST_ASSERT(gpa >= MEM_GPA, "Too low gpa to translate"); + TEST_ASSERT(gpa < MEM_GPA + data->npages * 4096, + "Too high gpa to translate"); + gpa -= MEM_GPA; + + gpage = gpa / 4096; + pgoffs = gpa % 4096; + slot = min(gpage / data->pages_per_slot, (uint64_t)data->nslots - 1); + slotoffs = gpage - (slot * data->pages_per_slot); + + if (rempages) { + uint64_t slotpages; + + if (slot == data->nslots - 1) + slotpages = data->npages - slot * data->pages_per_slot; + else + slotpages = data->pages_per_slot; + + TEST_ASSERT(!pgoffs, + "Asking for remaining pages in slot but gpa not page aligned"); + *rempages = slotpages - slotoffs; + } + + base = data->hva_slots[slot]; + return (uint8_t *)base + slotoffs * 4096 + pgoffs; +} + +static uint64_t vm_slot2gpa(struct vm_data *data, uint32_t slot) +{ + TEST_ASSERT(slot < data->nslots, "Too high slot number"); + + return MEM_GPA + slot * data->pages_per_slot * 4096; +} + +static struct vm_data *alloc_vm(void) +{ + struct vm_data *data; + + data = malloc(sizeof(*data)); + TEST_ASSERT(data, "malloc(vmdata) failed"); + + data->vm = NULL; + data->hva_slots = NULL; + + return data; +} + +static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, + void *guest_code, uint64_t mempages, + struct timespec *slot_runtime) +{ + uint32_t max_mem_slots; + uint64_t rempages; + uint64_t guest_addr; + uint32_t slot; + struct timespec tstart; + struct sync_area *sync; + + max_mem_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS); + TEST_ASSERT(max_mem_slots > 1, + "KVM_CAP_NR_MEMSLOTS should be greater than 1"); + TEST_ASSERT(nslots > 1 || nslots == -1, + "Slot count cap should be greater than 1"); + if (nslots != -1) + max_mem_slots = min(max_mem_slots, (uint32_t)nslots); + pr_info_v("Allowed number of memory slots: %"PRIu32"\n", max_mem_slots); + + TEST_ASSERT(mempages > 1, + "Can't test without any memory"); + + data->npages = mempages; + data->nslots = max_mem_slots - 1; + data->pages_per_slot = mempages / data->nslots; + if (!data->pages_per_slot) { + *maxslots = mempages + 1; + return false; + } + + rempages = mempages % data->nslots; + data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots); + TEST_ASSERT(data->hva_slots, "malloc() fail"); + + data->vm = vm_create_default(VCPU_ID, mempages, guest_code); + + pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n", + max_mem_slots - 1, data->pages_per_slot, rempages); + + clock_gettime(CLOCK_MONOTONIC, &tstart); + for (slot = 1, guest_addr = MEM_GPA; slot < max_mem_slots; slot++) { + uint64_t npages; + + npages = data->pages_per_slot; + if (slot == max_mem_slots - 1) + npages += rempages; + + vm_userspace_mem_region_add(data->vm, VM_MEM_SRC_ANONYMOUS, + guest_addr, slot, npages, + 0); + guest_addr += npages * 4096; + } + *slot_runtime = timespec_elapsed(tstart); + + for (slot = 0, guest_addr = MEM_GPA; slot < max_mem_slots - 1; slot++) { + uint64_t npages; + uint64_t gpa; + + npages = data->pages_per_slot; + if (slot == max_mem_slots - 2) + npages += rempages; + + gpa = vm_phy_pages_alloc(data->vm, npages, guest_addr, + slot + 1); + TEST_ASSERT(gpa == guest_addr, + "vm_phy_pages_alloc() failed\n"); + + data->hva_slots[slot] = addr_gpa2hva(data->vm, guest_addr); + memset(data->hva_slots[slot], 0, npages * 4096); + + guest_addr += npages * 4096; + } + + virt_map(data->vm, MEM_GPA, MEM_GPA, mempages); + + sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + atomic_init(&sync->start_flag, false); + atomic_init(&sync->exit_flag, false); + atomic_init(&sync->sync_flag, false); + + data->mmio_ok = false; + + return true; +} + +static void launch_vm(struct vm_data *data) +{ + pr_info_v("Launching the test VM\n"); + + pthread_create(&data->vcpu_thread, NULL, vcpu_worker, data); + + /* Ensure the guest thread is spun up. */ + wait_for_vcpu(); +} + +static void free_vm(struct vm_data *data) +{ + kvm_vm_free(data->vm); + free(data->hva_slots); + free(data); +} + +static void wait_guest_exit(struct vm_data *data) +{ + pthread_join(data->vcpu_thread, NULL); +} + +static void let_guest_run(struct sync_area *sync) +{ + atomic_store_explicit(&sync->start_flag, true, memory_order_release); +} + +static void guest_spin_until_start(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + while (!atomic_load_explicit(&sync->start_flag, memory_order_acquire)) + ; +} + +static void make_guest_exit(struct sync_area *sync) +{ + atomic_store_explicit(&sync->exit_flag, true, memory_order_release); +} + +static bool _guest_should_exit(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + return atomic_load_explicit(&sync->exit_flag, memory_order_acquire); +} + +#define guest_should_exit() unlikely(_guest_should_exit()) + +/* + * noinline so we can easily see how much time the host spends waiting + * for the guest. + * For the same reason use alarm() instead of polling clock_gettime() + * to implement a wait timeout. + */ +static noinline void host_perform_sync(struct sync_area *sync) +{ + alarm(2); + + atomic_store_explicit(&sync->sync_flag, true, memory_order_release); + while (atomic_load_explicit(&sync->sync_flag, memory_order_acquire)) + ; + + alarm(0); +} + +static bool guest_perform_sync(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + bool expected; + + do { + if (guest_should_exit()) + return false; + + expected = true; + } while (!atomic_compare_exchange_weak_explicit(&sync->sync_flag, + &expected, false, + memory_order_acq_rel, + memory_order_relaxed)); + + return true; +} + +static void guest_code_test_memslot_move(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + uintptr_t base = (typeof(base))READ_ONCE(sync->move_area_ptr); + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (!guest_should_exit()) { + uintptr_t ptr; + + for (ptr = base; ptr < base + MEM_TEST_MOVE_SIZE; + ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + /* + * No host sync here since the MMIO exits are so expensive + * that the host would spend most of its time waiting for + * the guest and so instead of measuring memslot move + * performance we would measure the performance and + * likelihood of MMIO exits + */ + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_map(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr; + + for (ptr = MEM_TEST_GPA; + ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + for (ptr = MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; + ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_2; + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_unmap(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr = MEM_TEST_GPA; + + /* + * We can afford to access (map) just a small number of pages + * per host sync as otherwise the host will spend + * a significant amount of its time waiting for the guest + * (instead of doing unmap operations), so this will + * effectively turn this test into a map performance test. + * + * Just access a single page to be on the safe side. + */ + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + ptr += MEM_TEST_UNMAP_SIZE / 2; + *(uint64_t *)ptr = MEM_TEST_VAL_2; + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_rw(void) +{ + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr; + + for (ptr = MEM_TEST_GPA; + ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + for (ptr = MEM_TEST_GPA + 4096 / 2; + ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096) { + uint64_t val = *(uint64_t *)ptr; + + GUEST_ASSERT_1(val == MEM_TEST_VAL_2, val); + *(uint64_t *)ptr = 0; + } + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static bool test_memslot_move_prepare(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots, bool isactive) +{ + uint64_t movesrcgpa, movetestgpa; + + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); + + if (isactive) { + uint64_t lastpages; + + vm_gpa2hva(data, movesrcgpa, &lastpages); + if (lastpages < MEM_TEST_MOVE_SIZE_PAGES / 2) { + *maxslots = 0; + return false; + } + } + + movetestgpa = movesrcgpa - (MEM_TEST_MOVE_SIZE / (isactive ? 2 : 1)); + sync->move_area_ptr = (void *)movetestgpa; + + if (isactive) { + data->mmio_ok = true; + data->mmio_gpa_min = movesrcgpa; + data->mmio_gpa_max = movesrcgpa + MEM_TEST_MOVE_SIZE / 2 - 1; + } + + return true; +} + +static bool test_memslot_move_prepare_active(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots) +{ + return test_memslot_move_prepare(data, sync, maxslots, true); +} + +static bool test_memslot_move_prepare_inactive(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots) +{ + return test_memslot_move_prepare(data, sync, maxslots, false); +} + +static void test_memslot_move_loop(struct vm_data *data, struct sync_area *sync) +{ + uint64_t movesrcgpa; + + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); + vm_mem_region_move(data->vm, data->nslots - 1 + 1, + MEM_TEST_MOVE_GPA_DEST); + vm_mem_region_move(data->vm, data->nslots - 1 + 1, movesrcgpa); +} + +static void test_memslot_do_unmap(struct vm_data *data, + uint64_t offsp, uint64_t count) +{ + uint64_t gpa, ctr; + + for (gpa = MEM_TEST_GPA + offsp * 4096, ctr = 0; ctr < count; ) { + uint64_t npages; + void *hva; + int ret; + + hva = vm_gpa2hva(data, gpa, &npages); + TEST_ASSERT(npages, "Empty memory slot at gptr 0x%"PRIx64, gpa); + npages = min(npages, count - ctr); + ret = madvise(hva, npages * 4096, MADV_DONTNEED); + TEST_ASSERT(!ret, + "madvise(%p, MADV_DONTNEED) on VM memory should not fail for gptr 0x%"PRIx64, + hva, gpa); + ctr += npages; + gpa += npages * 4096; + } + TEST_ASSERT(ctr == count, + "madvise(MADV_DONTNEED) should exactly cover all of the requested area"); +} + +static void test_memslot_map_unmap_check(struct vm_data *data, + uint64_t offsp, uint64_t valexp) +{ + uint64_t gpa; + uint64_t *val; + + if (!map_unmap_verify) + return; + + gpa = MEM_TEST_GPA + offsp * 4096; + val = (typeof(val))vm_gpa2hva(data, gpa, NULL); + TEST_ASSERT(*val == valexp, + "Guest written values should read back correctly before unmap (%"PRIu64" vs %"PRIu64" @ %"PRIx64")", + *val, valexp, gpa); + *val = 0; +} + +static void test_memslot_map_loop(struct vm_data *data, struct sync_area *sync) +{ + /* + * Unmap the second half of the test area while guest writes to (maps) + * the first half. + */ + test_memslot_do_unmap(data, MEM_TEST_MAP_SIZE_PAGES / 2, + MEM_TEST_MAP_SIZE_PAGES / 2); + + /* + * Wait for the guest to finish writing the first half of the test + * area, verify the written value on the first and the last page of + * this area and then unmap it. + * Meanwhile, the guest is writing to (mapping) the second half of + * the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1); + test_memslot_map_unmap_check(data, + MEM_TEST_MAP_SIZE_PAGES / 2 - 1, + MEM_TEST_VAL_1); + test_memslot_do_unmap(data, 0, MEM_TEST_MAP_SIZE_PAGES / 2); + + + /* + * Wait for the guest to finish writing the second half of the test + * area and verify the written value on the first and the last page + * of this area. + * The area will be unmapped at the beginning of the next loop + * iteration. + * Meanwhile, the guest is writing to (mapping) the first half of + * the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES / 2, + MEM_TEST_VAL_2); + test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES - 1, + MEM_TEST_VAL_2); +} + +static void test_memslot_unmap_loop_common(struct vm_data *data, + struct sync_area *sync, + uint64_t chunk) +{ + uint64_t ctr; + + /* + * Wait for the guest to finish mapping page(s) in the first half + * of the test area, verify the written value and then perform unmap + * of this area. + * Meanwhile, the guest is writing to (mapping) page(s) in the second + * half of the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1); + for (ctr = 0; ctr < MEM_TEST_UNMAP_SIZE_PAGES / 2; ctr += chunk) + test_memslot_do_unmap(data, ctr, chunk); + + /* Likewise, but for the opposite host / guest areas */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, MEM_TEST_UNMAP_SIZE_PAGES / 2, + MEM_TEST_VAL_2); + for (ctr = MEM_TEST_UNMAP_SIZE_PAGES / 2; + ctr < MEM_TEST_UNMAP_SIZE_PAGES; ctr += chunk) + test_memslot_do_unmap(data, ctr, chunk); +} + +static void test_memslot_unmap_loop(struct vm_data *data, + struct sync_area *sync) +{ + test_memslot_unmap_loop_common(data, sync, 1); +} + +static void test_memslot_unmap_loop_chunked(struct vm_data *data, + struct sync_area *sync) +{ + test_memslot_unmap_loop_common(data, sync, MEM_TEST_UNMAP_CHUNK_PAGES); +} + +static void test_memslot_rw_loop(struct vm_data *data, struct sync_area *sync) +{ + uint64_t gptr; + + for (gptr = MEM_TEST_GPA + 4096 / 2; + gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096) + *(uint64_t *)vm_gpa2hva(data, gptr, NULL) = MEM_TEST_VAL_2; + + host_perform_sync(sync); + + for (gptr = MEM_TEST_GPA; + gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096) { + uint64_t *vptr = (typeof(vptr))vm_gpa2hva(data, gptr, NULL); + uint64_t val = *vptr; + + TEST_ASSERT(val == MEM_TEST_VAL_1, + "Guest written values should read back correctly (is %"PRIu64" @ %"PRIx64")", + val, gptr); + *vptr = 0; + } + + host_perform_sync(sync); +} + +struct test_data { + const char *name; + uint64_t mem_size; + void (*guest_code)(void); + bool (*prepare)(struct vm_data *data, struct sync_area *sync, + uint64_t *maxslots); + void (*loop)(struct vm_data *data, struct sync_area *sync); +}; + +static bool test_execute(int nslots, uint64_t *maxslots, + unsigned int maxtime, + const struct test_data *tdata, + uint64_t *nloops, + struct timespec *slot_runtime, + struct timespec *guest_runtime) +{ + uint64_t mem_size = tdata->mem_size ? : MEM_SIZE_PAGES; + struct vm_data *data; + struct sync_area *sync; + struct timespec tstart; + bool ret = true; + + data = alloc_vm(); + if (!prepare_vm(data, nslots, maxslots, tdata->guest_code, + mem_size, slot_runtime)) { + ret = false; + goto exit_free; + } + + sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + + if (tdata->prepare && + !tdata->prepare(data, sync, maxslots)) { + ret = false; + goto exit_free; + } + + launch_vm(data); + + clock_gettime(CLOCK_MONOTONIC, &tstart); + let_guest_run(sync); + + while (1) { + *guest_runtime = timespec_elapsed(tstart); + if (guest_runtime->tv_sec >= maxtime) + break; + + tdata->loop(data, sync); + + (*nloops)++; + } + + make_guest_exit(sync); + wait_guest_exit(data); + +exit_free: + free_vm(data); + + return ret; +} + +static const struct test_data tests[] = { + { + .name = "map", + .mem_size = MEM_SIZE_MAP_PAGES, + .guest_code = guest_code_test_memslot_map, + .loop = test_memslot_map_loop, + }, + { + .name = "unmap", + .mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1, + .guest_code = guest_code_test_memslot_unmap, + .loop = test_memslot_unmap_loop, + }, + { + .name = "unmap chunked", + .mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1, + .guest_code = guest_code_test_memslot_unmap, + .loop = test_memslot_unmap_loop_chunked, + }, + { + .name = "move active area", + .guest_code = guest_code_test_memslot_move, + .prepare = test_memslot_move_prepare_active, + .loop = test_memslot_move_loop, + }, + { + .name = "move inactive area", + .guest_code = guest_code_test_memslot_move, + .prepare = test_memslot_move_prepare_inactive, + .loop = test_memslot_move_loop, + }, + { + .name = "RW", + .guest_code = guest_code_test_memslot_rw, + .loop = test_memslot_rw_loop + }, +}; + +#define NTESTS ARRAY_SIZE(tests) + +struct test_args { + int tfirst; + int tlast; + int nslots; + int seconds; + int runs; +}; + +static void help(char *name, struct test_args *targs) +{ + int ctr; + + pr_info("usage: %s [-h] [-v] [-d] [-s slots] [-f first_test] [-e last_test] [-l test_length] [-r run_count]\n", + name); + pr_info(" -h: print this help screen.\n"); + pr_info(" -v: enable verbose mode (not for benchmarking).\n"); + pr_info(" -d: enable extra debug checks.\n"); + pr_info(" -s: specify memslot count cap (-1 means no cap; currently: %i)\n", + targs->nslots); + pr_info(" -f: specify the first test to run (currently: %i; max %zu)\n", + targs->tfirst, NTESTS - 1); + pr_info(" -e: specify the last test to run (currently: %i; max %zu)\n", + targs->tlast, NTESTS - 1); + pr_info(" -l: specify the test length in seconds (currently: %i)\n", + targs->seconds); + pr_info(" -r: specify the number of runs per test (currently: %i)\n", + targs->runs); + + pr_info("\nAvailable tests:\n"); + for (ctr = 0; ctr < NTESTS; ctr++) + pr_info("%d: %s\n", ctr, tests[ctr].name); +} + +static bool parse_args(int argc, char *argv[], + struct test_args *targs) +{ + int opt; + + while ((opt = getopt(argc, argv, "hvds:f:e:l:r:")) != -1) { + switch (opt) { + case 'h': + default: + help(argv[0], targs); + return false; + case 'v': + verbose = true; + break; + case 'd': + map_unmap_verify = true; + break; + case 's': + targs->nslots = atoi(optarg); + if (targs->nslots <= 0 && targs->nslots != -1) { + pr_info("Slot count cap has to be positive or -1 for no cap\n"); + return false; + } + break; + case 'f': + targs->tfirst = atoi(optarg); + if (targs->tfirst < 0) { + pr_info("First test to run has to be non-negative\n"); + return false; + } + break; + case 'e': + targs->tlast = atoi(optarg); + if (targs->tlast < 0 || targs->tlast >= NTESTS) { + pr_info("Last test to run has to be non-negative and less than %zu\n", + NTESTS); + return false; + } + break; + case 'l': + targs->seconds = atoi(optarg); + if (targs->seconds < 0) { + pr_info("Test length in seconds has to be non-negative\n"); + return false; + } + break; + case 'r': + targs->runs = atoi(optarg); + if (targs->runs <= 0) { + pr_info("Runs per test has to be positive\n"); + return false; + } + break; + } + } + + if (optind < argc) { + help(argv[0], targs); + return false; + } + + if (targs->tfirst > targs->tlast) { + pr_info("First test to run cannot be greater than the last test to run\n"); + return false; + } + + return true; +} + +struct test_result { + struct timespec slot_runtime, guest_runtime, iter_runtime; + int64_t slottimens, runtimens; + uint64_t nloops; +}; + +static bool test_loop(const struct test_data *data, + const struct test_args *targs, + struct test_result *rbestslottime, + struct test_result *rbestruntime) +{ + uint64_t maxslots; + struct test_result result; + + result.nloops = 0; + if (!test_execute(targs->nslots, &maxslots, targs->seconds, data, + &result.nloops, + &result.slot_runtime, &result.guest_runtime)) { + if (maxslots) + pr_info("Memslot count too high for this test, decrease the cap (max is %"PRIu64")\n", + maxslots); + else + pr_info("Memslot count may be too high for this test, try adjusting the cap\n"); + + return false; + } + + pr_info("Test took %ld.%.9lds for slot setup + %ld.%.9lds all iterations\n", + result.slot_runtime.tv_sec, result.slot_runtime.tv_nsec, + result.guest_runtime.tv_sec, result.guest_runtime.tv_nsec); + if (!result.nloops) { + pr_info("No full loops done - too short test time or system too loaded?\n"); + return true; + } + + result.iter_runtime = timespec_div(result.guest_runtime, + result.nloops); + pr_info("Done %"PRIu64" iterations, avg %ld.%.9lds each\n", + result.nloops, + result.iter_runtime.tv_sec, + result.iter_runtime.tv_nsec); + result.slottimens = timespec_to_ns(result.slot_runtime); + result.runtimens = timespec_to_ns(result.iter_runtime); + + /* + * Only rank the slot setup time for tests using the whole test memory + * area so they are comparable + */ + if (!data->mem_size && + (!rbestslottime->slottimens || + result.slottimens < rbestslottime->slottimens)) + *rbestslottime = result; + if (!rbestruntime->runtimens || + result.runtimens < rbestruntime->runtimens) + *rbestruntime = result; + + return true; +} + +int main(int argc, char *argv[]) +{ + struct test_args targs = { + .tfirst = 0, + .tlast = NTESTS - 1, + .nslots = -1, + .seconds = 5, + .runs = 1, + }; + struct test_result rbestslottime; + int tctr; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + if (!parse_args(argc, argv, &targs)) + return -1; + + rbestslottime.slottimens = 0; + for (tctr = targs.tfirst; tctr <= targs.tlast; tctr++) { + const struct test_data *data = &tests[tctr]; + unsigned int runctr; + struct test_result rbestruntime; + + if (tctr > targs.tfirst) + pr_info("\n"); + + pr_info("Testing %s performance with %i runs, %d seconds each\n", + data->name, targs.runs, targs.seconds); + + rbestruntime.runtimens = 0; + for (runctr = 0; runctr < targs.runs; runctr++) + if (!test_loop(data, &targs, + &rbestslottime, &rbestruntime)) + break; + + if (rbestruntime.runtimens) + pr_info("Best runtime result was %ld.%.9lds per iteration (with %"PRIu64" iterations)\n", + rbestruntime.iter_runtime.tv_sec, + rbestruntime.iter_runtime.tv_nsec, + rbestruntime.nloops); + } + + if (rbestslottime.slottimens) + pr_info("Best slot setup time for the whole test area was %ld.%.9lds\n", + rbestslottime.slot_runtime.tv_sec, + rbestslottime.slot_runtime.tv_nsec); + + return 0; +} diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 978f5b5f4dc0..d79d58eada9f 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -132,7 +132,7 @@ static struct kvm_vm *spawn_vm(pthread_t *vcpu_thread, void *guest_code) gpa = vm_phy_pages_alloc(vm, 2, MEM_REGION_GPA, MEM_REGION_SLOT); TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n"); - virt_map(vm, MEM_REGION_GPA, MEM_REGION_GPA, 2, 0); + virt_map(vm, MEM_REGION_GPA, MEM_REGION_GPA, 2); /* Ditto for the host mapping so that both pages can be zeroed. */ hva = addr_gpa2hva(vm, MEM_REGION_GPA); diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index fcc840088c91..b0031f2d38fd 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -73,8 +73,6 @@ static void steal_time_init(struct kvm_vm *vm) for (i = 0; i < NR_VCPUS; ++i) { int ret; - vcpu_set_cpuid(vm, i, kvm_get_supported_cpuid()); - /* ST_GPA_BASE is identity mapped */ st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE); sync_global_to_guest(vm, st_gva[i]); @@ -295,7 +293,7 @@ int main(int ac, char **av) vm = vm_create_default(0, 0, guest_code); gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, STEAL_TIME_SIZE * NR_VCPUS); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0); - virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, gpages, 0); + virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, gpages); ucall_init(vm, NULL); /* Add the rest of the VCPUs */ diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c new file mode 100644 index 000000000000..f070ff0224fa --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020, Google LLC. + * + * Tests for KVM_CAP_EXIT_ON_EMULATION_FAILURE capability. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ + +#include "test_util.h" +#include "kvm_util.h" +#include "vmx.h" + +#define VCPU_ID 1 +#define PAGE_SIZE 4096 +#define MAXPHYADDR 36 + +#define MEM_REGION_GVA 0x0000123456789000 +#define MEM_REGION_GPA 0x0000000700000000 +#define MEM_REGION_SLOT 10 +#define MEM_REGION_SIZE PAGE_SIZE + +static void guest_code(void) +{ + __asm__ __volatile__("flds (%[addr])" + :: [addr]"r"(MEM_REGION_GVA)); + + GUEST_DONE(); +} + +static void run_guest(struct kvm_vm *vm) +{ + int rc; + + rc = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); +} + +/* + * Accessors to get R/M, REG, and Mod bits described in the SDM vol 2, + * figure 2-2 "Table Interpretation of ModR/M Byte (C8H)". + */ +#define GET_RM(insn_byte) (insn_byte & 0x7) +#define GET_REG(insn_byte) ((insn_byte & 0x38) >> 3) +#define GET_MOD(insn_byte) ((insn_byte & 0xc) >> 6) + +/* Ensure we are dealing with a simple 2-byte flds instruction. */ +static bool is_flds(uint8_t *insn_bytes, uint8_t insn_size) +{ + return insn_size >= 2 && + insn_bytes[0] == 0xd9 && + GET_REG(insn_bytes[1]) == 0x0 && + GET_MOD(insn_bytes[1]) == 0x0 && + /* Ensure there is no SIB byte. */ + GET_RM(insn_bytes[1]) != 0x4 && + /* Ensure there is no displacement byte. */ + GET_RM(insn_bytes[1]) != 0x5; +} + +static void process_exit_on_emulation_error(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct kvm_regs regs; + uint8_t *insn_bytes; + uint8_t insn_size; + uint64_t flags; + + TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, + "Unexpected exit reason: %u (%s)", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION, + "Unexpected suberror: %u", + run->emulation_failure.suberror); + + if (run->emulation_failure.ndata >= 1) { + flags = run->emulation_failure.flags; + if ((flags & KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES) && + run->emulation_failure.ndata >= 3) { + insn_size = run->emulation_failure.insn_size; + insn_bytes = run->emulation_failure.insn_bytes; + + TEST_ASSERT(insn_size <= 15 && insn_size > 0, + "Unexpected instruction size: %u", + insn_size); + + TEST_ASSERT(is_flds(insn_bytes, insn_size), + "Unexpected instruction. Expected 'flds' (0xd9 /0)"); + + /* + * If is_flds() succeeded then the instruction bytes + * contained an flds instruction that is 2-bytes in + * length (ie: no prefix, no SIB, no displacement). + */ + vcpu_regs_get(vm, VCPU_ID, ®s); + regs.rip += 2; + vcpu_regs_set(vm, VCPU_ID, ®s); + } + } +} + +static void do_guest_assert(struct kvm_vm *vm, struct ucall *uc) +{ + TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], __FILE__, + uc->args[1]); +} + +static void check_for_guest_assert(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + if (run->exit_reason == KVM_EXIT_IO && + get_ucall(vm, VCPU_ID, &uc) == UCALL_ABORT) { + do_guest_assert(vm, &uc); + } +} + +static void process_ucall_done(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + check_for_guest_assert(vm); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s)", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + TEST_ASSERT(get_ucall(vm, VCPU_ID, &uc) == UCALL_DONE, + "Unexpected ucall command: %lu, expected UCALL_DONE (%d)", + uc.cmd, UCALL_DONE); +} + +static uint64_t process_ucall(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s)", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + break; + case UCALL_ABORT: + do_guest_assert(vm, &uc); + break; + case UCALL_DONE: + process_ucall_done(vm); + break; + default: + TEST_ASSERT(false, "Unexpected ucall"); + } + + return uc.cmd; +} + +int main(int argc, char *argv[]) +{ + struct kvm_enable_cap emul_failure_cap = { + .cap = KVM_CAP_EXIT_ON_EMULATION_FAILURE, + .args[0] = 1, + }; + struct kvm_cpuid_entry2 *entry; + struct kvm_cpuid2 *cpuid; + struct kvm_vm *vm; + uint64_t gpa, pte; + uint64_t *hva; + int rc; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + vm = vm_create_default(VCPU_ID, 0, guest_code); + + if (!kvm_check_cap(KVM_CAP_SMALLER_MAXPHYADDR)) { + printf("module parameter 'allow_smaller_maxphyaddr' is not set. Skipping test.\n"); + return 0; + } + + cpuid = kvm_get_supported_cpuid(); + + entry = kvm_get_supported_cpuid_index(0x80000008, 0); + entry->eax = (entry->eax & 0xffffff00) | MAXPHYADDR; + set_cpuid(cpuid, entry); + + vcpu_set_cpuid(vm, VCPU_ID, cpuid); + + rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE); + TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable"); + vm_enable_cap(vm, &emul_failure_cap); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + MEM_REGION_GPA, MEM_REGION_SLOT, + MEM_REGION_SIZE / PAGE_SIZE, 0); + gpa = vm_phy_pages_alloc(vm, MEM_REGION_SIZE / PAGE_SIZE, + MEM_REGION_GPA, MEM_REGION_SLOT); + TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n"); + virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1); + hva = addr_gpa2hva(vm, MEM_REGION_GPA); + memset(hva, 0, PAGE_SIZE); + pte = vm_get_page_table_entry(vm, VCPU_ID, MEM_REGION_GVA); + vm_set_page_table_entry(vm, VCPU_ID, MEM_REGION_GVA, pte | (1ull << 36)); + + run_guest(vm); + process_exit_on_emulation_error(vm); + run_guest(vm); + + TEST_ASSERT(process_ucall(vm) == UCALL_DONE, "Expected UCALL_DONE"); + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index ca22ee6d19cb..d0a7a998e840 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -18,6 +18,19 @@ #include "vmx.h" #define VCPU_ID 5 +#define NMI_VECTOR 2 + +static int ud_count; + +static void guest_ud_handler(struct ex_regs *regs) +{ + ud_count++; + regs->rip += 3; /* VMLAUNCH */ +} + +static void guest_nmi_handler(struct ex_regs *regs) +{ +} void l2_guest_code(void) { @@ -25,15 +38,23 @@ void l2_guest_code(void) GUEST_SYNC(8); + /* Forced exit to L1 upon restore */ + GUEST_SYNC(9); + /* Done, exit to L1 and never come back. */ vmcall(); } -void l1_guest_code(struct vmx_pages *vmx_pages) +void guest_code(struct vmx_pages *vmx_pages) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + x2apic_enable(); + + GUEST_SYNC(1); + GUEST_SYNC(2); + enable_vp_assist(vmx_pages->vp_assist_gpa, vmx_pages->vp_assist); GUEST_ASSERT(vmx_pages->vmcs_gpa); @@ -55,37 +76,74 @@ void l1_guest_code(struct vmx_pages *vmx_pages) current_evmcs->revision_id = EVMCS_VERSION; GUEST_SYNC(6); + current_evmcs->pin_based_vm_exec_control |= + PIN_BASED_NMI_EXITING; GUEST_ASSERT(!vmlaunch()); GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); - GUEST_SYNC(9); + + /* + * NMI forces L2->L1 exit, resuming L2 and hope that EVMCS is + * up-to-date (RIP points where it should and not at the beginning + * of l2_guest_code(). GUEST_SYNC(9) checkes that. + */ GUEST_ASSERT(!vmresume()); - GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + GUEST_SYNC(10); + + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + GUEST_SYNC(11); + + /* Try enlightened vmptrld with an incorrect GPA */ + evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs); + GUEST_ASSERT(vmlaunch()); + GUEST_ASSERT(ud_count == 1); + GUEST_DONE(); } -void guest_code(struct vmx_pages *vmx_pages) +void inject_nmi(struct kvm_vm *vm) { - GUEST_SYNC(1); - GUEST_SYNC(2); + struct kvm_vcpu_events events; - if (vmx_pages) - l1_guest_code(vmx_pages); + vcpu_events_get(vm, VCPU_ID, &events); - GUEST_DONE(); + events.nmi.pending = 1; + events.flags |= KVM_VCPUEVENT_VALID_NMI_PENDING; - /* Try enlightened vmptrld with an incorrect GPA */ - evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs); - GUEST_ASSERT(vmlaunch()); + vcpu_events_set(vm, VCPU_ID, &events); +} + +static void save_restore_vm(struct kvm_vm *vm) +{ + struct kvm_regs regs1, regs2; + struct kvm_x86_state *state; + + state = vcpu_save_state(vm, VCPU_ID); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®s1); + + kvm_vm_release(vm); + + /* Restore state in a new VM. */ + kvm_vm_restart(vm, O_RDWR); + vm_vcpu_add(vm, VCPU_ID); + vcpu_set_hv_cpuid(vm, VCPU_ID); + vcpu_enable_evmcs(vm, VCPU_ID); + vcpu_load_state(vm, VCPU_ID, state); + free(state); + + memset(®s2, 0, sizeof(regs2)); + vcpu_regs_get(vm, VCPU_ID, ®s2); + TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), + "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", + (ulong) regs2.rdi, (ulong) regs2.rsi); } int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva = 0; - struct kvm_regs regs1, regs2; struct kvm_vm *vm; struct kvm_run *run; - struct kvm_x86_state *state; struct ucall uc; int stage; @@ -102,14 +160,18 @@ int main(int argc, char *argv[]) vcpu_set_hv_cpuid(vm, VCPU_ID); vcpu_enable_evmcs(vm, VCPU_ID); - run = vcpu_state(vm, VCPU_ID); - - vcpu_regs_get(vm, VCPU_ID, ®s1); - vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_handle_exception(vm, UD_VECTOR, guest_ud_handler); + vm_handle_exception(vm, NMI_VECTOR, guest_nmi_handler); + + pr_info("Running L1 which uses EVMCS to run L2\n"); + for (stage = 1;; stage++) { + run = vcpu_state(vm, VCPU_ID); _vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", @@ -124,7 +186,7 @@ int main(int argc, char *argv[]) case UCALL_SYNC: break; case UCALL_DONE: - goto part1_done; + goto done; default: TEST_FAIL("Unknown ucall %lu", uc.cmd); } @@ -134,32 +196,25 @@ int main(int argc, char *argv[]) uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx", stage, (ulong)uc.args[1]); - state = vcpu_save_state(vm, VCPU_ID); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); + save_restore_vm(vm); - kvm_vm_release(vm); - - /* Restore state in a new VM. */ - kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); - vcpu_set_hv_cpuid(vm, VCPU_ID); - vcpu_enable_evmcs(vm, VCPU_ID); - vcpu_load_state(vm, VCPU_ID, state); - run = vcpu_state(vm, VCPU_ID); - free(state); + /* Force immediate L2->L1 exit before resuming */ + if (stage == 8) { + pr_info("Injecting NMI into L1 before L2 had a chance to run after restore\n"); + inject_nmi(vm); + } - memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vm, VCPU_ID, ®s2); - TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), - "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", - (ulong) regs2.rdi, (ulong) regs2.rsi); + /* + * Do KVM_GET_NESTED_STATE/KVM_SET_NESTED_STATE for a freshly + * restored VM (before the first KVM_RUN) to check that + * KVM_STATE_NESTED_EVMCS is not lost. + */ + if (stage == 9) { + pr_info("Trying extra KVM_GET_NESTED_STATE/KVM_SET_NESTED_STATE cycle\n"); + save_restore_vm(vm); + } } -part1_done: - _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, - "Unexpected successful VMEnter with invalid eVMCS pointer!"); - +done: kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c index 9b78e8889638..a711f83749ea 100644 --- a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c @@ -19,7 +19,12 @@ struct { u32 function; u32 index; } mangled_cpuids[] = { + /* + * These entries depend on the vCPU's XCR0 register and IA32_XSS MSR, + * which are not controlled for by this test. + */ {.function = 0xd, .index = 0}, + {.function = 0xd, .index = 1}, }; static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid) @@ -140,8 +145,7 @@ static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage) struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct kvm_cpuid2 *cpuid) { int size = sizeof(*cpuid) + cpuid->nent * sizeof(cpuid->entries[0]); - vm_vaddr_t gva = vm_vaddr_alloc(vm, size, - getpagesize(), 0, 0); + vm_vaddr_t gva = vm_vaddr_alloc(vm, size, KVM_UTIL_MIN_VADDR); struct kvm_cpuid2 *guest_cpuids = addr_gva2hva(vm, gva); memcpy(guest_cpuids, cpuid, size); diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c index cb953df4d7d0..8aed0db1331d 100644 --- a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c +++ b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c @@ -37,9 +37,7 @@ static void test_get_msr_index(void) int old_res, res, kvm_fd, r; struct kvm_msr_list *list; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); old_res = kvm_num_index_msrs(kvm_fd, 0); TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); @@ -101,9 +99,7 @@ static void test_get_msr_feature(void) int res, old_res, i, kvm_fd; struct kvm_msr_list *feature_list; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); old_res = kvm_num_feature_msrs(kvm_fd, 0); TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c index 7f1d2765572c..bab10ae787b6 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c @@ -7,6 +7,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "hyperv.h" struct ms_hyperv_tsc_page { volatile u32 tsc_sequence; @@ -15,13 +16,6 @@ struct ms_hyperv_tsc_page { volatile s64 tsc_offset; } __packed; -#define HV_X64_MSR_GUEST_OS_ID 0x40000000 -#define HV_X64_MSR_TIME_REF_COUNT 0x40000020 -#define HV_X64_MSR_REFERENCE_TSC 0x40000021 -#define HV_X64_MSR_TSC_FREQUENCY 0x40000022 -#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 -#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 - /* Simplified mul_u64_u64_shr() */ static inline u64 mul_u64_u64_shr64(u64 a, u64 b) { @@ -220,7 +214,7 @@ int main(void) vcpu_set_hv_cpuid(vm, VCPU_ID); - tsc_page_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + tsc_page_gva = vm_vaddr_alloc_page(vm); memset(addr_gpa2hva(vm, tsc_page_gva), 0x0, getpagesize()); TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0, "TSC page has to be page aligned\n"); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c new file mode 100644 index 000000000000..42bd658f52a8 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -0,0 +1,649 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021, Red Hat, Inc. + * + * Tests for Hyper-V features enablement + */ +#include <asm/kvm_para.h> +#include <linux/kvm_para.h> +#include <stdint.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "hyperv.h" + +#define VCPU_ID 0 +#define LINUX_OS_ID ((u64)0x8100 << 48) + +extern unsigned char rdmsr_start; +extern unsigned char rdmsr_end; + +static u64 do_rdmsr(u32 idx) +{ + u32 lo, hi; + + asm volatile("rdmsr_start: rdmsr;" + "rdmsr_end:" + : "=a"(lo), "=c"(hi) + : "c"(idx)); + + return (((u64) hi) << 32) | lo; +} + +extern unsigned char wrmsr_start; +extern unsigned char wrmsr_end; + +static void do_wrmsr(u32 idx, u64 val) +{ + u32 lo, hi; + + lo = val; + hi = val >> 32; + + asm volatile("wrmsr_start: wrmsr;" + "wrmsr_end:" + : : "a"(lo), "c"(idx), "d"(hi)); +} + +static int nr_gp; + +static inline u64 hypercall(u64 control, vm_vaddr_t input_address, + vm_vaddr_t output_address) +{ + u64 hv_status; + + asm volatile("mov %3, %%r8\n" + "vmcall" + : "=a" (hv_status), + "+c" (control), "+d" (input_address) + : "r" (output_address) + : "cc", "memory", "r8", "r9", "r10", "r11"); + + return hv_status; +} + +static void guest_gp_handler(struct ex_regs *regs) +{ + unsigned char *rip = (unsigned char *)regs->rip; + bool r, w; + + r = rip == &rdmsr_start; + w = rip == &wrmsr_start; + GUEST_ASSERT(r || w); + + nr_gp++; + + if (r) + regs->rip = (uint64_t)&rdmsr_end; + else + regs->rip = (uint64_t)&wrmsr_end; +} + +struct msr_data { + uint32_t idx; + bool available; + bool write; + u64 write_val; +}; + +struct hcall_data { + uint64_t control; + uint64_t expect; +}; + +static void guest_msr(struct msr_data *msr) +{ + int i = 0; + + while (msr->idx) { + WRITE_ONCE(nr_gp, 0); + if (!msr->write) + do_rdmsr(msr->idx); + else + do_wrmsr(msr->idx, msr->write_val); + + if (msr->available) + GUEST_ASSERT(READ_ONCE(nr_gp) == 0); + else + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + + GUEST_SYNC(i++); + } + + GUEST_DONE(); +} + +static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) +{ + int i = 0; + + wrmsr(HV_X64_MSR_GUEST_OS_ID, LINUX_OS_ID); + wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); + + while (hcall->control) { + GUEST_ASSERT(hypercall(hcall->control, pgs_gpa, + pgs_gpa + 4096) == hcall->expect); + GUEST_SYNC(i++); + } + + GUEST_DONE(); +} + +static void hv_set_cpuid(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 *feat, + struct kvm_cpuid_entry2 *recomm, + struct kvm_cpuid_entry2 *dbg) +{ + TEST_ASSERT(set_cpuid(cpuid, feat), + "failed to set KVM_CPUID_FEATURES leaf"); + TEST_ASSERT(set_cpuid(cpuid, recomm), + "failed to set HYPERV_CPUID_ENLIGHTMENT_INFO leaf"); + TEST_ASSERT(set_cpuid(cpuid, dbg), + "failed to set HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES leaf"); + vcpu_set_cpuid(vm, VCPU_ID, cpuid); +} + +static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, + struct kvm_cpuid2 *best) +{ + struct kvm_run *run; + struct ucall uc; + int stage = 0, r; + struct kvm_cpuid_entry2 feat = { + .function = HYPERV_CPUID_FEATURES + }; + struct kvm_cpuid_entry2 recomm = { + .function = HYPERV_CPUID_ENLIGHTMENT_INFO + }; + struct kvm_cpuid_entry2 dbg = { + .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES + }; + struct kvm_enable_cap cap = {0}; + + run = vcpu_state(vm, VCPU_ID); + + while (true) { + switch (stage) { + case 0: + /* + * Only available when Hyper-V identification is set + */ + msr->idx = HV_X64_MSR_GUEST_OS_ID; + msr->write = 0; + msr->available = 0; + break; + case 1: + msr->idx = HV_X64_MSR_HYPERCALL; + msr->write = 0; + msr->available = 0; + break; + case 2: + feat.eax |= HV_MSR_HYPERCALL_AVAILABLE; + /* + * HV_X64_MSR_GUEST_OS_ID has to be written first to make + * HV_X64_MSR_HYPERCALL available. + */ + msr->idx = HV_X64_MSR_GUEST_OS_ID; + msr->write = 1; + msr->write_val = LINUX_OS_ID; + msr->available = 1; + break; + case 3: + msr->idx = HV_X64_MSR_GUEST_OS_ID; + msr->write = 0; + msr->available = 1; + break; + case 4: + msr->idx = HV_X64_MSR_HYPERCALL; + msr->write = 0; + msr->available = 1; + break; + + case 5: + msr->idx = HV_X64_MSR_VP_RUNTIME; + msr->write = 0; + msr->available = 0; + break; + case 6: + feat.eax |= HV_MSR_VP_RUNTIME_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 7: + /* Read only */ + msr->write = 1; + msr->write_val = 1; + msr->available = 0; + break; + + case 8: + msr->idx = HV_X64_MSR_TIME_REF_COUNT; + msr->write = 0; + msr->available = 0; + break; + case 9: + feat.eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 10: + /* Read only */ + msr->write = 1; + msr->write_val = 1; + msr->available = 0; + break; + + case 11: + msr->idx = HV_X64_MSR_VP_INDEX; + msr->write = 0; + msr->available = 0; + break; + case 12: + feat.eax |= HV_MSR_VP_INDEX_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 13: + /* Read only */ + msr->write = 1; + msr->write_val = 1; + msr->available = 0; + break; + + case 14: + msr->idx = HV_X64_MSR_RESET; + msr->write = 0; + msr->available = 0; + break; + case 15: + feat.eax |= HV_MSR_RESET_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 16: + msr->write = 1; + msr->write_val = 0; + msr->available = 1; + break; + + case 17: + msr->idx = HV_X64_MSR_REFERENCE_TSC; + msr->write = 0; + msr->available = 0; + break; + case 18: + feat.eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 19: + msr->write = 1; + msr->write_val = 0; + msr->available = 1; + break; + + case 20: + msr->idx = HV_X64_MSR_EOM; + msr->write = 0; + msr->available = 0; + break; + case 21: + /* + * Remains unavailable even with KVM_CAP_HYPERV_SYNIC2 + * capability enabled and guest visible CPUID bit unset. + */ + cap.cap = KVM_CAP_HYPERV_SYNIC2; + vcpu_enable_cap(vm, VCPU_ID, &cap); + break; + case 22: + feat.eax |= HV_MSR_SYNIC_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 23: + msr->write = 1; + msr->write_val = 0; + msr->available = 1; + break; + + case 24: + msr->idx = HV_X64_MSR_STIMER0_CONFIG; + msr->write = 0; + msr->available = 0; + break; + case 25: + feat.eax |= HV_MSR_SYNTIMER_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 26: + msr->write = 1; + msr->write_val = 0; + msr->available = 1; + break; + case 27: + /* Direct mode test */ + msr->write = 1; + msr->write_val = 1 << 12; + msr->available = 0; + break; + case 28: + feat.edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + msr->available = 1; + break; + + case 29: + msr->idx = HV_X64_MSR_EOI; + msr->write = 0; + msr->available = 0; + break; + case 30: + feat.eax |= HV_MSR_APIC_ACCESS_AVAILABLE; + msr->write = 1; + msr->write_val = 1; + msr->available = 1; + break; + + case 31: + msr->idx = HV_X64_MSR_TSC_FREQUENCY; + msr->write = 0; + msr->available = 0; + break; + case 32: + feat.eax |= HV_ACCESS_FREQUENCY_MSRS; + msr->write = 0; + msr->available = 1; + break; + case 33: + /* Read only */ + msr->write = 1; + msr->write_val = 1; + msr->available = 0; + break; + + case 34: + msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; + msr->write = 0; + msr->available = 0; + break; + case 35: + feat.eax |= HV_ACCESS_REENLIGHTENMENT; + msr->write = 0; + msr->available = 1; + break; + case 36: + msr->write = 1; + msr->write_val = 1; + msr->available = 1; + break; + case 37: + /* Can only write '0' */ + msr->idx = HV_X64_MSR_TSC_EMULATION_STATUS; + msr->write = 1; + msr->write_val = 1; + msr->available = 0; + break; + + case 38: + msr->idx = HV_X64_MSR_CRASH_P0; + msr->write = 0; + msr->available = 0; + break; + case 39: + feat.edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 40: + msr->write = 1; + msr->write_val = 1; + msr->available = 1; + break; + + case 41: + msr->idx = HV_X64_MSR_SYNDBG_STATUS; + msr->write = 0; + msr->available = 0; + break; + case 42: + feat.edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; + dbg.eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + msr->write = 0; + msr->available = 1; + break; + case 43: + msr->write = 1; + msr->write_val = 0; + msr->available = 1; + break; + + case 44: + /* END */ + msr->idx = 0; + break; + } + + hv_set_cpuid(vm, best, &feat, &recomm, &dbg); + + if (msr->idx) + pr_debug("Stage %d: testing msr: 0x%x for %s\n", stage, + msr->idx, msr->write ? "write" : "read"); + else + pr_debug("Stage %d: finish\n", stage); + + r = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + TEST_ASSERT(uc.args[1] == stage, + "Unexpected stage: %ld (%d expected)\n", + uc.args[1], stage); + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); + return; + case UCALL_DONE: + return; + } + + stage++; + } +} + +static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall, + void *input, void *output, struct kvm_cpuid2 *best) +{ + struct kvm_run *run; + struct ucall uc; + int stage = 0, r; + struct kvm_cpuid_entry2 feat = { + .function = HYPERV_CPUID_FEATURES, + .eax = HV_MSR_HYPERCALL_AVAILABLE + }; + struct kvm_cpuid_entry2 recomm = { + .function = HYPERV_CPUID_ENLIGHTMENT_INFO + }; + struct kvm_cpuid_entry2 dbg = { + .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES + }; + + run = vcpu_state(vm, VCPU_ID); + + while (true) { + switch (stage) { + case 0: + hcall->control = 0xdeadbeef; + hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + + case 1: + hcall->control = HVCALL_POST_MESSAGE; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 2: + feat.ebx |= HV_POST_MESSAGES; + hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + + case 3: + hcall->control = HVCALL_SIGNAL_EVENT; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 4: + feat.ebx |= HV_SIGNAL_EVENTS; + hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + + case 5: + hcall->control = HVCALL_RESET_DEBUG_SESSION; + hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + case 6: + dbg.eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 7: + feat.ebx |= HV_DEBUGGING; + hcall->expect = HV_STATUS_OPERATION_DENIED; + break; + + case 8: + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 9: + recomm.eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + hcall->expect = HV_STATUS_SUCCESS; + break; + case 10: + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 11: + recomm.eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; + hcall->expect = HV_STATUS_SUCCESS; + break; + + case 12: + hcall->control = HVCALL_SEND_IPI; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 13: + recomm.eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + case 14: + /* Nothing in 'sparse banks' -> success */ + hcall->control = HVCALL_SEND_IPI_EX; + hcall->expect = HV_STATUS_SUCCESS; + break; + + case 15: + hcall->control = HVCALL_NOTIFY_LONG_SPIN_WAIT; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 16: + recomm.ebx = 0xfff; + hcall->expect = HV_STATUS_SUCCESS; + break; + + case 17: + /* END */ + hcall->control = 0; + break; + } + + hv_set_cpuid(vm, best, &feat, &recomm, &dbg); + + if (hcall->control) + pr_debug("Stage %d: testing hcall: 0x%lx\n", stage, + hcall->control); + else + pr_debug("Stage %d: finish\n", stage); + + r = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + TEST_ASSERT(uc.args[1] == stage, + "Unexpected stage: %ld (%d expected)\n", + uc.args[1], stage); + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); + return; + case UCALL_DONE: + return; + } + + stage++; + } +} + +int main(void) +{ + struct kvm_cpuid2 *best; + struct kvm_vm *vm; + vm_vaddr_t msr_gva, hcall_page, hcall_params; + struct kvm_enable_cap cap = { + .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, + .args = {1} + }; + + /* Test MSRs */ + vm = vm_create_default(VCPU_ID, 0, guest_msr); + + msr_gva = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); + vcpu_args_set(vm, VCPU_ID, 1, msr_gva); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_handle_exception(vm, GP_VECTOR, guest_gp_handler); + + pr_info("Testing access to Hyper-V specific MSRs\n"); + guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva), + best); + kvm_vm_free(vm); + + /* Test hypercalls */ + vm = vm_create_default(VCPU_ID, 0, guest_hcall); + + /* Hypercall input/output */ + hcall_page = vm_vaddr_alloc_pages(vm, 2); + memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); + + hcall_params = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); + + vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + pr_info("Testing access to Hyper-V hypercalls\n"); + guest_test_hcalls_access(vm, addr_gva2hva(vm, hcall_params), + addr_gva2hva(vm, hcall_page), + addr_gva2hva(vm, hcall_page) + getpagesize(), + best); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c new file mode 100644 index 000000000000..523371cf8e8f --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c @@ -0,0 +1,147 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "kvm_util.h" +#include "processor.h" + +#define VCPU_ID 1 + +#define MMIO_GPA 0x100000000ull + +static void guest_code(void) +{ + (void)READ_ONCE(*((uint64_t *)MMIO_GPA)); + (void)READ_ONCE(*((uint64_t *)MMIO_GPA)); + + GUEST_ASSERT(0); +} + +static void guest_pf_handler(struct ex_regs *regs) +{ + /* PFEC == RSVD | PRESENT (read, kernel). */ + GUEST_ASSERT(regs->error_code == 0x9); + GUEST_DONE(); +} + +static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val) +{ + u32 good_cpuid_val = *cpuid_reg; + struct kvm_run *run; + struct kvm_vm *vm; + uint64_t cmd; + int r; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + run = vcpu_state(vm, VCPU_ID); + + /* Map 1gb page without a backing memlot. */ + __virt_pg_map(vm, MMIO_GPA, MMIO_GPA, X86_PAGE_SIZE_1G); + + r = _vcpu_run(vm, VCPU_ID); + + /* Guest access to the 1gb page should trigger MMIO. */ + TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r); + TEST_ASSERT(run->exit_reason == KVM_EXIT_MMIO, + "Unexpected exit reason: %u (%s), expected MMIO exit (1gb page w/o memslot)\n", + run->exit_reason, exit_reason_str(run->exit_reason)); + + TEST_ASSERT(run->mmio.len == 8, "Unexpected exit mmio size = %u", run->mmio.len); + + TEST_ASSERT(run->mmio.phys_addr == MMIO_GPA, + "Unexpected exit mmio address = 0x%llx", run->mmio.phys_addr); + + /* + * Effect the CPUID change for the guest and re-enter the guest. Its + * access should now #PF due to the PAGE_SIZE bit being reserved or + * the resulting GPA being invalid. Note, kvm_get_supported_cpuid() + * returns the struct that contains the entry being modified. Eww. + */ + *cpuid_reg = evil_cpuid_val; + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + /* + * Add a dummy memslot to coerce KVM into bumping the MMIO generation. + * KVM does not "officially" support mucking with CPUID after KVM_RUN, + * and will incorrectly reuse MMIO SPTEs. Don't delete the memslot! + * KVM x86 zaps all shadow pages on memslot deletion. + */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + MMIO_GPA << 1, 10, 1, 0); + + /* Set up a #PF handler to eat the RSVD #PF and signal all done! */ + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_handle_exception(vm, PF_VECTOR, guest_pf_handler); + + r = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r); + + cmd = get_ucall(vm, VCPU_ID, NULL); + TEST_ASSERT(cmd == UCALL_DONE, + "Unexpected guest exit, exit_reason=%s, ucall.cmd = %lu\n", + exit_reason_str(run->exit_reason), cmd); + + /* + * Restore the happy CPUID value for the next test. Yes, changes are + * indeed persistent across VM destruction. + */ + *cpuid_reg = good_cpuid_val; + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + struct kvm_cpuid_entry2 *entry; + int opt; + + /* + * All tests are opt-in because TDP doesn't play nice with reserved #PF + * in the GVA->GPA translation. The hardware page walker doesn't let + * software change GBPAGES or MAXPHYADDR, and KVM doesn't manually walk + * the GVA on fault for performance reasons. + */ + bool do_gbpages = false; + bool do_maxphyaddr = false; + + setbuf(stdout, NULL); + + while ((opt = getopt(argc, argv, "gm")) != -1) { + switch (opt) { + case 'g': + do_gbpages = true; + break; + case 'm': + do_maxphyaddr = true; + break; + case 'h': + default: + printf("usage: %s [-g (GBPAGES)] [-m (MAXPHYADDR)]\n", argv[0]); + break; + } + } + + if (!do_gbpages && !do_maxphyaddr) { + print_skip("No sub-tests selected"); + return 0; + } + + entry = kvm_get_supported_cpuid_entry(0x80000001); + if (!(entry->edx & CPUID_GBPAGES)) { + print_skip("1gb hugepages not supported"); + return 0; + } + + if (do_gbpages) { + pr_info("Test MMIO after toggling CPUID.GBPAGES\n\n"); + mmu_role_test(&entry->edx, entry->edx & ~CPUID_GBPAGES); + } + + if (do_maxphyaddr) { + pr_info("Test MMIO after changing CPUID.MAXPHYADDR\n\n"); + entry = kvm_get_supported_cpuid_entry(0x80000008); + mmu_role_test(&entry->eax, (entry->eax & ~0xff) | 0x20); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c index 12c558fc8074..ae76436af0cc 100644 --- a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c +++ b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c @@ -14,16 +14,12 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "apic.h" #define N_VCPU 2 #define VCPU_ID0 0 #define VCPU_ID1 1 -static uint32_t get_bsp_flag(void) -{ - return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP; -} - static void guest_bsp_vcpu(void *arg) { GUEST_SYNC(1); @@ -94,7 +90,7 @@ static struct kvm_vm *create_vm(void) pages = vm_adjust_num_guest_pages(VM_MODE_DEFAULT, pages); vm = vm_create(VM_MODE_DEFAULT, pages, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); + kvm_vm_elf_load(vm, program_invocation_name); vm_create_irqchip(vm); return vm; @@ -106,8 +102,6 @@ static void add_x86_vcpu(struct kvm_vm *vm, uint32_t vcpuid, bool bsp_code) vm_vcpu_add_default(vm, vcpuid, guest_bsp_vcpu); else vm_vcpu_add_default(vm, vcpuid, guest_not_bsp_vcpu); - - vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid()); } static void run_vm_bsp(uint32_t bsp_vcpu) diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index 613c42c5a9b8..c1f831803ad2 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -55,8 +55,8 @@ static inline void sync_with_host(uint64_t phase) void self_smi(void) { - wrmsr(APIC_BASE_MSR + (APIC_ICR >> 4), - APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI); + x2apic_write_reg(APIC_ICR, + APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI); } void guest_code(void *arg) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c index d14888b34adb..d438c4d3228a 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c @@ -96,7 +96,7 @@ int main(int argc, char *argv[]) } vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); - prepare_virtualize_apic_accesses(vmx, vm, 0); + prepare_virtualize_apic_accesses(vmx, vm); vcpu_args_set(vm, VCPU_ID, 2, vmx_pages_gva, high_gpa); while (!done) { diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index 537de1068554..06a64980a5d2 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -97,7 +97,7 @@ int main(int argc, char *argv[]) * Add an identity map for GVA range [0xc0000000, 0xc0002000). This * affects both L1 and L2. However... */ - virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM, TEST_MEM_PAGES, 0); + virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM, TEST_MEM_PAGES); /* * ... pages in the L2 GPA range [0xc0001000, 0xc0003000) will map to @@ -107,9 +107,9 @@ int main(int argc, char *argv[]) * meaning after the last call to virt_map. */ prepare_eptp(vmx, vm, 0); - nested_map_memslot(vmx, vm, 0, 0); - nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096, 0); - nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096, 0); + nested_map_memslot(vmx, vm, 0); + nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096); + nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096); bmap = bitmap_alloc(TEST_MEM_PAGES); host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c new file mode 100644 index 000000000000..280c01fd2412 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vmx_nested_tsc_scaling_test + * + * Copyright 2021 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * + * This test case verifies that nested TSC scaling behaves as expected when + * both L1 and L2 are scaled using different ratios. For this test we scale + * L1 down and scale L2 up. + */ + +#include <time.h> + +#include "kvm_util.h" +#include "vmx.h" +#include "kselftest.h" + + +#define VCPU_ID 0 + +/* L2 is scaled up (from L1's perspective) by this factor */ +#define L2_SCALE_FACTOR 4ULL + +#define TSC_OFFSET_L2 ((uint64_t) -33125236320908) +#define TSC_MULTIPLIER_L2 (L2_SCALE_FACTOR << 48) + +#define L2_GUEST_STACK_SIZE 64 + +enum { USLEEP, UCHECK_L1, UCHECK_L2 }; +#define GUEST_SLEEP(sec) ucall(UCALL_SYNC, 2, USLEEP, sec) +#define GUEST_CHECK(level, freq) ucall(UCALL_SYNC, 2, level, freq) + + +/* + * This function checks whether the "actual" TSC frequency of a guest matches + * its expected frequency. In order to account for delays in taking the TSC + * measurements, a difference of 1% between the actual and the expected value + * is tolerated. + */ +static void compare_tsc_freq(uint64_t actual, uint64_t expected) +{ + uint64_t tolerance, thresh_low, thresh_high; + + tolerance = expected / 100; + thresh_low = expected - tolerance; + thresh_high = expected + tolerance; + + TEST_ASSERT(thresh_low < actual, + "TSC freq is expected to be between %"PRIu64" and %"PRIu64 + " but it actually is %"PRIu64, + thresh_low, thresh_high, actual); + TEST_ASSERT(thresh_high > actual, + "TSC freq is expected to be between %"PRIu64" and %"PRIu64 + " but it actually is %"PRIu64, + thresh_low, thresh_high, actual); +} + +static void check_tsc_freq(int level) +{ + uint64_t tsc_start, tsc_end, tsc_freq; + + /* + * Reading the TSC twice with about a second's difference should give + * us an approximation of the TSC frequency from the guest's + * perspective. Now, this won't be completely accurate, but it should + * be good enough for the purposes of this test. + */ + tsc_start = rdmsr(MSR_IA32_TSC); + GUEST_SLEEP(1); + tsc_end = rdmsr(MSR_IA32_TSC); + + tsc_freq = tsc_end - tsc_start; + + GUEST_CHECK(level, tsc_freq); +} + +static void l2_guest_code(void) +{ + check_tsc_freq(UCHECK_L2); + + /* exit to L1 */ + __asm__ __volatile__("vmcall"); +} + +static void l1_guest_code(struct vmx_pages *vmx_pages) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + uint32_t control; + + /* check that L1's frequency looks alright before launching L2 */ + check_tsc_freq(UCHECK_L1); + + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_vmcs(vmx_pages)); + + /* prepare the VMCS for L2 execution */ + prepare_vmcs(vmx_pages, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* enable TSC offsetting and TSC scaling for L2 */ + control = vmreadz(CPU_BASED_VM_EXEC_CONTROL); + control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETTING; + vmwrite(CPU_BASED_VM_EXEC_CONTROL, control); + + control = vmreadz(SECONDARY_VM_EXEC_CONTROL); + control |= SECONDARY_EXEC_TSC_SCALING; + vmwrite(SECONDARY_VM_EXEC_CONTROL, control); + + vmwrite(TSC_OFFSET, TSC_OFFSET_L2); + vmwrite(TSC_MULTIPLIER, TSC_MULTIPLIER_L2); + vmwrite(TSC_MULTIPLIER_HIGH, TSC_MULTIPLIER_L2 >> 32); + + /* launch L2 */ + GUEST_ASSERT(!vmlaunch()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + + /* check that L1's frequency still looks good */ + check_tsc_freq(UCHECK_L1); + + GUEST_DONE(); +} + +static void tsc_scaling_check_supported(void) +{ + if (!kvm_check_cap(KVM_CAP_TSC_CONTROL)) { + print_skip("TSC scaling not supported by the HW"); + exit(KSFT_SKIP); + } +} + +static void stable_tsc_check_supported(void) +{ + FILE *fp; + char buf[4]; + + fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r"); + if (fp == NULL) + goto skip_test; + + if (fgets(buf, sizeof(buf), fp) == NULL) + goto skip_test; + + if (strncmp(buf, "tsc", sizeof(buf))) + goto skip_test; + + return; +skip_test: + print_skip("Kernel does not use TSC clocksource - assuming that host TSC is not stable"); + exit(KSFT_SKIP); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + vm_vaddr_t vmx_pages_gva; + + uint64_t tsc_start, tsc_end; + uint64_t tsc_khz; + uint64_t l1_scale_factor; + uint64_t l0_tsc_freq = 0; + uint64_t l1_tsc_freq = 0; + uint64_t l2_tsc_freq = 0; + + nested_vmx_check_supported(); + tsc_scaling_check_supported(); + stable_tsc_check_supported(); + + /* + * We set L1's scale factor to be a random number from 2 to 10. + * Ideally we would do the same for L2's factor but that one is + * referenced by both main() and l1_guest_code() and using a global + * variable does not work. + */ + srand(time(NULL)); + l1_scale_factor = (rand() % 9) + 2; + printf("L1's scale down factor is: %"PRIu64"\n", l1_scale_factor); + printf("L2's scale up factor is: %llu\n", L2_SCALE_FACTOR); + + tsc_start = rdtsc(); + sleep(1); + tsc_end = rdtsc(); + + l0_tsc_freq = tsc_end - tsc_start; + printf("real TSC frequency is around: %"PRIu64"\n", l0_tsc_freq); + + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + + tsc_khz = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_TSC_KHZ, NULL); + TEST_ASSERT(tsc_khz != -1, "vcpu ioctl KVM_GET_TSC_KHZ failed"); + + /* scale down L1's TSC frequency */ + vcpu_ioctl(vm, VCPU_ID, KVM_SET_TSC_KHZ, + (void *) (tsc_khz / l1_scale_factor)); + + for (;;) { + volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("%s", (const char *) uc.args[0]); + case UCALL_SYNC: + switch (uc.args[0]) { + case USLEEP: + sleep(uc.args[1]); + break; + case UCHECK_L1: + l1_tsc_freq = uc.args[1]; + printf("L1's TSC frequency is around: %"PRIu64 + "\n", l1_tsc_freq); + + compare_tsc_freq(l1_tsc_freq, + l0_tsc_freq / l1_scale_factor); + break; + case UCHECK_L2: + l2_tsc_freq = uc.args[1]; + printf("L2's TSC frequency is around: %"PRIu64 + "\n", l2_tsc_freq); + + compare_tsc_freq(l2_tsc_freq, + l1_tsc_freq * L2_SCALE_FACTOR); + break; + } + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } + +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c index 2f964cdc273c..1846117ad584 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c @@ -42,8 +42,6 @@ #define HALTER_VCPU_ID 0 #define SENDER_VCPU_ID 1 -volatile uint32_t *apic_base = (volatile uint32_t *)APIC_DEFAULT_GPA; - /* * Vector for IPI from sender vCPU to halting vCPU. * Value is arbitrary and was chosen for the alternating bit pattern. Any @@ -86,45 +84,6 @@ struct thread_params { uint64_t *pipis_rcvd; /* host address of ipis_rcvd global */ }; -uint32_t read_apic_reg(uint reg) -{ - return apic_base[reg >> 2]; -} - -void write_apic_reg(uint reg, uint32_t val) -{ - apic_base[reg >> 2] = val; -} - -void disable_apic(void) -{ - wrmsr(MSR_IA32_APICBASE, - rdmsr(MSR_IA32_APICBASE) & - ~(MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD)); -} - -void enable_xapic(void) -{ - uint64_t val = rdmsr(MSR_IA32_APICBASE); - - /* Per SDM: to enable xAPIC when in x2APIC must first disable APIC */ - if (val & MSR_IA32_APICBASE_EXTD) { - disable_apic(); - wrmsr(MSR_IA32_APICBASE, - rdmsr(MSR_IA32_APICBASE) | MSR_IA32_APICBASE_ENABLE); - } else if (!(val & MSR_IA32_APICBASE_ENABLE)) { - wrmsr(MSR_IA32_APICBASE, val | MSR_IA32_APICBASE_ENABLE); - } - - /* - * Per SDM: reset value of spurious interrupt vector register has the - * APIC software enabled bit=0. It must be enabled in addition to the - * enable bit in the MSR. - */ - val = read_apic_reg(APIC_SPIV) | APIC_SPIV_APIC_ENABLED; - write_apic_reg(APIC_SPIV, val); -} - void verify_apic_base_addr(void) { uint64_t msr = rdmsr(MSR_IA32_APICBASE); @@ -136,10 +95,10 @@ void verify_apic_base_addr(void) static void halter_guest_code(struct test_data_page *data) { verify_apic_base_addr(); - enable_xapic(); + xapic_enable(); - data->halter_apic_id = GET_APIC_ID_FIELD(read_apic_reg(APIC_ID)); - data->halter_lvr = read_apic_reg(APIC_LVR); + data->halter_apic_id = GET_APIC_ID_FIELD(xapic_read_reg(APIC_ID)); + data->halter_lvr = xapic_read_reg(APIC_LVR); /* * Loop forever HLTing and recording halts & wakes. Disable interrupts @@ -150,8 +109,8 @@ static void halter_guest_code(struct test_data_page *data) * TPR and PPR for diagnostic purposes in case the test fails. */ for (;;) { - data->halter_tpr = read_apic_reg(APIC_TASKPRI); - data->halter_ppr = read_apic_reg(APIC_PROCPRI); + data->halter_tpr = xapic_read_reg(APIC_TASKPRI); + data->halter_ppr = xapic_read_reg(APIC_PROCPRI); data->hlt_count++; asm volatile("sti; hlt; cli"); data->wake_count++; @@ -166,7 +125,7 @@ static void halter_guest_code(struct test_data_page *data) static void guest_ipi_handler(struct ex_regs *regs) { ipis_rcvd++; - write_apic_reg(APIC_EOI, 77); + xapic_write_reg(APIC_EOI, 77); } static void sender_guest_code(struct test_data_page *data) @@ -179,7 +138,7 @@ static void sender_guest_code(struct test_data_page *data) uint64_t tsc_start; verify_apic_base_addr(); - enable_xapic(); + xapic_enable(); /* * Init interrupt command register for sending IPIs @@ -206,8 +165,8 @@ static void sender_guest_code(struct test_data_page *data) * First IPI can be sent unconditionally because halter vCPU * starts earlier. */ - write_apic_reg(APIC_ICR2, icr2_val); - write_apic_reg(APIC_ICR, icr_val); + xapic_write_reg(APIC_ICR2, icr2_val); + xapic_write_reg(APIC_ICR, icr_val); data->ipis_sent++; /* @@ -464,11 +423,11 @@ int main(int argc, char *argv[]) vcpu_init_descriptor_tables(vm, HALTER_VCPU_ID); vm_handle_exception(vm, IPI_VECTOR, guest_ipi_handler); - virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA, 0); + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); vm_vcpu_add_default(vm, SENDER_VCPU_ID, sender_guest_code); - test_data_page_vaddr = vm_vaddr_alloc(vm, 0x1000, 0x1000, 0, 0); + test_data_page_vaddr = vm_vaddr_alloc_page(vm); data = (struct test_data_page *)addr_gva2hva(vm, test_data_page_vaddr); memset(data, 0, sizeof(*data)); diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 1f4a0599683c..117bf49a3d79 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -146,7 +146,7 @@ int main(int argc, char *argv[]) /* Map a region for the shared_info page */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 2, 0); - virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2, 0); + virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2); struct kvm_xen_hvm_config hvmc = { .flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL, diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c index 8389e0bfd711..adc94452b57c 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -103,7 +103,7 @@ int main(int argc, char *argv[]) /* Map a region for the hypercall pages */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, HCALL_REGION_GPA, HCALL_REGION_SLOT, 2, 0); - virt_map(vm, HCALL_REGION_GPA, HCALL_REGION_GPA, 2, 0); + virt_map(vm, HCALL_REGION_GPA, HCALL_REGION_GPA, 2); for (;;) { volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 1c37ccd5d402..62b39149b8c8 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -63,3 +63,6 @@ config HAVE_KVM_NO_POLL config KVM_XFER_TO_GUEST_WORK bool + +config HAVE_KVM_PM_NOTIFIER + bool diff --git a/virt/kvm/binary_stats.c b/virt/kvm/binary_stats.c new file mode 100644 index 000000000000..e609d428811a --- /dev/null +++ b/virt/kvm/binary_stats.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM binary statistics interface implementation + * + * Copyright 2021 Google LLC + */ + +#include <linux/kvm_host.h> +#include <linux/kvm.h> +#include <linux/errno.h> +#include <linux/uaccess.h> + +/** + * kvm_stats_read() - Common function to read from the binary statistics + * file descriptor. + * + * @id: identification string of the stats + * @header: stats header for a vm or a vcpu + * @desc: start address of an array of stats descriptors for a vm or a vcpu + * @stats: start address of stats data block for a vm or a vcpu + * @size_stats: the size of stats data block pointed by @stats + * @user_buffer: start address of userspace buffer + * @size: requested read size from userspace + * @offset: the start position from which the content will be read for the + * corresponding vm or vcp file descriptor + * + * The file content of a vm/vcpu file descriptor is now defined as below: + * +-------------+ + * | Header | + * +-------------+ + * | id string | + * +-------------+ + * | Descriptors | + * +-------------+ + * | Stats Data | + * +-------------+ + * Although this function allows userspace to read any amount of data (as long + * as in the limit) from any position, the typical usage would follow below + * steps: + * 1. Read header from offset 0. Get the offset of descriptors and stats data + * and some other necessary information. This is a one-time work for the + * lifecycle of the corresponding vm/vcpu stats fd. + * 2. Read id string from its offset. This is a one-time work for the lifecycle + * of the corresponding vm/vcpu stats fd. + * 3. Read descriptors from its offset and discover all the stats by parsing + * descriptors. This is a one-time work for the lifecycle of the + * corresponding vm/vcpu stats fd. + * 4. Periodically read stats data from its offset using pread. + * + * Return: the number of bytes that has been successfully read + */ +ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, + const struct _kvm_stats_desc *desc, + void *stats, size_t size_stats, + char __user *user_buffer, size_t size, loff_t *offset) +{ + ssize_t len; + ssize_t copylen; + ssize_t remain = size; + size_t size_desc; + size_t size_header; + void *src; + loff_t pos = *offset; + char __user *dest = user_buffer; + + size_header = sizeof(*header); + size_desc = header->num_desc * sizeof(*desc); + + len = KVM_STATS_NAME_SIZE + size_header + size_desc + size_stats - pos; + len = min(len, remain); + if (len <= 0) + return 0; + remain = len; + + /* + * Copy kvm stats header. + * The header is the first block of content userspace usually read out. + * The pos is 0 and the copylen and remain would be the size of header. + * The copy of the header would be skipped if offset is larger than the + * size of header. That usually happens when userspace reads stats + * descriptors and stats data. + */ + copylen = size_header - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = (void *)header + pos; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + remain -= copylen; + pos += copylen; + dest += copylen; + } + + /* + * Copy kvm stats header id string. + * The id string is unique for every vm/vcpu, which is stored in kvm + * and kvm_vcpu structure. + * The id string is part of the stat header from the perspective of + * userspace, it is usually read out together with previous constant + * header part and could be skipped for later descriptors and stats + * data readings. + */ + copylen = header->id_offset + KVM_STATS_NAME_SIZE - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = id + pos - header->id_offset; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + remain -= copylen; + pos += copylen; + dest += copylen; + } + + /* + * Copy kvm stats descriptors. + * The descriptors copy would be skipped in the typical case that + * userspace periodically read stats data, since the pos would be + * greater than the end address of descriptors + * (header->header.desc_offset + size_desc) causing copylen <= 0. + */ + copylen = header->desc_offset + size_desc - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = (void *)desc + pos - header->desc_offset; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + remain -= copylen; + pos += copylen; + dest += copylen; + } + + /* Copy kvm stats values */ + copylen = header->data_offset + size_stats - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = stats + pos - header->data_offset; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + remain -= copylen; + pos += copylen; + dest += copylen; + } + + *offset = pos; + return len; +} diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2799c6660cce..3dcc2abbfc60 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -51,6 +51,7 @@ #include <linux/io.h> #include <linux/lockdep.h> #include <linux/kthread.h> +#include <linux/suspend.h> #include <asm/processor.h> #include <asm/ioctl.h> @@ -114,7 +115,6 @@ static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu); struct dentry *kvm_debugfs_dir; EXPORT_SYMBOL_GPL(kvm_debugfs_dir); -static int kvm_debugfs_num_entries; static const struct file_operations stat_fops_per_vm; static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, @@ -307,6 +307,7 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) { return kvm_make_all_cpus_request_except(kvm, req, NULL); } +EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL void kvm_flush_remote_tlbs(struct kvm *kvm) @@ -330,7 +331,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) */ if (!kvm_arch_flush_remote_tlb(kvm) || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) - ++kvm->stat.remote_tlb_flush; + ++kvm->stat.generic.remote_tlb_flush; cmpxchg(&kvm->tlbs_dirty, dirty_count, 0); } EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); @@ -779,6 +780,38 @@ static int kvm_init_mmu_notifier(struct kvm *kvm) #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */ +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +static int kvm_pm_notifier_call(struct notifier_block *bl, + unsigned long state, + void *unused) +{ + struct kvm *kvm = container_of(bl, struct kvm, pm_notifier); + + return kvm_arch_pm_notifier(kvm, state); +} + +static void kvm_init_pm_notifier(struct kvm *kvm) +{ + kvm->pm_notifier.notifier_call = kvm_pm_notifier_call; + /* Suspend KVM before we suspend ftrace, RCU, etc. */ + kvm->pm_notifier.priority = INT_MAX; + register_pm_notifier(&kvm->pm_notifier); +} + +static void kvm_destroy_pm_notifier(struct kvm *kvm) +{ + unregister_pm_notifier(&kvm->pm_notifier); +} +#else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */ +static void kvm_init_pm_notifier(struct kvm *kvm) +{ +} + +static void kvm_destroy_pm_notifier(struct kvm *kvm) +{ +} +#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ + static struct kvm_memslots *kvm_alloc_memslots(void) { int i; @@ -826,9 +859,24 @@ static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) kvfree(slots); } +static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc) +{ + switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) { + case KVM_STATS_TYPE_INSTANT: + return 0444; + case KVM_STATS_TYPE_CUMULATIVE: + case KVM_STATS_TYPE_PEAK: + default: + return 0644; + } +} + + static void kvm_destroy_vm_debugfs(struct kvm *kvm) { int i; + int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + + kvm_vcpu_stats_header.num_desc; if (!kvm->debugfs_dentry) return; @@ -846,7 +894,10 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) { char dir_name[ITOA_MAX_LEN * 2]; struct kvm_stat_data *stat_data; - struct kvm_stats_debugfs_item *p; + const struct _kvm_stats_desc *pdesc; + int i; + int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + + kvm_vcpu_stats_header.num_desc; if (!debugfs_initialized()) return 0; @@ -860,15 +911,32 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) if (!kvm->debugfs_stat_data) return -ENOMEM; - for (p = debugfs_entries; p->name; p++) { + for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { + pdesc = &kvm_vm_stats_desc[i]; + stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); + if (!stat_data) + return -ENOMEM; + + stat_data->kvm = kvm; + stat_data->desc = pdesc; + stat_data->kind = KVM_STAT_VM; + kvm->debugfs_stat_data[i] = stat_data; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), + kvm->debugfs_dentry, stat_data, + &stat_fops_per_vm); + } + + for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { + pdesc = &kvm_vcpu_stats_desc[i]; stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); if (!stat_data) return -ENOMEM; stat_data->kvm = kvm; - stat_data->dbgfs_item = p; - kvm->debugfs_stat_data[p - debugfs_entries] = stat_data; - debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p), + stat_data->desc = pdesc; + stat_data->kind = KVM_STAT_VCPU; + kvm->debugfs_stat_data[i] = stat_data; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm->debugfs_dentry, stat_data, &stat_fops_per_vm); } @@ -908,6 +976,7 @@ static struct kvm *kvm_create_vm(unsigned long type) mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); mutex_init(&kvm->slots_lock); + mutex_init(&kvm->slots_arch_lock); INIT_LIST_HEAD(&kvm->devices); BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); @@ -962,6 +1031,7 @@ static struct kvm *kvm_create_vm(unsigned long type) mutex_unlock(&kvm_lock); preempt_notifier_inc(); + kvm_init_pm_notifier(kvm); return kvm; @@ -1009,6 +1079,7 @@ static void kvm_destroy_vm(struct kvm *kvm) int i; struct mm_struct *mm = kvm->mm; + kvm_destroy_pm_notifier(kvm); kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm); kvm_destroy_vm_debugfs(kvm); kvm_arch_sync_events(kvm); @@ -1280,6 +1351,14 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; rcu_assign_pointer(kvm->memslots[as_id], slots); + + /* + * Acquired in kvm_set_memslot. Must be released before synchronize + * SRCU below in order to avoid deadlock with another thread + * acquiring the slots_arch_lock in an srcu critical section. + */ + mutex_unlock(&kvm->slots_arch_lock); + synchronize_srcu_expedited(&kvm->srcu); /* @@ -1306,6 +1385,18 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, return old_memslots; } +static size_t kvm_memslots_size(int slots) +{ + return sizeof(struct kvm_memslots) + + (sizeof(struct kvm_memory_slot) * slots); +} + +static void kvm_copy_memslots(struct kvm_memslots *to, + struct kvm_memslots *from) +{ + memcpy(to, from, kvm_memslots_size(from->used_slots)); +} + /* * Note, at a minimum, the current number of used slots must be allocated, even * when deleting a memslot, as we need a complete duplicate of the memslots for @@ -1315,19 +1406,16 @@ static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old, enum kvm_mr_change change) { struct kvm_memslots *slots; - size_t old_size, new_size; - - old_size = sizeof(struct kvm_memslots) + - (sizeof(struct kvm_memory_slot) * old->used_slots); + size_t new_size; if (change == KVM_MR_CREATE) - new_size = old_size + sizeof(struct kvm_memory_slot); + new_size = kvm_memslots_size(old->used_slots + 1); else - new_size = old_size; + new_size = kvm_memslots_size(old->used_slots); slots = kvzalloc(new_size, GFP_KERNEL_ACCOUNT); if (likely(slots)) - memcpy(slots, old, old_size); + kvm_copy_memslots(slots, old); return slots; } @@ -1342,9 +1430,27 @@ static int kvm_set_memslot(struct kvm *kvm, struct kvm_memslots *slots; int r; + /* + * Released in install_new_memslots. + * + * Must be held from before the current memslots are copied until + * after the new memslots are installed with rcu_assign_pointer, + * then released before the synchronize srcu in install_new_memslots. + * + * When modifying memslots outside of the slots_lock, must be held + * before reading the pointer to the current memslots until after all + * changes to those memslots are complete. + * + * These rules ensure that installing new memslots does not lose + * changes made to the previous memslots. + */ + mutex_lock(&kvm->slots_arch_lock); + slots = kvm_dup_memslots(__kvm_memslots(kvm, as_id), change); - if (!slots) + if (!slots) { + mutex_unlock(&kvm->slots_arch_lock); return -ENOMEM; + } if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { /* @@ -1355,10 +1461,9 @@ static int kvm_set_memslot(struct kvm *kvm, slot->flags |= KVM_MEMSLOT_INVALID; /* - * We can re-use the old memslots, the only difference from the - * newly installed memslots is the invalid flag, which will get - * dropped by update_memslots anyway. We'll also revert to the - * old memslots if preparing the new memory region fails. + * We can re-use the memory from the old memslots. + * It will be overwritten with a copy of the new memslots + * after reacquiring the slots_arch_lock below. */ slots = install_new_memslots(kvm, as_id, slots); @@ -1370,6 +1475,17 @@ static int kvm_set_memslot(struct kvm *kvm, * - kvm_is_visible_gfn (mmu_check_root) */ kvm_arch_flush_shadow_memslot(kvm, slot); + + /* Released in install_new_memslots. */ + mutex_lock(&kvm->slots_arch_lock); + + /* + * The arch-specific fields of the memslots could have changed + * between releasing the slots_arch_lock in + * install_new_memslots and here, so get a fresh copy of the + * slots. + */ + kvm_copy_memslots(slots, __kvm_memslots(kvm, as_id)); } r = kvm_arch_prepare_memory_region(kvm, new, mem, change); @@ -1385,8 +1501,13 @@ static int kvm_set_memslot(struct kvm *kvm, return 0; out_slots: - if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { + slot = id_to_memslot(slots, old->id); + slot->flags &= ~KVM_MEMSLOT_INVALID; slots = install_new_memslots(kvm, as_id, slots); + } else { + mutex_unlock(&kvm->slots_arch_lock); + } kvfree(slots); return r; } @@ -2893,8 +3014,8 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) if (val < grow_start) val = grow_start; - if (val > halt_poll_ns) - val = halt_poll_ns; + if (val > vcpu->kvm->max_halt_poll_ns) + val = vcpu->kvm->max_halt_poll_ns; vcpu->halt_poll_ns = val; out: @@ -2929,6 +3050,8 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) goto out; if (signal_pending(current)) goto out; + if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu)) + goto out; ret = 0; out: @@ -2940,9 +3063,9 @@ static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, u64 poll_ns, bool waited) { if (waited) - vcpu->stat.halt_poll_fail_ns += poll_ns; + vcpu->stat.generic.halt_poll_fail_ns += poll_ns; else - vcpu->stat.halt_poll_success_ns += poll_ns; + vcpu->stat.generic.halt_poll_success_ns += poll_ns; } /* @@ -2960,20 +3083,20 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) { ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns); - ++vcpu->stat.halt_attempted_poll; + ++vcpu->stat.generic.halt_attempted_poll; do { /* * This sets KVM_REQ_UNHALT if an interrupt * arrives. */ if (kvm_vcpu_check_block(vcpu) < 0) { - ++vcpu->stat.halt_successful_poll; + ++vcpu->stat.generic.halt_successful_poll; if (!vcpu_valid_wakeup(vcpu)) - ++vcpu->stat.halt_poll_invalid; + ++vcpu->stat.generic.halt_poll_invalid; goto out; } poll_end = cur = ktime_get(); - } while (single_task_running() && ktime_before(cur, stop)); + } while (kvm_vcpu_can_poll(cur, stop)); } prepare_to_rcuwait(&vcpu->wait); @@ -3026,7 +3149,7 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) waitp = kvm_arch_vcpu_get_wait(vcpu); if (rcuwait_wake_up(waitp)) { WRITE_ONCE(vcpu->ready, true); - ++vcpu->stat.halt_wakeup; + ++vcpu->stat.generic.halt_wakeup; return true; } @@ -3359,6 +3482,10 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); BUG_ON(kvm->vcpus[vcpu->vcpu_idx]); + /* Fill the stats id string for the vcpu */ + snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d", + task_pid_nr(current), id); + /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); @@ -3408,6 +3535,44 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) return 0; } +static ssize_t kvm_vcpu_stats_read(struct file *file, char __user *user_buffer, + size_t size, loff_t *offset) +{ + struct kvm_vcpu *vcpu = file->private_data; + + return kvm_stats_read(vcpu->stats_id, &kvm_vcpu_stats_header, + &kvm_vcpu_stats_desc[0], &vcpu->stat, + sizeof(vcpu->stat), user_buffer, size, offset); +} + +static const struct file_operations kvm_vcpu_stats_fops = { + .read = kvm_vcpu_stats_read, + .llseek = noop_llseek, +}; + +static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu) +{ + int fd; + struct file *file; + char name[15 + ITOA_MAX_LEN + 1]; + + snprintf(name, sizeof(name), "kvm-vcpu-stats:%d", vcpu->vcpu_id); + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + file = anon_inode_getfile(name, &kvm_vcpu_stats_fops, vcpu, O_RDONLY); + if (IS_ERR(file)) { + put_unused_fd(fd); + return PTR_ERR(file); + } + file->f_mode |= FMODE_PREAD; + fd_install(fd, file); + + return fd; +} + static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -3605,6 +3770,10 @@ out_free1: r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu); break; } + case KVM_GET_STATS_FD: { + r = kvm_vcpu_ioctl_get_stats_fd(vcpu); + break; + } default: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } @@ -3863,6 +4032,8 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) #else return 0; #endif + case KVM_CAP_BINARY_STATS_FD: + return 1; default: break; } @@ -3966,6 +4137,42 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, } } +static ssize_t kvm_vm_stats_read(struct file *file, char __user *user_buffer, + size_t size, loff_t *offset) +{ + struct kvm *kvm = file->private_data; + + return kvm_stats_read(kvm->stats_id, &kvm_vm_stats_header, + &kvm_vm_stats_desc[0], &kvm->stat, + sizeof(kvm->stat), user_buffer, size, offset); +} + +static const struct file_operations kvm_vm_stats_fops = { + .read = kvm_vm_stats_read, + .llseek = noop_llseek, +}; + +static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm) +{ + int fd; + struct file *file; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + file = anon_inode_getfile("kvm-vm-stats", + &kvm_vm_stats_fops, kvm, O_RDONLY); + if (IS_ERR(file)) { + put_unused_fd(fd); + return PTR_ERR(file); + } + file->f_mode |= FMODE_PREAD; + fd_install(fd, file); + + return fd; +} + static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4148,6 +4355,9 @@ static long kvm_vm_ioctl(struct file *filp, case KVM_RESET_DIRTY_RINGS: r = kvm_vm_ioctl_reset_dirty_pages(kvm); break; + case KVM_GET_STATS_FD: + r = kvm_vm_ioctl_get_stats_fd(kvm); + break; default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); } @@ -4227,6 +4437,9 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) if (r < 0) goto put_kvm; + snprintf(kvm->stats_id, sizeof(kvm->stats_id), + "kvm-%d", task_pid_nr(current)); + file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); if (IS_ERR(file)) { put_unused_fd(r); @@ -4721,7 +4934,7 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file, return -ENOENT; if (simple_attr_open(inode, file, get, - KVM_DBGFS_GET_MODE(stat_data->dbgfs_item) & 0222 + kvm_stats_debugfs_mode(stat_data->desc) & 0222 ? set : NULL, fmt)) { kvm_put_kvm(stat_data->kvm); @@ -4744,14 +4957,14 @@ static int kvm_debugfs_release(struct inode *inode, struct file *file) static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val) { - *val = *(ulong *)((void *)kvm + offset); + *val = *(u64 *)((void *)(&kvm->stat) + offset); return 0; } static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset) { - *(ulong *)((void *)kvm + offset) = 0; + *(u64 *)((void *)(&kvm->stat) + offset) = 0; return 0; } @@ -4764,7 +4977,7 @@ static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) *val = 0; kvm_for_each_vcpu(i, vcpu, kvm) - *val += *(u64 *)((void *)vcpu + offset); + *val += *(u64 *)((void *)(&vcpu->stat) + offset); return 0; } @@ -4775,7 +4988,7 @@ static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset) struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) - *(u64 *)((void *)vcpu + offset) = 0; + *(u64 *)((void *)(&vcpu->stat) + offset) = 0; return 0; } @@ -4785,14 +4998,14 @@ static int kvm_stat_data_get(void *data, u64 *val) int r = -EFAULT; struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data; - switch (stat_data->dbgfs_item->kind) { + switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_get_stat_per_vm(stat_data->kvm, - stat_data->dbgfs_item->offset, val); + stat_data->desc->desc.offset, val); break; case KVM_STAT_VCPU: r = kvm_get_stat_per_vcpu(stat_data->kvm, - stat_data->dbgfs_item->offset, val); + stat_data->desc->desc.offset, val); break; } @@ -4807,14 +5020,14 @@ static int kvm_stat_data_clear(void *data, u64 val) if (val) return -EINVAL; - switch (stat_data->dbgfs_item->kind) { + switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_clear_stat_per_vm(stat_data->kvm, - stat_data->dbgfs_item->offset); + stat_data->desc->desc.offset); break; case KVM_STAT_VCPU: r = kvm_clear_stat_per_vcpu(stat_data->kvm, - stat_data->dbgfs_item->offset); + stat_data->desc->desc.offset); break; } @@ -4871,6 +5084,7 @@ static int vm_stat_clear(void *_offset, u64 val) } DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(vm_stat_readonly_fops, vm_stat_get, NULL, "%llu\n"); static int vcpu_stat_get(void *_offset, u64 *val) { @@ -4907,11 +5121,7 @@ static int vcpu_stat_clear(void *_offset, u64 val) DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear, "%llu\n"); - -static const struct file_operations *stat_fops[] = { - [KVM_STAT_VCPU] = &vcpu_stat_fops, - [KVM_STAT_VM] = &vm_stat_fops, -}; +DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_readonly_fops, vcpu_stat_get, NULL, "%llu\n"); static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) { @@ -4965,15 +5175,32 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) static void kvm_init_debug(void) { - struct kvm_stats_debugfs_item *p; + const struct file_operations *fops; + const struct _kvm_stats_desc *pdesc; + int i; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); - kvm_debugfs_num_entries = 0; - for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) { - debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p), - kvm_debugfs_dir, (void *)(long)p->offset, - stat_fops[p->kind]); + for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { + pdesc = &kvm_vm_stats_desc[i]; + if (kvm_stats_debugfs_mode(pdesc) & 0222) + fops = &vm_stat_fops; + else + fops = &vm_stat_readonly_fops; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), + kvm_debugfs_dir, + (void *)(long)pdesc->desc.offset, fops); + } + + for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { + pdesc = &kvm_vcpu_stats_desc[i]; + if (kvm_stats_debugfs_mode(pdesc) & 0222) + fops = &vcpu_stat_fops; + else + fops = &vcpu_stat_readonly_fops; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), + kvm_debugfs_dir, + (void *)(long)pdesc->desc.offset, fops); } } @@ -5123,7 +5350,8 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align, SLAB_ACCOUNT, offsetof(struct kvm_vcpu, arch), - sizeof_field(struct kvm_vcpu, arch), + offsetofend(struct kvm_vcpu, stats_id) + - offsetof(struct kvm_vcpu, arch), NULL); if (!kvm_vcpu_cache) { r = -ENOMEM; diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c index c9bb3957f58a..28fda42e471b 100644 --- a/virt/lib/irqbypass.c +++ b/virt/lib/irqbypass.c @@ -40,21 +40,17 @@ static int __connect(struct irq_bypass_producer *prod, if (prod->add_consumer) ret = prod->add_consumer(prod, cons); - if (ret) - goto err_add_consumer; - - ret = cons->add_producer(cons, prod); - if (ret) - goto err_add_producer; + if (!ret) { + ret = cons->add_producer(cons, prod); + if (ret && prod->del_consumer) + prod->del_consumer(prod, cons); + } if (cons->start) cons->start(cons); if (prod->start) prod->start(prod); -err_add_producer: - if (prod->del_consumer) - prod->del_consumer(prod, cons); -err_add_consumer: + return ret; } |