diff options
| author |   Linus Torvalds <torvalds@linux-foundation.org> | 2020-04-02 15:13:15 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-04-02 15:13:15 -0700 |
| commit | 8c1b724ddb218f221612d4c649bc9c7819d8d7a6 (patch) | |
| tree | 0e226f4156b554eec2690adb8f30ba54b15b68cc | |
| parent | Merge tag 'x86-urgent-2020-04-02' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip (diff) | |
| parent | x86/kvm: fix a missing-prototypes "vmread_error" (diff) | |
| download | linux-dev-8c1b724ddb218f221612d4c649bc9c7819d8d7a6.tar.xz linux-dev-8c1b724ddb218f221612d4c649bc9c7819d8d7a6.zip | |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"ARM:
- GICv4.1 support
- 32bit host removal
PPC:
- secure (encrypted) using under the Protected Execution Framework
ultravisor
s390:
- allow disabling GISA (hardware interrupt injection) and protected
VMs/ultravisor support.
x86:
- New dirty bitmap flag that sets all bits in the bitmap when dirty
page logging is enabled; this is faster because it doesn't require
bulk modification of the page tables.
- Initial work on making nested SVM event injection more similar to
VMX, and less buggy.
- Various cleanups to MMU code (though the big ones and related
optimizations were delayed to 5.8). Instead of using cr3 in
function names which occasionally means eptp, KVM too has
standardized on "pgd".
- A large refactoring of CPUID features, which now use an array that
parallels the core x86_features.
- Some removal of pointer chasing from kvm_x86_ops, which will also
be switched to static calls as soon as they are available.
- New Tigerlake CPUID features.
- More bugfixes, optimizations and cleanups.
Generic:
- selftests: cleanups, new MMU notifier stress test, steal-time test
- CSV output for kvm_stat"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (277 commits)
x86/kvm: fix a missing-prototypes "vmread_error"
KVM: x86: Fix BUILD_BUG() in __cpuid_entry_get_reg() w/ CONFIG_UBSAN=y
KVM: VMX: Add a trampoline to fix VMREAD error handling
KVM: SVM: Annotate svm_x86_ops as __initdata
KVM: VMX: Annotate vmx_x86_ops as __initdata
KVM: x86: Drop __exit from kvm_x86_ops' hardware_unsetup()
KVM: x86: Copy kvm_x86_ops by value to eliminate layer of indirection
KVM: x86: Set kvm_x86_ops only after ->hardware_setup() completes
KVM: VMX: Configure runtime hooks using vmx_x86_ops
KVM: VMX: Move hardware_setup() definition below vmx_x86_ops
KVM: x86: Move init-only kvm_x86_ops to separate struct
KVM: Pass kvm_init()'s opaque param to additional arch funcs
s390/gmap: return proper error code on ksm unsharing
KVM: selftests: Fix cosmetic copy-paste error in vm_mem_region_move()
KVM: Fix out of range accesses to memslots
KVM: X86: Micro-optimize IPI fastpath delay
KVM: X86: Delay read msr data iff writes ICR MSR
KVM: PPC: Book3S HV: Add a capability for enabling secure guests
KVM: arm64: GICv4.1: Expose HW-based SGIs in debugfs
KVM: arm64: GICv4.1: Allow non-trapping WFI when using HW SGIs
...
206 files changed, 7867 insertions, 9698 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index ed73df5f1369..4d5a4fe22703 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3821,6 +3821,11 @@ before loading. See Documentation/admin-guide/blockdev/ramdisk.rst. + prot_virt= [S390] enable hosting protected virtual machines + isolated from the hypervisor (if hardware supports + that). + Format: <bool> + psi= [KNL] Enable or disable pressure stall information tracking. Format: <bool> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index ebd383fba939..efbbe570aa9b 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1574,8 +1574,8 @@ This ioctl would set vcpu's xcr to the value userspace specified. }; #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) - #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) - #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) + #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) /* deprecated */ + #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* deprecated */ struct kvm_cpuid_entry2 { __u32 function; @@ -1626,13 +1626,6 @@ emulate them efficiently. The fields in each entry are defined as follows: KVM_CPUID_FLAG_SIGNIFCANT_INDEX: if the index field is valid - KVM_CPUID_FLAG_STATEFUL_FUNC: - if cpuid for this function returns different values for successive - invocations; there will be several entries with the same function, - all with this flag set - KVM_CPUID_FLAG_STATE_READ_NEXT: - for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is - the first entry to be read by a cpu eax, ebx, ecx, edx: the values returned by the cpuid instruction for @@ -2117,7 +2110,8 @@ Errors: ====== ============================================================ Â ENOENT Â Â no such register - Â EINVAL Â Â invalid register ID, or no such register + Â EINVAL Â Â invalid register ID, or no such register or used with VMs in + protected virtualization mode on s390 Â EPERM Â Â Â (arm64) register access not allowed before vcpu finalization ====== ============================================================ @@ -2552,7 +2546,8 @@ Errors include: ======== ============================================================ Â ENOENT Â Â no such register - Â EINVAL Â Â invalid register ID, or no such register + Â EINVAL Â Â invalid register ID, or no such register or used with VMs in + protected virtualization mode on s390 Â EPERM Â Â Â (arm64) register access not allowed before vcpu finalization ======== ============================================================ @@ -3347,8 +3342,8 @@ The member 'flags' is used for passing flags from userspace. :: #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) - #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) - #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) + #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) /* deprecated */ + #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* deprecated */ struct kvm_cpuid_entry2 { __u32 function; @@ -3394,13 +3389,6 @@ The fields in each entry are defined as follows: KVM_CPUID_FLAG_SIGNIFCANT_INDEX: if the index field is valid - KVM_CPUID_FLAG_STATEFUL_FUNC: - if cpuid for this function returns different values for successive - invocations; there will be several entries with the same function, - all with this flag set - KVM_CPUID_FLAG_STATE_READ_NEXT: - for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is - the first entry to be read by a cpu eax, ebx, ecx, edx: @@ -4649,6 +4637,60 @@ the clear cpu reset definition in the POP. However, the cpu is not put into ESA mode. This reset is a superset of the initial reset. +4.125 KVM_S390_PV_COMMAND +------------------------- + +:Capability: KVM_CAP_S390_PROTECTED +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_pv_cmd +:Returns: 0 on success, < 0 on error + +:: + + struct kvm_pv_cmd { + __u32 cmd; /* Command to be executed */ + __u16 rc; /* Ultravisor return code */ + __u16 rrc; /* Ultravisor return reason code */ + __u64 data; /* Data or address */ + __u32 flags; /* flags for future extensions. Must be 0 for now */ + __u32 reserved[3]; + }; + +cmd values: + +KVM_PV_ENABLE + Allocate memory and register the VM with the Ultravisor, thereby + donating memory to the Ultravisor that will become inaccessible to + KVM. All existing CPUs are converted to protected ones. After this + command has succeeded, any CPU added via hotplug will become + protected during its creation as well. + + Errors: + + ===== ============================= + EINTR an unmasked signal is pending + ===== ============================= + +KVM_PV_DISABLE + + Deregister the VM from the Ultravisor and reclaim the memory that + had been donated to the Ultravisor, making it usable by the kernel + again. All registered VCPUs are converted back to non-protected + ones. + +KVM_PV_VM_SET_SEC_PARMS + Pass the image header from VM memory to the Ultravisor in + preparation of image unpacking and verification. + +KVM_PV_VM_UNPACK + Unpack (protect and decrypt) a page of the encrypted boot image. + +KVM_PV_VM_VERIFY + Verify the integrity of the unpacked image. Only if this succeeds, + KVM is allowed to start protected VCPUs. + + 5. The kvm_run structure ======================== @@ -5707,8 +5749,13 @@ and injected exceptions. :Architectures: x86, arm, arm64, mips :Parameters: args[0] whether feature should be enabled or not -With this capability enabled, KVM_GET_DIRTY_LOG will not automatically -clear and write-protect all pages that are returned as dirty. +Valid flags are:: + + #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) + #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) + +With KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE is set, KVM_GET_DIRTY_LOG will not +automatically clear and write-protect all pages that are returned as dirty. Rather, userspace will have to do this operation separately using KVM_CLEAR_DIRTY_LOG. @@ -5719,18 +5766,42 @@ than requiring to sync a full memslot; this ensures that KVM does not take spinlocks for an extended period of time. Second, in some cases a large amount of time can pass between a call to KVM_GET_DIRTY_LOG and userspace actually using the data in the page. Pages can be modified -during this time, which is inefficint for both the guest and userspace: +during this time, which is inefficient for both the guest and userspace: the guest will incur a higher penalty due to write protection faults, while userspace can see false reports of dirty pages. Manual reprotection helps reducing this time, improving guest performance and reducing the number of dirty log false positives. +With KVM_DIRTY_LOG_INITIALLY_SET set, all the bits of the dirty bitmap +will be initialized to 1 when created. This also improves performance because +dirty logging can be enabled gradually in small chunks on the first call +to KVM_CLEAR_DIRTY_LOG. KVM_DIRTY_LOG_INITIALLY_SET depends on +KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (it is also only available on +x86 for now). + KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 was previously available under the name KVM_CAP_MANUAL_DIRTY_LOG_PROTECT, but the implementation had bugs that make it hard or impossible to use it correctly. The availability of KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 signals that those bugs are fixed. Userspace should not try to use KVM_CAP_MANUAL_DIRTY_LOG_PROTECT. +7.19 KVM_CAP_PPC_SECURE_GUEST +------------------------------ + +:Architectures: ppc + +This capability indicates that KVM is running on a host that has +ultravisor firmware and thus can support a secure guest. On such a +system, a guest can ask the ultravisor to make it a secure guest, +one whose memory is inaccessible to the host except for pages which +are explicitly requested to be shared with the host. The ultravisor +notifies KVM when a guest requests to become a secure guest, and KVM +has the opportunity to veto the transition. + +If present, this capability can be enabled for a VM, meaning that KVM +will allow the transition to secure guest mode. Otherwise KVM will +veto the transition. + 8. Other capabilities. ====================== @@ -6027,3 +6098,14 @@ Architectures: s390 This capability indicates that the KVM_S390_NORMAL_RESET and KVM_S390_CLEAR_RESET ioctls are available. + +8.23 KVM_CAP_S390_PROTECTED + +Architecture: s390 + + +This capability indicates that the Ultravisor has been initialized and +KVM can therefore start protected VMs. +This capability governs the KVM_S390_PV_COMMAND ioctl and the +KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected +guests when the state change is invalid. diff --git a/Documentation/virt/kvm/arm/hyp-abi.rst b/Documentation/virt/kvm/arm/hyp-abi.rst index d1fc27d848e9..d9eba93aa364 100644 --- a/Documentation/virt/kvm/arm/hyp-abi.rst +++ b/Documentation/virt/kvm/arm/hyp-abi.rst @@ -11,6 +11,11 @@ hypervisor when running as a guest (under Xen, KVM or any other hypervisor), or any hypervisor-specific interaction when the kernel is used as a host. +Note: KVM/arm has been removed from the kernel. The API described +here is still valid though, as it allows the kernel to kexec when +booted at HYP. It can also be used by a hypervisor other than KVM +if necessary. + On arm and arm64 (without VHE), the kernel doesn't run in hypervisor mode, but still needs to interact with it, allowing a built-in hypervisor to be either installed or torn down. diff --git a/Documentation/virt/kvm/devices/s390_flic.rst b/Documentation/virt/kvm/devices/s390_flic.rst index 954190da7d04..ea96559ba501 100644 --- a/Documentation/virt/kvm/devices/s390_flic.rst +++ b/Documentation/virt/kvm/devices/s390_flic.rst @@ -108,16 +108,9 @@ Groups: mask or unmask the adapter, as specified in mask KVM_S390_IO_ADAPTER_MAP - perform a gmap translation for the guest address provided in addr, - pin a userspace page for the translated address and add it to the - list of mappings - - .. note:: A new mapping will be created unconditionally; therefore, - the calling code should avoid making duplicate mappings. - + This is now a no-op. The mapping is purely done by the irq route. KVM_S390_IO_ADAPTER_UNMAP - release a userspace page for the translated address specified in addr - from the list of mappings + This is now a no-op. The mapping is purely done by the irq route. KVM_DEV_FLIC_AISM modify the adapter-interruption-suppression mode for a given isc if the diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst index 774deaebf7fa..dcc252634cf9 100644 --- a/Documentation/virt/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -18,6 +18,8 @@ KVM nested-vmx ppc-pv s390-diag + s390-pv + s390-pv-boot timekeeping vcpu-requests diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index c02291beac3f..b21a34c34a21 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -96,19 +96,18 @@ will happen: We dirty-log for gfn1, that means gfn2 is lost in dirty-bitmap. For direct sp, we can easily avoid it since the spte of direct sp is fixed -to gfn. For indirect sp, before we do cmpxchg, we call gfn_to_pfn_atomic() -to pin gfn to pfn, because after gfn_to_pfn_atomic(): +to gfn. For indirect sp, we disabled fast page fault for simplicity. + +A solution for indirect sp could be to pin the gfn, for example via +kvm_vcpu_gfn_to_pfn_atomic, before the cmpxchg. After the pinning: - We have held the refcount of pfn that means the pfn can not be freed and be reused for another gfn. -- The pfn is writable that means it can not be shared between different gfns +- The pfn is writable and therefore it cannot be shared between different gfns by KSM. Then, we can ensure the dirty bitmaps is correctly set for a gfn. -Currently, to simplify the whole things, we disable fast page fault for -indirect shadow page. - 2) Dirty bit tracking In the origin code, the spte can be fast updated (non-atomically) if the diff --git a/Documentation/virt/kvm/s390-pv-boot.rst b/Documentation/virt/kvm/s390-pv-boot.rst new file mode 100644 index 000000000000..8b8fa0390409 --- /dev/null +++ b/Documentation/virt/kvm/s390-pv-boot.rst @@ -0,0 +1,84 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====================================== +s390 (IBM Z) Boot/IPL of Protected VMs +====================================== + +Summary +------- +The memory of Protected Virtual Machines (PVMs) is not accessible to +I/O or the hypervisor. In those cases where the hypervisor needs to +access the memory of a PVM, that memory must be made accessible. +Memory made accessible to the hypervisor will be encrypted. See +:doc:`s390-pv` for details." + +On IPL (boot) a small plaintext bootloader is started, which provides +information about the encrypted components and necessary metadata to +KVM to decrypt the protected virtual machine. + +Based on this data, KVM will make the protected virtual machine known +to the Ultravisor (UV) and instruct it to secure the memory of the +PVM, decrypt the components and verify the data and address list +hashes, to ensure integrity. Afterwards KVM can run the PVM via the +SIE instruction which the UV will intercept and execute on KVM's +behalf. + +As the guest image is just like an opaque kernel image that does the +switch into PV mode itself, the user can load encrypted guest +executables and data via every available method (network, dasd, scsi, +direct kernel, ...) without the need to change the boot process. + + +Diag308 +------- +This diagnose instruction is the basic mechanism to handle IPL and +related operations for virtual machines. The VM can set and retrieve +IPL information blocks, that specify the IPL method/devices and +request VM memory and subsystem resets, as well as IPLs. + +For PVMs this concept has been extended with new subcodes: + +Subcode 8: Set an IPL Information Block of type 5 (information block +for PVMs) +Subcode 9: Store the saved block in guest memory +Subcode 10: Move into Protected Virtualization mode + +The new PV load-device-specific-parameters field specifies all data +that is necessary to move into PV mode. + +* PV Header origin +* PV Header length +* List of Components composed of + * AES-XTS Tweak prefix + * Origin + * Size + +The PV header contains the keys and hashes, which the UV will use to +decrypt and verify the PV, as well as control flags and a start PSW. + +The components are for instance an encrypted kernel, kernel parameters +and initrd. The components are decrypted by the UV. + +After the initial import of the encrypted data, all defined pages will +contain the guest content. All non-specified pages will start out as +zero pages on first access. + + +When running in protected virtualization mode, some subcodes will result in +exceptions or return error codes. + +Subcodes 4 and 7, which specify operations that do not clear the guest +memory, will result in specification exceptions. This is because the +UV will clear all memory when a secure VM is removed, and therefore +non-clearing IPL subcodes are not allowed. + +Subcodes 8, 9, 10 will result in specification exceptions. +Re-IPL into a protected mode is only possible via a detour into non +protected mode. + +Keys +---- +Every CEC will have a unique public key to enable tooling to build +encrypted images. +See `s390-tools <https://github.com/ibm-s390-tools/s390-tools/>`_ +for the tooling. diff --git a/Documentation/virt/kvm/s390-pv.rst b/Documentation/virt/kvm/s390-pv.rst new file mode 100644 index 000000000000..774a8c606091 --- /dev/null +++ b/Documentation/virt/kvm/s390-pv.rst @@ -0,0 +1,116 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================================= +s390 (IBM Z) Ultravisor and Protected VMs +========================================= + +Summary +------- +Protected virtual machines (PVM) are KVM VMs that do not allow KVM to +access VM state like guest memory or guest registers. Instead, the +PVMs are mostly managed by a new entity called Ultravisor (UV). The UV +provides an API that can be used by PVMs and KVM to request management +actions. + +Each guest starts in non-protected mode and then may make a request to +transition into protected mode. On transition, KVM registers the guest +and its VCPUs with the Ultravisor and prepares everything for running +it. + +The Ultravisor will secure and decrypt the guest's boot memory +(i.e. kernel/initrd). It will safeguard state changes like VCPU +starts/stops and injected interrupts while the guest is running. + +As access to the guest's state, such as the SIE state description, is +normally needed to be able to run a VM, some changes have been made in +the behavior of the SIE instruction. A new format 4 state description +has been introduced, where some fields have different meanings for a +PVM. SIE exits are minimized as much as possible to improve speed and +reduce exposed guest state. + + +Interrupt injection +------------------- +Interrupt injection is safeguarded by the Ultravisor. As KVM doesn't +have access to the VCPUs' lowcores, injection is handled via the +format 4 state description. + +Machine check, external, IO and restart interruptions each can be +injected on SIE entry via a bit in the interrupt injection control +field (offset 0x54). If the guest cpu is not enabled for the interrupt +at the time of injection, a validity interception is recognized. The +format 4 state description contains fields in the interception data +block where data associated with the interrupt can be transported. + +Program and Service Call exceptions have another layer of +safeguarding; they can only be injected for instructions that have +been intercepted into KVM. The exceptions need to be a valid outcome +of an instruction emulation by KVM, e.g. we can never inject a +addressing exception as they are reported by SIE since KVM has no +access to the guest memory. + + +Mask notification interceptions +------------------------------- +KVM cannot intercept lctl(g) and lpsw(e) anymore in order to be +notified when a PVM enables a certain class of interrupt. As a +replacement, two new interception codes have been introduced: One +indicating that the contents of CRs 0, 6, or 14 have been changed, +indicating different interruption subclasses; and one indicating that +PSW bit 13 has been changed, indicating that a machine check +intervention was requested and those are now enabled. + +Instruction emulation +--------------------- +With the format 4 state description for PVMs, the SIE instruction already +interprets more instructions than it does with format 2. It is not able +to interpret every instruction, but needs to hand some tasks to KVM; +therefore, the SIE and the ultravisor safeguard emulation inputs and outputs. + +The control structures associated with SIE provide the Secure +Instruction Data Area (SIDA), the Interception Parameters (IP) and the +Secure Interception General Register Save Area. Guest GRs and most of +the instruction data, such as I/O data structures, are filtered. +Instruction data is copied to and from the SIDA when needed. Guest +GRs are put into / retrieved from the Secure Interception General +Register Save Area. + +Only GR values needed to emulate an instruction will be copied into this +save area and the real register numbers will be hidden. + +The Interception Parameters state description field still contains the +the bytes of the instruction text, but with pre-set register values +instead of the actual ones. I.e. each instruction always uses the same +instruction text, in order not to leak guest instruction text. +This also implies that the register content that a guest had in r<n> +may be in r<m> from the hypervisor's point of view. + +The Secure Instruction Data Area contains instruction storage +data. Instruction data, i.e. data being referenced by an instruction +like the SCCB for sclp, is moved via the SIDA. When an instruction is +intercepted, the SIE will only allow data and program interrupts for +this instruction to be moved to the guest via the two data areas +discussed before. Other data is either ignored or results in validity +interceptions. + + +Instruction emulation interceptions +----------------------------------- +There are two types of SIE secure instruction intercepts: the normal +and the notification type. Normal secure instruction intercepts will +make the guest pending for instruction completion of the intercepted +instruction type, i.e. on SIE entry it is attempted to complete +emulation of the instruction with the data provided by KVM. That might +be a program exception or instruction completion. + +The notification type intercepts inform KVM about guest environment +changes due to guest instruction interpretation. Such an interception +is recognized, for example, for the store prefix instruction to provide +the new lowcore location. On SIE reentry, any KVM data in the data areas +is ignored and execution continues as if the guest instruction had +completed. For that reason KVM is not allowed to inject a program +interrupt. + +Links +----- +`KVM Forum 2019 presentation <https://static.sched.com/hosted_files/kvmforum2019/3b/ibm_protected_vms_s390x.pdf>`_ diff --git a/MAINTAINERS b/MAINTAINERS index 40e40c9ee9d2..6849e8ddf55a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9244,7 +9244,7 @@ F: virt/kvm/* F: tools/kvm/ F: tools/testing/selftests/kvm/ -KERNEL VIRTUAL MACHINE FOR ARM/ARM64 (KVM/arm, KVM/arm64) +KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) M: Marc Zyngier <maz@kernel.org> R: James Morse <james.morse@arm.com> R: Julien Thierry <julien.thierry.kdev@gmail.com> @@ -9253,9 +9253,6 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kvmarm@lists.cs.columbia.edu T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git S: Maintained -F: arch/arm/include/uapi/asm/kvm* -F: arch/arm/include/asm/kvm* -F: arch/arm/kvm/ F: arch/arm64/include/uapi/asm/kvm* F: arch/arm64/include/asm/kvm* F: arch/arm64/kvm/ @@ -9290,6 +9287,7 @@ L: kvm@vger.kernel.org W: http://www.ibm.com/developerworks/linux/linux390/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git S: Supported +F: Documentation/virt/kvm/s390* F: arch/s390/include/uapi/asm/kvm* F: arch/s390/include/asm/gmap.h F: arch/s390/include/asm/kvm* diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 03bbfc312fe7..66a04f6f4775 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -2090,5 +2090,3 @@ source "drivers/firmware/Kconfig" if CRYPTO source "arch/arm/crypto/Kconfig" endif - -source "arch/arm/kvm/Kconfig" diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 1fc32b611f8a..e1d13d779e08 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -278,7 +278,6 @@ core-$(CONFIG_FPE_NWFPE) += arch/arm/nwfpe/ core-$(CONFIG_FPE_FASTFPE) += $(patsubst $(srctree)/%,%,$(wildcard $(srctree)/arch/arm/fastfpe/)) core-$(CONFIG_VFP) += arch/arm/vfp/ core-$(CONFIG_XEN) += arch/arm/xen/ -core-$(CONFIG_KVM_ARM_HOST) += arch/arm/kvm/ core-$(CONFIG_VDSO) += arch/arm/vdso/ # If we have a machine-specific directory, then include it in the build. diff --git a/arch/arm/configs/axm55xx_defconfig b/arch/arm/configs/axm55xx_defconfig index 6ea7dafa4c9e..46075216ee6d 100644 --- a/arch/arm/configs/axm55xx_defconfig +++ b/arch/arm/configs/axm55xx_defconfig @@ -236,5 +236,3 @@ CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_XCBC=y CONFIG_CRYPTO_SHA256=y # CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_VIRTUALIZATION=y -CONFIG_KVM=y diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index c815477b4303..413abfb42989 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -38,71 +38,6 @@ #define ICC_AP1R2 __ICC_AP1Rx(2) #define ICC_AP1R3 __ICC_AP1Rx(3) -#define ICC_HSRE __ACCESS_CP15(c12, 4, c9, 5) - -#define ICH_VSEIR __ACCESS_CP15(c12, 4, c9, 4) -#define ICH_HCR __ACCESS_CP15(c12, 4, c11, 0) -#define ICH_VTR __ACCESS_CP15(c12, 4, c11, 1) -#define ICH_MISR __ACCESS_CP15(c12, 4, c11, 2) -#define ICH_EISR __ACCESS_CP15(c12, 4, c11, 3) -#define ICH_ELRSR __ACCESS_CP15(c12, 4, c11, 5) -#define ICH_VMCR __ACCESS_CP15(c12, 4, c11, 7) - -#define __LR0(x) __ACCESS_CP15(c12, 4, c12, x) -#define __LR8(x) __ACCESS_CP15(c12, 4, c13, x) - -#define ICH_LR0 __LR0(0) -#define ICH_LR1 __LR0(1) -#define ICH_LR2 __LR0(2) -#define ICH_LR3 __LR0(3) -#define ICH_LR4 __LR0(4) -#define ICH_LR5 __LR0(5) -#define ICH_LR6 __LR0(6) -#define ICH_LR7 __LR0(7) -#define ICH_LR8 __LR8(0) -#define ICH_LR9 __LR8(1) -#define ICH_LR10 __LR8(2) -#define ICH_LR11 __LR8(3) -#define ICH_LR12 __LR8(4) -#define ICH_LR13 __LR8(5) -#define ICH_LR14 __LR8(6) -#define ICH_LR15 __LR8(7) - -/* LR top half */ -#define __LRC0(x) __ACCESS_CP15(c12, 4, c14, x) -#define __LRC8(x) __ACCESS_CP15(c12, 4, c15, x) - -#define ICH_LRC0 __LRC0(0) -#define ICH_LRC1 __LRC0(1) -#define ICH_LRC2 __LRC0(2) -#define ICH_LRC3 __LRC0(3) -#define ICH_LRC4 __LRC0(4) -#define ICH_LRC5 __LRC0(5) -#define ICH_LRC6 __LRC0(6) -#define ICH_LRC7 __LRC0(7) -#define ICH_LRC8 __LRC8(0) -#define ICH_LRC9 __LRC8(1) -#define ICH_LRC10 __LRC8(2) -#define ICH_LRC11 __LRC8(3) -#define ICH_LRC12 __LRC8(4) -#define ICH_LRC13 __LRC8(5) -#define ICH_LRC14 __LRC8(6) -#define ICH_LRC15 __LRC8(7) - -#define __ICH_AP0Rx(x) __ACCESS_CP15(c12, 4, c8, x) -#define ICH_AP0R0 __ICH_AP0Rx(0) -#define ICH_AP0R1 __ICH_AP0Rx(1) -#define ICH_AP0R2 __ICH_AP0Rx(2) -#define ICH_AP0R3 __ICH_AP0Rx(3) - -#define __ICH_AP1Rx(x) __ACCESS_CP15(c12, 4, c9, x) -#define ICH_AP1R0 __ICH_AP1Rx(0) -#define ICH_AP1R1 __ICH_AP1Rx(1) -#define ICH_AP1R2 __ICH_AP1Rx(2) -#define ICH_AP1R3 __ICH_AP1Rx(3) - -/* A32-to-A64 mappings used by VGIC save/restore */ - #define CPUIF_MAP(a32, a64) \ static inline void write_ ## a64(u32 val) \ { \ @@ -113,21 +48,6 @@ static inline u32 read_ ## a64(void) \ return read_sysreg(a32); \ } \ -#define CPUIF_MAP_LO_HI(a32lo, a32hi, a64) \ -static inline void write_ ## a64(u64 val) \ -{ \ - write_sysreg(lower_32_bits(val), a32lo);\ - write_sysreg(upper_32_bits(val), a32hi);\ -} \ -static inline u64 read_ ## a64(void) \ -{ \ - u64 val = read_sysreg(a32lo); \ - \ - val |= (u64)read_sysreg(a32hi) << 32; \ - \ - return val; \ -} - CPUIF_MAP(ICC_PMR, ICC_PMR_EL1) CPUIF_MAP(ICC_AP0R0, ICC_AP0R0_EL1) CPUIF_MAP(ICC_AP0R1, ICC_AP0R1_EL1) @@ -138,40 +58,6 @@ CPUIF_MAP(ICC_AP1R1, ICC_AP1R1_EL1) CPUIF_MAP(ICC_AP1R2, ICC_AP1R2_EL1) CPUIF_MAP(ICC_AP1R3, ICC_AP1R3_EL1) -CPUIF_MAP(ICH_HCR, ICH_HCR_EL2) -CPUIF_MAP(ICH_VTR, ICH_VTR_EL2) -CPUIF_MAP(ICH_MISR, ICH_MISR_EL2) -CPUIF_MAP(ICH_EISR, ICH_EISR_EL2) -CPUIF_MAP(ICH_ELRSR, ICH_ELRSR_EL2) -CPUIF_MAP(ICH_VMCR, ICH_VMCR_EL2) -CPUIF_MAP(ICH_AP0R3, ICH_AP0R3_EL2) -CPUIF_MAP(ICH_AP0R2, ICH_AP0R2_EL2) -CPUIF_MAP(ICH_AP0R1, ICH_AP0R1_EL2) -CPUIF_MAP(ICH_AP0R0, ICH_AP0R0_EL2) -CPUIF_MAP(ICH_AP1R3, ICH_AP1R3_EL2) -CPUIF_MAP(ICH_AP1R2, ICH_AP1R2_EL2) -CPUIF_MAP(ICH_AP1R1, ICH_AP1R1_EL2) -CPUIF_MAP(ICH_AP1R0, ICH_AP1R0_EL2) -CPUIF_MAP(ICC_HSRE, ICC_SRE_EL2) -CPUIF_MAP(ICC_SRE, ICC_SRE_EL1) - -CPUIF_MAP_LO_HI(ICH_LR15, ICH_LRC15, ICH_LR15_EL2) -CPUIF_MAP_LO_HI(ICH_LR14, ICH_LRC14, ICH_LR14_EL2) -CPUIF_MAP_LO_HI(ICH_LR13, ICH_LRC13, ICH_LR13_EL2) -CPUIF_MAP_LO_HI(ICH_LR12, ICH_LRC12, ICH_LR12_EL2) -CPUIF_MAP_LO_HI(ICH_LR11, ICH_LRC11, ICH_LR11_EL2) -CPUIF_MAP_LO_HI(ICH_LR10, ICH_LRC10, ICH_LR10_EL2) -CPUIF_MAP_LO_HI(ICH_LR9, ICH_LRC9, ICH_LR9_EL2) -CPUIF_MAP_LO_HI(ICH_LR8, ICH_LRC8, ICH_LR8_EL2) -CPUIF_MAP_LO_HI(ICH_LR7, ICH_LRC7, ICH_LR7_EL2) -CPUIF_MAP_LO_HI(ICH_LR6, ICH_LRC6, ICH_LR6_EL2) -CPUIF_MAP_LO_HI(ICH_LR5, ICH_LRC5, ICH_LR5_EL2) -CPUIF_MAP_LO_HI(ICH_LR4, ICH_LRC4, ICH_LR4_EL2) -CPUIF_MAP_LO_HI(ICH_LR3, ICH_LRC3, ICH_LR3_EL2) -CPUIF_MAP_LO_HI(ICH_LR2, ICH_LRC2, ICH_LR2_EL2) -CPUIF_MAP_LO_HI(ICH_LR1, ICH_LRC1, ICH_LR1_EL2) -CPUIF_MAP_LO_HI(ICH_LR0, ICH_LRC0, ICH_LR0_EL2) - #define read_gicreg(r) read_##r() #define write_gicreg(v, r) write_##r(v) diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h deleted file mode 100644 index 9c04bd810d07..000000000000 --- a/arch/arm/include/asm/kvm_arm.h +++ /dev/null @@ -1,239 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_ARM_H__ -#define __ARM_KVM_ARM_H__ - -#include <linux/const.h> -#include <linux/types.h> - -/* Hyp Configuration Register (HCR) bits */ -#define HCR_TGE (1 << 27) -#define HCR_TVM (1 << 26) -#define HCR_TTLB (1 << 25) -#define HCR_TPU (1 << 24) -#define HCR_TPC (1 << 23) -#define HCR_TSW (1 << 22) -#define HCR_TAC (1 << 21) -#define HCR_TIDCP (1 << 20) -#define HCR_TSC (1 << 19) -#define HCR_TID3 (1 << 18) -#define HCR_TID2 (1 << 17) -#define HCR_TID1 (1 << 16) -#define HCR_TID0 (1 << 15) -#define HCR_TWE (1 << 14) -#define HCR_TWI (1 << 13) -#define HCR_DC (1 << 12) -#define HCR_BSU (3 << 10) -#define HCR_BSU_IS (1 << 10) -#define HCR_FB (1 << 9) -#define HCR_VA (1 << 8) -#define HCR_VI (1 << 7) -#define HCR_VF (1 << 6) -#define HCR_AMO (1 << 5) -#define HCR_IMO (1 << 4) -#define HCR_FMO (1 << 3) -#define HCR_PTW (1 << 2) -#define HCR_SWIO (1 << 1) -#define HCR_VM 1 - -/* - * The bits we set in HCR: - * TAC: Trap ACTLR - * TSC: Trap SMC - * TVM: Trap VM ops (until MMU and caches are on) - * TSW: Trap cache operations by set/way - * TWI: Trap WFI - * TWE: Trap WFE - * TIDCP: Trap L2CTLR/L2ECTLR - * BSU_IS: Upgrade barriers to the inner shareable domain - * FB: Force broadcast of all maintainance operations - * AMO: Override CPSR.A and enable signaling with VA - * IMO: Override CPSR.I and enable signaling with VI - * FMO: Override CPSR.F and enable signaling with VF - * SWIO: Turn set/way invalidates into set/way clean+invalidate - */ -#define HCR_GUEST_MASK (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \ - HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \ - HCR_TVM | HCR_TWE | HCR_SWIO | HCR_TIDCP) - -/* System Control Register (SCTLR) bits */ -#define SCTLR_TE (1 << 30) -#define SCTLR_EE (1 << 25) -#define SCTLR_V (1 << 13) - -/* Hyp System Control Register (HSCTLR) bits */ -#define HSCTLR_TE (1 << 30) -#define HSCTLR_EE (1 << 25) -#define HSCTLR_FI (1 << 21) -#define HSCTLR_WXN (1 << 19) -#define HSCTLR_I (1 << 12) -#define HSCTLR_C (1 << 2) -#define HSCTLR_A (1 << 1) -#define HSCTLR_M 1 -#define HSCTLR_MASK (HSCTLR_M | HSCTLR_A | HSCTLR_C | HSCTLR_I | \ - HSCTLR_WXN | HSCTLR_FI | HSCTLR_EE | HSCTLR_TE) - -/* TTBCR and HTCR Registers bits */ -#define TTBCR_EAE (1 << 31) -#define TTBCR_IMP (1 << 30) -#define TTBCR_SH1 (3 << 28) -#define TTBCR_ORGN1 (3 << 26) -#define TTBCR_IRGN1 (3 << 24) -#define TTBCR_EPD1 (1 << 23) -#define TTBCR_A1 (1 << 22) -#define TTBCR_T1SZ (7 << 16) -#define TTBCR_SH0 (3 << 12) -#define TTBCR_ORGN0 (3 << 10) -#define TTBCR_IRGN0 (3 << 8) -#define TTBCR_EPD0 (1 << 7) -#define TTBCR_T0SZ (7 << 0) -#define HTCR_MASK (TTBCR_T0SZ | TTBCR_IRGN0 | TTBCR_ORGN0 | TTBCR_SH0) - -/* Hyp System Trap Register */ -#define HSTR_T(x) (1 << x) -#define HSTR_TTEE (1 << 16) -#define HSTR_TJDBX (1 << 17) - -/* Hyp Coprocessor Trap Register */ -#define HCPTR_TCP(x) (1 << x) -#define HCPTR_TCP_MASK (0x3fff) -#define HCPTR_TASE (1 << 15) -#define HCPTR_TTA (1 << 20) -#define HCPTR_TCPAC (1 << 31) - -/* Hyp Debug Configuration Register bits */ -#define HDCR_TDRA (1 << 11) -#define HDCR_TDOSA (1 << 10) -#define HDCR_TDA (1 << 9) -#define HDCR_TDE (1 << 8) -#define HDCR_HPME (1 << 7) -#define HDCR_TPM (1 << 6) -#define HDCR_TPMCR (1 << 5) -#define HDCR_HPMN_MASK (0x1F) - -/* - * The architecture supports 40-bit IPA as input to the 2nd stage translations - * and PTRS_PER_S2_PGD becomes 1024, because each entry covers 1GB of address - * space. - */ -#define KVM_PHYS_SHIFT (40) - -#define PTRS_PER_S2_PGD (_AC(1, ULL) << (KVM_PHYS_SHIFT - 30)) - -/* Virtualization Translation Control Register (VTCR) bits */ -#define VTCR_SH0 (3 << 12) -#define VTCR_ORGN0 (3 << 10) -#define VTCR_IRGN0 (3 << 8) -#define VTCR_SL0 (3 << 6) -#define VTCR_S (1 << 4) -#define VTCR_T0SZ (0xf) -#define VTCR_MASK (VTCR_SH0 | VTCR_ORGN0 | VTCR_IRGN0 | VTCR_SL0 | \ - VTCR_S | VTCR_T0SZ) -#define VTCR_HTCR_SH (VTCR_SH0 | VTCR_ORGN0 | VTCR_IRGN0) -#define VTCR_SL_L2 (0 << 6) /* Starting-level: 2 */ -#define VTCR_SL_L1 (1 << 6) /* Starting-level: 1 */ -#define KVM_VTCR_SL0 VTCR_SL_L1 -/* stage-2 input address range defined as 2^(32-T0SZ) */ -#define KVM_T0SZ (32 - KVM_PHYS_SHIFT) -#define KVM_VTCR_T0SZ (KVM_T0SZ & VTCR_T0SZ) -#define KVM_VTCR_S ((KVM_VTCR_T0SZ << 1) & VTCR_S) - -/* Virtualization Translation Table Base Register (VTTBR) bits */ -#if KVM_VTCR_SL0 == VTCR_SL_L2 /* see ARM DDI 0406C: B4-1720 */ -#define VTTBR_X (14 - KVM_T0SZ) -#else -#define VTTBR_X (5 - KVM_T0SZ) -#endif -#define VTTBR_CNP_BIT _AC(1, UL) -#define VTTBR_BADDR_MASK (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_X) -#define VTTBR_VMID_SHIFT _AC(48, ULL) -#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT) - -/* Hyp Syndrome Register (HSR) bits */ -#define HSR_EC_SHIFT (26) -#define HSR_EC (_AC(0x3f, UL) << HSR_EC_SHIFT) -#define HSR_IL (_AC(1, UL) << 25) -#define HSR_ISS (HSR_IL - 1) -#define HSR_ISV_SHIFT (24) -#define HSR_ISV (_AC(1, UL) << HSR_ISV_SHIFT) -#define HSR_SRT_SHIFT (16) -#define HSR_SRT_MASK (0xf << HSR_SRT_SHIFT) -#define HSR_CM (1 << 8) -#define HSR_FSC (0x3f) -#define HSR_FSC_TYPE (0x3c) -#define HSR_SSE (1 << 21) -#define HSR_WNR (1 << 6) -#define HSR_CV_SHIFT (24) -#define HSR_CV (_AC(1, UL) << HSR_CV_SHIFT) -#define HSR_COND_SHIFT (20) -#define HSR_COND (_AC(0xf, UL) << HSR_COND_SHIFT) - -#define FSC_FAULT (0x04) -#define FSC_ACCESS (0x08) -#define FSC_PERM (0x0c) -#define FSC_SEA (0x10) -#define FSC_SEA_TTW0 (0x14) -#define FSC_SEA_TTW1 (0x15) -#define FSC_SEA_TTW2 (0x16) -#define FSC_SEA_TTW3 (0x17) -#define FSC_SECC (0x18) -#define FSC_SECC_TTW0 (0x1c) -#define FSC_SECC_TTW1 (0x1d) -#define FSC_SECC_TTW2 (0x1e) -#define FSC_SECC_TTW3 (0x1f) - -/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ -#define HPFAR_MASK (~0xf) - -#define HSR_EC_UNKNOWN (0x00) -#define HSR_EC_WFI (0x01) -#define HSR_EC_CP15_32 (0x03) -#define HSR_EC_CP15_64 (0x04) -#define HSR_EC_CP14_MR (0x05) -#define HSR_EC_CP14_LS (0x06) -#define HSR_EC_CP_0_13 (0x07) -#define HSR_EC_CP10_ID (0x08) -#define HSR_EC_JAZELLE (0x09) -#define HSR_EC_BXJ (0x0A) -#define HSR_EC_CP14_64 (0x0C) -#define HSR_EC_SVC_HYP (0x11) -#define HSR_EC_HVC (0x12) -#define HSR_EC_SMC (0x13) -#define HSR_EC_IABT (0x20) -#define HSR_EC_IABT_HYP (0x21) -#define HSR_EC_DABT (0x24) -#define HSR_EC_DABT_HYP (0x25) -#define HSR_EC_MAX (0x3f) - -#define HSR_WFI_IS_WFE (_AC(1, UL) << 0) - -#define HSR_HVC_IMM_MASK ((_AC(1, UL) << 16) - 1) - -#define HSR_DABT_S1PTW (_AC(1, UL) << 7) -#define HSR_DABT_CM (_AC(1, UL) << 8) - -#define kvm_arm_exception_type \ - {0, "RESET" }, \ - {1, "UNDEFINED" }, \ - {2, "SOFTWARE" }, \ - {3, "PREF_ABORT" }, \ - {4, "DATA_ABORT" }, \ - {5, "IRQ" }, \ - {6, "FIQ" }, \ - {7, "HVC" } - -#define HSRECN(x) { HSR_EC_##x, #x } - -#define kvm_arm_exception_class \ - HSRECN(UNKNOWN), HSRECN(WFI), HSRECN(CP15_32), HSRECN(CP15_64), \ - HSRECN(CP14_MR), HSRECN(CP14_LS), HSRECN(CP_0_13), HSRECN(CP10_ID), \ - HSRECN(JAZELLE), HSRECN(BXJ), HSRECN(CP14_64), HSRECN(SVC_HYP), \ - HSRECN(HVC), HSRECN(SMC), HSRECN(IABT), HSRECN(IABT_HYP), \ - HSRECN(DABT), HSRECN(DABT_HYP) - - -#endif /* __ARM_KVM_ARM_H__ */ diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h deleted file mode 100644 index f615830f9f57..000000000000 --- a/arch/arm/include/asm/kvm_asm.h +++ /dev/null @@ -1,77 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_ASM_H__ -#define __ARM_KVM_ASM_H__ - -#include <asm/virt.h> - -#define ARM_EXIT_WITH_ABORT_BIT 31 -#define ARM_EXCEPTION_CODE(x) ((x) & ~(1U << ARM_EXIT_WITH_ABORT_BIT)) -#define ARM_EXCEPTION_IS_TRAP(x) \ - (ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_PREF_ABORT || \ - ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_DATA_ABORT || \ - ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_HVC) -#define ARM_ABORT_PENDING(x) !!((x) & (1U << ARM_EXIT_WITH_ABORT_BIT)) - -#define ARM_EXCEPTION_RESET 0 -#define ARM_EXCEPTION_UNDEFINED 1 -#define ARM_EXCEPTION_SOFTWARE 2 -#define ARM_EXCEPTION_PREF_ABORT 3 -#define ARM_EXCEPTION_DATA_ABORT 4 -#define ARM_EXCEPTION_IRQ 5 -#define ARM_EXCEPTION_FIQ 6 -#define ARM_EXCEPTION_HVC 7 -#define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR -/* - * The rr_lo_hi macro swaps a pair of registers depending on - * current endianness. It is used in conjunction with ldrd and strd - * instructions that load/store a 64-bit value from/to memory to/from - * a pair of registers which are used with the mrrc and mcrr instructions. - * If used with the ldrd/strd instructions, the a1 parameter is the first - * source/destination register and the a2 parameter is the second - * source/destination register. Note that the ldrd/strd instructions - * already swap the bytes within the words correctly according to the - * endianness setting, but the order of the registers need to be effectively - * swapped when used with the mrrc/mcrr instructions. - */ -#ifdef CONFIG_CPU_ENDIAN_BE8 -#define rr_lo_hi(a1, a2) a2, a1 -#else -#define rr_lo_hi(a1, a2) a1, a2 -#endif - -#define kvm_ksym_ref(kva) (kva) - -#ifndef __ASSEMBLY__ -struct kvm; -struct kvm_vcpu; - -extern char __kvm_hyp_init[]; -extern char __kvm_hyp_init_end[]; - -extern void __kvm_flush_vm_context(void); -extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); -extern void __kvm_tlb_flush_vmid(struct kvm *kvm); -extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu); - -extern void __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high); - -/* no VHE on 32-bit :( */ -static inline int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { BUG(); return 0; } - -extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu); - -extern void __init_stage2_translation(void); - -extern u64 __vgic_v3_get_ich_vtr_el2(void); -extern u64 __vgic_v3_read_vmcr(void); -extern void __vgic_v3_write_vmcr(u32 vmcr); -extern void __vgic_v3_init_lrs(void); - -#endif - -#endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm/include/asm/kvm_coproc.h b/arch/arm/include/asm/kvm_coproc.h deleted file mode 100644 index a23826117dd6..000000000000 --- a/arch/arm/include/asm/kvm_coproc.h +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 Rusty Russell IBM Corporation - */ - -#ifndef __ARM_KVM_COPROC_H__ -#define __ARM_KVM_COPROC_H__ -#include <linux/kvm_host.h> - -void kvm_reset_coprocs(struct kvm_vcpu *vcpu); - -struct kvm_coproc_target_table { - unsigned target; - const struct coproc_reg *table; - size_t num; -}; -void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table); - -int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run); -int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run); - -unsigned long kvm_arm_num_guest_msrs(struct kvm_vcpu *vcpu); -int kvm_arm_copy_msrindices(struct kvm_vcpu *vcpu, u64 __user *uindices); -void kvm_coproc_table_init(void); - -struct kvm_one_reg; -int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); -int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); -int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); -unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu); -#endif /* __ARM_KVM_COPROC_H__ */ diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h deleted file mode 100644 index 3944305e81df..000000000000 --- a/arch/arm/include/asm/kvm_emulate.h +++ /dev/null @@ -1,372 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_EMULATE_H__ -#define __ARM_KVM_EMULATE_H__ - -#include <linux/kvm_host.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_arm.h> -#include <asm/cputype.h> - -/* arm64 compatibility macros */ -#define PSR_AA32_MODE_FIQ FIQ_MODE -#define PSR_AA32_MODE_SVC SVC_MODE -#define PSR_AA32_MODE_ABT ABT_MODE -#define PSR_AA32_MODE_UND UND_MODE -#define PSR_AA32_T_BIT PSR_T_BIT -#define PSR_AA32_F_BIT PSR_F_BIT -#define PSR_AA32_I_BIT PSR_I_BIT -#define PSR_AA32_A_BIT PSR_A_BIT -#define PSR_AA32_E_BIT PSR_E_BIT -#define PSR_AA32_IT_MASK PSR_IT_MASK -#define PSR_AA32_GE_MASK 0x000f0000 -#define PSR_AA32_DIT_BIT 0x00200000 -#define PSR_AA32_PAN_BIT 0x00400000 -#define PSR_AA32_SSBS_BIT 0x00800000 -#define PSR_AA32_Q_BIT PSR_Q_BIT -#define PSR_AA32_V_BIT PSR_V_BIT -#define PSR_AA32_C_BIT PSR_C_BIT -#define PSR_AA32_Z_BIT PSR_Z_BIT -#define PSR_AA32_N_BIT PSR_N_BIT - -unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num); - -static inline unsigned long *vcpu_reg32(struct kvm_vcpu *vcpu, u8 reg_num) -{ - return vcpu_reg(vcpu, reg_num); -} - -unsigned long *__vcpu_spsr(struct kvm_vcpu *vcpu); - -static inline unsigned long vpcu_read_spsr(struct kvm_vcpu *vcpu) -{ - return *__vcpu_spsr(vcpu); -} - -static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v) -{ - *__vcpu_spsr(vcpu) = v; -} - -static inline unsigned long host_spsr_to_spsr32(unsigned long spsr) -{ - return spsr; -} - -static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu, - u8 reg_num) -{ - return *vcpu_reg(vcpu, reg_num); -} - -static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, - unsigned long val) -{ - *vcpu_reg(vcpu, reg_num) = val; -} - -bool kvm_condition_valid32(const struct kvm_vcpu *vcpu); -void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr); -void kvm_inject_undef32(struct kvm_vcpu *vcpu); -void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr); -void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr); -void kvm_inject_vabt(struct kvm_vcpu *vcpu); - -static inline void kvm_inject_undefined(struct kvm_vcpu *vcpu) -{ - kvm_inject_undef32(vcpu); -} - -static inline void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr) -{ - kvm_inject_dabt32(vcpu, addr); -} - -static inline void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) -{ - kvm_inject_pabt32(vcpu, addr); -} - -static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu) -{ - return kvm_condition_valid32(vcpu); -} - -static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) -{ - kvm_skip_instr32(vcpu, is_wide_instr); -} - -static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr = HCR_GUEST_MASK; -} - -static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu) -{ - return (unsigned long *)&vcpu->arch.hcr; -} - -static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr &= ~HCR_TWE; -} - -static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr |= HCR_TWE; -} - -static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu) -{ - return true; -} - -static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu) -{ - return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_pc; -} - -static inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu) -{ - return (unsigned long *)&vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr; -} - -static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) -{ - *vcpu_cpsr(vcpu) |= PSR_T_BIT; -} - -static inline bool mode_has_spsr(struct kvm_vcpu *vcpu) -{ - unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK; - return (cpsr_mode > USR_MODE && cpsr_mode < SYSTEM_MODE); -} - -static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu) -{ - unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK; - return cpsr_mode > USR_MODE; -} - -static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) -{ - return vcpu->arch.fault.hsr; -} - -static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) -{ - u32 hsr = kvm_vcpu_get_hsr(vcpu); - - if (hsr & HSR_CV) - return (hsr & HSR_COND) >> HSR_COND_SHIFT; - - return -1; -} - -static inline unsigned long kvm_vcpu_get_hfar(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.fault.hxfar; -} - -static inline phys_addr_t kvm_vcpu_get_fault_ipa(struct kvm_vcpu *vcpu) -{ - return ((phys_addr_t)vcpu->arch.fault.hpfar & HPFAR_MASK) << 8; -} - -static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_ISV; -} - -static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & (HSR_CM | HSR_WNR | HSR_FSC); -} - -static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_WNR; -} - -static inline bool kvm_vcpu_dabt_issext(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_SSE; -} - -static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu) -{ - return false; -} - -static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu) -{ - return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT; -} - -static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW; -} - -static inline bool kvm_vcpu_dabt_is_cm(struct kvm_vcpu *vcpu) -{ - return !!(kvm_vcpu_get_hsr(vcpu) & HSR_DABT_CM); -} - -/* Get Access Size from a data abort */ -static inline unsigned int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu) -{ - switch ((kvm_vcpu_get_hsr(vcpu) >> 22) & 0x3) { - case 0: - return 1; - case 1: - return 2; - case 2: - return 4; - default: - kvm_err("Hardware is weird: SAS 0b11 is reserved\n"); - return 4; - } -} - -/* This one is not specific to Data Abort */ -static inline bool kvm_vcpu_trap_il_is32bit(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_IL; -} - -static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT; -} - -static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT; -} - -static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_FSC; -} - -static inline u8 kvm_vcpu_trap_get_fault_type(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE; -} - -static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu) -{ - switch (kvm_vcpu_trap_get_fault(vcpu)) { - case FSC_SEA: - case FSC_SEA_TTW0: - case FSC_SEA_TTW1: - case FSC_SEA_TTW2: - case FSC_SEA_TTW3: - case FSC_SECC: - case FSC_SECC_TTW0: - case FSC_SECC_TTW1: - case FSC_SECC_TTW2: - case FSC_SECC_TTW3: - return true; - default: - return false; - } -} - -static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu) -{ - if (kvm_vcpu_trap_is_iabt(vcpu)) - return false; - - return kvm_vcpu_dabt_iswrite(vcpu); -} - -static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK; -} - -static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu) -{ - return vcpu_cp15(vcpu, c0_MPIDR) & MPIDR_HWID_BITMASK; -} - -static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu) -{ - return false; -} - -static inline void kvm_arm_set_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu, - bool flag) -{ -} - -static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) -{ - *vcpu_cpsr(vcpu) |= PSR_E_BIT; -} - -static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) -{ - return !!(*vcpu_cpsr(vcpu) & PSR_E_BIT); -} - -static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu, - unsigned long data, - unsigned int len) -{ - if (kvm_vcpu_is_be(vcpu)) { - switch (len) { - case 1: - return data & 0xff; - case 2: - return be16_to_cpu(data & 0xffff); - default: - return be32_to_cpu(data); - } - } else { - switch (len) { - case 1: - return data & 0xff; - case 2: - return le16_to_cpu(data & 0xffff); - default: - return le32_to_cpu(data); - } - } -} - -static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, - unsigned long data, - unsigned int len) -{ - if (kvm_vcpu_is_be(vcpu)) { - switch (len) { - case 1: - return data & 0xff; - case 2: - return cpu_to_be16(data & 0xffff); - default: - return cpu_to_be32(data); - } - } else { - switch (len) { - case 1: - return data & 0xff; - case 2: - return cpu_to_le16(data & 0xffff); - default: - return cpu_to_le32(data); - } - } -} - -static inline void vcpu_ptrauth_setup_lazy(struct kvm_vcpu *vcpu) {} - -#endif /* __ARM_KVM_EMULATE_H__ */ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h deleted file mode 100644 index a827b4d60d38..000000000000 --- a/arch/arm/include/asm/kvm_host.h +++ /dev/null @@ -1,456 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_HOST_H__ -#define __ARM_KVM_HOST_H__ - -#include <linux/arm-smccc.h> -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/kvm_types.h> -#include <asm/cputype.h> -#include <asm/kvm.h> -#include <asm/kvm_asm.h> -#include <asm/fpstate.h> -#include <kvm/arm_arch_timer.h> - -#define __KVM_HAVE_ARCH_INTC_INITIALIZED - -#define KVM_USER_MEM_SLOTS 32 -#define KVM_HAVE_ONE_REG -#define KVM_HALT_POLL_NS_DEFAULT 500000 - -#define KVM_VCPU_MAX_FEATURES 2 - -#include <kvm/arm_vgic.h> - - -#ifdef CONFIG_ARM_GIC_V3 -#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS -#else -#define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS -#endif - -#define KVM_REQ_SLEEP \ - KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) -#define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) -#define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) - -DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); - -static inline int kvm_arm_init_sve(void) { return 0; } - -u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode); -int __attribute_const__ kvm_target_cpu(void); -int kvm_reset_vcpu(struct kvm_vcpu *vcpu); -void kvm_reset_coprocs(struct kvm_vcpu *vcpu); - -struct kvm_vmid { - /* The VMID generation used for the virt. memory system */ - u64 vmid_gen; - u32 vmid; -}; - -struct kvm_arch { - /* The last vcpu id that ran on each physical CPU */ - int __percpu *last_vcpu_ran; - - /* - * Anything that is not used directly from assembly code goes - * here. - */ - - /* The VMID generation used for the virt. memory system */ - struct kvm_vmid vmid; - - /* Stage-2 page table */ - pgd_t *pgd; - phys_addr_t pgd_phys; - - /* Interrupt controller */ - struct vgic_dist vgic; - int max_vcpus; - - /* Mandated version of PSCI */ - u32 psci_version; - - /* - * If we encounter a data abort without valid instruction syndrome - * information, report this to user space. User space can (and - * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is - * supported. - */ - bool return_nisv_io_abort_to_user; -}; - -#define KVM_NR_MEM_OBJS 40 - -/* - * We don't want allocation failures within the mmu code, so we preallocate - * enough memory for a single page fault in a cache. - */ -struct kvm_mmu_memory_cache { - int nobjs; - void *objects[KVM_NR_MEM_OBJS]; -}; - -struct kvm_vcpu_fault_info { - u32 hsr; /* Hyp Syndrome Register */ - u32 hxfar; /* Hyp Data/Inst. Fault Address Register */ - u32 hpfar; /* Hyp IPA Fault Address Register */ -}; - -/* - * 0 is reserved as an invalid value. - * Order should be kept in sync with the save/restore code. - */ -enum vcpu_sysreg { - __INVALID_SYSREG__, - c0_MPIDR, /* MultiProcessor ID Register */ - c0_CSSELR, /* Cache Size Selection Register */ - c1_SCTLR, /* System Control Register */ - c1_ACTLR, /* Auxiliary Control Register */ - c1_CPACR, /* Coprocessor Access Control */ - c2_TTBR0, /* Translation Table Base Register 0 */ - c2_TTBR0_high, /* TTBR0 top 32 bits */ - c2_TTBR1, /* Translation Table Base Register 1 */ - c2_TTBR1_high, /* TTBR1 top 32 bits */ - c2_TTBCR, /* Translation Table Base Control R. */ - c3_DACR, /* Domain Access Control Register */ - c5_DFSR, /* Data Fault Status Register */ - c5_IFSR, /* Instruction Fault Status Register */ - c5_ADFSR, /* Auxilary Data Fault Status R */ - c5_AIFSR, /* Auxilary Instrunction Fault Status R */ - c6_DFAR, /* Data Fault Address Register */ - c6_IFAR, /* Instruction Fault Address Register */ - c7_PAR, /* Physical Address Register */ - c7_PAR_high, /* PAR top 32 bits */ - c9_L2CTLR, /* Cortex A15/A7 L2 Control Register */ - c10_PRRR, /* Primary Region Remap Register */ - c10_NMRR, /* Normal Memory Remap Register */ - c12_VBAR, /* Vector Base Address Register */ - c13_CID, /* Context ID Register */ - c13_TID_URW, /* Thread ID, User R/W */ - c13_TID_URO, /* Thread ID, User R/O */ - c13_TID_PRIV, /* Thread ID, Privileged */ - c14_CNTKCTL, /* Timer Control Register (PL1) */ - c10_AMAIR0, /* Auxilary Memory Attribute Indirection Reg0 */ - c10_AMAIR1, /* Auxilary Memory Attribute Indirection Reg1 */ - NR_CP15_REGS /* Number of regs (incl. invalid) */ -}; - -struct kvm_cpu_context { - struct kvm_regs gp_regs; - struct vfp_hard_struct vfp; - u32 cp15[NR_CP15_REGS]; -}; - -struct kvm_host_data { - struct kvm_cpu_context host_ctxt; -}; - -typedef struct kvm_host_data kvm_host_data_t; - -static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) -{ - /* The host's MPIDR is immutable, so let's set it up at boot time */ - cpu_ctxt->cp15[c0_MPIDR] = read_cpuid_mpidr(); -} - -struct vcpu_reset_state { - unsigned long pc; - unsigned long r0; - bool be; - bool reset; -}; - -struct kvm_vcpu_arch { - struct kvm_cpu_context ctxt; - - int target; /* Processor target */ - DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES); - - /* The CPU type we expose to the VM */ - u32 midr; - - /* HYP trapping configuration */ - u32 hcr; - - /* Exception Information */ - struct kvm_vcpu_fault_info fault; - - /* Host FP context */ - struct kvm_cpu_context *host_cpu_context; - - /* VGIC state */ - struct vgic_cpu vgic_cpu; - struct arch_timer_cpu timer_cpu; - - /* - * Anything that is not used directly from assembly code goes - * here. - */ - - /* vcpu power-off state */ - bool power_off; - - /* Don't run the guest (internal implementation need) */ - bool pause; - - /* Cache some mmu pages needed inside spinlock regions */ - struct kvm_mmu_memory_cache mmu_page_cache; - - struct vcpu_reset_state reset_state; - - /* Detect first run of a vcpu */ - bool has_run_once; -}; - -struct kvm_vm_stat { - ulong remote_tlb_flush; -}; - -struct kvm_vcpu_stat { - u64 halt_successful_poll; - u64 halt_attempted_poll; - u64 halt_poll_invalid; - u64 halt_wakeup; - u64 hvc_exit_stat; - u64 wfe_exit_stat; - u64 wfi_exit_stat; - u64 mmio_exit_user; - u64 mmio_exit_kernel; - u64 exits; -}; - -#define vcpu_cp15(v,r) (v)->arch.ctxt.cp15[r] - -int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); -unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); -int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); -int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); -int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); - -unsigned long __kvm_call_hyp(void *hypfn, ...); - -/* - * The has_vhe() part doesn't get emitted, but is used for type-checking. - */ -#define kvm_call_hyp(f, ...) \ - do { \ - if (has_vhe()) { \ - f(__VA_ARGS__); \ - } else { \ - __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \ - } \ - } while(0) - -#define kvm_call_hyp_ret(f, ...) \ - ({ \ - typeof(f(__VA_ARGS__)) ret; \ - \ - if (has_vhe()) { \ - ret = f(__VA_ARGS__); \ - } else { \ - ret = __kvm_call_hyp(kvm_ksym_ref(f), \ - ##__VA_ARGS__); \ - } \ - \ - ret; \ - }) - -void force_vm_exit(const cpumask_t *mask); -int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, - struct kvm_vcpu_events *events); - -int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, - struct kvm_vcpu_events *events); - -#define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); -int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); - -unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); -int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); -int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); -int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); - -void kvm_arm_halt_guest(struct kvm *kvm); -void kvm_arm_resume_guest(struct kvm *kvm); - -int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); -unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu); -int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); -int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); - -int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, - int exception_index); - -static inline void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run, - int exception_index) {} - -/* MMIO helpers */ -void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); -unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len); - -int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); -int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, - phys_addr_t fault_ipa); - -static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, - unsigned long hyp_stack_ptr, - unsigned long vector_ptr) -{ - /* - * Call initialization code, and switch to the full blown HYP - * code. The init code doesn't need to preserve these - * registers as r0-r3 are already callee saved according to - * the AAPCS. - * Note that we slightly misuse the prototype by casting the - * stack pointer to a void *. - - * The PGDs are always passed as the third argument, in order - * to be passed into r2-r3 to the init code (yes, this is - * compliant with the PCS!). - */ - - __kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr); -} - -static inline void __cpu_init_stage2(void) -{ - kvm_call_hyp(__init_stage2_translation); -} - -static inline int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) -{ - return 0; -} - -int kvm_perf_init(void); -int kvm_perf_teardown(void); - -static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) -{ - return SMCCC_RET_NOT_SUPPORTED; -} - -static inline gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) -{ - return GPA_INVALID; -} - -static inline void kvm_update_stolen_time(struct kvm_vcpu *vcpu) -{ -} - -static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) -{ -} - -static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) -{ - return false; -} - -void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot); - -struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); - -static inline bool kvm_arch_requires_vhe(void) { return false; } -static inline void kvm_arch_hardware_unsetup(void) {} -static inline void kvm_arch_sync_events(struct kvm *kvm) {} -static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} -static inline void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) {} - -static inline void kvm_arm_init_debug(void) {} -static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {} -static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {} -static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {} - -int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr); -int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr); -int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr); - -/* - * VFP/NEON switching is all done by the hyp switch code, so no need to - * coordinate with host context handling for this state: - */ -static inline void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) {} -static inline void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) {} -static inline void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) {} - -static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} -static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} - -#define KVM_BP_HARDEN_UNKNOWN -1 -#define KVM_BP_HARDEN_WA_NEEDED 0 -#define KVM_BP_HARDEN_NOT_REQUIRED 1 - -static inline int kvm_arm_harden_branch_predictor(void) -{ - switch(read_cpuid_part()) { -#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR - case ARM_CPU_PART_BRAHMA_B15: - case ARM_CPU_PART_CORTEX_A12: - case ARM_CPU_PART_CORTEX_A15: - case ARM_CPU_PART_CORTEX_A17: - return KVM_BP_HARDEN_WA_NEEDED; -#endif - case ARM_CPU_PART_CORTEX_A7: - return KVM_BP_HARDEN_NOT_REQUIRED; - default: - return KVM_BP_HARDEN_UNKNOWN; - } -} - -#define KVM_SSBD_UNKNOWN -1 -#define KVM_SSBD_FORCE_DISABLE 0 -#define KVM_SSBD_KERNEL 1 -#define KVM_SSBD_FORCE_ENABLE 2 -#define KVM_SSBD_MITIGATED 3 - -static inline int kvm_arm_have_ssbd(void) -{ - /* No way to detect it yet, pretend it is not there. */ - return KVM_SSBD_UNKNOWN; -} - -static inline void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu) {} -static inline void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) {} - -#define __KVM_HAVE_ARCH_VM_ALLOC -struct kvm *kvm_arch_alloc_vm(void); -void kvm_arch_free_vm(struct kvm *kvm); - -static inline int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type) -{ - /* - * On 32bit ARM, VMs get a static 40bit IPA stage2 setup, - * so any non-zero value used as type is illegal. - */ - if (type) - return -EINVAL; - return 0; -} - -static inline int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature) -{ - return -EINVAL; -} - -static inline bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu) -{ - return true; -} - -#endif /* __ARM_KVM_HOST_H__ */ diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h deleted file mode 100644 index 3c1b55ecc578..000000000000 --- a/arch/arm/include/asm/kvm_hyp.h +++ /dev/null @@ -1,127 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2015 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ - -#ifndef __ARM_KVM_HYP_H__ -#define __ARM_KVM_HYP_H__ - -#include <linux/compiler.h> -#include <linux/kvm_host.h> -#include <asm/cp15.h> -#include <asm/kvm_arm.h> -#include <asm/vfp.h> - -#define __hyp_text __section(.hyp.text) notrace - -#define __ACCESS_VFP(CRn) \ - "mrc", "mcr", __stringify(p10, 7, %0, CRn, cr0, 0), u32 - -#define write_special(v, r) \ - asm volatile("msr " __stringify(r) ", %0" : : "r" (v)) -#define read_special(r) ({ \ - u32 __val; \ - asm volatile("mrs %0, " __stringify(r) : "=r" (__val)); \ - __val; \ -}) - -#define TTBR0 __ACCESS_CP15_64(0, c2) -#define TTBR1 __ACCESS_CP15_64(1, c2) -#define VTTBR __ACCESS_CP15_64(6, c2) -#define PAR __ACCESS_CP15_64(0, c7) -#define CNTP_CVAL __ACCESS_CP15_64(2, c14) -#define CNTV_CVAL __ACCESS_CP15_64(3, c14) -#define CNTVOFF __ACCESS_CP15_64(4, c14) - -#define MIDR __ACCESS_CP15(c0, 0, c0, 0) -#define CSSELR __ACCESS_CP15(c0, 2, c0, 0) -#define VPIDR __ACCESS_CP15(c0, 4, c0, 0) -#define VMPIDR __ACCESS_CP15(c0, 4, c0, 5) -#define SCTLR __ACCESS_CP15(c1, 0, c0, 0) -#define CPACR __ACCESS_CP15(c1, 0, c0, 2) -#define HCR __ACCESS_CP15(c1, 4, c1, 0) -#define HDCR __ACCESS_CP15(c1, 4, c1, 1) -#define HCPTR __ACCESS_CP15(c1, 4, c1, 2) -#define HSTR __ACCESS_CP15(c1, 4, c1, 3) -#define TTBCR __ACCESS_CP15(c2, 0, c0, 2) -#define HTCR __ACCESS_CP15(c2, 4, c0, 2) -#define VTCR __ACCESS_CP15(c2, 4, c1, 2) -#define DACR __ACCESS_CP15(c3, 0, c0, 0) -#define DFSR __ACCESS_CP15(c5, 0, c0, 0) -#define IFSR __ACCESS_CP15(c5, 0, c0, 1) -#define ADFSR __ACCESS_CP15(c5, 0, c1, 0) -#define AIFSR __ACCESS_CP15(c5, 0, c1, 1) -#define HSR __ACCESS_CP15(c5, 4, c2, 0) -#define DFAR __ACCESS_CP15(c6, 0, c0, 0) -#define IFAR __ACCESS_CP15(c6, 0, c0, 2) -#define HDFAR __ACCESS_CP15(c6, 4, c0, 0) -#define HIFAR __ACCESS_CP15(c6, 4, c0, 2) -#define HPFAR __ACCESS_CP15(c6, 4, c0, 4) -#define ICIALLUIS __ACCESS_CP15(c7, 0, c1, 0) -#define BPIALLIS __ACCESS_CP15(c7, 0, c1, 6) -#define ICIMVAU __ACCESS_CP15(c7, 0, c5, 1) -#define ATS1CPR __ACCESS_CP15(c7, 0, c8, 0) -#define TLBIALLIS __ACCESS_CP15(c8, 0, c3, 0) -#define TLBIALL __ACCESS_CP15(c8, 0, c7, 0) -#define TLBIALLNSNHIS __ACCESS_CP15(c8, 4, c3, 4) -#define PRRR __ACCESS_CP15(c10, 0, c2, 0) -#define NMRR __ACCESS_CP15(c10, 0, c2, 1) -#define AMAIR0 __ACCESS_CP15(c10, 0, c3, 0) -#define AMAIR1 __ACCESS_CP15(c10, 0, c3, 1) -#define VBAR __ACCESS_CP15(c12, 0, c0, 0) -#define CID __ACCESS_CP15(c13, 0, c0, 1) -#define TID_URW __ACCESS_CP15(c13, 0, c0, 2) -#define TID_URO __ACCESS_CP15(c13, 0, c0, 3) -#define TID_PRIV __ACCESS_CP15(c13, 0, c0, 4) -#define HTPIDR __ACCESS_CP15(c13, 4, c0, 2) -#define CNTKCTL __ACCESS_CP15(c14, 0, c1, 0) -#define CNTP_CTL __ACCESS_CP15(c14, 0, c2, 1) -#define CNTV_CTL __ACCESS_CP15(c14, 0, c3, 1) -#define CNTHCTL __ACCESS_CP15(c14, 4, c1, 0) - -#define VFP_FPEXC __ACCESS_VFP(FPEXC) - -/* AArch64 compatibility macros, only for the timer so far */ -#define read_sysreg_el0(r) read_sysreg(r##_EL0) -#define write_sysreg_el0(v, r) write_sysreg(v, r##_EL0) - -#define SYS_CNTP_CTL_EL0 CNTP_CTL -#define SYS_CNTP_CVAL_EL0 CNTP_CVAL -#define SYS_CNTV_CTL_EL0 CNTV_CTL -#define SYS_CNTV_CVAL_EL0 CNTV_CVAL - -#define cntvoff_el2 CNTVOFF -#define cnthctl_el2 CNTHCTL - -void __timer_enable_traps(struct kvm_vcpu *vcpu); -void __timer_disable_traps(struct kvm_vcpu *vcpu); - -void __vgic_v2_save_state(struct kvm_vcpu *vcpu); -void __vgic_v2_restore_state(struct kvm_vcpu *vcpu); - -void __sysreg_save_state(struct kvm_cpu_context *ctxt); -void __sysreg_restore_state(struct kvm_cpu_context *ctxt); - -void __vgic_v3_save_state(struct kvm_vcpu *vcpu); -void __vgic_v3_restore_state(struct kvm_vcpu *vcpu); -void __vgic_v3_activate_traps(struct kvm_vcpu *vcpu); -void __vgic_v3_deactivate_traps(struct kvm_vcpu *vcpu); -void __vgic_v3_save_aprs(struct kvm_vcpu *vcpu); -void __vgic_v3_restore_aprs(struct kvm_vcpu *vcpu); - -asmlinkage void __vfp_save_state(struct vfp_hard_struct *vfp); -asmlinkage void __vfp_restore_state(struct vfp_hard_struct *vfp); -static inline bool __vfp_enabled(void) -{ - return !(read_sysreg(HCPTR) & (HCPTR_TCP(11) | HCPTR_TCP(10))); -} - -void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt); -void __hyp_text __banked_restore_state(struct kvm_cpu_context *ctxt); - -asmlinkage int __guest_enter(struct kvm_vcpu *vcpu, - struct kvm_cpu_context *host); -asmlinkage int __hyp_do_panic(const char *, int, u32); - -#endif /* __ARM_KVM_HYP_H__ */ diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h deleted file mode 100644 index 0d84d50bf9ba..000000000000 --- a/arch/arm/include/asm/kvm_mmu.h +++ /dev/null @@ -1,435 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_MMU_H__ -#define __ARM_KVM_MMU_H__ - -#include <asm/memory.h> -#include <asm/page.h> - -/* - * We directly use the kernel VA for the HYP, as we can directly share - * the mapping (HTTBR "covers" TTBR1). - */ -#define kern_hyp_va(kva) (kva) - -/* Contrary to arm64, there is no need to generate a PC-relative address */ -#define hyp_symbol_addr(s) \ - ({ \ - typeof(s) *addr = &(s); \ - addr; \ - }) - -#ifndef __ASSEMBLY__ - -#include <linux/highmem.h> -#include <asm/cacheflush.h> -#include <asm/cputype.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_hyp.h> -#include <asm/pgalloc.h> -#include <asm/stage2_pgtable.h> - -/* Ensure compatibility with arm64 */ -#define VA_BITS 32 - -#define kvm_phys_shift(kvm) KVM_PHYS_SHIFT -#define kvm_phys_size(kvm) (1ULL << kvm_phys_shift(kvm)) -#define kvm_phys_mask(kvm) (kvm_phys_size(kvm) - 1ULL) -#define kvm_vttbr_baddr_mask(kvm) VTTBR_BADDR_MASK - -#define stage2_pgd_size(kvm) (PTRS_PER_S2_PGD * sizeof(pgd_t)) - -int create_hyp_mappings(void *from, void *to, pgprot_t prot); -int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, - void __iomem **kaddr, - void __iomem **haddr); -int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, - void **haddr); -void free_hyp_pgds(void); - -void stage2_unmap_vm(struct kvm *kvm); -int kvm_alloc_stage2_pgd(struct kvm *kvm); -void kvm_free_stage2_pgd(struct kvm *kvm); -int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, - phys_addr_t pa, unsigned long size, bool writable); - -int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run); - -void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu); - -phys_addr_t kvm_mmu_get_httbr(void); -phys_addr_t kvm_get_idmap_vector(void); -int kvm_mmu_init(void); -void kvm_clear_hyp_idmap(void); - -#define kvm_mk_pmd(ptep) __pmd(__pa(ptep) | PMD_TYPE_TABLE) -#define kvm_mk_pud(pmdp) __pud(__pa(pmdp) | PMD_TYPE_TABLE) -#define kvm_mk_pgd(pudp) ({ BUILD_BUG(); 0; }) - -#define kvm_pfn_pte(pfn, prot) pfn_pte(pfn, prot) -#define kvm_pfn_pmd(pfn, prot) pfn_pmd(pfn, prot) -#define kvm_pfn_pud(pfn, prot) (__pud(0)) - -#define kvm_pud_pfn(pud) ({ WARN_ON(1); 0; }) - - -#define kvm_pmd_mkhuge(pmd) pmd_mkhuge(pmd) -/* No support for pud hugepages */ -#define kvm_pud_mkhuge(pud) ( {WARN_ON(1); pud; }) - -/* - * The following kvm_*pud*() functions are provided strictly to allow - * sharing code with arm64. They should never be called in practice. - */ -static inline void kvm_set_s2pud_readonly(pud_t *pud) -{ - WARN_ON(1); -} - -static inline bool kvm_s2pud_readonly(pud_t *pud) -{ - WARN_ON(1); - return false; -} - -static inline void kvm_set_pud(pud_t *pud, pud_t new_pud) -{ - WARN_ON(1); -} - -static inline pud_t kvm_s2pud_mkwrite(pud_t pud) -{ - WARN_ON(1); - return pud; -} - -static inline pud_t kvm_s2pud_mkexec(pud_t pud) -{ - WARN_ON(1); - return pud; -} - -static inline bool kvm_s2pud_exec(pud_t *pud) -{ - WARN_ON(1); - return false; -} - -static inline pud_t kvm_s2pud_mkyoung(pud_t pud) -{ - BUG(); - return pud; -} - -static inline bool kvm_s2pud_young(pud_t pud) -{ - WARN_ON(1); - return false; -} - -static inline pte_t kvm_s2pte_mkwrite(pte_t pte) -{ - pte_val(pte) |= L_PTE_S2_RDWR; - return pte; -} - -static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd) -{ - pmd_val(pmd) |= L_PMD_S2_RDWR; - return pmd; -} - -static inline pte_t kvm_s2pte_mkexec(pte_t pte) -{ - pte_val(pte) &= ~L_PTE_XN; - return pte; -} - -static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd) -{ - pmd_val(pmd) &= ~PMD_SECT_XN; - return pmd; -} - -static inline void kvm_set_s2pte_readonly(pte_t *pte) -{ - pte_val(*pte) = (pte_val(*pte) & ~L_PTE_S2_RDWR) | L_PTE_S2_RDONLY; -} - -static inline bool kvm_s2pte_readonly(pte_t *pte) -{ - return (pte_val(*pte) & L_PTE_S2_RDWR) == L_PTE_S2_RDONLY; -} - -static inline bool kvm_s2pte_exec(pte_t *pte) -{ - return !(pte_val(*pte) & L_PTE_XN); -} - -static inline void kvm_set_s2pmd_readonly(pmd_t *pmd) -{ - pmd_val(*pmd) = (pmd_val(*pmd) & ~L_PMD_S2_RDWR) | L_PMD_S2_RDONLY; -} - -static inline bool kvm_s2pmd_readonly(pmd_t *pmd) -{ - return (pmd_val(*pmd) & L_PMD_S2_RDWR) == L_PMD_S2_RDONLY; -} - -static inline bool kvm_s2pmd_exec(pmd_t *pmd) -{ - return !(pmd_val(*pmd) & PMD_SECT_XN); -} - -static inline bool kvm_page_empty(void *ptr) -{ - struct page *ptr_page = virt_to_page(ptr); - return page_count(ptr_page) == 1; -} - -#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep) -#define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp) -#define kvm_pud_table_empty(kvm, pudp) false - -#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep) -#define hyp_pmd_table_empty(pmdp) kvm_page_empty(pmdp) -#define hyp_pud_table_empty(pudp) false - -struct kvm; - -#define kvm_flush_dcache_to_poc(a,l) __cpuc_flush_dcache_area((a), (l)) - -static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) -{ - return (vcpu_cp15(vcpu, c1_SCTLR) & 0b101) == 0b101; -} - -static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size) -{ - /* - * Clean the dcache to the Point of Coherency. - * - * We need to do this through a kernel mapping (using the - * user-space mapping has proved to be the wrong - * solution). For that, we need to kmap one page at a time, - * and iterate over the range. - */ - - VM_BUG_ON(size & ~PAGE_MASK); - - while (size) { - void *va = kmap_atomic_pfn(pfn); - - kvm_flush_dcache_to_poc(va, PAGE_SIZE); - - size -= PAGE_SIZE; - pfn++; - - kunmap_atomic(va); - } -} - -static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn, - unsigned long size) -{ - u32 iclsz; - - /* - * If we are going to insert an instruction page and the icache is - * either VIPT or PIPT, there is a potential problem where the host - * (or another VM) may have used the same page as this guest, and we - * read incorrect data from the icache. If we're using a PIPT cache, - * we can invalidate just that page, but if we are using a VIPT cache - * we need to invalidate the entire icache - damn shame - as written - * in the ARM ARM (DDI 0406C.b - Page B3-1393). - * - * VIVT caches are tagged using both the ASID and the VMID and doesn't - * need any kind of flushing (DDI 0406C.b - Page B3-1392). - */ - - VM_BUG_ON(size & ~PAGE_MASK); - - if (icache_is_vivt_asid_tagged()) - return; - - if (!icache_is_pipt()) { - /* any kind of VIPT cache */ - __flush_icache_all(); - return; - } - - /* - * CTR IminLine contains Log2 of the number of words in the - * cache line, so we can get the number of words as - * 2 << (IminLine - 1). To get the number of bytes, we - * multiply by 4 (the number of bytes in a 32-bit word), and - * get 4 << (IminLine). - */ - iclsz = 4 << (read_cpuid(CPUID_CACHETYPE) & 0xf); - - while (size) { - void *va = kmap_atomic_pfn(pfn); - void *end = va + PAGE_SIZE; - void *addr = va; - - do { - write_sysreg(addr, ICIMVAU); - addr += iclsz; - } while (addr < end); - - dsb(ishst); - isb(); - - size -= PAGE_SIZE; - pfn++; - - kunmap_atomic(va); - } - - /* Check if we need to invalidate the BTB */ - if ((read_cpuid_ext(CPUID_EXT_MMFR1) >> 28) != 4) { - write_sysreg(0, BPIALLIS); - dsb(ishst); - isb(); - } -} - -static inline void __kvm_flush_dcache_pte(pte_t pte) -{ - void *va = kmap_atomic(pte_page(pte)); - - kvm_flush_dcache_to_poc(va, PAGE_SIZE); - - kunmap_atomic(va); -} - -static inline void __kvm_flush_dcache_pmd(pmd_t pmd) -{ - unsigned long size = PMD_SIZE; - kvm_pfn_t pfn = pmd_pfn(pmd); - - while (size) { - void *va = kmap_atomic_pfn(pfn); - - kvm_flush_dcache_to_poc(va, PAGE_SIZE); - - pfn++; - size -= PAGE_SIZE; - - kunmap_atomic(va); - } -} - -static inline void __kvm_flush_dcache_pud(pud_t pud) -{ -} - -#define kvm_virt_to_phys(x) virt_to_idmap((unsigned long)(x)) - -void kvm_set_way_flush(struct kvm_vcpu *vcpu); -void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled); - -static inline bool __kvm_cpu_uses_extended_idmap(void) -{ - return false; -} - -static inline unsigned long __kvm_idmap_ptrs_per_pgd(void) -{ - return PTRS_PER_PGD; -} - -static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd, - pgd_t *hyp_pgd, - pgd_t *merged_hyp_pgd, - unsigned long hyp_idmap_start) { } - -static inline unsigned int kvm_get_vmid_bits(void) -{ - return 8; -} - -/* - * We are not in the kvm->srcu critical section most of the time, so we take - * the SRCU read lock here. Since we copy the data from the user page, we - * can immediately drop the lock again. - */ -static inline int kvm_read_guest_lock(struct kvm *kvm, - gpa_t gpa, void *data, unsigned long len) -{ - int srcu_idx = srcu_read_lock(&kvm->srcu); - int ret = kvm_read_guest(kvm, gpa, data, len); - - srcu_read_unlock(&kvm->srcu, srcu_idx); - - return ret; -} - -static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, - const void *data, unsigned long len) -{ - int srcu_idx = srcu_read_lock(&kvm->srcu); - int ret = kvm_write_guest(kvm, gpa, data, len); - - srcu_read_unlock(&kvm->srcu, srcu_idx); - - return ret; -} - -static inline void *kvm_get_hyp_vector(void) -{ - switch(read_cpuid_part()) { -#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR - case ARM_CPU_PART_CORTEX_A12: - case ARM_CPU_PART_CORTEX_A17: - { - extern char __kvm_hyp_vector_bp_inv[]; - return kvm_ksym_ref(__kvm_hyp_vector_bp_inv); - } - - case ARM_CPU_PART_BRAHMA_B15: - case ARM_CPU_PART_CORTEX_A15: - { - extern char __kvm_hyp_vector_ic_inv[]; - return kvm_ksym_ref(__kvm_hyp_vector_ic_inv); - } -#endif - default: - { - extern char __kvm_hyp_vector[]; - return kvm_ksym_ref(__kvm_hyp_vector); - } - } -} - -static inline int kvm_map_vectors(void) -{ - return 0; -} - -static inline int hyp_map_aux_data(void) -{ - return 0; -} - -#define kvm_phys_to_vttbr(addr) (addr) - -static inline void kvm_set_ipa_limit(void) {} - -static __always_inline u64 kvm_get_vttbr(struct kvm *kvm) -{ - struct kvm_vmid *vmid = &kvm->arch.vmid; - u64 vmid_field, baddr; - - baddr = kvm->arch.pgd_phys; - vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT; - return kvm_phys_to_vttbr(baddr) | vmid_field; -} - -#endif /* !__ASSEMBLY__ */ - -#endif /* __ARM_KVM_MMU_H__ */ diff --git a/arch/arm/include/asm/kvm_ras.h b/arch/arm/include/asm/kvm_ras.h deleted file mode 100644 index e9577292dfe4..000000000000 --- a/arch/arm/include/asm/kvm_ras.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2018 - Arm Ltd */ - -#ifndef __ARM_KVM_RAS_H__ -#define __ARM_KVM_RAS_H__ - -#include <linux/types.h> - -static inline int kvm_handle_guest_sea(phys_addr_t addr, unsigned int esr) -{ - return -1; -} - -#endif /* __ARM_KVM_RAS_H__ */ diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index ad55ab068dbf..36805f94939e 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -104,26 +104,6 @@ */ #define L_PGD_SWAPPER (_AT(pgdval_t, 1) << 55) /* swapper_pg_dir entry */ -/* - * 2nd stage PTE definitions for LPAE. - */ -#define L_PTE_S2_MT_UNCACHED (_AT(pteval_t, 0x0) << 2) /* strongly ordered */ -#define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* normal inner write-through */ -#define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* normal inner write-back */ -#define L_PTE_S2_MT_DEV_SHARED (_AT(pteval_t, 0x1) << 2) /* device */ -#define L_PTE_S2_MT_MASK (_AT(pteval_t, 0xf) << 2) - -#define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ -#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ - -#define L_PMD_S2_RDONLY (_AT(pmdval_t, 1) << 6) /* HAP[1] */ -#define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ - -/* - * Hyp-mode PL2 PTE definitions for LPAE. - */ -#define L_PTE_HYP L_PTE_USER - #ifndef __ASSEMBLY__ #define pud_none(pud) (!pud_val(pud)) diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index eabcb48a7840..0483cf413315 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -80,9 +80,6 @@ extern void __pgd_error(const char *file, int line, pgd_t); extern pgprot_t pgprot_user; extern pgprot_t pgprot_kernel; -extern pgprot_t pgprot_hyp_device; -extern pgprot_t pgprot_s2; -extern pgprot_t pgprot_s2_device; #define _MOD_PROT(p, b) __pgprot(pgprot_val(p) | (b)) @@ -95,12 +92,6 @@ extern pgprot_t pgprot_s2_device; #define PAGE_READONLY_EXEC _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY) #define PAGE_KERNEL _MOD_PROT(pgprot_kernel, L_PTE_XN) #define PAGE_KERNEL_EXEC pgprot_kernel -#define PAGE_HYP _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_XN) -#define PAGE_HYP_EXEC _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY) -#define PAGE_HYP_RO _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY | L_PTE_XN) -#define PAGE_HYP_DEVICE _MOD_PROT(pgprot_hyp_device, L_PTE_HYP) -#define PAGE_S2 _MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY | L_PTE_XN) -#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY | L_PTE_XN) #define __PAGE_NONE __pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE) #define __PAGE_SHARED __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN) diff --git a/arch/arm/include/asm/sections.h b/arch/arm/include/asm/sections.h index 4ceb4f757d4d..700b8bcdf9bd 100644 --- a/arch/arm/include/asm/sections.h +++ b/arch/arm/include/asm/sections.h @@ -10,8 +10,6 @@ extern char __idmap_text_start[]; extern char __idmap_text_end[]; extern char __entry_text_start[]; extern char __entry_text_end[]; -extern char __hyp_idmap_text_start[]; -extern char __hyp_idmap_text_end[]; static inline bool in_entry_text(unsigned long addr) { @@ -22,9 +20,7 @@ static inline bool in_entry_text(unsigned long addr) static inline bool in_idmap_text(unsigned long addr) { void *a = (void *)addr; - return memory_contains(__idmap_text_start, __idmap_text_end, a, 1) || - memory_contains(__hyp_idmap_text_start, __hyp_idmap_text_end, - a, 1); + return memory_contains(__idmap_text_start, __idmap_text_end, a, 1); } #endif /* _ASM_ARM_SECTIONS_H */ diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h deleted file mode 100644 index aaceec7855ec..000000000000 --- a/arch/arm/include/asm/stage2_pgtable.h +++ /dev/null @@ -1,75 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2016 - ARM Ltd - * - * stage2 page table helpers - */ - -#ifndef __ARM_S2_PGTABLE_H_ -#define __ARM_S2_PGTABLE_H_ - -/* - * kvm_mmu_cache_min_pages() is the number of pages required - * to install a stage-2 translation. We pre-allocate the entry - * level table at VM creation. Since we have a 3 level page-table, - * we need only two pages to add a new mapping. - */ -#define kvm_mmu_cache_min_pages(kvm) 2 - -#define stage2_pgd_none(kvm, pgd) pgd_none(pgd) -#define stage2_pgd_clear(kvm, pgd) pgd_clear(pgd) -#define stage2_pgd_present(kvm, pgd) pgd_present(pgd) -#define stage2_pgd_populate(kvm, pgd, pud) pgd_populate(NULL, pgd, pud) -#define stage2_pud_offset(kvm, pgd, address) pud_offset(pgd, address) -#define stage2_pud_free(kvm, pud) do { } while (0) - -#define stage2_pud_none(kvm, pud) pud_none(pud) -#define stage2_pud_clear(kvm, pud) pud_clear(pud) -#define stage2_pud_present(kvm, pud) pud_present(pud) -#define stage2_pud_populate(kvm, pud, pmd) pud_populate(NULL, pud, pmd) -#define stage2_pmd_offset(kvm, pud, address) pmd_offset(pud, address) -#define stage2_pmd_free(kvm, pmd) free_page((unsigned long)pmd) - -#define stage2_pud_huge(kvm, pud) pud_huge(pud) - -/* Open coded p*d_addr_end that can deal with 64bit addresses */ -static inline phys_addr_t -stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) -{ - phys_addr_t boundary = (addr + PGDIR_SIZE) & PGDIR_MASK; - - return (boundary - 1 < end - 1) ? boundary : end; -} - -#define stage2_pud_addr_end(kvm, addr, end) (end) - -static inline phys_addr_t -stage2_pmd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) -{ - phys_addr_t boundary = (addr + PMD_SIZE) & PMD_MASK; - - return (boundary - 1 < end - 1) ? boundary : end; -} - -#define stage2_pgd_index(kvm, addr) pgd_index(addr) - -#define stage2_pte_table_empty(kvm, ptep) kvm_page_empty(ptep) -#define stage2_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp) -#define stage2_pud_table_empty(kvm, pudp) false - -static inline bool kvm_stage2_has_pud(struct kvm *kvm) -{ - return false; -} - -#define S2_PMD_MASK PMD_MASK -#define S2_PMD_SIZE PMD_SIZE -#define S2_PUD_MASK PUD_MASK -#define S2_PUD_SIZE PUD_SIZE - -static inline bool kvm_stage2_has_pmd(struct kvm *kvm) -{ - return true; -} - -#endif /* __ARM_S2_PGTABLE_H_ */ diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h index 17c26ccd126d..dd9697b2bde8 100644 --- a/arch/arm/include/asm/virt.h +++ b/arch/arm/include/asm/virt.h @@ -39,8 +39,6 @@ static inline void sync_boot_mode(void) sync_cache_r(&__boot_cpu_mode); } -void __hyp_set_vectors(unsigned long phys_vector_base); -void __hyp_reset_vectors(void); #else #define __boot_cpu_mode (SVC_MODE) #define sync_boot_mode() @@ -67,18 +65,6 @@ static inline bool is_kernel_in_hyp_mode(void) return false; } -static inline bool has_vhe(void) -{ - return false; -} - -/* The section containing the hypervisor idmap text */ -extern char __hyp_idmap_text_start[]; -extern char __hyp_idmap_text_end[]; - -/* The section containing the hypervisor text */ -extern char __hyp_text_start[]; -extern char __hyp_text_end[]; #endif #else @@ -87,9 +73,6 @@ extern char __hyp_text_end[]; #define HVC_SET_VECTORS 0 #define HVC_SOFT_RESTART 1 -#define HVC_RESET_VECTORS 2 - -#define HVC_STUB_HCALL_NR 3 #endif /* __ASSEMBLY__ */ diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h deleted file mode 100644 index 03cd7c19a683..000000000000 --- a/arch/arm/include/uapi/asm/kvm.h +++ /dev/null @@ -1,314 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License, version 2, as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - */ - -#ifndef __ARM_KVM_H__ -#define __ARM_KVM_H__ - -#include <linux/types.h> -#include <linux/psci.h> -#include <asm/ptrace.h> - -#define __KVM_HAVE_GUEST_DEBUG -#define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_READONLY_MEM -#define __KVM_HAVE_VCPU_EVENTS - -#define KVM_COALESCED_MMIO_PAGE_OFFSET 1 - -#define KVM_REG_SIZE(id) \ - (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) - -/* Valid for svc_regs, abt_regs, und_regs, irq_regs in struct kvm_regs */ -#define KVM_ARM_SVC_sp svc_regs[0] -#define KVM_ARM_SVC_lr svc_regs[1] -#define KVM_ARM_SVC_spsr svc_regs[2] -#define KVM_ARM_ABT_sp abt_regs[0] -#define KVM_ARM_ABT_lr abt_regs[1] -#define KVM_ARM_ABT_spsr abt_regs[2] -#define KVM_ARM_UND_sp und_regs[0] -#define KVM_ARM_UND_lr und_regs[1] -#define KVM_ARM_UND_spsr und_regs[2] -#define KVM_ARM_IRQ_sp irq_regs[0] -#define KVM_ARM_IRQ_lr irq_regs[1] -#define KVM_ARM_IRQ_spsr irq_regs[2] - -/* Valid only for fiq_regs in struct kvm_regs */ -#define KVM_ARM_FIQ_r8 fiq_regs[0] -#define KVM_ARM_FIQ_r9 fiq_regs[1] -#define KVM_ARM_FIQ_r10 fiq_regs[2] -#define KVM_ARM_FIQ_fp fiq_regs[3] -#define KVM_ARM_FIQ_ip fiq_regs[4] -#define KVM_ARM_FIQ_sp fiq_regs[5] -#define KVM_ARM_FIQ_lr fiq_regs[6] -#define KVM_ARM_FIQ_spsr fiq_regs[7] - -struct kvm_regs { - struct pt_regs usr_regs; /* R0_usr - R14_usr, PC, CPSR */ - unsigned long svc_regs[3]; /* SP_svc, LR_svc, SPSR_svc */ - unsigned long abt_regs[3]; /* SP_abt, LR_abt, SPSR_abt */ - unsigned long und_regs[3]; /* SP_und, LR_und, SPSR_und */ - unsigned long irq_regs[3]; /* SP_irq, LR_irq, SPSR_irq */ - unsigned long fiq_regs[8]; /* R8_fiq - R14_fiq, SPSR_fiq */ -}; - -/* Supported Processor Types */ -#define KVM_ARM_TARGET_CORTEX_A15 0 -#define KVM_ARM_TARGET_CORTEX_A7 1 -#define KVM_ARM_NUM_TARGETS 2 - -/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ -#define KVM_ARM_DEVICE_TYPE_SHIFT 0 -#define KVM_ARM_DEVICE_TYPE_MASK (0xffff << KVM_ARM_DEVICE_TYPE_SHIFT) -#define KVM_ARM_DEVICE_ID_SHIFT 16 -#define KVM_ARM_DEVICE_ID_MASK (0xffff << KVM_ARM_DEVICE_ID_SHIFT) - -/* Supported device IDs */ -#define KVM_ARM_DEVICE_VGIC_V2 0 - -/* Supported VGIC address types */ -#define KVM_VGIC_V2_ADDR_TYPE_DIST 0 -#define KVM_VGIC_V2_ADDR_TYPE_CPU 1 - -#define KVM_VGIC_V2_DIST_SIZE 0x1000 -#define KVM_VGIC_V2_CPU_SIZE 0x2000 - -/* Supported VGICv3 address types */ -#define KVM_VGIC_V3_ADDR_TYPE_DIST 2 -#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3 -#define KVM_VGIC_ITS_ADDR_TYPE 4 -#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5 - -#define KVM_VGIC_V3_DIST_SIZE SZ_64K -#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K) -#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K) - -#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */ -#define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */ - -struct kvm_vcpu_init { - __u32 target; - __u32 features[7]; -}; - -struct kvm_sregs { -}; - -struct kvm_fpu { -}; - -struct kvm_guest_debug_arch { -}; - -struct kvm_debug_exit_arch { -}; - -struct kvm_sync_regs { - /* Used with KVM_CAP_ARM_USER_IRQ */ - __u64 device_irq_level; -}; - -struct kvm_arch_memory_slot { -}; - -/* for KVM_GET/SET_VCPU_EVENTS */ -struct kvm_vcpu_events { - struct { - __u8 serror_pending; - __u8 serror_has_esr; - __u8 ext_dabt_pending; - /* Align it to 8 bytes */ - __u8 pad[5]; - __u64 serror_esr; - } exception; - __u32 reserved[12]; -}; - -/* If you need to interpret the index values, here is the key: */ -#define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 -#define KVM_REG_ARM_COPROC_SHIFT 16 -#define KVM_REG_ARM_32_OPC2_MASK 0x0000000000000007 -#define KVM_REG_ARM_32_OPC2_SHIFT 0 -#define KVM_REG_ARM_OPC1_MASK 0x0000000000000078 -#define KVM_REG_ARM_OPC1_SHIFT 3 -#define KVM_REG_ARM_CRM_MASK 0x0000000000000780 -#define KVM_REG_ARM_CRM_SHIFT 7 -#define KVM_REG_ARM_32_CRN_MASK 0x0000000000007800 -#define KVM_REG_ARM_32_CRN_SHIFT 11 -/* - * For KVM currently all guest registers are nonsecure, but we reserve a bit - * in the encoding to distinguish secure from nonsecure for AArch32 system - * registers that are banked by security. This is 1 for the secure banked - * register, and 0 for the nonsecure banked register or if the register is - * not banked by security. - */ -#define KVM_REG_ARM_SECURE_MASK 0x0000000010000000 -#define KVM_REG_ARM_SECURE_SHIFT 28 - -#define ARM_CP15_REG_SHIFT_MASK(x,n) \ - (((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK) - -#define __ARM_CP15_REG(op1,crn,crm,op2) \ - (KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT) | \ - ARM_CP15_REG_SHIFT_MASK(op1, OPC1) | \ - ARM_CP15_REG_SHIFT_MASK(crn, 32_CRN) | \ - ARM_CP15_REG_SHIFT_MASK(crm, CRM) | \ - ARM_CP15_REG_SHIFT_MASK(op2, 32_OPC2)) - -#define ARM_CP15_REG32(...) (__ARM_CP15_REG(__VA_ARGS__) | KVM_REG_SIZE_U32) - -#define __ARM_CP15_REG64(op1,crm) \ - (__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64) -#define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__) - -/* PL1 Physical Timer Registers */ -#define KVM_REG_ARM_PTIMER_CTL ARM_CP15_REG32(0, 14, 2, 1) -#define KVM_REG_ARM_PTIMER_CNT ARM_CP15_REG64(0, 14) -#define KVM_REG_ARM_PTIMER_CVAL ARM_CP15_REG64(2, 14) - -/* Virtual Timer Registers */ -#define KVM_REG_ARM_TIMER_CTL ARM_CP15_REG32(0, 14, 3, 1) -#define KVM_REG_ARM_TIMER_CNT ARM_CP15_REG64(1, 14) -#define KVM_REG_ARM_TIMER_CVAL ARM_CP15_REG64(3, 14) - -/* Normal registers are mapped as coprocessor 16. */ -#define KVM_REG_ARM_CORE (0x0010 << KVM_REG_ARM_COPROC_SHIFT) -#define KVM_REG_ARM_CORE_REG(name) (offsetof(struct kvm_regs, name) / 4) - -/* Some registers need more space to represent values. */ -#define KVM_REG_ARM_DEMUX (0x0011 << KVM_REG_ARM_COPROC_SHIFT) -#define KVM_REG_ARM_DEMUX_ID_MASK 0x000000000000FF00 -#define KVM_REG_ARM_DEMUX_ID_SHIFT 8 -#define KVM_REG_ARM_DEMUX_ID_CCSIDR (0x00 << KVM_REG_ARM_DEMUX_ID_SHIFT) -#define KVM_REG_ARM_DEMUX_VAL_MASK 0x00000000000000FF -#define KVM_REG_ARM_DEMUX_VAL_SHIFT 0 - -/* VFP registers: we could overload CP10 like ARM does, but that's ugly. */ -#define KVM_REG_ARM_VFP (0x0012 << KVM_REG_ARM_COPROC_SHIFT) -#define KVM_REG_ARM_VFP_MASK 0x000000000000FFFF -#define KVM_REG_ARM_VFP_BASE_REG 0x0 -#define KVM_REG_ARM_VFP_FPSID 0x1000 -#define KVM_REG_ARM_VFP_FPSCR 0x1001 -#define KVM_REG_ARM_VFP_MVFR1 0x1006 -#define KVM_REG_ARM_VFP_MVFR0 0x1007 -#define KVM_REG_ARM_VFP_FPEXC 0x1008 -#define KVM_REG_ARM_VFP_FPINST 0x1009 -#define KVM_REG_ARM_VFP_FPINST2 0x100A - -/* KVM-as-firmware specific pseudo-registers */ -#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT) -#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \ - KVM_REG_ARM_FW | ((r) & 0xffff)) -#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) - /* Higher values mean better protection. */ -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) - /* Higher values mean better protection. */ -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) - -/* Device Control API: ARM VGIC */ -#define KVM_DEV_ARM_VGIC_GRP_ADDR 0 -#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 -#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2 -#define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32 -#define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT) -#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32 -#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \ - (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT) -#define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 -#define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) -#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff) -#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3 -#define KVM_DEV_ARM_VGIC_GRP_CTRL 4 -#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 -#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 -#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 -#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8 -#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 -#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ - (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) -#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff -#define VGIC_LEVEL_INFO_LINE_LEVEL 0 - -/* Device Control API on vcpu fd */ -#define KVM_ARM_VCPU_PMU_V3_CTRL 0 -#define KVM_ARM_VCPU_PMU_V3_IRQ 0 -#define KVM_ARM_VCPU_PMU_V3_INIT 1 -#define KVM_ARM_VCPU_TIMER_CTRL 1 -#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 -#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 - -#define KVM_DEV_ARM_VGIC_CTRL_INIT 0 -#define KVM_DEV_ARM_ITS_SAVE_TABLES 1 -#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 -#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 -#define KVM_DEV_ARM_ITS_CTRL_RESET 4 - -/* KVM_IRQ_LINE irq field index values */ -#define KVM_ARM_IRQ_VCPU2_SHIFT 28 -#define KVM_ARM_IRQ_VCPU2_MASK 0xf -#define KVM_ARM_IRQ_TYPE_SHIFT 24 -#define KVM_ARM_IRQ_TYPE_MASK 0xf -#define KVM_ARM_IRQ_VCPU_SHIFT 16 -#define KVM_ARM_IRQ_VCPU_MASK 0xff -#define KVM_ARM_IRQ_NUM_SHIFT 0 -#define KVM_ARM_IRQ_NUM_MASK 0xffff - -/* irq_type field */ -#define KVM_ARM_IRQ_TYPE_CPU 0 -#define KVM_ARM_IRQ_TYPE_SPI 1 -#define KVM_ARM_IRQ_TYPE_PPI 2 - -/* out-of-kernel GIC cpu interrupt injection irq_number field */ -#define KVM_ARM_IRQ_CPU_IRQ 0 -#define KVM_ARM_IRQ_CPU_FIQ 1 - -/* - * This used to hold the highest supported SPI, but it is now obsolete - * and only here to provide source code level compatibility with older - * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS. - */ -#ifndef __KERNEL__ -#define KVM_ARM_IRQ_GIC_MAX 127 -#endif - -/* One single KVM irqchip, ie. the VGIC */ -#define KVM_NR_IRQCHIPS 1 - -/* PSCI interface */ -#define KVM_PSCI_FN_BASE 0x95c1ba5e -#define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n)) - -#define KVM_PSCI_FN_CPU_SUSPEND KVM_PSCI_FN(0) -#define KVM_PSCI_FN_CPU_OFF KVM_PSCI_FN(1) -#define KVM_PSCI_FN_CPU_ON KVM_PSCI_FN(2) -#define KVM_PSCI_FN_MIGRATE KVM_PSCI_FN(3) - -#define KVM_PSCI_RET_SUCCESS PSCI_RET_SUCCESS -#define KVM_PSCI_RET_NI PSCI_RET_NOT_SUPPORTED -#define KVM_PSCI_RET_INVAL PSCI_RET_INVALID_PARAMS -#define KVM_PSCI_RET_DENIED PSCI_RET_DENIED - -#endif /* __ARM_KVM_H__ */ diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index c773b829ee8e..c036a4a2f8e2 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -11,9 +11,6 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/dma-mapping.h> -#ifdef CONFIG_KVM_ARM_HOST -#include <linux/kvm_host.h> -#endif #include <asm/cacheflush.h> #include <asm/glue-df.h> #include <asm/glue-pf.h> @@ -167,14 +164,6 @@ int main(void) DEFINE(CACHE_WRITEBACK_ORDER, __CACHE_WRITEBACK_ORDER); DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE); BLANK(); -#ifdef CONFIG_KVM_ARM_HOST - DEFINE(VCPU_GUEST_CTXT, offsetof(struct kvm_vcpu, arch.ctxt)); - DEFINE(VCPU_HOST_CTXT, offsetof(struct kvm_vcpu, arch.host_cpu_context)); - DEFINE(CPU_CTXT_VFP, offsetof(struct kvm_cpu_context, vfp)); - DEFINE(CPU_CTXT_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs)); - DEFINE(GP_REGS_USR, offsetof(struct kvm_regs, usr_regs)); -#endif - BLANK(); #ifdef CONFIG_VDSO DEFINE(VDSO_DATA_SIZE, sizeof(union vdso_data_store)); #endif diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S index 6607fa817bba..26d8e03b1dd3 100644 --- a/arch/arm/kernel/hyp-stub.S +++ b/arch/arm/kernel/hyp-stub.S @@ -189,19 +189,19 @@ ARM_BE8(orr r7, r7, #(1 << 25)) @ HSCTLR.EE ENDPROC(__hyp_stub_install_secondary) __hyp_stub_do_trap: +#ifdef ZIMAGE teq r0, #HVC_SET_VECTORS bne 1f + /* Only the ZIMAGE stubs can change the HYP vectors */ mcr p15, 4, r1, c12, c0, 0 @ set HVBAR b __hyp_stub_exit +#endif 1: teq r0, #HVC_SOFT_RESTART - bne 1f + bne 2f bx r1 -1: teq r0, #HVC_RESET_VECTORS - beq __hyp_stub_exit - - ldr r0, =HVC_STUB_ERR +2: ldr r0, =HVC_STUB_ERR __ERET __hyp_stub_exit: @@ -210,26 +210,9 @@ __hyp_stub_exit: ENDPROC(__hyp_stub_do_trap) /* - * __hyp_set_vectors: Call this after boot to set the initial hypervisor - * vectors as part of hypervisor installation. On an SMP system, this should - * be called on each CPU. - * - * r0 must be the physical address of the new vector table (which must lie in - * the bottom 4GB of physical address space. - * - * r0 must be 32-byte aligned. - * - * Before calling this, you must check that the stub hypervisor is installed - * everywhere, by waiting for any secondary CPUs to be brought up and then - * checking that BOOT_CPU_MODE_HAVE_HYP(__boot_cpu_mode) is true. - * - * If not, there is a pre-existing hypervisor, some CPUs failed to boot, or - * something else went wrong... in such cases, trying to install a new - * hypervisor is unlikely to work as desired. - * - * When you call into your shiny new hypervisor, sp_hyp will contain junk, - * so you will need to set that to something sensible at the new hypervisor's - * initialisation entry point. + * __hyp_set_vectors is only used when ZIMAGE must bounce between HYP + * and SVC. For the kernel itself, the vectors are set once and for + * all by the stubs. */ ENTRY(__hyp_set_vectors) mov r1, r0 @@ -245,12 +228,6 @@ ENTRY(__hyp_soft_restart) ret lr ENDPROC(__hyp_soft_restart) -ENTRY(__hyp_reset_vectors) - mov r0, #HVC_RESET_VECTORS - __HVC(0) - ret lr -ENDPROC(__hyp_reset_vectors) - #ifndef ZIMAGE .align 2 .L__boot_cpu_mode_offset: diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S index 21b8b271c80d..6d2be994ae58 100644 --- a/arch/arm/kernel/vmlinux-xip.lds.S +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -162,14 +162,6 @@ SECTIONS ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support") ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined") -/* - * The HYP init code can't be more than a page long, - * and should not cross a page boundary. - * The above comment applies as well. - */ -ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & PAGE_MASK) <= PAGE_SIZE, - "HYP init code too big or misaligned") - #ifdef CONFIG_XIP_DEFLATED_DATA /* * The .bss is used as a stack area for __inflate_kernel_data() whose stack diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 319ccb10846a..88a720da443b 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -170,12 +170,4 @@ __start_rodata_section_aligned = ALIGN(__start_rodata, 1 << SECTION_SHIFT); ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support") ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined") -/* - * The HYP init code can't be more than a page long, - * and should not cross a page boundary. - * The above comment applies as well. - */ -ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & PAGE_MASK) <= PAGE_SIZE, - "HYP init code too big or misaligned") - #endif /* CONFIG_XIP_KERNEL */ diff --git a/arch/arm/kernel/vmlinux.lds.h b/arch/arm/kernel/vmlinux.lds.h index 8247bc15addc..381a8e105fa5 100644 --- a/arch/arm/kernel/vmlinux.lds.h +++ b/arch/arm/kernel/vmlinux.lds.h @@ -31,20 +31,11 @@ *(.proc.info.init) \ __proc_info_end = .; -#define HYPERVISOR_TEXT \ - __hyp_text_start = .; \ - *(.hyp.text) \ - __hyp_text_end = .; - #define IDMAP_TEXT \ ALIGN_FUNCTION(); \ __idmap_text_start = .; \ *(.idmap.text) \ __idmap_text_end = .; \ - . = ALIGN(PAGE_SIZE); \ - __hyp_idmap_text_start = .; \ - *(.hyp.idmap.text) \ - __hyp_idmap_text_end = .; #define ARM_DISCARD \ *(.ARM.exidx.exit.text) \ @@ -72,7 +63,6 @@ SCHED_TEXT \ CPUIDLE_TEXT \ LOCK_TEXT \ - HYPERVISOR_TEXT \ KPROBES_TEXT \ *(.gnu.warning) \ *(.glue_7) \ diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig deleted file mode 100644 index f591026347a5..000000000000 --- a/arch/arm/kvm/Kconfig +++ /dev/null @@ -1,59 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# KVM configuration -# - -source "virt/kvm/Kconfig" -source "virt/lib/Kconfig" - -menuconfig VIRTUALIZATION - bool "Virtualization" - ---help--- - Say Y here to get to see options for using your Linux host to run - other operating systems inside virtual machines (guests). - This option alone does not add any kernel code. - - If you say N, all options in this submenu will be skipped and - disabled. - -if VIRTUALIZATION - -config KVM - bool "Kernel-based Virtual Machine (KVM) support" - depends on MMU && OF - select PREEMPT_NOTIFIERS - select ARM_GIC - select ARM_GIC_V3 - select ARM_GIC_V3_ITS - select HAVE_KVM_CPU_RELAX_INTERCEPT - select HAVE_KVM_ARCH_TLB_FLUSH_ALL - select KVM_MMIO - select KVM_ARM_HOST - select KVM_GENERIC_DIRTYLOG_READ_PROTECT - select SRCU - select MMU_NOTIFIER - select KVM_VFIO - select HAVE_KVM_EVENTFD - select HAVE_KVM_IRQFD - select HAVE_KVM_IRQCHIP - select HAVE_KVM_IRQ_ROUTING - select HAVE_KVM_MSI - select IRQ_BYPASS_MANAGER - select HAVE_KVM_IRQ_BYPASS - depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER - ---help--- - Support hosting virtualized guest machines. - - This module provides access to the hardware capabilities through - a character device node named /dev/kvm. - - If unsure, say N. - -config KVM_ARM_HOST - bool - ---help--- - Provides host support for ARM processors. - -source "drivers/vhost/Kconfig" - -endif # VIRTUALIZATION diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile deleted file mode 100644 index e442d82821df..000000000000 --- a/arch/arm/kvm/Makefile +++ /dev/null @@ -1,43 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for Kernel-based Virtual Machine module -# - -plus_virt := $(call as-instr,.arch_extension virt,+virt) -ifeq ($(plus_virt),+virt) - plus_virt_def := -DREQUIRES_VIRT=1 -endif - -KVM := ../../../virt/kvm - -ccflags-y += -I $(srctree)/$(src) -I $(srctree)/virt/kvm/arm/vgic -CFLAGS_$(KVM)/arm/arm.o := $(plus_virt_def) - -AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) -AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) - -kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o - -obj-$(CONFIG_KVM_ARM_HOST) += hyp/ - -obj-y += kvm-arm.o init.o interrupts.o -obj-y += handle_exit.o guest.o emulate.o reset.o -obj-y += coproc.o coproc_a15.o coproc_a7.o vgic-v3-coproc.o -obj-y += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o -obj-y += $(KVM)/arm/psci.o $(KVM)/arm/perf.o $(KVM)/arm/hypercalls.o -obj-y += $(KVM)/arm/aarch32.o - -obj-y += $(KVM)/arm/vgic/vgic.o -obj-y += $(KVM)/arm/vgic/vgic-init.o -obj-y += $(KVM)/arm/vgic/vgic-irqfd.o -obj-y += $(KVM)/arm/vgic/vgic-v2.o -obj-y += $(KVM)/arm/vgic/vgic-v3.o -obj-y += $(KVM)/arm/vgic/vgic-v4.o -obj-y += $(KVM)/arm/vgic/vgic-mmio.o -obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o -obj-y += $(KVM)/arm/vgic/vgic-mmio-v3.o -obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o -obj-y += $(KVM)/arm/vgic/vgic-its.o -obj-y += $(KVM)/arm/vgic/vgic-debug.o -obj-y += $(KVM)/irqchip.o -obj-y += $(KVM)/arm/arch_timer.o diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c deleted file mode 100644 index 07745ee022a1..000000000000 --- a/arch/arm/kvm/coproc.c +++ /dev/null @@ -1,1455 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Authors: Rusty Russell <rusty@rustcorp.com.au> - * Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/bsearch.h> -#include <linux/mm.h> -#include <linux/kvm_host.h> -#include <linux/uaccess.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_host.h> -#include <asm/kvm_emulate.h> -#include <asm/kvm_coproc.h> -#include <asm/kvm_mmu.h> -#include <asm/cacheflush.h> -#include <asm/cputype.h> -#include <trace/events/kvm.h> -#include <asm/vfp.h> -#include "../vfp/vfpinstr.h" - -#define CREATE_TRACE_POINTS -#include "trace.h" -#include "coproc.h" - - -/****************************************************************************** - * Co-processor emulation - *****************************************************************************/ - -static bool write_to_read_only(struct kvm_vcpu *vcpu, - const struct coproc_params *params) -{ - WARN_ONCE(1, "CP15 write to read-only register\n"); - print_cp_instr(params); - kvm_inject_undefined(vcpu); - return false; -} - -static bool read_from_write_only(struct kvm_vcpu *vcpu, - const struct coproc_params *params) -{ - WARN_ONCE(1, "CP15 read to write-only register\n"); - print_cp_instr(params); - kvm_inject_undefined(vcpu); - return false; -} - -/* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */ -static u32 cache_levels; - -/* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */ -#define CSSELR_MAX 12 - -/* - * kvm_vcpu_arch.cp15 holds cp15 registers as an array of u32, but some - * of cp15 registers can be viewed either as couple of two u32 registers - * or one u64 register. Current u64 register encoding is that least - * significant u32 word is followed by most significant u32 word. - */ -static inline void vcpu_cp15_reg64_set(struct kvm_vcpu *vcpu, - const struct coproc_reg *r, - u64 val) -{ - vcpu_cp15(vcpu, r->reg) = val & 0xffffffff; - vcpu_cp15(vcpu, r->reg + 1) = val >> 32; -} - -static inline u64 vcpu_cp15_reg64_get(struct kvm_vcpu *vcpu, - const struct coproc_reg *r) -{ - u64 val; - - val = vcpu_cp15(vcpu, r->reg + 1); - val = val << 32; - val = val | vcpu_cp15(vcpu, r->reg); - return val; -} - -int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - kvm_inject_undefined(vcpu); - return 1; -} - -int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* - * We can get here, if the host has been built without VFPv3 support, - * but the guest attempted a floating point operation. - */ - kvm_inject_undefined(vcpu); - return 1; -} - -int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - kvm_inject_undefined(vcpu); - return 1; -} - -static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) -{ - /* - * Compute guest MPIDR. We build a virtual cluster out of the - * vcpu_id, but we read the 'U' bit from the underlying - * hardware directly. - */ - vcpu_cp15(vcpu, c0_MPIDR) = ((read_cpuid_mpidr() & MPIDR_SMP_BITMASK) | - ((vcpu->vcpu_id >> 2) << MPIDR_LEVEL_BITS) | - (vcpu->vcpu_id & 3)); -} - -/* TRM entries A7:4.3.31 A15:4.3.28 - RO WI */ -static bool access_actlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - *vcpu_reg(vcpu, p->Rt1) = vcpu_cp15(vcpu, c1_ACTLR); - return true; -} - -/* TRM entries A7:4.3.56, A15:4.3.60 - R/O. */ -static bool access_cbar(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return write_to_read_only(vcpu, p); - return read_zero(vcpu, p); -} - -/* TRM entries A7:4.3.49, A15:4.3.48 - R/O WI */ -static bool access_l2ctlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - *vcpu_reg(vcpu, p->Rt1) = vcpu_cp15(vcpu, c9_L2CTLR); - return true; -} - -static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) -{ - u32 l2ctlr, ncores; - - asm volatile("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr)); - l2ctlr &= ~(3 << 24); - ncores = atomic_read(&vcpu->kvm->online_vcpus) - 1; - /* How many cores in the current cluster and the next ones */ - ncores -= (vcpu->vcpu_id & ~3); - /* Cap it to the maximum number of cores in a single cluster */ - ncores = min(ncores, 3U); - l2ctlr |= (ncores & 3) << 24; - - vcpu_cp15(vcpu, c9_L2CTLR) = l2ctlr; -} - -static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) -{ - u32 actlr; - - /* ACTLR contains SMP bit: make sure you create all cpus first! */ - asm volatile("mrc p15, 0, %0, c1, c0, 1\n" : "=r" (actlr)); - /* Make the SMP bit consistent with the guest configuration */ - if (atomic_read(&vcpu->kvm->online_vcpus) > 1) - actlr |= 1U << 6; - else - actlr &= ~(1U << 6); - - vcpu_cp15(vcpu, c1_ACTLR) = actlr; -} - -/* - * TRM entries: A7:4.3.50, A15:4.3.49 - * R/O WI (even if NSACR.NS_L2ERR, a write of 1 is ignored). - */ -static bool access_l2ectlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - *vcpu_reg(vcpu, p->Rt1) = 0; - return true; -} - -/* - * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). - */ -static bool access_dcsw(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (!p->is_write) - return read_from_write_only(vcpu, p); - - kvm_set_way_flush(vcpu); - return true; -} - -/* - * Generic accessor for VM registers. Only called as long as HCR_TVM - * is set. If the guest enables the MMU, we stop trapping the VM - * sys_regs and leave it in complete control of the caches. - * - * Used by the cpu-specific code. - */ -bool access_vm_reg(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - bool was_enabled = vcpu_has_cache_enabled(vcpu); - - BUG_ON(!p->is_write); - - vcpu_cp15(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt1); - if (p->is_64bit) - vcpu_cp15(vcpu, r->reg + 1) = *vcpu_reg(vcpu, p->Rt2); - - kvm_toggle_cache(vcpu, was_enabled); - return true; -} - -static bool access_gic_sgi(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - u64 reg; - bool g1; - - if (!p->is_write) - return read_from_write_only(vcpu, p); - - reg = (u64)*vcpu_reg(vcpu, p->Rt2) << 32; - reg |= *vcpu_reg(vcpu, p->Rt1) ; - - /* - * In a system where GICD_CTLR.DS=1, a ICC_SGI0R access generates - * Group0 SGIs only, while ICC_SGI1R can generate either group, - * depending on the SGI configuration. ICC_ASGI1R is effectively - * equivalent to ICC_SGI0R, as there is no "alternative" secure - * group. - */ - switch (p->Op1) { - default: /* Keep GCC quiet */ - case 0: /* ICC_SGI1R */ - g1 = true; - break; - case 1: /* ICC_ASGI1R */ - case 2: /* ICC_SGI0R */ - g1 = false; - break; - } - - vgic_v3_dispatch_sgi(vcpu, reg, g1); - - return true; -} - -static bool access_gic_sre(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre; - - return true; -} - -static bool access_cntp_tval(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - u32 val; - - if (p->is_write) { - val = *vcpu_reg(vcpu, p->Rt1); - kvm_arm_timer_write_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_TVAL, val); - } else { - val = kvm_arm_timer_read_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_TVAL); - *vcpu_reg(vcpu, p->Rt1) = val; - } - - return true; -} - -static bool access_cntp_ctl(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - u32 val; - - if (p->is_write) { - val = *vcpu_reg(vcpu, p->Rt1); - kvm_arm_timer_write_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_CTL, val); - } else { - val = kvm_arm_timer_read_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_CTL); - *vcpu_reg(vcpu, p->Rt1) = val; - } - - return true; -} - -static bool access_cntp_cval(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - u64 val; - - if (p->is_write) { - val = (u64)*vcpu_reg(vcpu, p->Rt2) << 32; - val |= *vcpu_reg(vcpu, p->Rt1); - kvm_arm_timer_write_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_CVAL, val); - } else { - val = kvm_arm_timer_read_sysreg(vcpu, - TIMER_PTIMER, TIMER_REG_CVAL); - *vcpu_reg(vcpu, p->Rt1) = val; - *vcpu_reg(vcpu, p->Rt2) = val >> 32; - } - - return true; -} - -/* - * We could trap ID_DFR0 and tell the guest we don't support performance - * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was - * NAKed, so it will read the PMCR anyway. - * - * Therefore we tell the guest we have 0 counters. Unfortunately, we - * must always support PMCCNTR (the cycle counter): we just RAZ/WI for - * all PM registers, which doesn't crash the guest kernel at least. - */ -static bool trap_raz_wi(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - else - return read_zero(vcpu, p); -} - -#define access_pmcr trap_raz_wi -#define access_pmcntenset trap_raz_wi -#define access_pmcntenclr trap_raz_wi -#define access_pmovsr trap_raz_wi -#define access_pmselr trap_raz_wi -#define access_pmceid0 trap_raz_wi -#define access_pmceid1 trap_raz_wi -#define access_pmccntr trap_raz_wi -#define access_pmxevtyper trap_raz_wi -#define access_pmxevcntr trap_raz_wi -#define access_pmuserenr trap_raz_wi -#define access_pmintenset trap_raz_wi -#define access_pmintenclr trap_raz_wi - -/* Architected CP15 registers. - * CRn denotes the primary register number, but is copied to the CRm in the - * user space API for 64-bit register access in line with the terminology used - * in the ARM ARM. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit - * registers preceding 32-bit ones. - */ -static const struct coproc_reg cp15_regs[] = { - /* MPIDR: we use VMPIDR for guest access. */ - { CRn( 0), CRm( 0), Op1( 0), Op2( 5), is32, - NULL, reset_mpidr, c0_MPIDR }, - - /* CSSELR: swapped by interrupt.S. */ - { CRn( 0), CRm( 0), Op1( 2), Op2( 0), is32, - NULL, reset_unknown, c0_CSSELR }, - - /* ACTLR: trapped by HCR.TAC bit. */ - { CRn( 1), CRm( 0), Op1( 0), Op2( 1), is32, - access_actlr, reset_actlr, c1_ACTLR }, - - /* CPACR: swapped by interrupt.S. */ - { CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32, - NULL, reset_val, c1_CPACR, 0x00000000 }, - - /* TTBR0/TTBR1/TTBCR: swapped by interrupt.S. */ - { CRm64( 2), Op1( 0), is64, access_vm_reg, reset_unknown64, c2_TTBR0 }, - { CRn(2), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c2_TTBR0 }, - { CRn(2), CRm( 0), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_unknown, c2_TTBR1 }, - { CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32, - access_vm_reg, reset_val, c2_TTBCR, 0x00000000 }, - { CRm64( 2), Op1( 1), is64, access_vm_reg, reset_unknown64, c2_TTBR1 }, - - - /* DACR: swapped by interrupt.S. */ - { CRn( 3), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c3_DACR }, - - /* DFSR/IFSR/ADFSR/AIFSR: swapped by interrupt.S. */ - { CRn( 5), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c5_DFSR }, - { CRn( 5), CRm( 0), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_unknown, c5_IFSR }, - { CRn( 5), CRm( 1), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c5_ADFSR }, - { CRn( 5), CRm( 1), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_unknown, c5_AIFSR }, - - /* DFAR/IFAR: swapped by interrupt.S. */ - { CRn( 6), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c6_DFAR }, - { CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32, - access_vm_reg, reset_unknown, c6_IFAR }, - - /* PAR swapped by interrupt.S */ - { CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR }, - - /* - * DC{C,I,CI}SW operations: - */ - { CRn( 7), CRm( 6), Op1( 0), Op2( 2), is32, access_dcsw}, - { CRn( 7), CRm(10), Op1( 0), Op2( 2), is32, access_dcsw}, - { CRn( 7), CRm(14), Op1( 0), Op2( 2), is32, access_dcsw}, - /* - * L2CTLR access (guest wants to know #CPUs). - */ - { CRn( 9), CRm( 0), Op1( 1), Op2( 2), is32, - access_l2ctlr, reset_l2ctlr, c9_L2CTLR }, - { CRn( 9), CRm( 0), Op1( 1), Op2( 3), is32, access_l2ectlr}, - - /* - * Dummy performance monitor implementation. - */ - { CRn( 9), CRm(12), Op1( 0), Op2( 0), is32, access_pmcr}, - { CRn( 9), CRm(12), Op1( 0), Op2( 1), is32, access_pmcntenset}, - { CRn( 9), CRm(12), Op1( 0), Op2( 2), is32, access_pmcntenclr}, - { CRn( 9), CRm(12), Op1( 0), Op2( 3), is32, access_pmovsr}, - { CRn( 9), CRm(12), Op1( 0), Op2( 5), is32, access_pmselr}, - { CRn( 9), CRm(12), Op1( 0), Op2( 6), is32, access_pmceid0}, - { CRn( 9), CRm(12), Op1( 0), Op2( 7), is32, access_pmceid1}, - { CRn( 9), CRm(13), Op1( 0), Op2( 0), is32, access_pmccntr}, - { CRn( 9), CRm(13), Op1( 0), Op2( 1), is32, access_pmxevtyper}, - { CRn( 9), CRm(13), Op1( 0), Op2( 2), is32, access_pmxevcntr}, - { CRn( 9), CRm(14), Op1( 0), Op2( 0), is32, access_pmuserenr}, - { CRn( 9), CRm(14), Op1( 0), Op2( 1), is32, access_pmintenset}, - { CRn( 9), CRm(14), Op1( 0), Op2( 2), is32, access_pmintenclr}, - - /* PRRR/NMRR (aka MAIR0/MAIR1): swapped by interrupt.S. */ - { CRn(10), CRm( 2), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c10_PRRR}, - { CRn(10), CRm( 2), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_unknown, c10_NMRR}, - - /* AMAIR0/AMAIR1: swapped by interrupt.S. */ - { CRn(10), CRm( 3), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_unknown, c10_AMAIR0}, - { CRn(10), CRm( 3), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_unknown, c10_AMAIR1}, - - /* ICC_SGI1R */ - { CRm64(12), Op1( 0), is64, access_gic_sgi}, - - /* VBAR: swapped by interrupt.S. */ - { CRn(12), CRm( 0), Op1( 0), Op2( 0), is32, - NULL, reset_val, c12_VBAR, 0x00000000 }, - - /* ICC_ASGI1R */ - { CRm64(12), Op1( 1), is64, access_gic_sgi}, - /* ICC_SGI0R */ - { CRm64(12), Op1( 2), is64, access_gic_sgi}, - /* ICC_SRE */ - { CRn(12), CRm(12), Op1( 0), Op2(5), is32, access_gic_sre }, - - /* CONTEXTIDR/TPIDRURW/TPIDRURO/TPIDRPRW: swapped by interrupt.S. */ - { CRn(13), CRm( 0), Op1( 0), Op2( 1), is32, - access_vm_reg, reset_val, c13_CID, 0x00000000 }, - { CRn(13), CRm( 0), Op1( 0), Op2( 2), is32, - NULL, reset_unknown, c13_TID_URW }, - { CRn(13), CRm( 0), Op1( 0), Op2( 3), is32, - NULL, reset_unknown, c13_TID_URO }, - { CRn(13), CRm( 0), Op1( 0), Op2( 4), is32, - NULL, reset_unknown, c13_TID_PRIV }, - - /* CNTP */ - { CRm64(14), Op1( 2), is64, access_cntp_cval}, - - /* CNTKCTL: swapped by interrupt.S. */ - { CRn(14), CRm( 1), Op1( 0), Op2( 0), is32, - NULL, reset_val, c14_CNTKCTL, 0x00000000 }, - - /* CNTP */ - { CRn(14), CRm( 2), Op1( 0), Op2( 0), is32, access_cntp_tval }, - { CRn(14), CRm( 2), Op1( 0), Op2( 1), is32, access_cntp_ctl }, - - /* The Configuration Base Address Register. */ - { CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar}, -}; - -static int check_reg_table(const struct coproc_reg *table, unsigned int n) -{ - unsigned int i; - - for (i = 1; i < n; i++) { - if (cmp_reg(&table[i-1], &table[i]) >= 0) { - kvm_err("reg table %p out of order (%d)\n", table, i - 1); - return 1; - } - } - - return 0; -} - -/* Target specific emulation tables */ -static struct kvm_coproc_target_table *target_tables[KVM_ARM_NUM_TARGETS]; - -void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table) -{ - BUG_ON(check_reg_table(table->table, table->num)); - target_tables[table->target] = table; -} - -/* Get specific register table for this target. */ -static const struct coproc_reg *get_target_table(unsigned target, size_t *num) -{ - struct kvm_coproc_target_table *table; - - table = target_tables[target]; - *num = table->num; - return table->table; -} - -#define reg_to_match_value(x) \ - ({ \ - unsigned long val; \ - val = (x)->CRn << 11; \ - val |= (x)->CRm << 7; \ - val |= (x)->Op1 << 4; \ - val |= (x)->Op2 << 1; \ - val |= !(x)->is_64bit; \ - val; \ - }) - -static int match_reg(const void *key, const void *elt) -{ - const unsigned long pval = (unsigned long)key; - const struct coproc_reg *r = elt; - - return pval - reg_to_match_value(r); -} - -static const struct coproc_reg *find_reg(const struct coproc_params *params, - const struct coproc_reg table[], - unsigned int num) -{ - unsigned long pval = reg_to_match_value(params); - - return bsearch((void *)pval, table, num, sizeof(table[0]), match_reg); -} - -static int emulate_cp15(struct kvm_vcpu *vcpu, - const struct coproc_params *params) -{ - size_t num; - const struct coproc_reg *table, *r; - - trace_kvm_emulate_cp15_imp(params->Op1, params->Rt1, params->CRn, - params->CRm, params->Op2, params->is_write); - - table = get_target_table(vcpu->arch.target, &num); - - /* Search target-specific then generic table. */ - r = find_reg(params, table, num); - if (!r) - r = find_reg(params, cp15_regs, ARRAY_SIZE(cp15_regs)); - - if (likely(r)) { - /* If we don't have an accessor, we should never get here! */ - BUG_ON(!r->access); - - if (likely(r->access(vcpu, params, r))) { - /* Skip instruction, since it was emulated */ - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - } - } else { - /* If access function fails, it should complain. */ - kvm_err("Unsupported guest CP15 access at: %08lx [%08lx]\n", - *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); - print_cp_instr(params); - kvm_inject_undefined(vcpu); - } - - return 1; -} - -static struct coproc_params decode_64bit_hsr(struct kvm_vcpu *vcpu) -{ - struct coproc_params params; - - params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; - params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf; - params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0); - params.is_64bit = true; - - params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf; - params.Op2 = 0; - params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf; - params.CRm = 0; - - return params; -} - -/** - * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access - * @vcpu: The VCPU pointer - * @run: The kvm_run struct - */ -int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - struct coproc_params params = decode_64bit_hsr(vcpu); - - return emulate_cp15(vcpu, ¶ms); -} - -/** - * kvm_handle_cp14_64 -- handles a mrrc/mcrr trap on a guest CP14 access - * @vcpu: The VCPU pointer - * @run: The kvm_run struct - */ -int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - struct coproc_params params = decode_64bit_hsr(vcpu); - - /* raz_wi cp14 */ - trap_raz_wi(vcpu, ¶ms, NULL); - - /* handled */ - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - return 1; -} - -static void reset_coproc_regs(struct kvm_vcpu *vcpu, - const struct coproc_reg *table, size_t num, - unsigned long *bmap) -{ - unsigned long i; - - for (i = 0; i < num; i++) - if (table[i].reset) { - int reg = table[i].reg; - - table[i].reset(vcpu, &table[i]); - if (reg > 0 && reg < NR_CP15_REGS) { - set_bit(reg, bmap); - if (table[i].is_64bit) - set_bit(reg + 1, bmap); - } - } -} - -static struct coproc_params decode_32bit_hsr(struct kvm_vcpu *vcpu) -{ - struct coproc_params params; - - params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; - params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf; - params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0); - params.is_64bit = false; - - params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf; - params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 14) & 0x7; - params.Op2 = (kvm_vcpu_get_hsr(vcpu) >> 17) & 0x7; - params.Rt2 = 0; - - return params; -} - -/** - * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access - * @vcpu: The VCPU pointer - * @run: The kvm_run struct - */ -int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - struct coproc_params params = decode_32bit_hsr(vcpu); - return emulate_cp15(vcpu, ¶ms); -} - -/** - * kvm_handle_cp14_32 -- handles a mrc/mcr trap on a guest CP14 access - * @vcpu: The VCPU pointer - * @run: The kvm_run struct - */ -int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - struct coproc_params params = decode_32bit_hsr(vcpu); - - /* raz_wi cp14 */ - trap_raz_wi(vcpu, ¶ms, NULL); - - /* handled */ - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - return 1; -} - -/****************************************************************************** - * Userspace API - *****************************************************************************/ - -static bool index_to_params(u64 id, struct coproc_params *params) -{ - switch (id & KVM_REG_SIZE_MASK) { - case KVM_REG_SIZE_U32: - /* Any unused index bits means it's not valid. */ - if (id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK - | KVM_REG_ARM_COPROC_MASK - | KVM_REG_ARM_32_CRN_MASK - | KVM_REG_ARM_CRM_MASK - | KVM_REG_ARM_OPC1_MASK - | KVM_REG_ARM_32_OPC2_MASK)) - return false; - - params->is_64bit = false; - params->CRn = ((id & KVM_REG_ARM_32_CRN_MASK) - >> KVM_REG_ARM_32_CRN_SHIFT); - params->CRm = ((id & KVM_REG_ARM_CRM_MASK) - >> KVM_REG_ARM_CRM_SHIFT); - params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK) - >> KVM_REG_ARM_OPC1_SHIFT); - params->Op2 = ((id & KVM_REG_ARM_32_OPC2_MASK) - >> KVM_REG_ARM_32_OPC2_SHIFT); - return true; - case KVM_REG_SIZE_U64: - /* Any unused index bits means it's not valid. */ - if (id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK - | KVM_REG_ARM_COPROC_MASK - | KVM_REG_ARM_CRM_MASK - | KVM_REG_ARM_OPC1_MASK)) - return false; - params->is_64bit = true; - /* CRm to CRn: see cp15_to_index for details */ - params->CRn = ((id & KVM_REG_ARM_CRM_MASK) - >> KVM_REG_ARM_CRM_SHIFT); - params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK) - >> KVM_REG_ARM_OPC1_SHIFT); - params->Op2 = 0; - params->CRm = 0; - return true; - default: - return false; - } -} - -/* Decode an index value, and find the cp15 coproc_reg entry. */ -static const struct coproc_reg *index_to_coproc_reg(struct kvm_vcpu *vcpu, - u64 id) -{ - size_t num; - const struct coproc_reg *table, *r; - struct coproc_params params; - - /* We only do cp15 for now. */ - if ((id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT != 15) - return NULL; - - if (!index_to_params(id, ¶ms)) - return NULL; - - table = get_target_table(vcpu->arch.target, &num); - r = find_reg(¶ms, table, num); - if (!r) - r = find_reg(¶ms, cp15_regs, ARRAY_SIZE(cp15_regs)); - - /* Not saved in the cp15 array? */ - if (r && !r->reg) - r = NULL; - - return r; -} - -/* - * These are the invariant cp15 registers: we let the guest see the host - * versions of these, so they're part of the guest state. - * - * A future CPU may provide a mechanism to present different values to - * the guest, or a future kvm may trap them. - */ -/* Unfortunately, there's no register-argument for mrc, so generate. */ -#define FUNCTION_FOR32(crn, crm, op1, op2, name) \ - static void get_##name(struct kvm_vcpu *v, \ - const struct coproc_reg *r) \ - { \ - u32 val; \ - \ - asm volatile("mrc p15, " __stringify(op1) \ - ", %0, c" __stringify(crn) \ - ", c" __stringify(crm) \ - ", " __stringify(op2) "\n" : "=r" (val)); \ - ((struct coproc_reg *)r)->val = val; \ - } - -FUNCTION_FOR32(0, 0, 0, 0, MIDR) -FUNCTION_FOR32(0, 0, 0, 1, CTR) -FUNCTION_FOR32(0, 0, 0, 2, TCMTR) -FUNCTION_FOR32(0, 0, 0, 3, TLBTR) -FUNCTION_FOR32(0, 0, 0, 6, REVIDR) -FUNCTION_FOR32(0, 1, 0, 0, ID_PFR0) -FUNCTION_FOR32(0, 1, 0, 1, ID_PFR1) -FUNCTION_FOR32(0, 1, 0, 2, ID_DFR0) -FUNCTION_FOR32(0, 1, 0, 3, ID_AFR0) -FUNCTION_FOR32(0, 1, 0, 4, ID_MMFR0) -FUNCTION_FOR32(0, 1, 0, 5, ID_MMFR1) -FUNCTION_FOR32(0, 1, 0, 6, ID_MMFR2) -FUNCTION_FOR32(0, 1, 0, 7, ID_MMFR3) -FUNCTION_FOR32(0, 2, 0, 0, ID_ISAR0) -FUNCTION_FOR32(0, 2, 0, 1, ID_ISAR1) -FUNCTION_FOR32(0, 2, 0, 2, ID_ISAR2) -FUNCTION_FOR32(0, 2, 0, 3, ID_ISAR3) -FUNCTION_FOR32(0, 2, 0, 4, ID_ISAR4) -FUNCTION_FOR32(0, 2, 0, 5, ID_ISAR5) -FUNCTION_FOR32(0, 0, 1, 1, CLIDR) -FUNCTION_FOR32(0, 0, 1, 7, AIDR) - -/* ->val is filled in by kvm_invariant_coproc_table_init() */ -static struct coproc_reg invariant_cp15[] = { - { CRn( 0), CRm( 0), Op1( 0), Op2( 0), is32, NULL, get_MIDR }, - { CRn( 0), CRm( 0), Op1( 0), Op2( 1), is32, NULL, get_CTR }, - { CRn( 0), CRm( 0), Op1( 0), Op2( 2), is32, NULL, get_TCMTR }, - { CRn( 0), CRm( 0), Op1( 0), Op2( 3), is32, NULL, get_TLBTR }, - { CRn( 0), CRm( 0), Op1( 0), Op2( 6), is32, NULL, get_REVIDR }, - - { CRn( 0), CRm( 0), Op1( 1), Op2( 1), is32, NULL, get_CLIDR }, - { CRn( 0), CRm( 0), Op1( 1), Op2( 7), is32, NULL, get_AIDR }, - - { CRn( 0), CRm( 1), Op1( 0), Op2( 0), is32, NULL, get_ID_PFR0 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 1), is32, NULL, get_ID_PFR1 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 2), is32, NULL, get_ID_DFR0 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 3), is32, NULL, get_ID_AFR0 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 4), is32, NULL, get_ID_MMFR0 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 5), is32, NULL, get_ID_MMFR1 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 6), is32, NULL, get_ID_MMFR2 }, - { CRn( 0), CRm( 1), Op1( 0), Op2( 7), is32, NULL, get_ID_MMFR3 }, - - { CRn( 0), CRm( 2), Op1( 0), Op2( 0), is32, NULL, get_ID_ISAR0 }, - { CRn( 0), CRm( 2), Op1( 0), Op2( 1), is32, NULL, get_ID_ISAR1 }, - { CRn( 0), CRm( 2), Op1( 0), Op2( 2), is32, NULL, get_ID_ISAR2 }, - { CRn( 0), CRm( 2), Op1( 0), Op2( 3), is32, NULL, get_ID_ISAR3 }, - { CRn( 0), CRm( 2), Op1( 0), Op2( 4), is32, NULL, get_ID_ISAR4 }, - { CRn( 0), CRm( 2), Op1( 0), Op2( 5), is32, NULL, get_ID_ISAR5 }, -}; - -/* - * Reads a register value from a userspace address to a kernel - * variable. Make sure that register size matches sizeof(*__val). - */ -static int reg_from_user(void *val, const void __user *uaddr, u64 id) -{ - if (copy_from_user(val, uaddr, KVM_REG_SIZE(id)) != 0) - return -EFAULT; - return 0; -} - -/* - * Writes a register value to a userspace address from a kernel variable. - * Make sure that register size matches sizeof(*__val). - */ -static int reg_to_user(void __user *uaddr, const void *val, u64 id) -{ - if (copy_to_user(uaddr, val, KVM_REG_SIZE(id)) != 0) - return -EFAULT; - return 0; -} - -static int get_invariant_cp15(u64 id, void __user *uaddr) -{ - struct coproc_params params; - const struct coproc_reg *r; - int ret; - - if (!index_to_params(id, ¶ms)) - return -ENOENT; - - r = find_reg(¶ms, invariant_cp15, ARRAY_SIZE(invariant_cp15)); - if (!r) - return -ENOENT; - - ret = -ENOENT; - if (KVM_REG_SIZE(id) == 4) { - u32 val = r->val; - - ret = reg_to_user(uaddr, &val, id); - } else if (KVM_REG_SIZE(id) == 8) { - ret = reg_to_user(uaddr, &r->val, id); - } - return ret; -} - -static int set_invariant_cp15(u64 id, void __user *uaddr) -{ - struct coproc_params params; - const struct coproc_reg *r; - int err; - u64 val; - - if (!index_to_params(id, ¶ms)) - return -ENOENT; - r = find_reg(¶ms, invariant_cp15, ARRAY_SIZE(invariant_cp15)); - if (!r) - return -ENOENT; - - err = -ENOENT; - if (KVM_REG_SIZE(id) == 4) { - u32 val32; - - err = reg_from_user(&val32, uaddr, id); - if (!err) - val = val32; - } else if (KVM_REG_SIZE(id) == 8) { - err = reg_from_user(&val, uaddr, id); - } - if (err) - return err; - - /* This is what we mean by invariant: you can't change it. */ - if (r->val != val) - return -EINVAL; - - return 0; -} - -static bool is_valid_cache(u32 val) -{ - u32 level, ctype; - - if (val >= CSSELR_MAX) - return false; - - /* Bottom bit is Instruction or Data bit. Next 3 bits are level. */ - level = (val >> 1); - ctype = (cache_levels >> (level * 3)) & 7; - - switch (ctype) { - case 0: /* No cache */ - return false; - case 1: /* Instruction cache only */ - return (val & 1); - case 2: /* Data cache only */ - case 4: /* Unified cache */ - return !(val & 1); - case 3: /* Separate instruction and data caches */ - return true; - default: /* Reserved: we can't know instruction or data. */ - return false; - } -} - -/* Which cache CCSIDR represents depends on CSSELR value. */ -static u32 get_ccsidr(u32 csselr) -{ - u32 ccsidr; - - /* Make sure noone else changes CSSELR during this! */ - local_irq_disable(); - /* Put value into CSSELR */ - asm volatile("mcr p15, 2, %0, c0, c0, 0" : : "r" (csselr)); - isb(); - /* Read result out of CCSIDR */ - asm volatile("mrc p15, 1, %0, c0, c0, 0" : "=r" (ccsidr)); - local_irq_enable(); - - return ccsidr; -} - -static int demux_c15_get(u64 id, void __user *uaddr) -{ - u32 val; - u32 __user *uval = uaddr; - - /* Fail if we have unknown bits set. */ - if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK - | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) - return -ENOENT; - - switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { - case KVM_REG_ARM_DEMUX_ID_CCSIDR: - if (KVM_REG_SIZE(id) != 4) - return -ENOENT; - val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) - >> KVM_REG_ARM_DEMUX_VAL_SHIFT; - if (!is_valid_cache(val)) - return -ENOENT; - - return put_user(get_ccsidr(val), uval); - default: - return -ENOENT; - } -} - -static int demux_c15_set(u64 id, void __user *uaddr) -{ - u32 val, newval; - u32 __user *uval = uaddr; - - /* Fail if we have unknown bits set. */ - if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK - | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) - return -ENOENT; - - switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { - case KVM_REG_ARM_DEMUX_ID_CCSIDR: - if (KVM_REG_SIZE(id) != 4) - return -ENOENT; - val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) - >> KVM_REG_ARM_DEMUX_VAL_SHIFT; - if (!is_valid_cache(val)) - return -ENOENT; - - if (get_user(newval, uval)) - return -EFAULT; - - /* This is also invariant: you can't change it. */ - if (newval != get_ccsidr(val)) - return -EINVAL; - return 0; - default: - return -ENOENT; - } -} - -#ifdef CONFIG_VFPv3 -static const int vfp_sysregs[] = { KVM_REG_ARM_VFP_FPEXC, - KVM_REG_ARM_VFP_FPSCR, - KVM_REG_ARM_VFP_FPINST, - KVM_REG_ARM_VFP_FPINST2, - KVM_REG_ARM_VFP_MVFR0, - KVM_REG_ARM_VFP_MVFR1, - KVM_REG_ARM_VFP_FPSID }; - -static unsigned int num_fp_regs(void) -{ - if (((fmrx(MVFR0) & MVFR0_A_SIMD_MASK) >> MVFR0_A_SIMD_BIT) == 2) - return 32; - else - return 16; -} - -static unsigned int num_vfp_regs(void) -{ - /* Normal FP regs + control regs. */ - return num_fp_regs() + ARRAY_SIZE(vfp_sysregs); -} - -static int copy_vfp_regids(u64 __user *uindices) -{ - unsigned int i; - const u64 u32reg = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_VFP; - const u64 u64reg = KVM_REG_ARM | KVM_REG_SIZE_U64 | KVM_REG_ARM_VFP; - - for (i = 0; i < num_fp_regs(); i++) { - if (put_user((u64reg | KVM_REG_ARM_VFP_BASE_REG) + i, - uindices)) - return -EFAULT; - uindices++; - } - - for (i = 0; i < ARRAY_SIZE(vfp_sysregs); i++) { - if (put_user(u32reg | vfp_sysregs[i], uindices)) - return -EFAULT; - uindices++; - } - - return num_vfp_regs(); -} - -static int vfp_get_reg(const struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) -{ - u32 vfpid = (id & KVM_REG_ARM_VFP_MASK); - u32 val; - - /* Fail if we have unknown bits set. */ - if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK - | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) - return -ENOENT; - - if (vfpid < num_fp_regs()) { - if (KVM_REG_SIZE(id) != 8) - return -ENOENT; - return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpregs[vfpid], - id); - } - - /* FP control registers are all 32 bit. */ - if (KVM_REG_SIZE(id) != 4) - return -ENOENT; - - switch (vfpid) { - case KVM_REG_ARM_VFP_FPEXC: - return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpexc, id); - case KVM_REG_ARM_VFP_FPSCR: - return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpscr, id); - case KVM_REG_ARM_VFP_FPINST: - return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpinst, id); - case KVM_REG_ARM_VFP_FPINST2: - return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpinst2, id); - case KVM_REG_ARM_VFP_MVFR0: - val = fmrx(MVFR0); - return reg_to_user(uaddr, &val, id); - case KVM_REG_ARM_VFP_MVFR1: - val = fmrx(MVFR1); - return reg_to_user(uaddr, &val, id); - case KVM_REG_ARM_VFP_FPSID: - val = fmrx(FPSID); - return reg_to_user(uaddr, &val, id); - default: - return -ENOENT; - } -} - -static int vfp_set_reg(struct kvm_vcpu *vcpu, u64 id, const void __user *uaddr) -{ - u32 vfpid = (id & KVM_REG_ARM_VFP_MASK); - u32 val; - - /* Fail if we have unknown bits set. */ - if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK - | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) - return -ENOENT; - - if (vfpid < num_fp_regs()) { - if (KVM_REG_SIZE(id) != 8) - return -ENOENT; - return reg_from_user(&vcpu->arch.ctxt.vfp.fpregs[vfpid], - uaddr, id); - } - - /* FP control registers are all 32 bit. */ - if (KVM_REG_SIZE(id) != 4) - return -ENOENT; - - switch (vfpid) { - case KVM_REG_ARM_VFP_FPEXC: - return reg_from_user(&vcpu->arch.ctxt.vfp.fpexc, uaddr, id); - case KVM_REG_ARM_VFP_FPSCR: - return reg_from_user(&vcpu->arch.ctxt.vfp.fpscr, uaddr, id); - case KVM_REG_ARM_VFP_FPINST: - return reg_from_user(&vcpu->arch.ctxt.vfp.fpinst, uaddr, id); - case KVM_REG_ARM_VFP_FPINST2: - return reg_from_user(&vcpu->arch.ctxt.vfp.fpinst2, uaddr, id); - /* These are invariant. */ - case KVM_REG_ARM_VFP_MVFR0: - if (reg_from_user(&val, uaddr, id)) - return -EFAULT; - if (val != fmrx(MVFR0)) - return -EINVAL; - return 0; - case KVM_REG_ARM_VFP_MVFR1: - if (reg_from_user(&val, uaddr, id)) - return -EFAULT; - if (val != fmrx(MVFR1)) - return -EINVAL; - return 0; - case KVM_REG_ARM_VFP_FPSID: - if (reg_from_user(&val, uaddr, id)) - return -EFAULT; - if (val != fmrx(FPSID)) - return -EINVAL; - return 0; - default: - return -ENOENT; - } -} -#else /* !CONFIG_VFPv3 */ -static unsigned int num_vfp_regs(void) -{ - return 0; -} - -static int copy_vfp_regids(u64 __user *uindices) -{ - return 0; -} - -static int vfp_get_reg(const struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) -{ - return -ENOENT; -} - -static int vfp_set_reg(struct kvm_vcpu *vcpu, u64 id, const void __user *uaddr) -{ - return -ENOENT; -} -#endif /* !CONFIG_VFPv3 */ - -int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - const struct coproc_reg *r; - void __user *uaddr = (void __user *)(long)reg->addr; - int ret; - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) - return demux_c15_get(reg->id, uaddr); - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_VFP) - return vfp_get_reg(vcpu, reg->id, uaddr); - - r = index_to_coproc_reg(vcpu, reg->id); - if (!r) - return get_invariant_cp15(reg->id, uaddr); - - ret = -ENOENT; - if (KVM_REG_SIZE(reg->id) == 8) { - u64 val; - - val = vcpu_cp15_reg64_get(vcpu, r); - ret = reg_to_user(uaddr, &val, reg->id); - } else if (KVM_REG_SIZE(reg->id) == 4) { - ret = reg_to_user(uaddr, &vcpu_cp15(vcpu, r->reg), reg->id); - } - - return ret; -} - -int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - const struct coproc_reg *r; - void __user *uaddr = (void __user *)(long)reg->addr; - int ret; - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) - return demux_c15_set(reg->id, uaddr); - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_VFP) - return vfp_set_reg(vcpu, reg->id, uaddr); - - r = index_to_coproc_reg(vcpu, reg->id); - if (!r) - return set_invariant_cp15(reg->id, uaddr); - - ret = -ENOENT; - if (KVM_REG_SIZE(reg->id) == 8) { - u64 val; - - ret = reg_from_user(&val, uaddr, reg->id); - if (!ret) - vcpu_cp15_reg64_set(vcpu, r, val); - } else if (KVM_REG_SIZE(reg->id) == 4) { - ret = reg_from_user(&vcpu_cp15(vcpu, r->reg), uaddr, reg->id); - } - - return ret; -} - -static unsigned int num_demux_regs(void) -{ - unsigned int i, count = 0; - - for (i = 0; i < CSSELR_MAX; i++) - if (is_valid_cache(i)) - count++; - - return count; -} - -static int write_demux_regids(u64 __user *uindices) -{ - u64 val = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX; - unsigned int i; - - val |= KVM_REG_ARM_DEMUX_ID_CCSIDR; - for (i = 0; i < CSSELR_MAX; i++) { - if (!is_valid_cache(i)) - continue; - if (put_user(val | i, uindices)) - return -EFAULT; - uindices++; - } - return 0; -} - -static u64 cp15_to_index(const struct coproc_reg *reg) -{ - u64 val = KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT); - if (reg->is_64bit) { - val |= KVM_REG_SIZE_U64; - val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); - /* - * CRn always denotes the primary coproc. reg. nr. for the - * in-kernel representation, but the user space API uses the - * CRm for the encoding, because it is modelled after the - * MRRC/MCRR instructions: see the ARM ARM rev. c page - * B3-1445 - */ - val |= (reg->CRn << KVM_REG_ARM_CRM_SHIFT); - } else { - val |= KVM_REG_SIZE_U32; - val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); - val |= (reg->Op2 << KVM_REG_ARM_32_OPC2_SHIFT); - val |= (reg->CRm << KVM_REG_ARM_CRM_SHIFT); - val |= (reg->CRn << KVM_REG_ARM_32_CRN_SHIFT); - } - return val; -} - -static bool copy_reg_to_user(const struct coproc_reg *reg, u64 __user **uind) -{ - if (!*uind) - return true; - - if (put_user(cp15_to_index(reg), *uind)) - return false; - - (*uind)++; - return true; -} - -/* Assumed ordered tables, see kvm_coproc_table_init. */ -static int walk_cp15(struct kvm_vcpu *vcpu, u64 __user *uind) -{ - const struct coproc_reg *i1, *i2, *end1, *end2; - unsigned int total = 0; - size_t num; - - /* We check for duplicates here, to allow arch-specific overrides. */ - i1 = get_target_table(vcpu->arch.target, &num); - end1 = i1 + num; - i2 = cp15_regs; - end2 = cp15_regs + ARRAY_SIZE(cp15_regs); - - BUG_ON(i1 == end1 || i2 == end2); - - /* Walk carefully, as both tables may refer to the same register. */ - while (i1 || i2) { - int cmp = cmp_reg(i1, i2); - /* target-specific overrides generic entry. */ - if (cmp <= 0) { - /* Ignore registers we trap but don't save. */ - if (i1->reg) { - if (!copy_reg_to_user(i1, &uind)) - return -EFAULT; - total++; - } - } else { - /* Ignore registers we trap but don't save. */ - if (i2->reg) { - if (!copy_reg_to_user(i2, &uind)) - return -EFAULT; - total++; - } - } - - if (cmp <= 0 && ++i1 == end1) - i1 = NULL; - if (cmp >= 0 && ++i2 == end2) - i2 = NULL; - } - return total; -} - -unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu) -{ - return ARRAY_SIZE(invariant_cp15) - + num_demux_regs() - + num_vfp_regs() - + walk_cp15(vcpu, (u64 __user *)NULL); -} - -int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) -{ - unsigned int i; - int err; - - /* Then give them all the invariant registers' indices. */ - for (i = 0; i < ARRAY_SIZE(invariant_cp15); i++) { - if (put_user(cp15_to_index(&invariant_cp15[i]), uindices)) - return -EFAULT; - uindices++; - } - - err = walk_cp15(vcpu, uindices); - if (err < 0) - return err; - uindices += err; - - err = copy_vfp_regids(uindices); - if (err < 0) - return err; - uindices += err; - - return write_demux_regids(uindices); -} - -void kvm_coproc_table_init(void) -{ - unsigned int i; - - /* Make sure tables are unique and in order. */ - BUG_ON(check_reg_table(cp15_regs, ARRAY_SIZE(cp15_regs))); - BUG_ON(check_reg_table(invariant_cp15, ARRAY_SIZE(invariant_cp15))); - - /* We abuse the reset function to overwrite the table itself. */ - for (i = 0; i < ARRAY_SIZE(invariant_cp15); i++) - invariant_cp15[i].reset(NULL, &invariant_cp15[i]); - - /* - * CLIDR format is awkward, so clean it up. See ARM B4.1.20: - * - * If software reads the Cache Type fields from Ctype1 - * upwards, once it has seen a value of 0b000, no caches - * exist at further-out levels of the hierarchy. So, for - * example, if Ctype3 is the first Cache Type field with a - * value of 0b000, the values of Ctype4 to Ctype7 must be - * ignored. - */ - asm volatile("mrc p15, 1, %0, c0, c0, 1" : "=r" (cache_levels)); - for (i = 0; i < 7; i++) - if (((cache_levels >> (i*3)) & 7) == 0) - break; - /* Clear all higher bits. */ - cache_levels &= (1 << (i*3))-1; -} - -/** - * kvm_reset_coprocs - sets cp15 registers to reset value - * @vcpu: The VCPU pointer - * - * This function finds the right table above and sets the registers on the - * virtual CPU struct to their architecturally defined reset values. - */ -void kvm_reset_coprocs(struct kvm_vcpu *vcpu) -{ - size_t num; - const struct coproc_reg *table; - DECLARE_BITMAP(bmap, NR_CP15_REGS) = { 0, }; - - /* Generic chip reset first (so target could override). */ - reset_coproc_regs(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs), bmap); - - table = get_target_table(vcpu->arch.target, &num); - reset_coproc_regs(vcpu, table, num, bmap); - - for (num = 1; num < NR_CP15_REGS; num++) - WARN(!test_bit(num, bmap), - "Didn't reset vcpu_cp15(vcpu, %zi)", num); -} diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h deleted file mode 100644 index 637065b13012..000000000000 --- a/arch/arm/kvm/coproc.h +++ /dev/null @@ -1,130 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Authors: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#ifndef __ARM_KVM_COPROC_LOCAL_H__ -#define __ARM_KVM_COPROC_LOCAL_H__ - -struct coproc_params { - unsigned long CRn; - unsigned long CRm; - unsigned long Op1; - unsigned long Op2; - unsigned long Rt1; - unsigned long Rt2; - bool is_64bit; - bool is_write; -}; - -struct coproc_reg { - /* MRC/MCR/MRRC/MCRR instruction which accesses it. */ - unsigned long CRn; - unsigned long CRm; - unsigned long Op1; - unsigned long Op2; - - bool is_64bit; - - /* Trapped access from guest, if non-NULL. */ - bool (*access)(struct kvm_vcpu *, - const struct coproc_params *, - const struct coproc_reg *); - - /* Initialization for vcpu. */ - void (*reset)(struct kvm_vcpu *, const struct coproc_reg *); - - /* Index into vcpu_cp15(vcpu, ...), or 0 if we don't need to save it. */ - unsigned long reg; - - /* Value (usually reset value) */ - u64 val; -}; - -static inline void print_cp_instr(const struct coproc_params *p) -{ - /* Look, we even formatted it for you to paste into the table! */ - if (p->is_64bit) { - kvm_pr_unimpl(" { CRm64(%2lu), Op1(%2lu), is64, func_%s },\n", - p->CRn, p->Op1, p->is_write ? "write" : "read"); - } else { - kvm_pr_unimpl(" { CRn(%2lu), CRm(%2lu), Op1(%2lu), Op2(%2lu), is32," - " func_%s },\n", - p->CRn, p->CRm, p->Op1, p->Op2, - p->is_write ? "write" : "read"); - } -} - -static inline bool ignore_write(struct kvm_vcpu *vcpu, - const struct coproc_params *p) -{ - return true; -} - -static inline bool read_zero(struct kvm_vcpu *vcpu, - const struct coproc_params *p) -{ - *vcpu_reg(vcpu, p->Rt1) = 0; - return true; -} - -/* Reset functions */ -static inline void reset_unknown(struct kvm_vcpu *vcpu, - const struct coproc_reg *r) -{ - BUG_ON(!r->reg); - BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.ctxt.cp15)); - vcpu_cp15(vcpu, r->reg) = 0xdecafbad; -} - -static inline void reset_val(struct kvm_vcpu *vcpu, const struct coproc_reg *r) -{ - BUG_ON(!r->reg); - BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.ctxt.cp15)); - vcpu_cp15(vcpu, r->reg) = r->val; -} - -static inline void reset_unknown64(struct kvm_vcpu *vcpu, - const struct coproc_reg *r) -{ - BUG_ON(!r->reg); - BUG_ON(r->reg + 1 >= ARRAY_SIZE(vcpu->arch.ctxt.cp15)); - - vcpu_cp15(vcpu, r->reg) = 0xdecafbad; - vcpu_cp15(vcpu, r->reg+1) = 0xd0c0ffee; -} - -static inline int cmp_reg(const struct coproc_reg *i1, - const struct coproc_reg *i2) -{ - BUG_ON(i1 == i2); - if (!i1) - return 1; - else if (!i2) - return -1; - if (i1->CRn != i2->CRn) - return i1->CRn - i2->CRn; - if (i1->CRm != i2->CRm) - return i1->CRm - i2->CRm; - if (i1->Op1 != i2->Op1) - return i1->Op1 - i2->Op1; - if (i1->Op2 != i2->Op2) - return i1->Op2 - i2->Op2; - return i2->is_64bit - i1->is_64bit; -} - - -#define CRn(_x) .CRn = _x -#define CRm(_x) .CRm = _x -#define CRm64(_x) .CRn = _x, .CRm = 0 -#define Op1(_x) .Op1 = _x -#define Op2(_x) .Op2 = _x -#define is64 .is_64bit = true -#define is32 .is_64bit = false - -bool access_vm_reg(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r); - -#endif /* __ARM_KVM_COPROC_LOCAL_H__ */ diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c deleted file mode 100644 index 36bf15421ae8..000000000000 --- a/arch/arm/kvm/coproc_a15.c +++ /dev/null @@ -1,39 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Authors: Rusty Russell <rusty@rustcorp.au> - * Christoffer Dall <c.dall@virtualopensystems.com> - */ -#include <linux/kvm_host.h> -#include <asm/kvm_coproc.h> -#include <asm/kvm_emulate.h> -#include <linux/init.h> - -#include "coproc.h" - -/* - * A15-specific CP15 registers. - * CRn denotes the primary register number, but is copied to the CRm in the - * user space API for 64-bit register access in line with the terminology used - * in the ARM ARM. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit - * registers preceding 32-bit ones. - */ -static const struct coproc_reg a15_regs[] = { - /* SCTLR: swapped by interrupt.S. */ - { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_val, c1_SCTLR, 0x00C50078 }, -}; - -static struct kvm_coproc_target_table a15_target_table = { - .target = KVM_ARM_TARGET_CORTEX_A15, - .table = a15_regs, - .num = ARRAY_SIZE(a15_regs), -}; - -static int __init coproc_a15_init(void) -{ - kvm_register_target_coproc_table(&a15_target_table); - return 0; -} -late_initcall(coproc_a15_init); diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c deleted file mode 100644 index 40f643e1e05c..000000000000 --- a/arch/arm/kvm/coproc_a7.c +++ /dev/null @@ -1,42 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Copyright (C) 2013 - ARM Ltd - * - * Authors: Rusty Russell <rusty@rustcorp.au> - * Christoffer Dall <c.dall@virtualopensystems.com> - * Jonathan Austin <jonathan.austin@arm.com> - */ -#include <linux/kvm_host.h> -#include <asm/kvm_coproc.h> -#include <asm/kvm_emulate.h> -#include <linux/init.h> - -#include "coproc.h" - -/* - * Cortex-A7 specific CP15 registers. - * CRn denotes the primary register number, but is copied to the CRm in the - * user space API for 64-bit register access in line with the terminology used - * in the ARM ARM. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit - * registers preceding 32-bit ones. - */ -static const struct coproc_reg a7_regs[] = { - /* SCTLR: swapped by interrupt.S. */ - { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, - access_vm_reg, reset_val, c1_SCTLR, 0x00C50878 }, -}; - -static struct kvm_coproc_target_table a7_target_table = { - .target = KVM_ARM_TARGET_CORTEX_A7, - .table = a7_regs, - .num = ARRAY_SIZE(a7_regs), -}; - -static int __init coproc_a7_init(void) -{ - kvm_register_target_coproc_table(&a7_target_table); - return 0; -} -late_initcall(coproc_a7_init); diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c deleted file mode 100644 index 29bb852140c5..000000000000 --- a/arch/arm/kvm/emulate.c +++ /dev/null @@ -1,166 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/mm.h> -#include <linux/kvm_host.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_emulate.h> -#include <asm/opcodes.h> -#include <trace/events/kvm.h> - -#include "trace.h" - -#define VCPU_NR_MODES 6 -#define VCPU_REG_OFFSET_USR 0 -#define VCPU_REG_OFFSET_FIQ 1 -#define VCPU_REG_OFFSET_IRQ 2 -#define VCPU_REG_OFFSET_SVC 3 -#define VCPU_REG_OFFSET_ABT 4 -#define VCPU_REG_OFFSET_UND 5 -#define REG_OFFSET(_reg) \ - (offsetof(struct kvm_regs, _reg) / sizeof(u32)) - -#define USR_REG_OFFSET(_num) REG_OFFSET(usr_regs.uregs[_num]) - -static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][15] = { - /* USR/SYS Registers */ - [VCPU_REG_OFFSET_USR] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), USR_REG_OFFSET(13), USR_REG_OFFSET(14), - }, - - /* FIQ Registers */ - [VCPU_REG_OFFSET_FIQ] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), - REG_OFFSET(fiq_regs[0]), /* r8 */ - REG_OFFSET(fiq_regs[1]), /* r9 */ - REG_OFFSET(fiq_regs[2]), /* r10 */ - REG_OFFSET(fiq_regs[3]), /* r11 */ - REG_OFFSET(fiq_regs[4]), /* r12 */ - REG_OFFSET(fiq_regs[5]), /* r13 */ - REG_OFFSET(fiq_regs[6]), /* r14 */ - }, - - /* IRQ Registers */ - [VCPU_REG_OFFSET_IRQ] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(irq_regs[0]), /* r13 */ - REG_OFFSET(irq_regs[1]), /* r14 */ - }, - - /* SVC Registers */ - [VCPU_REG_OFFSET_SVC] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(svc_regs[0]), /* r13 */ - REG_OFFSET(svc_regs[1]), /* r14 */ - }, - - /* ABT Registers */ - [VCPU_REG_OFFSET_ABT] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(abt_regs[0]), /* r13 */ - REG_OFFSET(abt_regs[1]), /* r14 */ - }, - - /* UND Registers */ - [VCPU_REG_OFFSET_UND] = { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(und_regs[0]), /* r13 */ - REG_OFFSET(und_regs[1]), /* r14 */ - }, -}; - -/* - * Return a pointer to the register number valid in the current mode of - * the virtual CPU. - */ -unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num) -{ - unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs; - unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK; - - switch (mode) { - case USR_MODE...SVC_MODE: - mode &= ~MODE32_BIT; /* 0 ... 3 */ - break; - - case ABT_MODE: - mode = VCPU_REG_OFFSET_ABT; - break; - - case UND_MODE: - mode = VCPU_REG_OFFSET_UND; - break; - - case SYSTEM_MODE: - mode = VCPU_REG_OFFSET_USR; - break; - - default: - BUG(); - } - - return reg_array + vcpu_reg_offsets[mode][reg_num]; -} - -/* - * Return the SPSR for the current mode of the virtual CPU. - */ -unsigned long *__vcpu_spsr(struct kvm_vcpu *vcpu) -{ - unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK; - switch (mode) { - case SVC_MODE: - return &vcpu->arch.ctxt.gp_regs.KVM_ARM_SVC_spsr; - case ABT_MODE: - return &vcpu->arch.ctxt.gp_regs.KVM_ARM_ABT_spsr; - case UND_MODE: - return &vcpu->arch.ctxt.gp_regs.KVM_ARM_UND_spsr; - case IRQ_MODE: - return &vcpu->arch.ctxt.gp_regs.KVM_ARM_IRQ_spsr; - case FIQ_MODE: - return &vcpu->arch.ctxt.gp_regs.KVM_ARM_FIQ_spsr; - default: - BUG(); - } -} - -/****************************************************************************** - * Inject exceptions into the guest - */ - -/** - * kvm_inject_vabt - inject an async abort / SError into the guest - * @vcpu: The VCPU to receive the exception - * - * It is assumed that this code is called from the VCPU thread and that the - * VCPU therefore is not currently executing guest code. - */ -void kvm_inject_vabt(struct kvm_vcpu *vcpu) -{ - *vcpu_hcr(vcpu) |= HCR_VA; -} diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c deleted file mode 100644 index 9f7ae0d8690f..000000000000 --- a/arch/arm/kvm/guest.c +++ /dev/null @@ -1,387 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/errno.h> -#include <linux/err.h> -#include <linux/kvm_host.h> -#include <linux/module.h> -#include <linux/vmalloc.h> -#include <linux/fs.h> -#include <kvm/arm_psci.h> -#include <asm/cputype.h> -#include <linux/uaccess.h> -#include <asm/kvm.h> -#include <asm/kvm_emulate.h> -#include <asm/kvm_coproc.h> - -#define VM_STAT(x) { #x, offsetof(struct kvm, stat.x), KVM_STAT_VM } -#define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU } - -struct kvm_stats_debugfs_item debugfs_entries[] = { - VCPU_STAT(halt_successful_poll), - VCPU_STAT(halt_attempted_poll), - VCPU_STAT(halt_poll_invalid), - VCPU_STAT(halt_wakeup), - VCPU_STAT(hvc_exit_stat), - VCPU_STAT(wfe_exit_stat), - VCPU_STAT(wfi_exit_stat), - VCPU_STAT(mmio_exit_user), - VCPU_STAT(mmio_exit_kernel), - VCPU_STAT(exits), - { NULL } -}; - -static u64 core_reg_offset_from_id(u64 id) -{ - return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); -} - -static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - u32 __user *uaddr = (u32 __user *)(long)reg->addr; - struct kvm_regs *regs = &vcpu->arch.ctxt.gp_regs; - u64 off; - - if (KVM_REG_SIZE(reg->id) != 4) - return -ENOENT; - - /* Our ID is an index into the kvm_regs struct. */ - off = core_reg_offset_from_id(reg->id); - if (off >= sizeof(*regs) / KVM_REG_SIZE(reg->id)) - return -ENOENT; - - return put_user(((u32 *)regs)[off], uaddr); -} - -static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - u32 __user *uaddr = (u32 __user *)(long)reg->addr; - struct kvm_regs *regs = &vcpu->arch.ctxt.gp_regs; - u64 off, val; - - if (KVM_REG_SIZE(reg->id) != 4) - return -ENOENT; - - /* Our ID is an index into the kvm_regs struct. */ - off = core_reg_offset_from_id(reg->id); - if (off >= sizeof(*regs) / KVM_REG_SIZE(reg->id)) - return -ENOENT; - - if (get_user(val, uaddr) != 0) - return -EFAULT; - - if (off == KVM_REG_ARM_CORE_REG(usr_regs.ARM_cpsr)) { - unsigned long mode = val & MODE_MASK; - switch (mode) { - case USR_MODE: - case FIQ_MODE: - case IRQ_MODE: - case SVC_MODE: - case ABT_MODE: - case UND_MODE: - break; - default: - return -EINVAL; - } - } - - ((u32 *)regs)[off] = val; - return 0; -} - -int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) -{ - return -EINVAL; -} - -int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) -{ - return -EINVAL; -} - -#define NUM_TIMER_REGS 3 - -static bool is_timer_reg(u64 index) -{ - switch (index) { - case KVM_REG_ARM_TIMER_CTL: - case KVM_REG_ARM_TIMER_CNT: - case KVM_REG_ARM_TIMER_CVAL: - return true; - } - return false; -} - -static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) -{ - if (put_user(KVM_REG_ARM_TIMER_CTL, uindices)) - return -EFAULT; - uindices++; - if (put_user(KVM_REG_ARM_TIMER_CNT, uindices)) - return -EFAULT; - uindices++; - if (put_user(KVM_REG_ARM_TIMER_CVAL, uindices)) - return -EFAULT; - - return 0; -} - -static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - void __user *uaddr = (void __user *)(long)reg->addr; - u64 val; - int ret; - - ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)); - if (ret != 0) - return -EFAULT; - - return kvm_arm_timer_set_reg(vcpu, reg->id, val); -} - -static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - void __user *uaddr = (void __user *)(long)reg->addr; - u64 val; - - val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; -} - -static unsigned long num_core_regs(void) -{ - return sizeof(struct kvm_regs) / sizeof(u32); -} - -/** - * kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG - * - * This is for all registers. - */ -unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu) -{ - return num_core_regs() + kvm_arm_num_coproc_regs(vcpu) - + kvm_arm_get_fw_num_regs(vcpu) - + NUM_TIMER_REGS; -} - -/** - * kvm_arm_copy_reg_indices - get indices of all registers. - * - * We do core registers right here, then we append coproc regs. - */ -int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) -{ - unsigned int i; - const u64 core_reg = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE; - int ret; - - for (i = 0; i < sizeof(struct kvm_regs)/sizeof(u32); i++) { - if (put_user(core_reg | i, uindices)) - return -EFAULT; - uindices++; - } - - ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices); - if (ret) - return ret; - uindices += kvm_arm_get_fw_num_regs(vcpu); - - ret = copy_timer_indices(vcpu, uindices); - if (ret) - return ret; - uindices += NUM_TIMER_REGS; - - return kvm_arm_copy_coproc_indices(vcpu, uindices); -} - -int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - /* We currently use nothing arch-specific in upper 32 bits */ - if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM >> 32) - return -EINVAL; - - /* Register group 16 means we want a core register. */ - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) - return get_core_reg(vcpu, reg); - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) - return kvm_arm_get_fw_reg(vcpu, reg); - - if (is_timer_reg(reg->id)) - return get_timer_reg(vcpu, reg); - - return kvm_arm_coproc_get_reg(vcpu, reg); -} - -int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - /* We currently use nothing arch-specific in upper 32 bits */ - if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM >> 32) - return -EINVAL; - - /* Register group 16 means we set a core register. */ - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) - return set_core_reg(vcpu, reg); - - if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) - return kvm_arm_set_fw_reg(vcpu, reg); - - if (is_timer_reg(reg->id)) - return set_timer_reg(vcpu, reg); - - return kvm_arm_coproc_set_reg(vcpu, reg); -} - -int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) -{ - return -EINVAL; -} - -int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) -{ - return -EINVAL; -} - - -int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, - struct kvm_vcpu_events *events) -{ - events->exception.serror_pending = !!(*vcpu_hcr(vcpu) & HCR_VA); - - /* - * We never return a pending ext_dabt here because we deliver it to - * the virtual CPU directly when setting the event and it's no longer - * 'pending' at this point. - */ - - return 0; -} - -int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, - struct kvm_vcpu_events *events) -{ - bool serror_pending = events->exception.serror_pending; - bool has_esr = events->exception.serror_has_esr; - bool ext_dabt_pending = events->exception.ext_dabt_pending; - - if (serror_pending && has_esr) - return -EINVAL; - else if (serror_pending) - kvm_inject_vabt(vcpu); - - if (ext_dabt_pending) - kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); - - return 0; -} - -int __attribute_const__ kvm_target_cpu(void) -{ - switch (read_cpuid_part()) { - case ARM_CPU_PART_CORTEX_A7: - return KVM_ARM_TARGET_CORTEX_A7; - case ARM_CPU_PART_CORTEX_A15: - return KVM_ARM_TARGET_CORTEX_A15; - default: - return -EINVAL; - } -} - -int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) -{ - int target = kvm_target_cpu(); - - if (target < 0) - return -ENODEV; - - memset(init, 0, sizeof(*init)); - - /* - * For now, we don't return any features. - * In future, we might use features to return target - * specific features available for the preferred - * target type. - */ - init->target = (__u32)target; - - return 0; -} - -int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) -{ - return -EINVAL; -} - -int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) -{ - return -EINVAL; -} - -int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, - struct kvm_translation *tr) -{ - return -EINVAL; -} - -int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, - struct kvm_guest_debug *dbg) -{ - return -EINVAL; -} - -int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr) -{ - int ret; - - switch (attr->group) { - case KVM_ARM_VCPU_TIMER_CTRL: - ret = kvm_arm_timer_set_attr(vcpu, attr); - break; - default: - ret = -ENXIO; - break; - } - - return ret; -} - -int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr) -{ - int ret; - - switch (attr->group) { - case KVM_ARM_VCPU_TIMER_CTRL: - ret = kvm_arm_timer_get_attr(vcpu, attr); - break; - default: - ret = -ENXIO; - break; - } - - return ret; -} - -int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, - struct kvm_device_attr *attr) -{ - int ret; - - switch (attr->group) { - case KVM_ARM_VCPU_TIMER_CTRL: - ret = kvm_arm_timer_has_attr(vcpu, attr); - break; - default: - ret = -ENXIO; - break; - } - - return ret; -} diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c deleted file mode 100644 index e58a89d2f13f..000000000000 --- a/arch/arm/kvm/handle_exit.c +++ /dev/null @@ -1,175 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <asm/kvm_emulate.h> -#include <asm/kvm_coproc.h> -#include <asm/kvm_mmu.h> -#include <kvm/arm_hypercalls.h> -#include <trace/events/kvm.h> - -#include "trace.h" - -typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *); - -static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - int ret; - - trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0), - kvm_vcpu_hvc_get_imm(vcpu)); - vcpu->stat.hvc_exit_stat++; - - ret = kvm_hvc_call_handler(vcpu); - if (ret < 0) { - vcpu_set_reg(vcpu, 0, ~0UL); - return 1; - } - - return ret; -} - -static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* - * "If an SMC instruction executed at Non-secure EL1 is - * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a - * Trap exception, not a Secure Monitor Call exception [...]" - * - * We need to advance the PC after the trap, as it would - * otherwise return to the same address... - */ - vcpu_set_reg(vcpu, 0, ~0UL); - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - return 1; -} - -/** - * kvm_handle_wfx - handle a WFI or WFE instructions trapped in guests - * @vcpu: the vcpu pointer - * @run: the kvm_run structure pointer - * - * WFE: Yield the CPU and come back to this vcpu when the scheduler - * decides to. - * WFI: Simply call kvm_vcpu_block(), which will halt execution of - * world-switches and schedule other host processes until there is an - * incoming IRQ or FIQ to the VM. - */ -static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) { - trace_kvm_wfx(*vcpu_pc(vcpu), true); - vcpu->stat.wfe_exit_stat++; - kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu)); - } else { - trace_kvm_wfx(*vcpu_pc(vcpu), false); - vcpu->stat.wfi_exit_stat++; - kvm_vcpu_block(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); - } - - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - - return 1; -} - -static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - u32 hsr = kvm_vcpu_get_hsr(vcpu); - - kvm_pr_unimpl("Unknown exception class: hsr: %#08x\n", - hsr); - - kvm_inject_undefined(vcpu); - return 1; -} - -static exit_handle_fn arm_exit_handlers[] = { - [0 ... HSR_EC_MAX] = kvm_handle_unknown_ec, - [HSR_EC_WFI] = kvm_handle_wfx, - [HSR_EC_CP15_32] = kvm_handle_cp15_32, - [HSR_EC_CP15_64] = kvm_handle_cp15_64, - [HSR_EC_CP14_MR] = kvm_handle_cp14_32, - [HSR_EC_CP14_LS] = kvm_handle_cp14_load_store, - [HSR_EC_CP14_64] = kvm_handle_cp14_64, - [HSR_EC_CP_0_13] = kvm_handle_cp_0_13_access, - [HSR_EC_CP10_ID] = kvm_handle_cp10_id, - [HSR_EC_HVC] = handle_hvc, - [HSR_EC_SMC] = handle_smc, - [HSR_EC_IABT] = kvm_handle_guest_abort, - [HSR_EC_DABT] = kvm_handle_guest_abort, -}; - -static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) -{ - u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu); - - return arm_exit_handlers[hsr_ec]; -} - -/* - * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on - * proper exit to userspace. - */ -int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, - int exception_index) -{ - exit_handle_fn exit_handler; - - if (ARM_ABORT_PENDING(exception_index)) { - u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu); - - /* - * HVC/SMC already have an adjusted PC, which we need - * to correct in order to return to after having - * injected the abort. - */ - if (hsr_ec == HSR_EC_HVC || hsr_ec == HSR_EC_SMC) { - u32 adj = kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2; - *vcpu_pc(vcpu) -= adj; - } - - kvm_inject_vabt(vcpu); - return 1; - } - - exception_index = ARM_EXCEPTION_CODE(exception_index); - - switch (exception_index) { - case ARM_EXCEPTION_IRQ: - return 1; - case ARM_EXCEPTION_HVC: - /* - * See ARM ARM B1.14.1: "Hyp traps on instructions - * that fail their condition code check" - */ - if (!kvm_condition_valid(vcpu)) { - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - return 1; - } - - exit_handler = kvm_get_exit_handler(vcpu); - - return exit_handler(vcpu, run); - case ARM_EXCEPTION_DATA_ABORT: - kvm_inject_vabt(vcpu); - return 1; - case ARM_EXCEPTION_HYP_GONE: - /* - * HYP has been reset to the hyp-stub. This happens - * when a guest is pre-empted by kvm_reboot()'s - * shutdown call. - */ - run->exit_reason = KVM_EXIT_FAIL_ENTRY; - return 0; - default: - kvm_pr_unimpl("Unsupported exception type: %d", - exception_index); - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - return 0; - } -} diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile deleted file mode 100644 index ba88b1eca93c..000000000000 --- a/arch/arm/kvm/hyp/Makefile +++ /dev/null @@ -1,34 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for Kernel-based Virtual Machine module, HYP part -# - -ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING - -KVM=../../../../virt/kvm - -CFLAGS_ARMV7VE :=$(call cc-option, -march=armv7ve) - -obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o -obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o -obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/aarch32.o - -obj-$(CONFIG_KVM_ARM_HOST) += tlb.o -obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o -obj-$(CONFIG_KVM_ARM_HOST) += vfp.o -obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o -CFLAGS_banked-sr.o += $(CFLAGS_ARMV7VE) - -obj-$(CONFIG_KVM_ARM_HOST) += entry.o -obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o -obj-$(CONFIG_KVM_ARM_HOST) += switch.o -CFLAGS_switch.o += $(CFLAGS_ARMV7VE) -obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o - -# KVM code is run at a different exception code with a different map, so -# compiler instrumentation that inserts callbacks or checks into the code may -# cause crashes. Just disable it. -GCOV_PROFILE := n -KASAN_SANITIZE := n -UBSAN_SANITIZE := n -KCOV_INSTRUMENT := n diff --git a/arch/arm/kvm/hyp/banked-sr.c b/arch/arm/kvm/hyp/banked-sr.c deleted file mode 100644 index c4632ed9e819..000000000000 --- a/arch/arm/kvm/hyp/banked-sr.c +++ /dev/null @@ -1,70 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Original code: - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - * - * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <asm/kvm_hyp.h> - -/* - * gcc before 4.9 doesn't understand -march=armv7ve, so we have to - * trick the assembler. - */ -__asm__(".arch_extension virt"); - -void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt) -{ - ctxt->gp_regs.usr_regs.ARM_sp = read_special(SP_usr); - ctxt->gp_regs.usr_regs.ARM_pc = read_special(ELR_hyp); - ctxt->gp_regs.usr_regs.ARM_cpsr = read_special(SPSR); - ctxt->gp_regs.KVM_ARM_SVC_sp = read_special(SP_svc); - ctxt->gp_regs.KVM_ARM_SVC_lr = read_special(LR_svc); - ctxt->gp_regs.KVM_ARM_SVC_spsr = read_special(SPSR_svc); - ctxt->gp_regs.KVM_ARM_ABT_sp = read_special(SP_abt); - ctxt->gp_regs.KVM_ARM_ABT_lr = read_special(LR_abt); - ctxt->gp_regs.KVM_ARM_ABT_spsr = read_special(SPSR_abt); - ctxt->gp_regs.KVM_ARM_UND_sp = read_special(SP_und); - ctxt->gp_regs.KVM_ARM_UND_lr = read_special(LR_und); - ctxt->gp_regs.KVM_ARM_UND_spsr = read_special(SPSR_und); - ctxt->gp_regs.KVM_ARM_IRQ_sp = read_special(SP_irq); - ctxt->gp_regs.KVM_ARM_IRQ_lr = read_special(LR_irq); - ctxt->gp_regs.KVM_ARM_IRQ_spsr = read_special(SPSR_irq); - ctxt->gp_regs.KVM_ARM_FIQ_r8 = read_special(R8_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_r9 = read_special(R9_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_r10 = read_special(R10_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_fp = read_special(R11_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_ip = read_special(R12_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_sp = read_special(SP_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_lr = read_special(LR_fiq); - ctxt->gp_regs.KVM_ARM_FIQ_spsr = read_special(SPSR_fiq); -} - -void __hyp_text __banked_restore_state(struct kvm_cpu_context *ctxt) -{ - write_special(ctxt->gp_regs.usr_regs.ARM_sp, SP_usr); - write_special(ctxt->gp_regs.usr_regs.ARM_pc, ELR_hyp); - write_special(ctxt->gp_regs.usr_regs.ARM_cpsr, SPSR_cxsf); - write_special(ctxt->gp_regs.KVM_ARM_SVC_sp, SP_svc); - write_special(ctxt->gp_regs.KVM_ARM_SVC_lr, LR_svc); - write_special(ctxt->gp_regs.KVM_ARM_SVC_spsr, SPSR_svc); - write_special(ctxt->gp_regs.KVM_ARM_ABT_sp, SP_abt); - write_special(ctxt->gp_regs.KVM_ARM_ABT_lr, LR_abt); - write_special(ctxt->gp_regs.KVM_ARM_ABT_spsr, SPSR_abt); - write_special(ctxt->gp_regs.KVM_ARM_UND_sp, SP_und); - write_special(ctxt->gp_regs.KVM_ARM_UND_lr, LR_und); - write_special(ctxt->gp_regs.KVM_ARM_UND_spsr, SPSR_und); - write_special(ctxt->gp_regs.KVM_ARM_IRQ_sp, SP_irq); - write_special(ctxt->gp_regs.KVM_ARM_IRQ_lr, LR_irq); - write_special(ctxt->gp_regs.KVM_ARM_IRQ_spsr, SPSR_irq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_r8, R8_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_r9, R9_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_r10, R10_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_fp, R11_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_ip, R12_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_sp, SP_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_lr, LR_fiq); - write_special(ctxt->gp_regs.KVM_ARM_FIQ_spsr, SPSR_fiq); -} diff --git a/arch/arm/kvm/hyp/cp15-sr.c b/arch/arm/kvm/hyp/cp15-sr.c deleted file mode 100644 index e6923306f698..000000000000 --- a/arch/arm/kvm/hyp/cp15-sr.c +++ /dev/null @@ -1,72 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Original code: - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - * - * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <asm/kvm_hyp.h> - -static u64 *cp15_64(struct kvm_cpu_context *ctxt, int idx) -{ - return (u64 *)(ctxt->cp15 + idx); -} - -void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt) -{ - ctxt->cp15[c0_CSSELR] = read_sysreg(CSSELR); - ctxt->cp15[c1_SCTLR] = read_sysreg(SCTLR); - ctxt->cp15[c1_CPACR] = read_sysreg(CPACR); - *cp15_64(ctxt, c2_TTBR0) = read_sysreg(TTBR0); - *cp15_64(ctxt, c2_TTBR1) = read_sysreg(TTBR1); - ctxt->cp15[c2_TTBCR] = read_sysreg(TTBCR); - ctxt->cp15[c3_DACR] = read_sysreg(DACR); - ctxt->cp15[c5_DFSR] = read_sysreg(DFSR); - ctxt->cp15[c5_IFSR] = read_sysreg(IFSR); - ctxt->cp15[c5_ADFSR] = read_sysreg(ADFSR); - ctxt->cp15[c5_AIFSR] = read_sysreg(AIFSR); - ctxt->cp15[c6_DFAR] = read_sysreg(DFAR); - ctxt->cp15[c6_IFAR] = read_sysreg(IFAR); - *cp15_64(ctxt, c7_PAR) = read_sysreg(PAR); - ctxt->cp15[c10_PRRR] = read_sysreg(PRRR); - ctxt->cp15[c10_NMRR] = read_sysreg(NMRR); - ctxt->cp15[c10_AMAIR0] = read_sysreg(AMAIR0); - ctxt->cp15[c10_AMAIR1] = read_sysreg(AMAIR1); - ctxt->cp15[c12_VBAR] = read_sysreg(VBAR); - ctxt->cp15[c13_CID] = read_sysreg(CID); - ctxt->cp15[c13_TID_URW] = read_sysreg(TID_URW); - ctxt->cp15[c13_TID_URO] = read_sysreg(TID_URO); - ctxt->cp15[c13_TID_PRIV] = read_sysreg(TID_PRIV); - ctxt->cp15[c14_CNTKCTL] = read_sysreg(CNTKCTL); -} - -void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt) -{ - write_sysreg(ctxt->cp15[c0_MPIDR], VMPIDR); - write_sysreg(ctxt->cp15[c0_CSSELR], CSSELR); - write_sysreg(ctxt->cp15[c1_SCTLR], SCTLR); - write_sysreg(ctxt->cp15[c1_CPACR], CPACR); - write_sysreg(*cp15_64(ctxt, c2_TTBR0), TTBR0); - write_sysreg(*cp15_64(ctxt, c2_TTBR1), TTBR1); - write_sysreg(ctxt->cp15[c2_TTBCR], TTBCR); - write_sysreg(ctxt->cp15[c3_DACR], DACR); - write_sysreg(ctxt->cp15[c5_DFSR], DFSR); - write_sysreg(ctxt->cp15[c5_IFSR], IFSR); - write_sysreg(ctxt->cp15[c5_ADFSR], ADFSR); - write_sysreg(ctxt->cp15[c5_AIFSR], AIFSR); - write_sysreg(ctxt->cp15[c6_DFAR], DFAR); - write_sysreg(ctxt->cp15[c6_IFAR], IFAR); - write_sysreg(*cp15_64(ctxt, c7_PAR), PAR); - write_sysreg(ctxt->cp15[c10_PRRR], PRRR); - write_sysreg(ctxt->cp15[c10_NMRR], NMRR); - write_sysreg(ctxt->cp15[c10_AMAIR0], AMAIR0); - write_sysreg(ctxt->cp15[c10_AMAIR1], AMAIR1); - write_sysreg(ctxt->cp15[c12_VBAR], VBAR); - write_sysreg(ctxt->cp15[c13_CID], CID); - write_sysreg(ctxt->cp15[c13_TID_URW], TID_URW); - write_sysreg(ctxt->cp15[c13_TID_URO], TID_URO); - write_sysreg(ctxt->cp15[c13_TID_PRIV], TID_PRIV); - write_sysreg(ctxt->cp15[c14_CNTKCTL], CNTKCTL); -} diff --git a/arch/arm/kvm/hyp/entry.S b/arch/arm/kvm/hyp/entry.S deleted file mode 100644 index 4bd1f6a74180..000000000000 --- a/arch/arm/kvm/hyp/entry.S +++ /dev/null @@ -1,121 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2016 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> -*/ - -#include <linux/linkage.h> -#include <asm/asm-offsets.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_asm.h> - - .arch_extension virt - - .text - .pushsection .hyp.text, "ax" - -#define USR_REGS_OFFSET (CPU_CTXT_GP_REGS + GP_REGS_USR) - -/* int __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host) */ -ENTRY(__guest_enter) - @ Save host registers - add r1, r1, #(USR_REGS_OFFSET + S_R4) - stm r1!, {r4-r12} - str lr, [r1, #4] @ Skip SP_usr (already saved) - - @ Restore guest registers - add r0, r0, #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R0) - ldr lr, [r0, #S_LR] - ldm r0, {r0-r12} - - clrex - eret -ENDPROC(__guest_enter) - -ENTRY(__guest_exit) - /* - * return convention: - * guest r0, r1, r2 saved on the stack - * r0: vcpu pointer - * r1: exception code - */ - - add r2, r0, #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R3) - stm r2!, {r3-r12} - str lr, [r2, #4] - add r2, r0, #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R0) - pop {r3, r4, r5} @ r0, r1, r2 - stm r2, {r3-r5} - - ldr r0, [r0, #VCPU_HOST_CTXT] - add r0, r0, #(USR_REGS_OFFSET + S_R4) - ldm r0!, {r4-r12} - ldr lr, [r0, #4] - - mov r0, r1 - mrs r1, SPSR - mrs r2, ELR_hyp - mrc p15, 4, r3, c5, c2, 0 @ HSR - - /* - * Force loads and stores to complete before unmasking aborts - * and forcing the delivery of the exception. This gives us a - * single instruction window, which the handler will try to - * match. - */ - dsb sy - cpsie a - - .global abort_guest_exit_start -abort_guest_exit_start: - - isb - - .global abort_guest_exit_end -abort_guest_exit_end: - - /* - * If we took an abort, r0[31] will be set, and cmp will set - * the N bit in PSTATE. - */ - cmp r0, #0 - msrmi SPSR_cxsf, r1 - msrmi ELR_hyp, r2 - mcrmi p15, 4, r3, c5, c2, 0 @ HSR - - bx lr -ENDPROC(__guest_exit) - -/* - * If VFPv3 support is not available, then we will not switch the VFP - * registers; however cp10 and cp11 accesses will still trap and fallback - * to the regular coprocessor emulation code, which currently will - * inject an undefined exception to the guest. - */ -#ifdef CONFIG_VFPv3 -ENTRY(__vfp_guest_restore) - push {r3, r4, lr} - - @ NEON/VFP used. Turn on VFP access. - mrc p15, 4, r1, c1, c1, 2 @ HCPTR - bic r1, r1, #(HCPTR_TCP(10) | HCPTR_TCP(11)) - mcr p15, 4, r1, c1, c1, 2 @ HCPTR - isb - - @ Switch VFP/NEON hardware state to the guest's - mov r4, r0 - ldr r0, [r0, #VCPU_HOST_CTXT] - add r0, r0, #CPU_CTXT_VFP - bl __vfp_save_state - add r0, r4, #(VCPU_GUEST_CTXT + CPU_CTXT_VFP) - bl __vfp_restore_state - - pop {r3, r4, lr} - pop {r0, r1, r2} - clrex - eret -ENDPROC(__vfp_guest_restore) -#endif - - .popsection - diff --git a/arch/arm/kvm/hyp/hyp-entry.S b/arch/arm/kvm/hyp/hyp-entry.S deleted file mode 100644 index fe3d7811a908..000000000000 --- a/arch/arm/kvm/hyp/hyp-entry.S +++ /dev/null @@ -1,295 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/arm-smccc.h> -#include <linux/linkage.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_asm.h> - - .arch_extension virt - - .text - .pushsection .hyp.text, "ax" - -.macro load_vcpu reg - mrc p15, 4, \reg, c13, c0, 2 @ HTPIDR -.endm - -/******************************************************************** - * Hypervisor exception vector and handlers - * - * - * The KVM/ARM Hypervisor ABI is defined as follows: - * - * Entry to Hyp mode from the host kernel will happen _only_ when an HVC - * instruction is issued since all traps are disabled when running the host - * kernel as per the Hyp-mode initialization at boot time. - * - * HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc - * below) when the HVC instruction is called from SVC mode (i.e. a guest or the - * host kernel) and they cause a trap to the vector page + offset 0x8 when HVC - * instructions are called from within Hyp-mode. - * - * Hyp-ABI: Calling HYP-mode functions from host (in SVC mode): - * Switching to Hyp mode is done through a simple HVC #0 instruction. The - * exception vector code will check that the HVC comes from VMID==0. - * - r0 contains a pointer to a HYP function - * - r1, r2, and r3 contain arguments to the above function. - * - The HYP function will be called with its arguments in r0, r1 and r2. - * On HYP function return, we return directly to SVC. - * - * Note that the above is used to execute code in Hyp-mode from a host-kernel - * point of view, and is a different concept from performing a world-switch and - * executing guest code SVC mode (with a VMID != 0). - */ - - .align 5 -__kvm_hyp_vector: - .global __kvm_hyp_vector - - @ Hyp-mode exception vector - W(b) hyp_reset - W(b) hyp_undef - W(b) hyp_svc - W(b) hyp_pabt - W(b) hyp_dabt - W(b) hyp_hvc - W(b) hyp_irq - W(b) hyp_fiq - -#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR - .align 5 -__kvm_hyp_vector_ic_inv: - .global __kvm_hyp_vector_ic_inv - - /* - * We encode the exception entry in the bottom 3 bits of - * SP, and we have to guarantee to be 8 bytes aligned. - */ - W(add) sp, sp, #1 /* Reset 7 */ - W(add) sp, sp, #1 /* Undef 6 */ - W(add) sp, sp, #1 /* Syscall 5 */ - W(add) sp, sp, #1 /* Prefetch abort 4 */ - W(add) sp, sp, #1 /* Data abort 3 */ - W(add) sp, sp, #1 /* HVC 2 */ - W(add) sp, sp, #1 /* IRQ 1 */ - W(nop) /* FIQ 0 */ - - mcr p15, 0, r0, c7, c5, 0 /* ICIALLU */ - isb - - b decode_vectors - - .align 5 -__kvm_hyp_vector_bp_inv: - .global __kvm_hyp_vector_bp_inv - - /* - * We encode the exception entry in the bottom 3 bits of - * SP, and we have to guarantee to be 8 bytes aligned. - */ - W(add) sp, sp, #1 /* Reset 7 */ - W(add) sp, sp, #1 /* Undef 6 */ - W(add) sp, sp, #1 /* Syscall 5 */ - W(add) sp, sp, #1 /* Prefetch abort 4 */ - W(add) sp, sp, #1 /* Data abort 3 */ - W(add) sp, sp, #1 /* HVC 2 */ - W(add) sp, sp, #1 /* IRQ 1 */ - W(nop) /* FIQ 0 */ - - mcr p15, 0, r0, c7, c5, 6 /* BPIALL */ - isb - -decode_vectors: - -#ifdef CONFIG_THUMB2_KERNEL - /* - * Yet another silly hack: Use VPIDR as a temp register. - * Thumb2 is really a pain, as SP cannot be used with most - * of the bitwise instructions. The vect_br macro ensures - * things gets cleaned-up. - */ - mcr p15, 4, r0, c0, c0, 0 /* VPIDR */ - mov r0, sp - and r0, r0, #7 - sub sp, sp, r0 - push {r1, r2} - mov r1, r0 - mrc p15, 4, r0, c0, c0, 0 /* VPIDR */ - mrc p15, 0, r2, c0, c0, 0 /* MIDR */ - mcr p15, 4, r2, c0, c0, 0 /* VPIDR */ -#endif - -.macro vect_br val, targ -ARM( eor sp, sp, #\val ) -ARM( tst sp, #7 ) -ARM( eorne sp, sp, #\val ) - -THUMB( cmp r1, #\val ) -THUMB( popeq {r1, r2} ) - - beq \targ -.endm - - vect_br 0, hyp_fiq - vect_br 1, hyp_irq - vect_br 2, hyp_hvc - vect_br 3, hyp_dabt - vect_br 4, hyp_pabt - vect_br 5, hyp_svc - vect_br 6, hyp_undef - vect_br 7, hyp_reset -#endif - -.macro invalid_vector label, cause - .align -\label: mov r0, #\cause - b __hyp_panic -.endm - - invalid_vector hyp_reset ARM_EXCEPTION_RESET - invalid_vector hyp_undef ARM_EXCEPTION_UNDEFINED - invalid_vector hyp_svc ARM_EXCEPTION_SOFTWARE - invalid_vector hyp_pabt ARM_EXCEPTION_PREF_ABORT - invalid_vector hyp_fiq ARM_EXCEPTION_FIQ - -ENTRY(__hyp_do_panic) - mrs lr, cpsr - bic lr, lr, #MODE_MASK - orr lr, lr, #SVC_MODE -THUMB( orr lr, lr, #PSR_T_BIT ) - msr spsr_cxsf, lr - ldr lr, =panic - msr ELR_hyp, lr - ldr lr, =__kvm_call_hyp - clrex - eret -ENDPROC(__hyp_do_panic) - -hyp_hvc: - /* - * Getting here is either because of a trap from a guest, - * or from executing HVC from the host kernel, which means - * "do something in Hyp mode". - */ - push {r0, r1, r2} - - @ Check syndrome register - mrc p15, 4, r1, c5, c2, 0 @ HSR - lsr r0, r1, #HSR_EC_SHIFT - cmp r0, #HSR_EC_HVC - bne guest_trap @ Not HVC instr. - - /* - * Let's check if the HVC came from VMID 0 and allow simple - * switch to Hyp mode - */ - mrrc p15, 6, r0, r2, c2 - lsr r2, r2, #16 - and r2, r2, #0xff - cmp r2, #0 - bne guest_hvc_trap @ Guest called HVC - - /* - * Getting here means host called HVC, we shift parameters and branch - * to Hyp function. - */ - pop {r0, r1, r2} - - /* - * Check if we have a kernel function, which is guaranteed to be - * bigger than the maximum hyp stub hypercall - */ - cmp r0, #HVC_STUB_HCALL_NR - bhs 1f - - /* - * Not a kernel function, treat it as a stub hypercall. - * Compute the physical address for __kvm_handle_stub_hvc - * (as the code lives in the idmaped page) and branch there. - * We hijack ip (r12) as a tmp register. - */ - push {r1} - ldr r1, =kimage_voffset - ldr r1, [r1] - ldr ip, =__kvm_handle_stub_hvc - sub ip, ip, r1 - pop {r1} - - bx ip - -1: - /* - * Pushing r2 here is just a way of keeping the stack aligned to - * 8 bytes on any path that can trigger a HYP exception. Here, - * we may well be about to jump into the guest, and the guest - * exit would otherwise be badly decoded by our fancy - * "decode-exception-without-a-branch" code... - */ - push {r2, lr} - - mov lr, r0 - mov r0, r1 - mov r1, r2 - mov r2, r3 - -THUMB( orr lr, #1) - blx lr @ Call the HYP function - - pop {r2, lr} - eret - -guest_hvc_trap: - movw r2, #:lower16:ARM_SMCCC_ARCH_WORKAROUND_1 - movt r2, #:upper16:ARM_SMCCC_ARCH_WORKAROUND_1 - ldr r0, [sp] @ Guest's r0 - teq r0, r2 - bne guest_trap - add sp, sp, #12 - @ Returns: - @ r0 = 0 - @ r1 = HSR value (perfectly predictable) - @ r2 = ARM_SMCCC_ARCH_WORKAROUND_1 - mov r0, #0 - eret - -guest_trap: - load_vcpu r0 @ Load VCPU pointer to r0 - -#ifdef CONFIG_VFPv3 - @ Check for a VFP access - lsr r1, r1, #HSR_EC_SHIFT - cmp r1, #HSR_EC_CP_0_13 - beq __vfp_guest_restore -#endif - - mov r1, #ARM_EXCEPTION_HVC - b __guest_exit - -hyp_irq: - push {r0, r1, r2} - mov r1, #ARM_EXCEPTION_IRQ - load_vcpu r0 @ Load VCPU pointer to r0 - b __guest_exit - -hyp_dabt: - push {r0, r1} - mrs r0, ELR_hyp - ldr r1, =abort_guest_exit_start -THUMB( add r1, r1, #1) - cmp r0, r1 - ldrne r1, =abort_guest_exit_end -THUMB( addne r1, r1, #1) - cmpne r0, r1 - pop {r0, r1} - bne __hyp_panic - - orr r0, r0, #(1 << ARM_EXIT_WITH_ABORT_BIT) - eret - - .ltorg - - .popsection diff --git a/arch/arm/kvm/hyp/s2-setup.c b/arch/arm/kvm/hyp/s2-setup.c deleted file mode 100644 index 5dfbea5adf65..000000000000 --- a/arch/arm/kvm/hyp/s2-setup.c +++ /dev/null @@ -1,22 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2016 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <linux/types.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_hyp.h> - -void __hyp_text __init_stage2_translation(void) -{ - u64 val; - - val = read_sysreg(VTCR) & ~VTCR_MASK; - - val |= read_sysreg(HTCR) & VTCR_HTCR_SH; - val |= KVM_VTCR_SL0 | KVM_VTCR_T0SZ | KVM_VTCR_S; - - write_sysreg(val, VTCR); -} diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c deleted file mode 100644 index 1efeef3fd0ee..000000000000 --- a/arch/arm/kvm/hyp/switch.c +++ /dev/null @@ -1,242 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2015 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ -#include <linux/jump_label.h> - -#include <asm/kvm_asm.h> -#include <asm/kvm_hyp.h> -#include <asm/kvm_mmu.h> - -__asm__(".arch_extension virt"); - -/* - * Activate the traps, saving the host's fpexc register before - * overwriting it. We'll restore it on VM exit. - */ -static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu, u32 *fpexc_host) -{ - u32 val; - - /* - * We are about to set HCPTR.TCP10/11 to trap all floating point - * register accesses to HYP, however, the ARM ARM clearly states that - * traps are only taken to HYP if the operation would not otherwise - * trap to SVC. Therefore, always make sure that for 32-bit guests, - * we set FPEXC.EN to prevent traps to SVC, when setting the TCP bits. - */ - val = read_sysreg(VFP_FPEXC); - *fpexc_host = val; - if (!(val & FPEXC_EN)) { - write_sysreg(val | FPEXC_EN, VFP_FPEXC); - isb(); - } - - write_sysreg(vcpu->arch.hcr, HCR); - /* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */ - write_sysreg(HSTR_T(15), HSTR); - write_sysreg(HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11), HCPTR); - val = read_sysreg(HDCR); - val |= HDCR_TPM | HDCR_TPMCR; /* trap performance monitors */ - val |= HDCR_TDRA | HDCR_TDOSA | HDCR_TDA; /* trap debug regs */ - write_sysreg(val, HDCR); -} - -static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu) -{ - u32 val; - - /* - * If we pended a virtual abort, preserve it until it gets - * cleared. See B1.9.9 (Virtual Abort exception) for details, - * but the crucial bit is the zeroing of HCR.VA in the - * pseudocode. - */ - if (vcpu->arch.hcr & HCR_VA) - vcpu->arch.hcr = read_sysreg(HCR); - - write_sysreg(0, HCR); - write_sysreg(0, HSTR); - val = read_sysreg(HDCR); - write_sysreg(val & ~(HDCR_TPM | HDCR_TPMCR), HDCR); - write_sysreg(0, HCPTR); -} - -static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu) -{ - struct kvm *kvm = kern_hyp_va(vcpu->kvm); - write_sysreg(kvm_get_vttbr(kvm), VTTBR); - write_sysreg(vcpu->arch.midr, VPIDR); -} - -static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu) -{ - write_sysreg(0, VTTBR); - write_sysreg(read_sysreg(MIDR), VPIDR); -} - - -static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu) -{ - if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { - __vgic_v3_save_state(vcpu); - __vgic_v3_deactivate_traps(vcpu); - } -} - -static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu) -{ - if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { - __vgic_v3_activate_traps(vcpu); - __vgic_v3_restore_state(vcpu); - } -} - -static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) -{ - u32 hsr = read_sysreg(HSR); - u8 ec = hsr >> HSR_EC_SHIFT; - u32 hpfar, far; - - vcpu->arch.fault.hsr = hsr; - - if (ec == HSR_EC_IABT) - far = read_sysreg(HIFAR); - else if (ec == HSR_EC_DABT) - far = read_sysreg(HDFAR); - else - return true; - - /* - * B3.13.5 Reporting exceptions taken to the Non-secure PL2 mode: - * - * Abort on the stage 2 translation for a memory access from a - * Non-secure PL1 or PL0 mode: - * - * For any Access flag fault or Translation fault, and also for any - * Permission fault on the stage 2 translation of a memory access - * made as part of a translation table walk for a stage 1 translation, - * the HPFAR holds the IPA that caused the fault. Otherwise, the HPFAR - * is UNKNOWN. - */ - if (!(hsr & HSR_DABT_S1PTW) && (hsr & HSR_FSC_TYPE) == FSC_PERM) { - u64 par, tmp; - - par = read_sysreg(PAR); - write_sysreg(far, ATS1CPR); - isb(); - - tmp = read_sysreg(PAR); - write_sysreg(par, PAR); - - if (unlikely(tmp & 1)) - return false; /* Translation failed, back to guest */ - - hpfar = ((tmp >> 12) & ((1UL << 28) - 1)) << 4; - } else { - hpfar = read_sysreg(HPFAR); - } - - vcpu->arch.fault.hxfar = far; - vcpu->arch.fault.hpfar = hpfar; - return true; -} - -int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) -{ - struct kvm_cpu_context *host_ctxt; - struct kvm_cpu_context *guest_ctxt; - bool fp_enabled; - u64 exit_code; - u32 fpexc; - - vcpu = kern_hyp_va(vcpu); - write_sysreg(vcpu, HTPIDR); - - host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context); - guest_ctxt = &vcpu->arch.ctxt; - - __sysreg_save_state(host_ctxt); - __banked_save_state(host_ctxt); - - __activate_traps(vcpu, &fpexc); - __activate_vm(vcpu); - - __vgic_restore_state(vcpu); - __timer_enable_traps(vcpu); - - __sysreg_restore_state(guest_ctxt); - __banked_restore_state(guest_ctxt); - - /* Jump in the fire! */ -again: - exit_code = __guest_enter(vcpu, host_ctxt); - /* And we're baaack! */ - - if (exit_code == ARM_EXCEPTION_HVC && !__populate_fault_info(vcpu)) - goto again; - - fp_enabled = __vfp_enabled(); - - __banked_save_state(guest_ctxt); - __sysreg_save_state(guest_ctxt); - __timer_disable_traps(vcpu); - - __vgic_save_state(vcpu); - - __deactivate_traps(vcpu); - __deactivate_vm(vcpu); - - __banked_restore_state(host_ctxt); - __sysreg_restore_state(host_ctxt); - - if (fp_enabled) { - __vfp_save_state(&guest_ctxt->vfp); - __vfp_restore_state(&host_ctxt->vfp); - } - - write_sysreg(fpexc, VFP_FPEXC); - - return exit_code; -} - -static const char * const __hyp_panic_string[] = { - [ARM_EXCEPTION_RESET] = "\nHYP panic: RST PC:%08x CPSR:%08x", - [ARM_EXCEPTION_UNDEFINED] = "\nHYP panic: UNDEF PC:%08x CPSR:%08x", - [ARM_EXCEPTION_SOFTWARE] = "\nHYP panic: SVC PC:%08x CPSR:%08x", - [ARM_EXCEPTION_PREF_ABORT] = "\nHYP panic: PABRT PC:%08x CPSR:%08x", - [ARM_EXCEPTION_DATA_ABORT] = "\nHYP panic: DABRT PC:%08x ADDR:%08x", - [ARM_EXCEPTION_IRQ] = "\nHYP panic: IRQ PC:%08x CPSR:%08x", - [ARM_EXCEPTION_FIQ] = "\nHYP panic: FIQ PC:%08x CPSR:%08x", - [ARM_EXCEPTION_HVC] = "\nHYP panic: HVC PC:%08x CPSR:%08x", -}; - -void __hyp_text __noreturn __hyp_panic(int cause) -{ - u32 elr = read_special(ELR_hyp); - u32 val; - - if (cause == ARM_EXCEPTION_DATA_ABORT) - val = read_sysreg(HDFAR); - else - val = read_special(SPSR); - - if (read_sysreg(VTTBR)) { - struct kvm_vcpu *vcpu; - struct kvm_cpu_context *host_ctxt; - - vcpu = (struct kvm_vcpu *)read_sysreg(HTPIDR); - host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context); - __timer_disable_traps(vcpu); - __deactivate_traps(vcpu); - __deactivate_vm(vcpu); - __banked_restore_state(host_ctxt); - __sysreg_restore_state(host_ctxt); - } - - /* Call panic for real */ - __hyp_do_panic(__hyp_panic_string[cause], elr, val); - - unreachable(); -} diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c deleted file mode 100644 index 848f27bbad9d..000000000000 --- a/arch/arm/kvm/hyp/tlb.c +++ /dev/null @@ -1,68 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Original code: - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - * - * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <asm/kvm_hyp.h> -#include <asm/kvm_mmu.h> - -/** - * Flush per-VMID TLBs - * - * __kvm_tlb_flush_vmid(struct kvm *kvm); - * - * We rely on the hardware to broadcast the TLB invalidation to all CPUs - * inside the inner-shareable domain (which is the case for all v7 - * implementations). If we come across a non-IS SMP implementation, we'll - * have to use an IPI based mechanism. Until then, we stick to the simple - * hardware assisted version. - * - * As v7 does not support flushing per IPA, just nuke the whole TLB - * instead, ignoring the ipa value. - */ -void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) -{ - dsb(ishst); - - /* Switch to requested VMID */ - kvm = kern_hyp_va(kvm); - write_sysreg(kvm_get_vttbr(kvm), VTTBR); - isb(); - - write_sysreg(0, TLBIALLIS); - dsb(ish); - isb(); - - write_sysreg(0, VTTBR); -} - -void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) -{ - __kvm_tlb_flush_vmid(kvm); -} - -void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) -{ - struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm); - - /* Switch to requested VMID */ - write_sysreg(kvm_get_vttbr(kvm), VTTBR); - isb(); - - write_sysreg(0, TLBIALL); - dsb(nsh); - isb(); - - write_sysreg(0, VTTBR); -} - -void __hyp_text __kvm_flush_vm_context(void) -{ - write_sysreg(0, TLBIALLNSNHIS); - write_sysreg(0, ICIALLUIS); - dsb(ish); -} diff --git a/arch/arm/kvm/hyp/vfp.S b/arch/arm/kvm/hyp/vfp.S deleted file mode 100644 index 675a52348d8d..000000000000 --- a/arch/arm/kvm/hyp/vfp.S +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/linkage.h> -#include <asm/vfpmacros.h> - - .text - .pushsection .hyp.text, "ax" - -/* void __vfp_save_state(struct vfp_hard_struct *vfp); */ -ENTRY(__vfp_save_state) - push {r4, r5} - VFPFMRX r1, FPEXC - - @ Make sure *really* VFP is enabled so we can touch the registers. - orr r5, r1, #FPEXC_EN - tst r5, #FPEXC_EX @ Check for VFP Subarchitecture - bic r5, r5, #FPEXC_EX @ FPEXC_EX disable - VFPFMXR FPEXC, r5 - isb - - VFPFMRX r2, FPSCR - beq 1f - - @ If FPEXC_EX is 0, then FPINST/FPINST2 reads are upredictable, so - @ we only need to save them if FPEXC_EX is set. - VFPFMRX r3, FPINST - tst r5, #FPEXC_FP2V - VFPFMRX r4, FPINST2, ne @ vmrsne -1: - VFPFSTMIA r0, r5 @ Save VFP registers - stm r0, {r1-r4} @ Save FPEXC, FPSCR, FPINST, FPINST2 - pop {r4, r5} - bx lr -ENDPROC(__vfp_save_state) - -/* void __vfp_restore_state(struct vfp_hard_struct *vfp); - * Assume FPEXC_EN is on and FPEXC_EX is off */ -ENTRY(__vfp_restore_state) - VFPFLDMIA r0, r1 @ Load VFP registers - ldm r0, {r0-r3} @ Load FPEXC, FPSCR, FPINST, FPINST2 - - VFPFMXR FPSCR, r1 - tst r0, #FPEXC_EX @ Check for VFP Subarchitecture - beq 1f - VFPFMXR FPINST, r2 - tst r0, #FPEXC_FP2V - VFPFMXR FPINST2, r3, ne -1: - VFPFMXR FPEXC, r0 @ FPEXC (last, in case !EN) - bx lr -ENDPROC(__vfp_restore_state) - - .popsection diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S deleted file mode 100644 index 33e34b6d24b2..000000000000 --- a/arch/arm/kvm/init.S +++ /dev/null @@ -1,157 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/linkage.h> -#include <asm/assembler.h> -#include <asm/unified.h> -#include <asm/asm-offsets.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_mmu.h> -#include <asm/virt.h> - -/******************************************************************** - * Hypervisor initialization - * - should be called with: - * r0 = top of Hyp stack (kernel VA) - * r1 = pointer to hyp vectors - * r2,r3 = Hypervisor pgd pointer - * - * The init scenario is: - * - We jump in HYP with 3 parameters: runtime HYP pgd, runtime stack, - * runtime vectors - * - Invalidate TLBs - * - Set stack and vectors - * - Setup the page tables - * - Enable the MMU - * - Profit! (or eret, if you only care about the code). - * - * Another possibility is to get a HYP stub hypercall. - * We discriminate between the two by checking if r0 contains a value - * that is less than HVC_STUB_HCALL_NR. - */ - - .text - .pushsection .hyp.idmap.text,"ax" - .align 5 -__kvm_hyp_init: - .globl __kvm_hyp_init - - @ Hyp-mode exception vector - W(b) . - W(b) . - W(b) . - W(b) . - W(b) . - W(b) __do_hyp_init - W(b) . - W(b) . - -__do_hyp_init: - @ Check for a stub hypercall - cmp r0, #HVC_STUB_HCALL_NR - blo __kvm_handle_stub_hvc - - @ Set stack pointer - mov sp, r0 - - @ Set HVBAR to point to the HYP vectors - mcr p15, 4, r1, c12, c0, 0 @ HVBAR - - @ Set the HTTBR to point to the hypervisor PGD pointer passed - mcrr p15, 4, rr_lo_hi(r2, r3), c2 - - @ Set the HTCR and VTCR to the same shareability and cacheability - @ settings as the non-secure TTBCR and with T0SZ == 0. - mrc p15, 4, r0, c2, c0, 2 @ HTCR - ldr r2, =HTCR_MASK - bic r0, r0, r2 - mrc p15, 0, r1, c2, c0, 2 @ TTBCR - and r1, r1, #(HTCR_MASK & ~TTBCR_T0SZ) - orr r0, r0, r1 - mcr p15, 4, r0, c2, c0, 2 @ HTCR - - @ Use the same memory attributes for hyp. accesses as the kernel - @ (copy MAIRx ro HMAIRx). - mrc p15, 0, r0, c10, c2, 0 - mcr p15, 4, r0, c10, c2, 0 - mrc p15, 0, r0, c10, c2, 1 - mcr p15, 4, r0, c10, c2, 1 - - @ Invalidate the stale TLBs from Bootloader - mcr p15, 4, r0, c8, c7, 0 @ TLBIALLH - dsb ish - - @ Set the HSCTLR to: - @ - ARM/THUMB exceptions: Kernel config (Thumb-2 kernel) - @ - Endianness: Kernel config - @ - Fast Interrupt Features: Kernel config - @ - Write permission implies XN: disabled - @ - Instruction cache: enabled - @ - Data/Unified cache: enabled - @ - MMU: enabled (this code must be run from an identity mapping) - mrc p15, 4, r0, c1, c0, 0 @ HSCR - ldr r2, =HSCTLR_MASK - bic r0, r0, r2 - mrc p15, 0, r1, c1, c0, 0 @ SCTLR - ldr r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C) - and r1, r1, r2 - ARM( ldr r2, =(HSCTLR_M) ) - THUMB( ldr r2, =(HSCTLR_M | HSCTLR_TE) ) - orr r1, r1, r2 - orr r0, r0, r1 - mcr p15, 4, r0, c1, c0, 0 @ HSCR - isb - - eret - -ENTRY(__kvm_handle_stub_hvc) - cmp r0, #HVC_SOFT_RESTART - bne 1f - - /* The target is expected in r1 */ - msr ELR_hyp, r1 - mrs r0, cpsr - bic r0, r0, #MODE_MASK - orr r0, r0, #HYP_MODE -THUMB( orr r0, r0, #PSR_T_BIT ) - msr spsr_cxsf, r0 - b reset - -1: cmp r0, #HVC_RESET_VECTORS - bne 1f - -reset: - /* We're now in idmap, disable MMU */ - mrc p15, 4, r1, c1, c0, 0 @ HSCTLR - ldr r0, =(HSCTLR_M | HSCTLR_A | HSCTLR_C | HSCTLR_I) - bic r1, r1, r0 - mcr p15, 4, r1, c1, c0, 0 @ HSCTLR - - /* - * Install stub vectors, using ardb's VA->PA trick. - */ -0: adr r0, 0b @ PA(0) - movw r1, #:lower16:__hyp_stub_vectors - 0b @ VA(stub) - VA(0) - movt r1, #:upper16:__hyp_stub_vectors - 0b - add r1, r1, r0 @ PA(stub) - mcr p15, 4, r1, c12, c0, 0 @ HVBAR - b exit - -1: ldr r0, =HVC_STUB_ERR - eret - -exit: - mov r0, #0 - eret -ENDPROC(__kvm_handle_stub_hvc) - - .ltorg - - .globl __kvm_hyp_init_end -__kvm_hyp_init_end: - - .popsection diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S deleted file mode 100644 index 064f4f118ca7..000000000000 --- a/arch/arm/kvm/interrupts.S +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/linkage.h> - - .text - -/******************************************************************** - * Call function in Hyp mode - * - * - * unsigned long kvm_call_hyp(void *hypfn, ...); - * - * This is not really a variadic function in the classic C-way and care must - * be taken when calling this to ensure parameters are passed in registers - * only, since the stack will change between the caller and the callee. - * - * Call the function with the first argument containing a pointer to the - * function you wish to call in Hyp mode, and subsequent arguments will be - * passed as r0, r1, and r2 (a maximum of 3 arguments in addition to the - * function pointer can be passed). The function being called must be mapped - * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are - * passed in r0 (strictly 32bit). - * - * The calling convention follows the standard AAPCS: - * r0 - r3: caller save - * r12: caller save - * rest: callee save - */ -ENTRY(__kvm_call_hyp) - hvc #0 - bx lr -ENDPROC(__kvm_call_hyp) diff --git a/arch/arm/kvm/irq.h b/arch/arm/kvm/irq.h deleted file mode 100644 index 0d257de42c10..000000000000 --- a/arch/arm/kvm/irq.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * irq.h: in kernel interrupt controller related definitions - * Copyright (c) 2016 Red Hat, Inc. - * - * This header is included by irqchip.c. However, on ARM, interrupt - * controller declarations are located in include/kvm/arm_vgic.h since - * they are mostly shared between arm and arm64. - */ - -#ifndef __IRQ_H -#define __IRQ_H - -#include <kvm/arm_vgic.h> - -#endif diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c deleted file mode 100644 index eb4174f6ebbd..000000000000 --- a/arch/arm/kvm/reset.c +++ /dev/null @@ -1,86 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ -#include <linux/compiler.h> -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/kvm_host.h> -#include <linux/kvm.h> - -#include <asm/unified.h> -#include <asm/ptrace.h> -#include <asm/cputype.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_coproc.h> -#include <asm/kvm_emulate.h> - -#include <kvm/arm_arch_timer.h> - -/****************************************************************************** - * Cortex-A15 and Cortex-A7 Reset Values - */ - -static struct kvm_regs cortexa_regs_reset = { - .usr_regs.ARM_cpsr = SVC_MODE | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT, -}; - - -/******************************************************************************* - * Exported reset function - */ - -/** - * kvm_reset_vcpu - sets core registers and cp15 registers to reset value - * @vcpu: The VCPU pointer - * - * This function finds the right table above and sets the registers on the - * virtual CPU struct to their architecturally defined reset values. - */ -int kvm_reset_vcpu(struct kvm_vcpu *vcpu) -{ - struct kvm_regs *reset_regs; - - switch (vcpu->arch.target) { - case KVM_ARM_TARGET_CORTEX_A7: - case KVM_ARM_TARGET_CORTEX_A15: - reset_regs = &cortexa_regs_reset; - vcpu->arch.midr = read_cpuid_id(); - break; - default: - return -ENODEV; - } - - /* Reset core registers */ - memcpy(&vcpu->arch.ctxt.gp_regs, reset_regs, sizeof(vcpu->arch.ctxt.gp_regs)); - - /* Reset CP15 registers */ - kvm_reset_coprocs(vcpu); - - /* - * Additional reset state handling that PSCI may have imposed on us. - * Must be done after all the sys_reg reset. - */ - if (READ_ONCE(vcpu->arch.reset_state.reset)) { - unsigned long target_pc = vcpu->arch.reset_state.pc; - - /* Gracefully handle Thumb2 entry point */ - if (target_pc & 1) { - target_pc &= ~1UL; - vcpu_set_thumb(vcpu); - } - - /* Propagate caller endianness */ - if (vcpu->arch.reset_state.be) - kvm_vcpu_set_be(vcpu); - - *vcpu_pc(vcpu) = target_pc; - vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0); - - vcpu->arch.reset_state.reset = false; - } - - /* Reset arch_timer context */ - return kvm_timer_vcpu_reset(vcpu); -} diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h deleted file mode 100644 index 69a9d62a0ac6..000000000000 --- a/arch/arm/kvm/trace.h +++ /dev/null @@ -1,86 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#if !defined(_TRACE_ARM_KVM_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_ARM_KVM_H - -#include <linux/tracepoint.h> - -#undef TRACE_SYSTEM -#define TRACE_SYSTEM kvm - -/* Architecturally implementation defined CP15 register access */ -TRACE_EVENT(kvm_emulate_cp15_imp, - TP_PROTO(unsigned long Op1, unsigned long Rt1, unsigned long CRn, - unsigned long CRm, unsigned long Op2, bool is_write), - TP_ARGS(Op1, Rt1, CRn, CRm, Op2, is_write), - - TP_STRUCT__entry( - __field( unsigned int, Op1 ) - __field( unsigned int, Rt1 ) - __field( unsigned int, CRn ) - __field( unsigned int, CRm ) - __field( unsigned int, Op2 ) - __field( bool, is_write ) - ), - - TP_fast_assign( - __entry->is_write = is_write; - __entry->Op1 = Op1; - __entry->Rt1 = Rt1; - __entry->CRn = CRn; - __entry->CRm = CRm; - __entry->Op2 = Op2; - ), - - TP_printk("Implementation defined CP15: %s\tp15, %u, r%u, c%u, c%u, %u", - (__entry->is_write) ? "mcr" : "mrc", - __entry->Op1, __entry->Rt1, __entry->CRn, - __entry->CRm, __entry->Op2) -); - -TRACE_EVENT(kvm_wfx, - TP_PROTO(unsigned long vcpu_pc, bool is_wfe), - TP_ARGS(vcpu_pc, is_wfe), - - TP_STRUCT__entry( - __field( unsigned long, vcpu_pc ) - __field( bool, is_wfe ) - ), - - TP_fast_assign( - __entry->vcpu_pc = vcpu_pc; - __entry->is_wfe = is_wfe; - ), - - TP_printk("guest executed wf%c at: 0x%08lx", - __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc) -); - -TRACE_EVENT(kvm_hvc, - TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), - TP_ARGS(vcpu_pc, r0, imm), - - TP_STRUCT__entry( - __field( unsigned long, vcpu_pc ) - __field( unsigned long, r0 ) - __field( unsigned long, imm ) - ), - - TP_fast_assign( - __entry->vcpu_pc = vcpu_pc; - __entry->r0 = r0; - __entry->imm = imm; - ), - - TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx", - __entry->vcpu_pc, __entry->r0, __entry->imm) -); - -#endif /* _TRACE_ARM_KVM_H */ - -#undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH . -#undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_FILE trace - -/* This part must be outside protection */ -#include <trace/define_trace.h> diff --git a/arch/arm/kvm/vgic-v3-coproc.c b/arch/arm/kvm/vgic-v3-coproc.c deleted file mode 100644 index ed3b2e4759ce..000000000000 --- a/arch/arm/kvm/vgic-v3-coproc.c +++ /dev/null @@ -1,27 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * VGIC system registers handling functions for AArch32 mode - */ - -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <asm/kvm_emulate.h> -#include "vgic.h" - -int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, bool is_write, u64 id, - u64 *reg) -{ - /* - * TODO: Implement for AArch32 - */ - return -ENXIO; -} - -int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, bool is_write, u64 id, - u64 *reg) -{ - /* - * TODO: Implement for AArch32 - */ - return -ENXIO; -} diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index cbbe03e96de8..76838255b5fa 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -21,7 +21,7 @@ menuconfig ARCH_EXYNOS select EXYNOS_SROM select EXYNOS_PM_DOMAINS if PM_GENERIC_DOMAINS select GPIOLIB - select HAVE_ARM_ARCH_TIMER if ARCH_EXYNOS5 && VIRTUALIZATION + select HAVE_ARM_ARCH_TIMER if ARCH_EXYNOS5 select HAVE_ARM_SCU if SMP select HAVE_S3C2410_I2C if I2C select HAVE_S3C2410_WATCHDOG if WATCHDOG diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 5d0d0f86e790..69a337df619f 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -63,9 +63,6 @@ static unsigned int cachepolicy __initdata = CPOLICY_WRITEBACK; static unsigned int ecc_mask __initdata = 0; pgprot_t pgprot_user; pgprot_t pgprot_kernel; -pgprot_t pgprot_hyp_device; -pgprot_t pgprot_s2; -pgprot_t pgprot_s2_device; EXPORT_SYMBOL(pgprot_user); EXPORT_SYMBOL(pgprot_kernel); @@ -75,15 +72,8 @@ struct cachepolicy { unsigned int cr_mask; pmdval_t pmd; pteval_t pte; - pteval_t pte_s2; }; -#ifdef CONFIG_ARM_LPAE -#define s2_policy(policy) policy -#else -#define s2_policy(policy) 0 -#endif - unsigned long kimage_voffset __ro_after_init; static struct cachepolicy cache_policies[] __initdata = { @@ -92,31 +82,26 @@ static struct cachepolicy cache_policies[] __initdata = { .cr_mask = CR_W|CR_C, .pmd = PMD_SECT_UNCACHED, .pte = L_PTE_MT_UNCACHED, - .pte_s2 = s2_policy(L_PTE_S2_MT_UNCACHED), }, { .policy = "buffered", .cr_mask = CR_C, .pmd = PMD_SECT_BUFFERED, .pte = L_PTE_MT_BUFFERABLE, - .pte_s2 = s2_policy(L_PTE_S2_MT_UNCACHED), }, { .policy = "writethrough", .cr_mask = 0, .pmd = PMD_SECT_WT, .pte = L_PTE_MT_WRITETHROUGH, - .pte_s2 = s2_policy(L_PTE_S2_MT_WRITETHROUGH), }, { .policy = "writeback", .cr_mask = 0, .pmd = PMD_SECT_WB, .pte = L_PTE_MT_WRITEBACK, - .pte_s2 = s2_policy(L_PTE_S2_MT_WRITEBACK), }, { .policy = "writealloc", .cr_mask = 0, .pmd = PMD_SECT_WBWA, .pte = L_PTE_MT_WRITEALLOC, - .pte_s2 = s2_policy(L_PTE_S2_MT_WRITEBACK), } }; @@ -246,9 +231,6 @@ static struct mem_type mem_types[] __ro_after_init = { [MT_DEVICE] = { /* Strongly ordered / ARMv6 shared device */ .prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED | L_PTE_SHARED, - .prot_pte_s2 = s2_policy(PROT_PTE_S2_DEVICE) | - s2_policy(L_PTE_S2_MT_DEV_SHARED) | - L_PTE_SHARED, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PROT_SECT_DEVICE | PMD_SECT_S, .domain = DOMAIN_IO, @@ -434,7 +416,6 @@ static void __init build_mem_type_table(void) struct cachepolicy *cp; unsigned int cr = get_cr(); pteval_t user_pgprot, kern_pgprot, vecs_pgprot; - pteval_t hyp_device_pgprot, s2_pgprot, s2_device_pgprot; int cpu_arch = cpu_architecture(); int i; @@ -558,9 +539,6 @@ static void __init build_mem_type_table(void) */ cp = &cache_policies[cachepolicy]; vecs_pgprot = kern_pgprot = user_pgprot = cp->pte; - s2_pgprot = cp->pte_s2; - hyp_device_pgprot = mem_types[MT_DEVICE].prot_pte; - s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2; #ifndef CONFIG_ARM_LPAE /* @@ -604,7 +582,6 @@ static void __init build_mem_type_table(void) user_pgprot |= L_PTE_SHARED; kern_pgprot |= L_PTE_SHARED; vecs_pgprot |= L_PTE_SHARED; - s2_pgprot |= L_PTE_SHARED; mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S; mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED; mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S; @@ -666,9 +643,6 @@ static void __init build_mem_type_table(void) pgprot_user = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | user_pgprot); pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | kern_pgprot); - pgprot_s2 = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | s2_pgprot); - pgprot_s2_device = __pgprot(s2_device_pgprot); - pgprot_hyp_device = __pgprot(hyp_device_pgprot); mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask; diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index f658dda12364..a30b4eec7cb4 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -89,7 +89,8 @@ static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu) static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr_el2 &= ~HCR_TWE; - if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count)) + if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count) || + vcpu->kvm->arch.vgic.nassgireq) vcpu->arch.hcr_el2 &= ~HCR_TWI; else vcpu->arch.hcr_el2 |= HCR_TWI; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 57fd46acd058..32c8a675e5a4 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -44,6 +44,7 @@ #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) #define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) +#define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 525010504f9d..e329a36b2bee 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -11,7 +11,6 @@ #include <linux/kvm_host.h> #include <asm/fpsimd.h> #include <asm/kvm_asm.h> -#include <asm/kvm_host.h> #include <asm/kvm_mmu.h> #include <asm/sysreg.h> diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 2bd92301d32f..23ebe51410f0 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -25,7 +25,6 @@ #include <asm/kvm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> -#include <asm/kvm_host.h> #include <asm/sigcontext.h> #include "trace.h" diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index eaa05c3c7235..8a1e81a400e0 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -17,7 +17,6 @@ #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> -#include <asm/kvm_host.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/fpsimd.h> diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 090f46d3add1..51db934702b6 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -22,7 +22,6 @@ #include <asm/kvm_arm.h> #include <asm/kvm_coproc.h> #include <asm/kvm_emulate.h> -#include <asm/kvm_host.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/perf_event.h> diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c index 2b4a3e2d1b89..9cb6b4c8355a 100644 --- a/arch/arm64/kvm/sys_regs_generic_v8.c +++ b/arch/arm64/kvm/sys_regs_generic_v8.c @@ -12,7 +12,6 @@ #include <asm/cputype.h> #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> -#include <asm/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> #include <asm/sysreg.h> diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 41204a49cf95..2c343c346b79 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -1133,7 +1133,7 @@ extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm); static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, - struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {} + struct kvm_memory_slot *slot) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 71244bf87c3a..8f05dd0a0f4e 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -118,12 +118,12 @@ void kvm_arch_hardware_disable(void) kvm_mips_callbacks->hardware_disable(); } -int kvm_arch_hardware_setup(void) +int kvm_arch_hardware_setup(void *opaque) { return 0; } -int kvm_arch_check_processor_compat(void) +int kvm_arch_check_processor_compat(void *opaque) { return 0; } @@ -188,12 +188,6 @@ long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, return -ENOIOCTLCMD; } -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) -{ - return 0; -} - void kvm_arch_flush_shadow_all(struct kvm *kvm) { /* Flush whole GPA */ @@ -230,7 +224,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { @@ -984,69 +978,16 @@ long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, return r; } -/** - * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot - * @kvm: kvm instance - * @log: slot id and address to which we copy the log - * - * Steps 1-4 below provide general overview of dirty page logging. See - * kvm_get_dirty_log_protect() function description for additional details. - * - * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we - * always flush the TLB (step 4) even if previous step failed and the dirty - * bitmap may be corrupt. Regardless of previous outcome the KVM logging API - * does not preclude user space subsequent dirty log read. Flushing TLB ensures - * writes will be marked dirty for next log read. - * - * 1. Take a snapshot of the bit and clear it if needed. - * 2. Write protect the corresponding page. - * 3. Copy the snapshot to the userspace. - * 4. Flush TLB's if needed. - */ -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { - struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; - bool flush = false; - int r; - - mutex_lock(&kvm->slots_lock); - - r = kvm_get_dirty_log_protect(kvm, log, &flush); - - if (flush) { - slots = kvm_memslots(kvm); - memslot = id_to_memslot(slots, log->slot); - /* Let implementation handle TLB/GVA invalidation */ - kvm_mips_callbacks->flush_shadow_memslot(kvm, memslot); - } - - mutex_unlock(&kvm->slots_lock); - return r; } -int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) +void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) { - struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; - bool flush = false; - int r; - - mutex_lock(&kvm->slots_lock); - - r = kvm_clear_dirty_log_protect(kvm, log, &flush); - - if (flush) { - slots = kvm_memslots(kvm); - memslot = id_to_memslot(slots, log->slot); - - /* Let implementation handle TLB/GVA invalidation */ - kvm_mips_callbacks->flush_shadow_memslot(kvm, memslot); - } - - mutex_unlock(&kvm->slots_lock); - return r; + /* Let implementation handle TLB/GVA invalidation */ + kvm_mips_callbacks->flush_shadow_memslot(kvm, memslot); } long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 635fb154b33f..a3633560493b 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -150,4 +150,7 @@ #define KVM_INST_FETCH_FAILED -1 +/* Extract PO and XOP opcode fields */ +#define PO_XOP_OPCODE_MASK 0xfc0007fe + #endif /* __POWERPC_KVM_ASM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h index 5a9834e0e2d1..9cb7d8be2366 100644 --- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h +++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h @@ -5,6 +5,7 @@ #ifdef CONFIG_PPC_UV int kvmppc_uvmem_init(void); void kvmppc_uvmem_free(void); +bool kvmppc_uvmem_available(void); int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot); void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot); @@ -30,6 +31,11 @@ static inline int kvmppc_uvmem_init(void) static inline void kvmppc_uvmem_free(void) { } +static inline bool kvmppc_uvmem_available(void) +{ + return false; +} + static inline int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) { diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 6e8b8ffd06ad..f99b4333dfba 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -303,6 +303,7 @@ struct kvm_arch { u8 radix; u8 fwnmi_enabled; u8 secure_guest; + u8 svm_enabled; bool threads_indep; bool nested_enable; pgd_t *pgtable; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index bc2494e5710a..94f5a32acaf1 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -107,8 +107,6 @@ extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr, unsigned int gtlb_idx); extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode); extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid); -extern void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu); -extern int kvmppc_mmu_init(struct kvm_vcpu *vcpu); extern int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); extern int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); extern gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index, @@ -200,14 +198,11 @@ extern void kvm_free_hpt_cma(struct page *page, unsigned long nr_pages); extern int kvmppc_core_init_vm(struct kvm *kvm); extern void kvmppc_core_destroy_vm(struct kvm *kvm); extern void kvmppc_core_free_memslot(struct kvm *kvm, - struct kvm_memory_slot *free, - struct kvm_memory_slot *dont); -extern int kvmppc_core_create_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot, - unsigned long npages); + struct kvm_memory_slot *slot); extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change); extern void kvmppc_core_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, @@ -280,7 +275,8 @@ struct kvmppc_ops { void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot); int (*prepare_memory_region)(struct kvm *kvm, struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change); void (*commit_memory_region)(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, @@ -291,11 +287,7 @@ struct kvmppc_ops { int (*age_hva)(struct kvm *kvm, unsigned long start, unsigned long end); int (*test_age_hva)(struct kvm *kvm, unsigned long hva); void (*set_spte_hva)(struct kvm *kvm, unsigned long hva, pte_t pte); - void (*mmu_destroy)(struct kvm_vcpu *vcpu); - void (*free_memslot)(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont); - int (*create_memslot)(struct kvm_memory_slot *slot, - unsigned long npages); + void (*free_memslot)(struct kvm_memory_slot *slot); int (*init_vm)(struct kvm *kvm); void (*destroy_vm)(struct kvm *kvm); int (*get_smmu_info)(struct kvm *kvm, struct kvm_ppc_smmu_info *info); @@ -321,6 +313,7 @@ struct kvmppc_ops { int size); int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr, int size); + int (*enable_svm)(struct kvm *kvm); int (*svm_off)(struct kvm *kvm); }; diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index d07a8e12fa15..5690a1f9b976 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -799,21 +799,19 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) return vcpu->kvm->arch.kvm_ops->check_requests(vcpu); } -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { - return kvm->arch.kvm_ops->get_dirty_log(kvm, log); + } -void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { - kvm->arch.kvm_ops->free_memslot(free, dont); + return kvm->arch.kvm_ops->get_dirty_log(kvm, log); } -int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) +void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - return kvm->arch.kvm_ops->create_memslot(slot, npages); + kvm->arch.kvm_ops->free_memslot(slot); } void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) @@ -823,9 +821,11 @@ void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) { - return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem); + return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem, + change); } void kvmppc_core_commit_memory_region(struct kvm *kvm, @@ -858,11 +858,6 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) return 0; } -void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) -{ - vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu); -} - int kvmppc_core_init_vm(struct kvm *kvm) { diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h index 3a4613985949..eae259ee49af 100644 --- a/arch/powerpc/kvm/book3s.h +++ b/arch/powerpc/kvm/book3s.h @@ -16,6 +16,7 @@ extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long start, extern int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva); extern void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte); +extern int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu); extern int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance); diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index f21e73492ce3..3fbd570f9c1e 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -234,7 +234,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, case 2: case 6: pte->may_write = true; - /* fall through */ + fallthrough; case 3: case 5: case 7: diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c index d4cb3bcf41b6..e8e7b2c530d1 100644 --- a/arch/powerpc/kvm/book3s_32_mmu_host.c +++ b/arch/powerpc/kvm/book3s_32_mmu_host.c @@ -356,7 +356,7 @@ void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu) /* From mm/mmu_context_hash32.c */ #define CTX_TO_VSID(c, id) ((((c) * (897 * 16)) + (id * 0x111)) & 0xffffff) -int kvmppc_mmu_init(struct kvm_vcpu *vcpu) +int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); int err; diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 599133256a95..26b8b27a3755 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -311,7 +311,7 @@ do_second: case 2: case 6: gpte->may_write = true; - /* fall through */ + fallthrough; case 3: case 5: case 7: diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index 044dd49eeb9d..e452158a18d7 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -384,7 +384,7 @@ void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu) __destroy_context(to_book3s(vcpu)->context_id[0]); } -int kvmppc_mmu_init(struct kvm_vcpu *vcpu) +int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); int err; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 6c372f5c61b6..3aecec890d6f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -485,18 +485,18 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, __be64 *hptep; unsigned long mmu_seq, psize, pte_size; unsigned long gpa_base, gfn_base; - unsigned long gpa, gfn, hva, pfn; + unsigned long gpa, gfn, hva, pfn, hpa; struct kvm_memory_slot *memslot; unsigned long *rmap; struct revmap_entry *rev; - struct page *page, *pages[1]; - long index, ret, npages; + struct page *page; + long index, ret; bool is_ci; - unsigned int writing, write_ok; - struct vm_area_struct *vma; + bool writing, write_ok; + unsigned int shift; unsigned long rcbits; long mmio_update; - struct mm_struct *mm; + pte_t pte, *ptep; if (kvm_is_radix(kvm)) return kvmppc_book3s_radix_page_fault(run, vcpu, ea, dsisr); @@ -570,59 +570,62 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, smp_rmb(); ret = -EFAULT; - is_ci = false; - pfn = 0; page = NULL; - mm = kvm->mm; - pte_size = PAGE_SIZE; writing = (dsisr & DSISR_ISSTORE) != 0; /* If writing != 0, then the HPTE must allow writing, if we get here */ write_ok = writing; hva = gfn_to_hva_memslot(memslot, gfn); - npages = get_user_pages_fast(hva, 1, writing ? FOLL_WRITE : 0, pages); - if (npages < 1) { - /* Check if it's an I/O mapping */ - down_read(&mm->mmap_sem); - vma = find_vma(mm, hva); - if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end && - (vma->vm_flags & VM_PFNMAP)) { - pfn = vma->vm_pgoff + - ((hva - vma->vm_start) >> PAGE_SHIFT); - pte_size = psize; - is_ci = pte_ci(__pte((pgprot_val(vma->vm_page_prot)))); - write_ok = vma->vm_flags & VM_WRITE; - } - up_read(&mm->mmap_sem); - if (!pfn) - goto out_put; + + /* + * Do a fast check first, since __gfn_to_pfn_memslot doesn't + * do it with !atomic && !async, which is how we call it. + * We always ask for write permission since the common case + * is that the page is writable. + */ + if (__get_user_pages_fast(hva, 1, 1, &page) == 1) { + write_ok = true; } else { - page = pages[0]; - pfn = page_to_pfn(page); - if (PageHuge(page)) { - page = compound_head(page); - pte_size <<= compound_order(page); - } - /* if the guest wants write access, see if that is OK */ - if (!writing && hpte_is_writable(r)) { - pte_t *ptep, pte; - unsigned long flags; - /* - * We need to protect against page table destruction - * hugepage split and collapse. - */ - local_irq_save(flags); - ptep = find_current_mm_pte(mm->pgd, hva, NULL, NULL); - if (ptep) { - pte = kvmppc_read_update_linux_pte(ptep, 1); - if (__pte_write(pte)) - write_ok = 1; - } - local_irq_restore(flags); + /* Call KVM generic code to do the slow-path check */ + pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, + writing, &write_ok); + if (is_error_noslot_pfn(pfn)) + return -EFAULT; + page = NULL; + if (pfn_valid(pfn)) { + page = pfn_to_page(pfn); + if (PageReserved(page)) + page = NULL; } } + /* + * Read the PTE from the process' radix tree and use that + * so we get the shift and attribute bits. + */ + local_irq_disable(); + ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); + /* + * If the PTE disappeared temporarily due to a THP + * collapse, just return and let the guest try again. + */ + if (!ptep) { + local_irq_enable(); + if (page) + put_page(page); + return RESUME_GUEST; + } + pte = *ptep; + local_irq_enable(); + hpa = pte_pfn(pte) << PAGE_SHIFT; + pte_size = PAGE_SIZE; + if (shift) + pte_size = 1ul << shift; + is_ci = pte_ci(pte); + if (psize > pte_size) goto out_put; + if (pte_size > psize) + hpa |= hva & (pte_size - psize); /* Check WIMG vs. the actual page we're accessing */ if (!hpte_cache_flags_ok(r, is_ci)) { @@ -636,14 +639,13 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } /* - * Set the HPTE to point to pfn. - * Since the pfn is at PAGE_SIZE granularity, make sure we + * Set the HPTE to point to hpa. + * Since the hpa is at PAGE_SIZE granularity, make sure we * don't mask out lower-order bits if psize < PAGE_SIZE. */ if (psize < PAGE_SIZE) psize = PAGE_SIZE; - r = (r & HPTE_R_KEY_HI) | (r & ~(HPTE_R_PP0 - psize)) | - ((pfn << PAGE_SHIFT) & ~(psize - 1)); + r = (r & HPTE_R_KEY_HI) | (r & ~(HPTE_R_PP0 - psize)) | hpa; if (hpte_is_writable(r) && !write_ok) r = hpte_make_readonly(r); ret = RESUME_GUEST; @@ -708,20 +710,13 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, asm volatile("ptesync" : : : "memory"); preempt_enable(); if (page && hpte_is_writable(r)) - SetPageDirty(page); + set_page_dirty_lock(page); out_put: trace_kvm_page_fault_exit(vcpu, hpte, ret); - if (page) { - /* - * We drop pages[0] here, not page because page might - * have been set to the head page of a compound, but - * we have to drop the reference on the correct tail - * page to match the get inside gup() - */ - put_page(pages[0]); - } + if (page) + put_page(page); return ret; out_unlock: diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 803940d79b73..134fbc1f029f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -425,7 +425,7 @@ static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full, unsigned int lpid) { if (full) { - memset(pte, 0, sizeof(long) << PTE_INDEX_SIZE); + memset(pte, 0, sizeof(long) << RADIX_PTE_INDEX_SIZE); } else { pte_t *p = pte; unsigned long it; diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index ee6c103bb7d5..50555ad1db93 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -27,7 +27,6 @@ #include <asm/hvcall.h> #include <asm/synch.h> #include <asm/ppc-opcode.h> -#include <asm/kvm_host.h> #include <asm/udbg.h> #include <asm/iommu.h> #include <asm/tce.h> diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index ab6eeb8e753e..6fcaf1fa8e02 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -24,7 +24,6 @@ #include <asm/hvcall.h> #include <asm/synch.h> #include <asm/ppc-opcode.h> -#include <asm/kvm_host.h> #include <asm/udbg.h> #include <asm/iommu.h> #include <asm/tce.h> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 2cefd071b848..fa6e4fc7d0e4 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -72,7 +72,6 @@ #include <asm/xics.h> #include <asm/xive.h> #include <asm/hw_breakpoint.h> -#include <asm/kvm_host.h> #include <asm/kvm_book3s_uvmem.h> #include <asm/ultravisor.h> @@ -1074,25 +1073,35 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) kvmppc_get_gpr(vcpu, 6)); break; case H_SVM_PAGE_IN: - ret = kvmppc_h_svm_page_in(vcpu->kvm, - kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5), - kvmppc_get_gpr(vcpu, 6)); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_page_in(vcpu->kvm, + kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); break; case H_SVM_PAGE_OUT: - ret = kvmppc_h_svm_page_out(vcpu->kvm, - kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5), - kvmppc_get_gpr(vcpu, 6)); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_page_out(vcpu->kvm, + kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); break; case H_SVM_INIT_START: - ret = kvmppc_h_svm_init_start(vcpu->kvm); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_init_start(vcpu->kvm); break; case H_SVM_INIT_DONE: - ret = kvmppc_h_svm_init_done(vcpu->kvm); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_init_done(vcpu->kvm); break; case H_SVM_INIT_ABORT: - ret = kvmppc_h_svm_init_abort(vcpu->kvm); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_init_abort(vcpu->kvm); break; default: @@ -3616,6 +3625,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && kvmppc_get_gpr(vcpu, 3) == H_CEDE) { kvmppc_nested_cede(vcpu); + kvmppc_set_gpr(vcpu, 3, 0); trap = 0; } } else { @@ -4400,7 +4410,7 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, slots = kvm_memslots(kvm); memslot = id_to_memslot(slots, log->slot); r = -ENOENT; - if (!memslot->dirty_bitmap) + if (!memslot || !memslot->dirty_bitmap) goto out; /* @@ -4447,29 +4457,26 @@ out: return r; } -static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *slot) { - if (!dont || free->arch.rmap != dont->arch.rmap) { - vfree(free->arch.rmap); - free->arch.rmap = NULL; - } + vfree(slot->arch.rmap); + slot->arch.rmap = NULL; } -static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot, - unsigned long npages) +static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, + struct kvm_memory_slot *slot, + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) { - slot->arch.rmap = vzalloc(array_size(npages, sizeof(*slot->arch.rmap))); - if (!slot->arch.rmap) - return -ENOMEM; + unsigned long npages = mem->memory_size >> PAGE_SHIFT; - return 0; -} + if (change == KVM_MR_CREATE) { + slot->arch.rmap = vzalloc(array_size(npages, + sizeof(*slot->arch.rmap))); + if (!slot->arch.rmap) + return -ENOMEM; + } -static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem) -{ return 0; } @@ -4558,11 +4565,6 @@ void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask) } } -static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu) -{ - return; -} - void kvmppc_setup_partition_table(struct kvm *kvm) { unsigned long dw0, dw1; @@ -5427,6 +5429,21 @@ static void unpin_vpa_reset(struct kvm *kvm, struct kvmppc_vpa *vpa) } /* + * Enable a guest to become a secure VM, or test whether + * that could be enabled. + * Called when the KVM_CAP_PPC_SECURE_GUEST capability is + * tested (kvm == NULL) or enabled (kvm != NULL). + */ +static int kvmhv_enable_svm(struct kvm *kvm) +{ + if (!kvmppc_uvmem_available()) + return -EINVAL; + if (kvm) + kvm->arch.svm_enabled = 1; + return 0; +} + +/* * IOCTL handler to turn off secure mode of guest * * - Release all device pages @@ -5526,9 +5543,7 @@ static struct kvmppc_ops kvm_ops_hv = { .age_hva = kvm_age_hva_hv, .test_age_hva = kvm_test_age_hva_hv, .set_spte_hva = kvm_set_spte_hva_hv, - .mmu_destroy = kvmppc_mmu_destroy_hv, .free_memslot = kvmppc_core_free_memslot_hv, - .create_memslot = kvmppc_core_create_memslot_hv, .init_vm = kvmppc_core_init_vm_hv, .destroy_vm = kvmppc_core_destroy_vm_hv, .get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv, @@ -5548,6 +5563,7 @@ static struct kvmppc_ops kvm_ops_hv = { .enable_nested = kvmhv_enable_nested, .load_from_eaddr = kvmhv_load_from_eaddr, .store_to_eaddr = kvmhv_store_to_eaddr, + .enable_svm = kvmhv_enable_svm, .svm_off = kvmhv_svm_off, }; diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c index 0db937497169..cc90b8b82329 100644 --- a/arch/powerpc/kvm/book3s_hv_tm.c +++ b/arch/powerpc/kvm/book3s_hv_tm.c @@ -3,6 +3,8 @@ * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <asm/kvm_ppc.h> @@ -44,7 +46,18 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) u64 newmsr, bescr; int ra, rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For treclaim., tsr., and trechkpt. instructions if bit + * 31 = 0 then they are per ISA invalid forms, however P9 UM, in section + * 4.6.10 Book II Invalid Forms, informs specifically that ignoring bit + * 31 is an acceptable way to handle these invalid forms that have + * bit 31 = 0. Moreover, for emulation purposes both forms (w/ and wo/ + * bit 31 set) can generate a softpatch interrupt. Hence both forms + * are handled below for these instructions so they behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -105,7 +118,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return RESUME_GUEST; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* check for PR=1 and arch 2.06 bit set in PCR */ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) { /* generate an illegal instruction interrupt */ @@ -140,7 +154,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = msr; return RESUME_GUEST; - case PPC_INST_TRECLAIM: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK): /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { /* generate an illegal instruction interrupt */ @@ -176,7 +191,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr &= ~MSR_TS_MASK; return RESUME_GUEST; - case PPC_INST_TRECHKPT: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECHKPT & PO_XOP_OPCODE_MASK): /* XXX do we need to check for PR=0 here? */ /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { @@ -208,6 +224,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) } /* What should we do here? We didn't recognize the instruction */ - WARN_ON_ONCE(1); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + pr_warn_ratelimited("Unrecognized TM-related instruction %#x for emulation", instr); + return RESUME_GUEST; } diff --git a/arch/powerpc/kvm/book3s_hv_tm_builtin.c b/arch/powerpc/kvm/book3s_hv_tm_builtin.c index 217246279dfa..fad931f224ef 100644 --- a/arch/powerpc/kvm/book3s_hv_tm_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_tm_builtin.c @@ -23,7 +23,18 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) u64 newmsr, msr, bescr; int rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For the tsr. instruction if bit 31 = 0 then it is per + * ISA an invalid form, however P9 UM, in section 4.6.10 Book II Invalid + * Forms, informs specifically that ignoring bit 31 is an acceptable way + * to handle TM-related invalid forms that have bit 31 = 0. Moreover, + * for emulation purposes both forms (w/ and wo/ bit 31 set) can + * generate a softpatch interrupt. Hence both forms are handled below + * for tsr. to make them behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -73,7 +84,8 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return 1; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* we know the MSR has the TS field = S (0b01) here */ msr = vcpu->arch.shregs.msr; /* check for PR=1 and arch 2.06 bit set in PCR */ diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index f44f6b27950f..76d05c71fb1f 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -113,6 +113,15 @@ struct kvmppc_uvmem_page_pvt { bool skip_page_out; }; +bool kvmppc_uvmem_available(void) +{ + /* + * If kvmppc_uvmem_bitmap != NULL, then there is an ultravisor + * and our data structures have been initialized successfully. + */ + return !!kvmppc_uvmem_bitmap; +} + int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) { struct kvmppc_uvmem_slot *p; @@ -209,6 +218,8 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) int ret = H_SUCCESS; int srcu_idx; + kvm->arch.secure_guest = KVMPPC_SECURE_INIT_START; + if (!kvmppc_uvmem_bitmap) return H_UNSUPPORTED; @@ -216,6 +227,10 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) if (!kvm_is_radix(kvm)) return H_UNSUPPORTED; + /* NAK the transition to secure if not enabled */ + if (!kvm->arch.svm_enabled) + return H_AUTHORITY; + srcu_idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, slots) { @@ -233,7 +248,6 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) goto out; } } - kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_START; out: srcu_read_unlock(&kvm->srcu, srcu_idx); return ret; @@ -809,6 +823,9 @@ out: void kvmppc_uvmem_free(void) { + if (!kvmppc_uvmem_bitmap) + return; + memunmap_pages(&kvmppc_uvmem_pgmap); release_mem_region(kvmppc_uvmem_pgmap.res.start, resource_size(&kvmppc_uvmem_pgmap.res)); diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index db3a87319642..a0f6813f4560 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -740,7 +740,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) && ((pte.raddr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS)) pte.raddr &= ~SPLIT_HACK_MASK; - /* fall through */ + fallthrough; case MSR_IR: vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid); @@ -1795,7 +1795,7 @@ static int kvmppc_core_vcpu_create_pr(struct kvm_vcpu *vcpu) vcpu->arch.shadow_msr = MSR_USER64 & ~MSR_LE; - err = kvmppc_mmu_init(vcpu); + err = kvmppc_mmu_init_pr(vcpu); if (err < 0) goto free_shared_page; @@ -1885,7 +1885,6 @@ out: static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm, struct kvm_dirty_log *log) { - struct kvm_memslots *slots; struct kvm_memory_slot *memslot; struct kvm_vcpu *vcpu; ulong ga, ga_end; @@ -1895,15 +1894,12 @@ static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm, mutex_lock(&kvm->slots_lock); - r = kvm_get_dirty_log(kvm, log, &is_dirty); + r = kvm_get_dirty_log(kvm, log, &is_dirty, &memslot); if (r) goto out; /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { - slots = kvm_memslots(kvm); - memslot = id_to_memslot(slots, log->slot); - ga = memslot->base_gfn << PAGE_SHIFT; ga_end = ga + (memslot->npages << PAGE_SHIFT); @@ -1928,7 +1924,8 @@ static void kvmppc_core_flush_memslot_pr(struct kvm *kvm, static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm, struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) { return 0; } @@ -1942,19 +1939,11 @@ static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm, return; } -static void kvmppc_core_free_memslot_pr(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +static void kvmppc_core_free_memslot_pr(struct kvm_memory_slot *slot) { return; } -static int kvmppc_core_create_memslot_pr(struct kvm_memory_slot *slot, - unsigned long npages) -{ - return 0; -} - - #ifdef CONFIG_PPC64 static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm, struct kvm_ppc_smmu_info *info) @@ -2098,9 +2087,7 @@ static struct kvmppc_ops kvm_ops_pr = { .age_hva = kvm_age_hva_pr, .test_age_hva = kvm_test_age_hva_pr, .set_spte_hva = kvm_set_spte_hva_pr, - .mmu_destroy = kvmppc_mmu_destroy_pr, .free_memslot = kvmppc_core_free_memslot_pr, - .create_memslot = kvmppc_core_create_memslot_pr, .init_vm = kvmppc_core_init_vm_pr, .destroy_vm = kvmppc_core_destroy_vm_pr, .get_smmu_info = kvm_vm_ioctl_get_smmu_info_pr, diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 7b27604adadf..6c18ea88fd25 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -421,11 +421,11 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, case BOOKE_IRQPRIO_DATA_STORAGE: case BOOKE_IRQPRIO_ALIGNMENT: update_dear = true; - /* fall through */ + fallthrough; case BOOKE_IRQPRIO_INST_STORAGE: case BOOKE_IRQPRIO_PROGRAM: update_esr = true; - /* fall through */ + fallthrough; case BOOKE_IRQPRIO_ITLB_MISS: case BOOKE_IRQPRIO_SYSCALL: case BOOKE_IRQPRIO_FP_UNAVAIL: @@ -459,7 +459,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, case BOOKE_IRQPRIO_DECREMENTER: case BOOKE_IRQPRIO_FIT: keep_irq = true; - /* fall through */ + fallthrough; case BOOKE_IRQPRIO_EXTERNAL: case BOOKE_IRQPRIO_DBELL: allowed = vcpu->arch.shared->msr & MSR_EE; @@ -1766,25 +1766,24 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, return r; } -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { - return -ENOTSUPP; + } -void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { + return -ENOTSUPP; } -int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) +void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - return 0; } int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) { return 0; } @@ -2074,11 +2073,6 @@ void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu) kvmppc_clear_dbsr(); } -void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) -{ - vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu); -} - int kvmppc_core_init_vm(struct kvm *kvm) { return kvm->arch.kvm_ops->init_vm(kvm); diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h index 9d3169fbce55..65b4d337d337 100644 --- a/arch/powerpc/kvm/booke.h +++ b/arch/powerpc/kvm/booke.h @@ -94,7 +94,6 @@ enum int_class { void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type); -extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu); extern int kvmppc_core_emulate_op_e500(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance); @@ -102,7 +101,6 @@ extern int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_val); extern int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val); -extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu); extern int kvmppc_core_emulate_op_e500(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance); diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index f2b4feaff6d2..7e8b69015d20 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -490,7 +490,6 @@ static struct kvmppc_ops kvm_ops_e500 = { .vcpu_put = kvmppc_core_vcpu_put_e500, .vcpu_create = kvmppc_core_vcpu_create_e500, .vcpu_free = kvmppc_core_vcpu_free_e500, - .mmu_destroy = kvmppc_mmu_destroy_e500, .init_vm = kvmppc_core_init_vm_e500, .destroy_vm = kvmppc_core_destroy_vm_e500, .emulate_op = kvmppc_core_emulate_op_e500, diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index 2d910b87e441..e131fbecdcc4 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -533,10 +533,6 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index, return get_tlb_raddr(gtlbe) | (eaddr & pgmask); } -void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu) -{ -} - /*****************************************/ static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500) diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index e6b06cb2b92c..1c189b5aadcc 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -376,7 +376,6 @@ static struct kvmppc_ops kvm_ops_e500mc = { .vcpu_put = kvmppc_core_vcpu_put_e500mc, .vcpu_create = kvmppc_core_vcpu_create_e500mc, .vcpu_free = kvmppc_core_vcpu_free_e500mc, - .mmu_destroy = kvmppc_mmu_destroy_e500, .init_vm = kvmppc_core_init_vm_e500mc, .destroy_vm = kvmppc_core_destroy_vm_e500mc, .emulate_op = kvmppc_core_emulate_op_e500, diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c index fe312c160d97..23e9c2bd9f27 100644 --- a/arch/powerpc/kvm/mpic.c +++ b/arch/powerpc/kvm/mpic.c @@ -32,7 +32,6 @@ #include <linux/uaccess.h> #include <asm/mpic.h> #include <asm/kvm_para.h> -#include <asm/kvm_host.h> #include <asm/kvm_ppc.h> #include <kvm/iodev.h> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 302e9dccdd6d..e15166b0a16d 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -32,7 +32,6 @@ #include <asm/plpar_wrappers.h> #endif #include <asm/ultravisor.h> -#include <asm/kvm_host.h> #include "timing.h" #include "irq.h" @@ -416,12 +415,12 @@ int kvm_arch_hardware_enable(void) return 0; } -int kvm_arch_hardware_setup(void) +int kvm_arch_hardware_setup(void *opaque) { return 0; } -int kvm_arch_check_processor_compat(void) +int kvm_arch_check_processor_compat(void *opaque) { return kvmppc_core_check_processor_compat(); } @@ -525,7 +524,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; case KVM_CAP_PPC_GUEST_DEBUG_SSTEP: - /* fall through */ case KVM_CAP_PPC_PAIRED_SINGLES: case KVM_CAP_PPC_OSI: case KVM_CAP_PPC_GET_PVINFO: @@ -671,6 +669,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) (hv_enabled && cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)); break; #endif +#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) + case KVM_CAP_PPC_SECURE_GUEST: + r = hv_enabled && kvmppc_hv_ops->enable_svm && + !kvmppc_hv_ops->enable_svm(NULL); + break; +#endif default: r = 0; break; @@ -685,16 +689,9 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) -{ - kvmppc_core_free_memslot(kvm, free, dont); -} - -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - return kvmppc_core_create_memslot(kvm, slot, npages); + kvmppc_core_free_memslot(kvm, slot); } int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -702,12 +699,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { - return kvmppc_core_prepare_memory_region(kvm, memslot, mem); + return kvmppc_core_prepare_memory_region(kvm, memslot, mem, change); } void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { @@ -2176,6 +2173,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, r = kvm->arch.kvm_ops->enable_nested(kvm); break; #endif +#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) + case KVM_CAP_PPC_SECURE_GUEST: + r = -EINVAL; + if (!is_kvmppc_hv_enabled(kvm) || !kvm->arch.kvm_ops->enable_svm) + break; + r = kvm->arch.kvm_ops->enable_svm(kvm); + break; +#endif default: r = -EINVAL; break; diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h index ace65f9fed30..feef7885ba82 100644 --- a/arch/powerpc/kvm/timing.h +++ b/arch/powerpc/kvm/timing.h @@ -10,7 +10,6 @@ #define __POWERPC_KVM_EXITTIMING_H__ #include <linux/kvm_host.h> -#include <asm/kvm_host.h> #ifdef CONFIG_KVM_EXIT_TIMING void kvmppc_init_timing_stats(struct kvm_vcpu *vcpu); diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index 0ff9261c915e..45b33b83de08 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -37,7 +37,7 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o obj-y += version.o pgm_check_info.o ctype.o text_dma.o -obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) += uv.o +obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o obj-$(CONFIG_RELOCATABLE) += machine_kexec_reloc.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o targets := bzImage startup.a section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y) diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c index 3f501159ee9f..8fde561f1d07 100644 --- a/arch/s390/boot/uv.c +++ b/arch/s390/boot/uv.c @@ -3,7 +3,13 @@ #include <asm/facility.h> #include <asm/sections.h> +/* will be used in arch/s390/kernel/uv.c */ +#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST int __bootdata_preserved(prot_virt_guest); +#endif +#if IS_ENABLED(CONFIG_KVM) +struct uv_info __bootdata_preserved(uv_info); +#endif void uv_query_info(void) { @@ -19,7 +25,21 @@ void uv_query_info(void) if (uv_call(0, (uint64_t)&uvcb) && uvcb.header.rc != 0x100) return; + if (IS_ENABLED(CONFIG_KVM)) { + memcpy(uv_info.inst_calls_list, uvcb.inst_calls_list, sizeof(uv_info.inst_calls_list)); + uv_info.uv_base_stor_len = uvcb.uv_base_stor_len; + uv_info.guest_base_stor_len = uvcb.conf_base_phys_stor_len; + uv_info.guest_virt_base_stor_len = uvcb.conf_base_virt_stor_len; + uv_info.guest_virt_var_stor_len = uvcb.conf_virt_var_stor_len; + uv_info.guest_cpu_stor_len = uvcb.cpu_stor_len; + uv_info.max_sec_stor_addr = ALIGN(uvcb.max_guest_stor_addr, PAGE_SIZE); + uv_info.max_num_sec_conf = uvcb.max_num_sec_conf; + uv_info.max_guest_cpus = uvcb.max_guest_cpus; + } + +#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) && test_bit_inv(BIT_UVC_CMD_REMOVE_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list)) prot_virt_guest = 1; +#endif } diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h index 37f96b6f0e61..a816fb4734b8 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -9,6 +9,7 @@ #ifndef _ASM_S390_GMAP_H #define _ASM_S390_GMAP_H +#include <linux/radix-tree.h> #include <linux/refcount.h> /* Generic bits for GMAP notification on DAT table entry changes. */ @@ -31,6 +32,7 @@ * @table: pointer to the page directory * @asce: address space control element for gmap page table * @pfault_enabled: defines if pfaults are applicable for the guest + * @guest_handle: protected virtual machine handle for the ultravisor * @host_to_rmap: radix tree with gmap_rmap lists * @children: list of shadow gmap structures * @pt_list: list of all page tables used in the shadow guest address space @@ -54,6 +56,8 @@ struct gmap { unsigned long asce_end; void *private; bool pfault_enabled; + /* only set for protected virtual machines */ + unsigned long guest_handle; /* Additional data for shadow guest address spaces */ struct radix_tree_root host_to_rmap; struct list_head children; @@ -144,4 +148,6 @@ int gmap_mprotect_notify(struct gmap *, unsigned long start, void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4], unsigned long gaddr, unsigned long vmaddr); +int gmap_mark_unmergeable(void); +void s390_reset_acc(struct mm_struct *mm); #endif /* _ASM_S390_GMAP_H */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 1726224e7772..d6bcd34f3ec3 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -127,6 +127,12 @@ struct mcck_volatile_info { #define CR14_INITIAL_MASK (CR14_UNUSED_32 | CR14_UNUSED_33 | \ CR14_EXTERNAL_DAMAGE_SUBMASK) +#define SIDAD_SIZE_MASK 0xff +#define sida_origin(sie_block) \ + ((sie_block)->sidad & PAGE_MASK) +#define sida_size(sie_block) \ + ((((sie_block)->sidad & SIDAD_SIZE_MASK) + 1) * PAGE_SIZE) + #define CPUSTAT_STOPPED 0x80000000 #define CPUSTAT_WAIT 0x10000000 #define CPUSTAT_ECALL_PEND 0x08000000 @@ -160,7 +166,13 @@ struct kvm_s390_sie_block { __u8 reserved08[4]; /* 0x0008 */ #define PROG_IN_SIE (1<<0) __u32 prog0c; /* 0x000c */ - __u8 reserved10[16]; /* 0x0010 */ + union { + __u8 reserved10[16]; /* 0x0010 */ + struct { + __u64 pv_handle_cpu; + __u64 pv_handle_config; + }; + }; #define PROG_BLOCK_SIE (1<<0) #define PROG_REQUEST (1<<1) atomic_t prog20; /* 0x0020 */ @@ -209,10 +221,23 @@ struct kvm_s390_sie_block { #define ICPT_PARTEXEC 0x38 #define ICPT_IOINST 0x40 #define ICPT_KSS 0x5c +#define ICPT_MCHKREQ 0x60 +#define ICPT_INT_ENABLE 0x64 +#define ICPT_PV_INSTR 0x68 +#define ICPT_PV_NOTIFY 0x6c +#define ICPT_PV_PREF 0x70 __u8 icptcode; /* 0x0050 */ __u8 icptstatus; /* 0x0051 */ __u16 ihcpu; /* 0x0052 */ - __u8 reserved54[2]; /* 0x0054 */ + __u8 reserved54; /* 0x0054 */ +#define IICTL_CODE_NONE 0x00 +#define IICTL_CODE_MCHK 0x01 +#define IICTL_CODE_EXT 0x02 +#define IICTL_CODE_IO 0x03 +#define IICTL_CODE_RESTART 0x04 +#define IICTL_CODE_SPECIFICATION 0x10 +#define IICTL_CODE_OPERAND 0x11 + __u8 iictl; /* 0x0055 */ __u16 ipa; /* 0x0056 */ __u32 ipb; /* 0x0058 */ __u32 scaoh; /* 0x005c */ @@ -233,7 +258,7 @@ struct kvm_s390_sie_block { #define ECB3_RI 0x01 __u8 ecb3; /* 0x0063 */ __u32 scaol; /* 0x0064 */ - __u8 reserved68; /* 0x0068 */ + __u8 sdf; /* 0x0068 */ __u8 epdx; /* 0x0069 */ __u8 reserved6a[2]; /* 0x006a */ __u32 todpr; /* 0x006c */ @@ -249,31 +274,58 @@ struct kvm_s390_sie_block { #define HPID_KVM 0x4 #define HPID_VSIE 0x5 __u8 hpid; /* 0x00b8 */ - __u8 reservedb9[11]; /* 0x00b9 */ - __u16 extcpuaddr; /* 0x00c4 */ - __u16 eic; /* 0x00c6 */ + __u8 reservedb9[7]; /* 0x00b9 */ + union { + struct { + __u32 eiparams; /* 0x00c0 */ + __u16 extcpuaddr; /* 0x00c4 */ + __u16 eic; /* 0x00c6 */ + }; + __u64 mcic; /* 0x00c0 */ + } __packed; __u32 reservedc8; /* 0x00c8 */ - __u16 pgmilc; /* 0x00cc */ - __u16 iprcc; /* 0x00ce */ - __u32 dxc; /* 0x00d0 */ - __u16 mcn; /* 0x00d4 */ - __u8 perc; /* 0x00d6 */ - __u8 peratmid; /* 0x00d7 */ + union { + struct { + __u16 pgmilc; /* 0x00cc */ + __u16 iprcc; /* 0x00ce */ + }; + __u32 edc; /* 0x00cc */ + } __packed; + union { + struct { + __u32 dxc; /* 0x00d0 */ + __u16 mcn; /* 0x00d4 */ + __u8 perc; /* 0x00d6 */ + __u8 peratmid; /* 0x00d7 */ + }; + __u64 faddr; /* 0x00d0 */ + } __packed; __u64 peraddr; /* 0x00d8 */ __u8 eai; /* 0x00e0 */ __u8 peraid; /* 0x00e1 */ __u8 oai; /* 0x00e2 */ __u8 armid; /* 0x00e3 */ __u8 reservede4[4]; /* 0x00e4 */ - __u64 tecmc; /* 0x00e8 */ - __u8 reservedf0[12]; /* 0x00f0 */ + union { + __u64 tecmc; /* 0x00e8 */ + struct { + __u16 subchannel_id; /* 0x00e8 */ + __u16 subchannel_nr; /* 0x00ea */ + __u32 io_int_parm; /* 0x00ec */ + __u32 io_int_word; /* 0x00f0 */ + }; + } __packed; + __u8 reservedf4[8]; /* 0x00f4 */ #define CRYCB_FORMAT_MASK 0x00000003 #define CRYCB_FORMAT0 0x00000000 #define CRYCB_FORMAT1 0x00000001 #define CRYCB_FORMAT2 0x00000003 __u32 crycbd; /* 0x00fc */ __u64 gcr[16]; /* 0x0100 */ - __u64 gbea; /* 0x0180 */ + union { + __u64 gbea; /* 0x0180 */ + __u64 sidad; + }; __u8 reserved188[8]; /* 0x0188 */ __u64 sdnxo; /* 0x0190 */ __u8 reserved198[8]; /* 0x0198 */ @@ -292,7 +344,7 @@ struct kvm_s390_sie_block { __u64 itdba; /* 0x01e8 */ __u64 riccbd; /* 0x01f0 */ __u64 gvrd; /* 0x01f8 */ -} __attribute__((packed)); +} __packed __aligned(512); struct kvm_s390_itdb { __u8 data[256]; @@ -301,7 +353,9 @@ struct kvm_s390_itdb { struct sie_page { struct kvm_s390_sie_block sie_block; struct mcck_volatile_info mcck_info; /* 0x0200 */ - __u8 reserved218[1000]; /* 0x0218 */ + __u8 reserved218[360]; /* 0x0218 */ + __u64 pv_grregs[16]; /* 0x0380 */ + __u8 reserved400[512]; /* 0x0400 */ struct kvm_s390_itdb itdb; /* 0x0600 */ __u8 reserved700[2304]; /* 0x0700 */ }; @@ -476,6 +530,7 @@ enum irq_types { IRQ_PEND_PFAULT_INIT, IRQ_PEND_EXT_HOST, IRQ_PEND_EXT_SERVICE, + IRQ_PEND_EXT_SERVICE_EV, IRQ_PEND_EXT_TIMING, IRQ_PEND_EXT_CPU_TIMER, IRQ_PEND_EXT_CLOCK_COMP, @@ -520,6 +575,7 @@ enum irq_types { (1UL << IRQ_PEND_EXT_TIMING) | \ (1UL << IRQ_PEND_EXT_HOST) | \ (1UL << IRQ_PEND_EXT_SERVICE) | \ + (1UL << IRQ_PEND_EXT_SERVICE_EV) | \ (1UL << IRQ_PEND_VIRTIO) | \ (1UL << IRQ_PEND_PFAULT_INIT) | \ (1UL << IRQ_PEND_PFAULT_DONE)) @@ -536,6 +592,13 @@ enum irq_types { #define IRQ_PEND_MCHK_MASK ((1UL << IRQ_PEND_MCHK_REP) | \ (1UL << IRQ_PEND_MCHK_EX)) +#define IRQ_PEND_EXT_II_MASK ((1UL << IRQ_PEND_EXT_CPU_TIMER) | \ + (1UL << IRQ_PEND_EXT_CLOCK_COMP) | \ + (1UL << IRQ_PEND_EXT_EMERGENCY) | \ + (1UL << IRQ_PEND_EXT_EXTERNAL) | \ + (1UL << IRQ_PEND_EXT_SERVICE) | \ + (1UL << IRQ_PEND_EXT_SERVICE_EV)) + struct kvm_s390_interrupt_info { struct list_head list; u64 type; @@ -594,6 +657,7 @@ struct kvm_s390_local_interrupt { struct kvm_s390_float_interrupt { unsigned long pending_irqs; + unsigned long masked_irqs; spinlock_t lock; struct list_head lists[FIRQ_LIST_COUNT]; int counters[FIRQ_MAX_COUNT]; @@ -645,6 +709,11 @@ struct kvm_guestdbg_info_arch { unsigned long last_bp; }; +struct kvm_s390_pv_vcpu { + u64 handle; + unsigned long stor_base; +}; + struct kvm_vcpu_arch { struct kvm_s390_sie_block *sie_block; /* if vsie is active, currently executed shadow sie control block */ @@ -673,6 +742,7 @@ struct kvm_vcpu_arch { __u64 cputm_start; bool gs_enabled; bool skey_enabled; + struct kvm_s390_pv_vcpu pv; }; struct kvm_vm_stat { @@ -701,9 +771,6 @@ struct s390_io_adapter { bool masked; bool swap; bool suppressible; - struct rw_semaphore maps_lock; - struct list_head maps; - atomic_t nr_maps; }; #define MAX_S390_IO_ADAPTERS ((MAX_ISC + 1) * 8) @@ -846,6 +913,13 @@ struct kvm_s390_gisa_interrupt { DECLARE_BITMAP(kicked_mask, KVM_MAX_VCPUS); }; +struct kvm_s390_pv { + u64 handle; + u64 guest_len; + unsigned long stor_base; + void *stor_var; +}; + struct kvm_arch{ void *sca; int use_esca; @@ -881,6 +955,7 @@ struct kvm_arch{ DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS); DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS); struct kvm_s390_gisa_interrupt gisa_int; + struct kvm_s390_pv pv; }; #define KVM_HVA_ERR_BAD (-1UL) @@ -921,7 +996,7 @@ static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, - struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {} + struct kvm_memory_slot *slot) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm, diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index bcfb6371086f..e21b618ad432 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -16,6 +16,8 @@ typedef struct { unsigned long asce; unsigned long asce_limit; unsigned long vdso_base; + /* The mmu context belongs to a secure guest. */ + atomic_t is_protected; /* * The following bitfields need a down_write on the mm * semaphore when they are written to. As they are only diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 8d04e6f3f796..afa836014076 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -23,6 +23,7 @@ static inline int init_new_context(struct task_struct *tsk, INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.flush_count, 0); + atomic_set(&mm->context.is_protected, 0); mm->context.gmap_asce = 0; mm->context.flush_mm = 0; mm->context.compat_mm = test_thread_flag(TIF_31BIT); diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 1019efd85b9d..62440a82731a 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -153,6 +153,11 @@ static inline int devmem_is_allowed(unsigned long pfn) #define HAVE_ARCH_FREE_PAGE #define HAVE_ARCH_ALLOC_PAGE +#if IS_ENABLED(CONFIG_PGSTE) +int arch_make_page_accessible(struct page *page); +#define HAVE_ARCH_MAKE_PAGE_ACCESSIBLE +#endif + #endif /* !__ASSEMBLY__ */ #define __PAGE_OFFSET 0x0UL diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 6d7c3b7e9281..6076c8c912d2 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -19,6 +19,7 @@ #include <linux/atomic.h> #include <asm/bug.h> #include <asm/page.h> +#include <asm/uv.h> extern pgd_t swapper_pg_dir[]; extern void paging_init(void); @@ -520,6 +521,15 @@ static inline int mm_has_pgste(struct mm_struct *mm) return 0; } +static inline int mm_is_protected(struct mm_struct *mm) +{ +#ifdef CONFIG_PGSTE + if (unlikely(atomic_read(&mm->context.is_protected))) + return 1; +#endif + return 0; +} + static inline int mm_alloc_pgste(struct mm_struct *mm) { #ifdef CONFIG_PGSTE @@ -1067,7 +1077,12 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - return ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID)); + pte_t res; + + res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID)); + if (mm_is_protected(mm) && pte_present(res)) + uv_convert_from_secure(pte_val(res) & PAGE_MASK); + return res; } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION @@ -1079,7 +1094,12 @@ void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, static inline pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - return ptep_xchg_direct(vma->vm_mm, addr, ptep, __pte(_PAGE_INVALID)); + pte_t res; + + res = ptep_xchg_direct(vma->vm_mm, addr, ptep, __pte(_PAGE_INVALID)); + if (mm_is_protected(vma->vm_mm) && pte_present(res)) + uv_convert_from_secure(pte_val(res) & PAGE_MASK); + return res; } /* @@ -1094,12 +1114,17 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full) { + pte_t res; + if (full) { - pte_t pte = *ptep; + res = *ptep; *ptep = __pte(_PAGE_INVALID); - return pte; + } else { + res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID)); } - return ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID)); + if (mm_is_protected(mm) && pte_present(res)) + uv_convert_from_secure(pte_val(res) & PAGE_MASK); + return res; } #define __HAVE_ARCH_PTEP_SET_WRPROTECT diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 4093a2856929..cff4b4c99b75 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -14,23 +14,62 @@ #include <linux/types.h> #include <linux/errno.h> #include <linux/bug.h> +#include <linux/sched.h> #include <asm/page.h> +#include <asm/gmap.h> #define UVC_RC_EXECUTED 0x0001 #define UVC_RC_INV_CMD 0x0002 #define UVC_RC_INV_STATE 0x0003 #define UVC_RC_INV_LEN 0x0005 #define UVC_RC_NO_RESUME 0x0007 +#define UVC_RC_NEED_DESTROY 0x8000 #define UVC_CMD_QUI 0x0001 +#define UVC_CMD_INIT_UV 0x000f +#define UVC_CMD_CREATE_SEC_CONF 0x0100 +#define UVC_CMD_DESTROY_SEC_CONF 0x0101 +#define UVC_CMD_CREATE_SEC_CPU 0x0120 +#define UVC_CMD_DESTROY_SEC_CPU 0x0121 +#define UVC_CMD_CONV_TO_SEC_STOR 0x0200 +#define UVC_CMD_CONV_FROM_SEC_STOR 0x0201 +#define UVC_CMD_SET_SEC_CONF_PARAMS 0x0300 +#define UVC_CMD_UNPACK_IMG 0x0301 +#define UVC_CMD_VERIFY_IMG 0x0302 +#define UVC_CMD_CPU_RESET 0x0310 +#define UVC_CMD_CPU_RESET_INITIAL 0x0311 +#define UVC_CMD_PREPARE_RESET 0x0320 +#define UVC_CMD_CPU_RESET_CLEAR 0x0321 +#define UVC_CMD_CPU_SET_STATE 0x0330 +#define UVC_CMD_SET_UNSHARE_ALL 0x0340 +#define UVC_CMD_PIN_PAGE_SHARED 0x0341 +#define UVC_CMD_UNPIN_PAGE_SHARED 0x0342 #define UVC_CMD_SET_SHARED_ACCESS 0x1000 #define UVC_CMD_REMOVE_SHARED_ACCESS 0x1001 /* Bits in installed uv calls */ enum uv_cmds_inst { BIT_UVC_CMD_QUI = 0, + BIT_UVC_CMD_INIT_UV = 1, + BIT_UVC_CMD_CREATE_SEC_CONF = 2, + BIT_UVC_CMD_DESTROY_SEC_CONF = 3, + BIT_UVC_CMD_CREATE_SEC_CPU = 4, + BIT_UVC_CMD_DESTROY_SEC_CPU = 5, + BIT_UVC_CMD_CONV_TO_SEC_STOR = 6, + BIT_UVC_CMD_CONV_FROM_SEC_STOR = 7, BIT_UVC_CMD_SET_SHARED_ACCESS = 8, BIT_UVC_CMD_REMOVE_SHARED_ACCESS = 9, + BIT_UVC_CMD_SET_SEC_PARMS = 11, + BIT_UVC_CMD_UNPACK_IMG = 13, + BIT_UVC_CMD_VERIFY_IMG = 14, + BIT_UVC_CMD_CPU_RESET = 15, + BIT_UVC_CMD_CPU_RESET_INITIAL = 16, + BIT_UVC_CMD_CPU_SET_STATE = 17, + BIT_UVC_CMD_PREPARE_RESET = 18, + BIT_UVC_CMD_CPU_PERFORM_CLEAR_RESET = 19, + BIT_UVC_CMD_UNSHARE_ALL = 20, + BIT_UVC_CMD_PIN_PAGE_SHARED = 21, + BIT_UVC_CMD_UNPIN_PAGE_SHARED = 22, }; struct uv_cb_header { @@ -40,13 +79,127 @@ struct uv_cb_header { u16 rrc; /* Return Reason Code */ } __packed __aligned(8); +/* Query Ultravisor Information */ struct uv_cb_qui { struct uv_cb_header header; u64 reserved08; u64 inst_calls_list[4]; - u64 reserved30[15]; + u64 reserved30[2]; + u64 uv_base_stor_len; + u64 reserved48; + u64 conf_base_phys_stor_len; + u64 conf_base_virt_stor_len; + u64 conf_virt_var_stor_len; + u64 cpu_stor_len; + u32 reserved70[3]; + u32 max_num_sec_conf; + u64 max_guest_stor_addr; + u8 reserved88[158 - 136]; + u16 max_guest_cpus; + u8 reserveda0[200 - 160]; } __packed __aligned(8); +/* Initialize Ultravisor */ +struct uv_cb_init { + struct uv_cb_header header; + u64 reserved08[2]; + u64 stor_origin; + u64 stor_len; + u64 reserved28[4]; +} __packed __aligned(8); + +/* Create Guest Configuration */ +struct uv_cb_cgc { + struct uv_cb_header header; + u64 reserved08[2]; + u64 guest_handle; + u64 conf_base_stor_origin; + u64 conf_virt_stor_origin; + u64 reserved30; + u64 guest_stor_origin; + u64 guest_stor_len; + u64 guest_sca; + u64 guest_asce; + u64 reserved58[5]; +} __packed __aligned(8); + +/* Create Secure CPU */ +struct uv_cb_csc { + struct uv_cb_header header; + u64 reserved08[2]; + u64 cpu_handle; + u64 guest_handle; + u64 stor_origin; + u8 reserved30[6]; + u16 num; + u64 state_origin; + u64 reserved40[4]; +} __packed __aligned(8); + +/* Convert to Secure */ +struct uv_cb_cts { + struct uv_cb_header header; + u64 reserved08[2]; + u64 guest_handle; + u64 gaddr; +} __packed __aligned(8); + +/* Convert from Secure / Pin Page Shared */ +struct uv_cb_cfs { + struct uv_cb_header header; + u64 reserved08[2]; + u64 paddr; +} __packed __aligned(8); + +/* Set Secure Config Parameter */ +struct uv_cb_ssc { + struct uv_cb_header header; + u64 reserved08[2]; + u64 guest_handle; + u64 sec_header_origin; + u32 sec_header_len; + u32 reserved2c; + u64 reserved30[4]; +} __packed __aligned(8); + +/* Unpack */ +struct uv_cb_unp { + struct uv_cb_header header; + u64 reserved08[2]; + u64 guest_handle; + u64 gaddr; + u64 tweak[2]; + u64 reserved38[3]; +} __packed __aligned(8); + +#define PV_CPU_STATE_OPR 1 +#define PV_CPU_STATE_STP 2 +#define PV_CPU_STATE_CHKSTP 3 +#define PV_CPU_STATE_OPR_LOAD 5 + +struct uv_cb_cpu_set_state { + struct uv_cb_header header; + u64 reserved08[2]; + u64 cpu_handle; + u8 reserved20[7]; + u8 state; + u64 reserved28[5]; +}; + +/* + * A common UV call struct for calls that take no payload + * Examples: + * Destroy cpu/config + * Verify + */ +struct uv_cb_nodata { + struct uv_cb_header header; + u64 reserved08[2]; + u64 handle; + u64 reserved20[4]; +} __packed __aligned(8); + +/* Set Shared Access */ struct uv_cb_share { struct uv_cb_header header; u64 reserved08[3]; @@ -54,21 +207,76 @@ struct uv_cb_share { u64 reserved28; } __packed __aligned(8); -static inline int uv_call(unsigned long r1, unsigned long r2) +static inline int __uv_call(unsigned long r1, unsigned long r2) { int cc; asm volatile( - "0: .insn rrf,0xB9A40000,%[r1],%[r2],0,0\n" - " brc 3,0b\n" - " ipm %[cc]\n" - " srl %[cc],28\n" + " .insn rrf,0xB9A40000,%[r1],%[r2],0,0\n" + " ipm %[cc]\n" + " srl %[cc],28\n" : [cc] "=d" (cc) : [r1] "a" (r1), [r2] "a" (r2) : "memory", "cc"); return cc; } +static inline int uv_call(unsigned long r1, unsigned long r2) +{ + int cc; + + do { + cc = __uv_call(r1, r2); + } while (cc > 1); + return cc; +} + +/* Low level uv_call that avoids stalls for long running busy conditions */ +static inline int uv_call_sched(unsigned long r1, unsigned long r2) +{ + int cc; + + do { + cc = __uv_call(r1, r2); + cond_resched(); + } while (cc > 1); + return cc; +} + +/* + * special variant of uv_call that only transports the cpu or guest + * handle and the command, like destroy or verify. + */ +static inline int uv_cmd_nodata(u64 handle, u16 cmd, u16 *rc, u16 *rrc) +{ + struct uv_cb_nodata uvcb = { + .header.cmd = cmd, + .header.len = sizeof(uvcb), + .handle = handle, + }; + int cc; + + WARN(!handle, "No handle provided to Ultravisor call cmd %x\n", cmd); + cc = uv_call_sched(0, (u64)&uvcb); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + return cc ? -EINVAL : 0; +} + +struct uv_info { + unsigned long inst_calls_list[4]; + unsigned long uv_base_stor_len; + unsigned long guest_base_stor_len; + unsigned long guest_virt_base_stor_len; + unsigned long guest_virt_var_stor_len; + unsigned long guest_cpu_stor_len; + unsigned long max_sec_stor_addr; + unsigned int max_num_sec_conf; + unsigned short max_guest_cpus; +}; + +extern struct uv_info uv_info; + #ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST extern int prot_virt_guest; @@ -121,11 +329,40 @@ static inline int uv_remove_shared(unsigned long addr) return share(addr, UVC_CMD_REMOVE_SHARED_ACCESS); } -void uv_query_info(void); #else #define is_prot_virt_guest() 0 static inline int uv_set_shared(unsigned long addr) { return 0; } static inline int uv_remove_shared(unsigned long addr) { return 0; } +#endif + +#if IS_ENABLED(CONFIG_KVM) +extern int prot_virt_host; + +static inline int is_prot_virt_host(void) +{ + return prot_virt_host; +} + +int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb); +int uv_convert_from_secure(unsigned long paddr); +int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr); + +void setup_uv(void); +void adjust_to_uv_max(unsigned long *vmax); +#else +#define is_prot_virt_host() 0 +static inline void setup_uv(void) {} +static inline void adjust_to_uv_max(unsigned long *vmax) {} + +static inline int uv_convert_from_secure(unsigned long paddr) +{ + return 0; +} +#endif + +#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || IS_ENABLED(CONFIG_KVM) +void uv_query_info(void); +#else static inline void uv_query_info(void) {} #endif diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 578a6fa82ea4..33d4de233c5b 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -78,6 +78,7 @@ obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_events.o perf_regs.o obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_diag.o obj-$(CONFIG_TRACEPOINTS) += trace.o +obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o # vdso obj-y += vdso64/ diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 1d3927e01a5f..faca269d5f27 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -24,6 +24,8 @@ asmlinkage void do_syscall_trace_exit(struct pt_regs *regs); void do_protection_exception(struct pt_regs *regs); void do_dat_exception(struct pt_regs *regs); +void do_secure_storage_access(struct pt_regs *regs); +void do_non_secure_storage_access(struct pt_regs *regs); void addressing_exception(struct pt_regs *regs); void data_exception(struct pt_regs *regs); diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S index eee3a482195a..2c27907a5ffc 100644 --- a/arch/s390/kernel/pgm_check.S +++ b/arch/s390/kernel/pgm_check.S @@ -78,8 +78,8 @@ PGM_CHECK(do_dat_exception) /* 39 */ PGM_CHECK(do_dat_exception) /* 3a */ PGM_CHECK(do_dat_exception) /* 3b */ PGM_CHECK_DEFAULT /* 3c */ -PGM_CHECK_DEFAULT /* 3d */ -PGM_CHECK_DEFAULT /* 3e */ +PGM_CHECK(do_secure_storage_access) /* 3d */ +PGM_CHECK(do_non_secure_storage_access) /* 3e */ PGM_CHECK_DEFAULT /* 3f */ PGM_CHECK(monitor_event_exception) /* 40 */ PGM_CHECK_DEFAULT /* 41 */ diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index b2c2f75860e8..1423090a2259 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -92,10 +92,6 @@ char elf_platform[ELF_PLATFORM_SIZE]; unsigned long int_hwcap = 0; -#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST -int __bootdata_preserved(prot_virt_guest); -#endif - int __bootdata(noexec_disabled); int __bootdata(memory_end_set); unsigned long __bootdata(memory_end); @@ -564,6 +560,9 @@ static void __init setup_memory_end(void) vmax = _REGION1_SIZE; /* 4-level kernel page table */ } + if (is_prot_virt_host()) + adjust_to_uv_max(&vmax); + /* module area is at the end of the kernel address space. */ MODULES_END = vmax; MODULES_VADDR = MODULES_END - MODULES_LEN; @@ -1138,6 +1137,8 @@ void __init setup_arch(char **cmdline_p) */ memblock_trim_memory(1UL << (MAX_ORDER - 1 + PAGE_SHIFT)); + if (is_prot_virt_host()) + setup_uv(); setup_memory_end(); setup_memory(); dma_contiguous_reserve(memory_end); diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c new file mode 100644 index 000000000000..c86d654351d1 --- /dev/null +++ b/arch/s390/kernel/uv.c @@ -0,0 +1,414 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Common Ultravisor functions and initialization + * + * Copyright IBM Corp. 2019, 2020 + */ +#define KMSG_COMPONENT "prot_virt" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/sizes.h> +#include <linux/bitmap.h> +#include <linux/memblock.h> +#include <linux/pagemap.h> +#include <linux/swap.h> +#include <asm/facility.h> +#include <asm/sections.h> +#include <asm/uv.h> + +/* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */ +#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST +int __bootdata_preserved(prot_virt_guest); +#endif + +#if IS_ENABLED(CONFIG_KVM) +int prot_virt_host; +EXPORT_SYMBOL(prot_virt_host); +struct uv_info __bootdata_preserved(uv_info); +EXPORT_SYMBOL(uv_info); + +static int __init prot_virt_setup(char *val) +{ + bool enabled; + int rc; + + rc = kstrtobool(val, &enabled); + if (!rc && enabled) + prot_virt_host = 1; + + if (is_prot_virt_guest() && prot_virt_host) { + prot_virt_host = 0; + pr_warn("Protected virtualization not available in protected guests."); + } + + if (prot_virt_host && !test_facility(158)) { + prot_virt_host = 0; + pr_warn("Protected virtualization not supported by the hardware."); + } + + return rc; +} +early_param("prot_virt", prot_virt_setup); + +static int __init uv_init(unsigned long stor_base, unsigned long stor_len) +{ + struct uv_cb_init uvcb = { + .header.cmd = UVC_CMD_INIT_UV, + .header.len = sizeof(uvcb), + .stor_origin = stor_base, + .stor_len = stor_len, + }; + + if (uv_call(0, (uint64_t)&uvcb)) { + pr_err("Ultravisor init failed with rc: 0x%x rrc: 0%x\n", + uvcb.header.rc, uvcb.header.rrc); + return -1; + } + return 0; +} + +void __init setup_uv(void) +{ + unsigned long uv_stor_base; + + uv_stor_base = (unsigned long)memblock_alloc_try_nid( + uv_info.uv_base_stor_len, SZ_1M, SZ_2G, + MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); + if (!uv_stor_base) { + pr_warn("Failed to reserve %lu bytes for ultravisor base storage\n", + uv_info.uv_base_stor_len); + goto fail; + } + + if (uv_init(uv_stor_base, uv_info.uv_base_stor_len)) { + memblock_free(uv_stor_base, uv_info.uv_base_stor_len); + goto fail; + } + + pr_info("Reserving %luMB as ultravisor base storage\n", + uv_info.uv_base_stor_len >> 20); + return; +fail: + pr_info("Disabling support for protected virtualization"); + prot_virt_host = 0; +} + +void adjust_to_uv_max(unsigned long *vmax) +{ + *vmax = min_t(unsigned long, *vmax, uv_info.max_sec_stor_addr); +} + +/* + * Requests the Ultravisor to pin the page in the shared state. This will + * cause an intercept when the guest attempts to unshare the pinned page. + */ +static int uv_pin_shared(unsigned long paddr) +{ + struct uv_cb_cfs uvcb = { + .header.cmd = UVC_CMD_PIN_PAGE_SHARED, + .header.len = sizeof(uvcb), + .paddr = paddr, + }; + + if (uv_call(0, (u64)&uvcb)) + return -EINVAL; + return 0; +} + +/* + * Requests the Ultravisor to encrypt a guest page and make it + * accessible to the host for paging (export). + * + * @paddr: Absolute host address of page to be exported + */ +int uv_convert_from_secure(unsigned long paddr) +{ + struct uv_cb_cfs uvcb = { + .header.cmd = UVC_CMD_CONV_FROM_SEC_STOR, + .header.len = sizeof(uvcb), + .paddr = paddr + }; + + if (uv_call(0, (u64)&uvcb)) + return -EINVAL; + return 0; +} + +/* + * Calculate the expected ref_count for a page that would otherwise have no + * further pins. This was cribbed from similar functions in other places in + * the kernel, but with some slight modifications. We know that a secure + * page can not be a huge page for example. + */ +static int expected_page_refs(struct page *page) +{ + int res; + + res = page_mapcount(page); + if (PageSwapCache(page)) { + res++; + } else if (page_mapping(page)) { + res++; + if (page_has_private(page)) + res++; + } + return res; +} + +static int make_secure_pte(pte_t *ptep, unsigned long addr, + struct page *exp_page, struct uv_cb_header *uvcb) +{ + pte_t entry = READ_ONCE(*ptep); + struct page *page; + int expected, rc = 0; + + if (!pte_present(entry)) + return -ENXIO; + if (pte_val(entry) & _PAGE_INVALID) + return -ENXIO; + + page = pte_page(entry); + if (page != exp_page) + return -ENXIO; + if (PageWriteback(page)) + return -EAGAIN; + expected = expected_page_refs(page); + if (!page_ref_freeze(page, expected)) + return -EBUSY; + set_bit(PG_arch_1, &page->flags); + rc = uv_call(0, (u64)uvcb); + page_ref_unfreeze(page, expected); + /* Return -ENXIO if the page was not mapped, -EINVAL otherwise */ + if (rc) + rc = uvcb->rc == 0x10a ? -ENXIO : -EINVAL; + return rc; +} + +/* + * Requests the Ultravisor to make a page accessible to a guest. + * If it's brought in the first time, it will be cleared. If + * it has been exported before, it will be decrypted and integrity + * checked. + */ +int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) +{ + struct vm_area_struct *vma; + bool local_drain = false; + spinlock_t *ptelock; + unsigned long uaddr; + struct page *page; + pte_t *ptep; + int rc; + +again: + rc = -EFAULT; + down_read(&gmap->mm->mmap_sem); + + uaddr = __gmap_translate(gmap, gaddr); + if (IS_ERR_VALUE(uaddr)) + goto out; + vma = find_vma(gmap->mm, uaddr); + if (!vma) + goto out; + /* + * Secure pages cannot be huge and userspace should not combine both. + * In case userspace does it anyway this will result in an -EFAULT for + * the unpack. The guest is thus never reaching secure mode. If + * userspace is playing dirty tricky with mapping huge pages later + * on this will result in a segmentation fault. + */ + if (is_vm_hugetlb_page(vma)) + goto out; + + rc = -ENXIO; + page = follow_page(vma, uaddr, FOLL_WRITE); + if (IS_ERR_OR_NULL(page)) + goto out; + + lock_page(page); + ptep = get_locked_pte(gmap->mm, uaddr, &ptelock); + rc = make_secure_pte(ptep, uaddr, page, uvcb); + pte_unmap_unlock(ptep, ptelock); + unlock_page(page); +out: + up_read(&gmap->mm->mmap_sem); + + if (rc == -EAGAIN) { + wait_on_page_writeback(page); + } else if (rc == -EBUSY) { + /* + * If we have tried a local drain and the page refcount + * still does not match our expected safe value, try with a + * system wide drain. This is needed if the pagevecs holding + * the page are on a different CPU. + */ + if (local_drain) { + lru_add_drain_all(); + /* We give up here, and let the caller try again */ + return -EAGAIN; + } + /* + * We are here if the page refcount does not match the + * expected safe value. The main culprits are usually + * pagevecs. With lru_add_drain() we drain the pagevecs + * on the local CPU so that hopefully the refcount will + * reach the expected safe value. + */ + lru_add_drain(); + local_drain = true; + /* And now we try again immediately after draining */ + goto again; + } else if (rc == -ENXIO) { + if (gmap_fault(gmap, gaddr, FAULT_FLAG_WRITE)) + return -EFAULT; + return -EAGAIN; + } + return rc; +} +EXPORT_SYMBOL_GPL(gmap_make_secure); + +int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr) +{ + struct uv_cb_cts uvcb = { + .header.cmd = UVC_CMD_CONV_TO_SEC_STOR, + .header.len = sizeof(uvcb), + .guest_handle = gmap->guest_handle, + .gaddr = gaddr, + }; + + return gmap_make_secure(gmap, gaddr, &uvcb); +} +EXPORT_SYMBOL_GPL(gmap_convert_to_secure); + +/* + * To be called with the page locked or with an extra reference! This will + * prevent gmap_make_secure from touching the page concurrently. Having 2 + * parallel make_page_accessible is fine, as the UV calls will become a + * no-op if the page is already exported. + */ +int arch_make_page_accessible(struct page *page) +{ + int rc = 0; + + /* Hugepage cannot be protected, so nothing to do */ + if (PageHuge(page)) + return 0; + + /* + * PG_arch_1 is used in 3 places: + * 1. for kernel page tables during early boot + * 2. for storage keys of huge pages and KVM + * 3. As an indication that this page might be secure. This can + * overindicate, e.g. we set the bit before calling + * convert_to_secure. + * As secure pages are never huge, all 3 variants can co-exists. + */ + if (!test_bit(PG_arch_1, &page->flags)) + return 0; + + rc = uv_pin_shared(page_to_phys(page)); + if (!rc) { + clear_bit(PG_arch_1, &page->flags); + return 0; + } + + rc = uv_convert_from_secure(page_to_phys(page)); + if (!rc) { + clear_bit(PG_arch_1, &page->flags); + return 0; + } + + return rc; +} +EXPORT_SYMBOL_GPL(arch_make_page_accessible); + +#endif + +#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || IS_ENABLED(CONFIG_KVM) +static ssize_t uv_query_facilities(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return snprintf(page, PAGE_SIZE, "%lx\n%lx\n%lx\n%lx\n", + uv_info.inst_calls_list[0], + uv_info.inst_calls_list[1], + uv_info.inst_calls_list[2], + uv_info.inst_calls_list[3]); +} + +static struct kobj_attribute uv_query_facilities_attr = + __ATTR(facilities, 0444, uv_query_facilities, NULL); + +static ssize_t uv_query_max_guest_cpus(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return snprintf(page, PAGE_SIZE, "%d\n", + uv_info.max_guest_cpus); +} + +static struct kobj_attribute uv_query_max_guest_cpus_attr = + __ATTR(max_cpus, 0444, uv_query_max_guest_cpus, NULL); + +static ssize_t uv_query_max_guest_vms(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return snprintf(page, PAGE_SIZE, "%d\n", + uv_info.max_num_sec_conf); +} + +static struct kobj_attribute uv_query_max_guest_vms_attr = + __ATTR(max_guests, 0444, uv_query_max_guest_vms, NULL); + +static ssize_t uv_query_max_guest_addr(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return snprintf(page, PAGE_SIZE, "%lx\n", + uv_info.max_sec_stor_addr); +} + +static struct kobj_attribute uv_query_max_guest_addr_attr = + __ATTR(max_address, 0444, uv_query_max_guest_addr, NULL); + +static struct attribute *uv_query_attrs[] = { + &uv_query_facilities_attr.attr, + &uv_query_max_guest_cpus_attr.attr, + &uv_query_max_guest_vms_attr.attr, + &uv_query_max_guest_addr_attr.attr, + NULL, +}; + +static struct attribute_group uv_query_attr_group = { + .attrs = uv_query_attrs, +}; + +static struct kset *uv_query_kset; +static struct kobject *uv_kobj; + +static int __init uv_info_init(void) +{ + int rc = -ENOMEM; + + if (!test_facility(158)) + return 0; + + uv_kobj = kobject_create_and_add("uv", firmware_kobj); + if (!uv_kobj) + return -ENOMEM; + + uv_query_kset = kset_create_and_add("query", NULL, uv_kobj); + if (!uv_query_kset) + goto out_kobj; + + rc = sysfs_create_group(&uv_query_kset->kobj, &uv_query_attr_group); + if (!rc) + return 0; + + kset_unregister(uv_query_kset); +out_kobj: + kobject_del(uv_kobj); + kobject_put(uv_kobj); + return rc; +} +device_initcall(uv_info_init); +#endif diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 05ee90a5ea08..12decca22e7c 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -9,6 +9,6 @@ common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqch ccflags-y := -Ivirt/kvm -Iarch/s390/kvm kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o -kvm-objs += diag.o gaccess.o guestdbg.o vsie.o +kvm-objs += diag.o gaccess.o guestdbg.o vsie.o pv.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 3fb54ec2cf3e..563429dece03 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -2,7 +2,7 @@ /* * handling diagnose instructions * - * Copyright IBM Corp. 2008, 2011 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -201,6 +201,10 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; } + /* + * no need to check the return value of vcpu_stop as it can only have + * an error for protvirt, but protvirt means user cpu state + */ if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) kvm_s390_vcpu_stop(vcpu); vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM; diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 07d30ffcfa41..47a67a958107 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -505,7 +505,7 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, switch (prot) { case PROT_TYPE_IEP: tec->b61 = 1; - /* FALL THROUGH */ + fallthrough; case PROT_TYPE_LA: tec->b56 = 1; break; @@ -514,12 +514,12 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, break; case PROT_TYPE_ALC: tec->b60 = 1; - /* FALL THROUGH */ + fallthrough; case PROT_TYPE_DAT: tec->b61 = 1; break; } - /* FALL THROUGH */ + fallthrough; case PGM_ASCE_TYPE: case PGM_PAGE_TRANSLATION: case PGM_REGION_FIRST_TRANS: @@ -534,7 +534,7 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, tec->addr = gva >> PAGE_SHIFT; tec->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH; tec->as = psw_bits(vcpu->arch.sie_block->gpsw).as; - /* FALL THROUGH */ + fallthrough; case PGM_ALEN_TRANSLATION: case PGM_ALE_SEQUENCE: case PGM_ASTE_VALIDITY: @@ -677,7 +677,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, dat_protection |= rfte.p; ptr = rfte.rto * PAGE_SIZE + vaddr.rsx * 8; } - /* fallthrough */ + fallthrough; case ASCE_TYPE_REGION2: { union region2_table_entry rste; @@ -695,7 +695,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, dat_protection |= rste.p; ptr = rste.rto * PAGE_SIZE + vaddr.rtx * 8; } - /* fallthrough */ + fallthrough; case ASCE_TYPE_REGION3: { union region3_table_entry rtte; @@ -723,7 +723,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, dat_protection |= rtte.fc0.p; ptr = rtte.fc0.sto * PAGE_SIZE + vaddr.sx * 8; } - /* fallthrough */ + fallthrough; case ASCE_TYPE_SEGMENT: { union segment_table_entry ste; @@ -1050,7 +1050,8 @@ shadow_r2t: rc = gmap_shadow_r2t(sg, saddr, rfte.val, *fake); if (rc) return rc; - } /* fallthrough */ + } + fallthrough; case ASCE_TYPE_REGION2: { union region2_table_entry rste; @@ -1076,7 +1077,8 @@ shadow_r3t: rc = gmap_shadow_r3t(sg, saddr, rste.val, *fake); if (rc) return rc; - } /* fallthrough */ + } + fallthrough; case ASCE_TYPE_REGION3: { union region3_table_entry rtte; @@ -1111,7 +1113,8 @@ shadow_sgt: rc = gmap_shadow_sgt(sg, saddr, rtte.val, *fake); if (rc) return rc; - } /* fallthrough */ + } + fallthrough; case ASCE_TYPE_SEGMENT: { union segment_table_entry ste; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index a389fa85cca2..e7a7c499a73f 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -2,7 +2,7 @@ /* * in-kernel handling for sie intercepts * - * Copyright IBM Corp. 2008, 2014 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -12,10 +12,10 @@ #include <linux/errno.h> #include <linux/pagemap.h> -#include <asm/kvm_host.h> #include <asm/asm-offsets.h> #include <asm/irq.h> #include <asm/sysinfo.h> +#include <asm/uv.h> #include "kvm-s390.h" #include "gaccess.h" @@ -79,6 +79,10 @@ static int handle_stop(struct kvm_vcpu *vcpu) return rc; } + /* + * no need to check the return value of vcpu_stop as it can only have + * an error for protvirt, but protvirt means user cpu state + */ if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) kvm_s390_vcpu_stop(vcpu); return -EOPNOTSUPP; @@ -231,6 +235,13 @@ static int handle_prog(struct kvm_vcpu *vcpu) vcpu->stat.exit_program_interruption++; + /* + * Intercept 8 indicates a loop of specification exceptions + * for protected guests. + */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) + return -EOPNOTSUPP; + if (guestdbg_enabled(vcpu) && per_event(vcpu)) { rc = kvm_s390_handle_per_event(vcpu); if (rc) @@ -384,7 +395,7 @@ int handle_sthyi(struct kvm_vcpu *vcpu) goto out; } - if (addr & ~PAGE_MASK) + if (!kvm_s390_pv_cpu_is_protected(vcpu) && (addr & ~PAGE_MASK)) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); sctns = (void *)get_zeroed_page(GFP_KERNEL); @@ -395,10 +406,15 @@ int handle_sthyi(struct kvm_vcpu *vcpu) out: if (!cc) { - r = write_guest(vcpu, addr, reg2, sctns, PAGE_SIZE); - if (r) { - free_page((unsigned long)sctns); - return kvm_s390_inject_prog_cond(vcpu, r); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy((void *)(sida_origin(vcpu->arch.sie_block)), + sctns, PAGE_SIZE); + } else { + r = write_guest(vcpu, addr, reg2, sctns, PAGE_SIZE); + if (r) { + free_page((unsigned long)sctns); + return kvm_s390_inject_prog_cond(vcpu, r); + } } } @@ -444,6 +460,77 @@ static int handle_operexc(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); } +static int handle_pv_spx(struct kvm_vcpu *vcpu) +{ + u32 pref = *(u32 *)vcpu->arch.sie_block->sidad; + + kvm_s390_set_prefix(vcpu, pref); + trace_kvm_s390_handle_prefix(vcpu, 1, pref); + return 0; +} + +static int handle_pv_sclp(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + + spin_lock(&fi->lock); + /* + * 2 cases: + * a: an sccb answering interrupt was already pending or in flight. + * As the sccb value is not known we can simply set some value to + * trigger delivery of a saved SCCB. UV will then use its saved + * copy of the SCCB value. + * b: an error SCCB interrupt needs to be injected so we also inject + * a fake SCCB address. Firmware will use the proper one. + * This makes sure, that both errors and real sccb returns will only + * be delivered after a notification intercept (instruction has + * finished) but not after others. + */ + fi->srv_signal.ext_params |= 0x43000; + set_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); + clear_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs); + spin_unlock(&fi->lock); + return 0; +} + +static int handle_pv_uvc(struct kvm_vcpu *vcpu) +{ + struct uv_cb_share *guest_uvcb = (void *)vcpu->arch.sie_block->sidad; + struct uv_cb_cts uvcb = { + .header.cmd = UVC_CMD_UNPIN_PAGE_SHARED, + .header.len = sizeof(uvcb), + .guest_handle = kvm_s390_pv_get_handle(vcpu->kvm), + .gaddr = guest_uvcb->paddr, + }; + int rc; + + if (guest_uvcb->header.cmd != UVC_CMD_REMOVE_SHARED_ACCESS) { + WARN_ONCE(1, "Unexpected notification intercept for UVC 0x%x\n", + guest_uvcb->header.cmd); + return 0; + } + rc = gmap_make_secure(vcpu->arch.gmap, uvcb.gaddr, &uvcb); + /* + * If the unpin did not succeed, the guest will exit again for the UVC + * and we will retry the unpin. + */ + if (rc == -EINVAL) + return 0; + return rc; +} + +static int handle_pv_notification(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.sie_block->ipa == 0xb210) + return handle_pv_spx(vcpu); + if (vcpu->arch.sie_block->ipa == 0xb220) + return handle_pv_sclp(vcpu); + if (vcpu->arch.sie_block->ipa == 0xb9a4) + return handle_pv_uvc(vcpu); + + return handle_instruction(vcpu); +} + int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu) { int rc, per_rc = 0; @@ -480,6 +567,28 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu) case ICPT_KSS: rc = kvm_s390_skey_check_enable(vcpu); break; + case ICPT_MCHKREQ: + case ICPT_INT_ENABLE: + /* + * PSW bit 13 or a CR (0, 6, 14) changed and we might + * now be able to deliver interrupts. The pre-run code + * will take care of this. + */ + rc = 0; + break; + case ICPT_PV_INSTR: + rc = handle_instruction(vcpu); + break; + case ICPT_PV_NOTIFY: + rc = handle_pv_notification(vcpu); + break; + case ICPT_PV_PREF: + rc = 0; + gmap_convert_to_secure(vcpu->arch.gmap, + kvm_s390_get_prefix(vcpu)); + gmap_convert_to_secure(vcpu->arch.gmap, + kvm_s390_get_prefix(vcpu) + PAGE_SIZE); + break; default: return -EOPNOTSUPP; } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c06c89d370a7..8191106bf7b9 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2,7 +2,7 @@ /* * handling kvm guest interrupts * - * Copyright IBM Corp. 2008, 2015 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> */ @@ -324,8 +324,11 @@ static inline int gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) static inline unsigned long pending_irqs_no_gisa(struct kvm_vcpu *vcpu) { - return vcpu->kvm->arch.float_int.pending_irqs | - vcpu->arch.local_int.pending_irqs; + unsigned long pending = vcpu->kvm->arch.float_int.pending_irqs | + vcpu->arch.local_int.pending_irqs; + + pending &= ~vcpu->kvm->arch.float_int.masked_irqs; + return pending; } static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu) @@ -383,10 +386,18 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) __clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask); if (!(vcpu->arch.sie_block->gcr[0] & CR0_CPU_TIMER_SUBMASK)) __clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask); - if (!(vcpu->arch.sie_block->gcr[0] & CR0_SERVICE_SIGNAL_SUBMASK)) + if (!(vcpu->arch.sie_block->gcr[0] & CR0_SERVICE_SIGNAL_SUBMASK)) { __clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask); + __clear_bit(IRQ_PEND_EXT_SERVICE_EV, &active_mask); + } if (psw_mchk_disabled(vcpu)) active_mask &= ~IRQ_PEND_MCHK_MASK; + /* PV guest cpus can have a single interruption injected at a time. */ + if (kvm_s390_pv_cpu_is_protected(vcpu) && + vcpu->arch.sie_block->iictl != IICTL_CODE_NONE) + active_mask &= ~(IRQ_PEND_EXT_II_MASK | + IRQ_PEND_IO_MASK | + IRQ_PEND_MCHK_MASK); /* * Check both floating and local interrupt's cr14 because * bit IRQ_PEND_MCHK_REP could be set in both cases. @@ -479,19 +490,23 @@ static void set_intercept_indicators(struct kvm_vcpu *vcpu) static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - int rc; + int rc = 0; vcpu->stat.deliver_cputm++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER, 0, 0); - - rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER, - (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_CPU_TIMER; + } else { + rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + } clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); return rc ? -EFAULT : 0; } @@ -499,19 +514,23 @@ static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu) static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - int rc; + int rc = 0; vcpu->stat.deliver_ckc++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP, 0, 0); - - rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP, - (u16 __user *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_CLK_COMP; + } else { + rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP, + (u16 __user *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + } clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); return rc ? -EFAULT : 0; } @@ -553,6 +572,20 @@ static int __write_machine_check(struct kvm_vcpu *vcpu, union mci mci; int rc; + /* + * All other possible payload for a machine check (e.g. the register + * contents in the save area) will be handled by the ultravisor, as + * the hypervisor does not not have the needed information for + * protected guests. + */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_MCHK; + vcpu->arch.sie_block->mcic = mchk->mcic; + vcpu->arch.sie_block->faddr = mchk->failing_storage_address; + vcpu->arch.sie_block->edc = mchk->ext_damage_code; + return 0; + } + mci.val = mchk->mcic; /* take care of lazy register loading */ save_fpu_regs(); @@ -696,17 +729,21 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu) static int __must_check __deliver_restart(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - int rc; + int rc = 0; VCPU_EVENT(vcpu, 3, "%s", "deliver: cpu restart"); vcpu->stat.deliver_restart_signal++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0); - rc = write_guest_lc(vcpu, - offsetof(struct lowcore, restart_old_psw), - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw), - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_RESTART; + } else { + rc = write_guest_lc(vcpu, + offsetof(struct lowcore, restart_old_psw), + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw), + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + } clear_bit(IRQ_PEND_RESTART, &li->pending_irqs); return rc ? -EFAULT : 0; } @@ -748,6 +785,12 @@ static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu) vcpu->stat.deliver_emergency_signal++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY, cpu_addr, 0); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_EMERGENCY_SIG; + vcpu->arch.sie_block->extcpuaddr = cpu_addr; + return 0; + } rc = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG, (u16 *)__LC_EXT_INT_CODE); @@ -776,6 +819,12 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu) trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL, extcall.code, 0); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_EXTERNAL_CALL; + vcpu->arch.sie_block->extcpuaddr = extcall.code; + return 0; + } rc = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL, (u16 *)__LC_EXT_INT_CODE); @@ -787,6 +836,21 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } +static int __deliver_prog_pv(struct kvm_vcpu *vcpu, u16 code) +{ + switch (code) { + case PGM_SPECIFICATION: + vcpu->arch.sie_block->iictl = IICTL_CODE_SPECIFICATION; + break; + case PGM_OPERAND: + vcpu->arch.sie_block->iictl = IICTL_CODE_OPERAND; + break; + default: + return -EINVAL; + } + return 0; +} + static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; @@ -807,6 +871,10 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, pgm_info.code, 0); + /* PER is handled by the ultravisor */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) + return __deliver_prog_pv(vcpu, pgm_info.code & ~PGM_PER); + switch (pgm_info.code & ~PGM_PER) { case PGM_AFX_TRANSLATION: case PGM_ASX_TRANSLATION: @@ -818,7 +886,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) case PGM_PRIMARY_AUTHORITY: case PGM_SECONDARY_AUTHORITY: nullifying = true; - /* fall through */ + fallthrough; case PGM_SPACE_SWITCH: rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, (u64 *)__LC_TRANS_EXC_CODE); @@ -902,20 +970,49 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } +#define SCCB_MASK 0xFFFFFFF8 +#define SCCB_EVENT_PENDING 0x3 + +static int write_sclp(struct kvm_vcpu *vcpu, u32 parm) +{ + int rc; + + if (kvm_s390_pv_cpu_get_handle(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_SERVICE_SIG; + vcpu->arch.sie_block->eiparams = parm; + return 0; + } + + rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, parm, + (u32 *)__LC_EXT_PARAMS); + + return rc ? -EFAULT : 0; +} + static int __must_check __deliver_service(struct kvm_vcpu *vcpu) { struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; struct kvm_s390_ext_info ext; - int rc = 0; spin_lock(&fi->lock); - if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) { + if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs) || + !(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) { spin_unlock(&fi->lock); return 0; } ext = fi->srv_signal; memset(&fi->srv_signal, 0, sizeof(ext)); clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); + clear_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs); + if (kvm_s390_pv_cpu_is_protected(vcpu)) + set_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs); spin_unlock(&fi->lock); VCPU_EVENT(vcpu, 4, "deliver: sclp parameter 0x%x", @@ -924,16 +1021,31 @@ static int __must_check __deliver_service(struct kvm_vcpu *vcpu) trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE, ext.ext_params, 0); - rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, ext.ext_params, - (u32 *)__LC_EXT_PARAMS); + return write_sclp(vcpu, ext.ext_params); +} - return rc ? -EFAULT : 0; +static int __must_check __deliver_service_ev(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_ext_info ext; + + spin_lock(&fi->lock); + if (!(test_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs))) { + spin_unlock(&fi->lock); + return 0; + } + ext = fi->srv_signal; + /* only clear the event bit */ + fi->srv_signal.ext_params &= ~SCCB_EVENT_PENDING; + clear_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs); + spin_unlock(&fi->lock); + + VCPU_EVENT(vcpu, 4, "%s", "deliver: sclp parameter event"); + vcpu->stat.deliver_service_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE, + ext.ext_params, 0); + + return write_sclp(vcpu, SCCB_EVENT_PENDING); } static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu) @@ -1028,6 +1140,15 @@ static int __do_deliver_io(struct kvm_vcpu *vcpu, struct kvm_s390_io_info *io) { int rc; + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_IO; + vcpu->arch.sie_block->subchannel_id = io->subchannel_id; + vcpu->arch.sie_block->subchannel_nr = io->subchannel_nr; + vcpu->arch.sie_block->io_int_parm = io->io_int_parm; + vcpu->arch.sie_block->io_int_word = io->io_int_word; + return 0; + } + rc = put_guest_lc(vcpu, io->subchannel_id, (u16 *)__LC_SUBCHANNEL_ID); rc |= put_guest_lc(vcpu, io->subchannel_nr, (u16 *)__LC_SUBCHANNEL_NR); rc |= put_guest_lc(vcpu, io->io_int_parm, (u32 *)__LC_IO_INT_PARM); @@ -1329,6 +1450,9 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) case IRQ_PEND_EXT_SERVICE: rc = __deliver_service(vcpu); break; + case IRQ_PEND_EXT_SERVICE_EV: + rc = __deliver_service_ev(vcpu); + break; case IRQ_PEND_PFAULT_DONE: rc = __deliver_pfault_done(vcpu); break; @@ -1421,7 +1545,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL) return -EINVAL; - if (sclp.has_sigpif) + if (sclp.has_sigpif && !kvm_s390_pv_cpu_get_handle(vcpu)) return sca_inject_ext_call(vcpu, src_id); if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs)) @@ -1681,9 +1805,6 @@ out: return inti; } -#define SCCB_MASK 0xFFFFFFF8 -#define SCCB_EVENT_PENDING 0x3 - static int __inject_service(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { @@ -1692,6 +1813,11 @@ static int __inject_service(struct kvm *kvm, kvm->stat.inject_service_signal++; spin_lock(&fi->lock); fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING; + + /* We always allow events, track them separately from the sccb ints */ + if (fi->srv_signal.ext_params & SCCB_EVENT_PENDING) + set_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs); + /* * Early versions of the QEMU s390 bios will inject several * service interrupts after another without handling a @@ -1773,7 +1899,14 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) kvm->stat.inject_io++; isc = int_word_to_isc(inti->io.io_int_word); - if (gi->origin && inti->type & KVM_S390_INT_IO_AI_MASK) { + /* + * Do not make use of gisa in protected mode. We do not use the lock + * checking variant as this is just a performance optimization and we + * do not hold the lock here. This is ok as the code will pick + * interrupts from both "lists" for delivery. + */ + if (!kvm_s390_pv_get_handle(kvm) && + gi->origin && inti->type & KVM_S390_INT_IO_AI_MASK) { VM_EVENT(kvm, 4, "%s isc %1u", "inject: I/O (AI/gisa)", isc); gisa_set_ipm_gisc(gi->origin, isc); kfree(inti); @@ -1834,7 +1967,8 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type) break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: if (!(type & KVM_S390_INT_IO_AI_MASK && - kvm->arch.gisa_int.origin)) + kvm->arch.gisa_int.origin) || + kvm_s390_pv_cpu_get_handle(dst_vcpu)) kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT); break; default: @@ -2080,6 +2214,10 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm) struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; int i; + mutex_lock(&kvm->lock); + if (!kvm_s390_pv_is_protected(kvm)) + fi->masked_irqs = 0; + mutex_unlock(&kvm->lock); spin_lock(&fi->lock); fi->pending_irqs = 0; memset(&fi->srv_signal, 0, sizeof(fi->srv_signal)); @@ -2146,7 +2284,8 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) n++; } } - if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs)) { + if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs) || + test_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs)) { if (n == max_irqs) { /* signal userspace to try again */ ret = -ENOMEM; @@ -2327,9 +2466,6 @@ static int register_io_adapter(struct kvm_device *dev, if (!adapter) return -ENOMEM; - INIT_LIST_HEAD(&adapter->maps); - init_rwsem(&adapter->maps_lock); - atomic_set(&adapter->nr_maps, 0); adapter->id = adapter_info.id; adapter->isc = adapter_info.isc; adapter->maskable = adapter_info.maskable; @@ -2354,87 +2490,12 @@ int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked) return ret; } -static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr) -{ - struct s390_io_adapter *adapter = get_io_adapter(kvm, id); - struct s390_map_info *map; - int ret; - - if (!adapter || !addr) - return -EINVAL; - - map = kzalloc(sizeof(*map), GFP_KERNEL); - if (!map) { - ret = -ENOMEM; - goto out; - } - INIT_LIST_HEAD(&map->list); - map->guest_addr = addr; - map->addr = gmap_translate(kvm->arch.gmap, addr); - if (map->addr == -EFAULT) { - ret = -EFAULT; - goto out; - } - ret = get_user_pages_fast(map->addr, 1, FOLL_WRITE, &map->page); - if (ret < 0) - goto out; - BUG_ON(ret != 1); - down_write(&adapter->maps_lock); - if (atomic_inc_return(&adapter->nr_maps) < MAX_S390_ADAPTER_MAPS) { - list_add_tail(&map->list, &adapter->maps); - ret = 0; - } else { - put_page(map->page); - ret = -EINVAL; - } - up_write(&adapter->maps_lock); -out: - if (ret) - kfree(map); - return ret; -} - -static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr) -{ - struct s390_io_adapter *adapter = get_io_adapter(kvm, id); - struct s390_map_info *map, *tmp; - int found = 0; - - if (!adapter || !addr) - return -EINVAL; - - down_write(&adapter->maps_lock); - list_for_each_entry_safe(map, tmp, &adapter->maps, list) { - if (map->guest_addr == addr) { - found = 1; - atomic_dec(&adapter->nr_maps); - list_del(&map->list); - put_page(map->page); - kfree(map); - break; - } - } - up_write(&adapter->maps_lock); - - return found ? 0 : -EINVAL; -} - void kvm_s390_destroy_adapters(struct kvm *kvm) { int i; - struct s390_map_info *map, *tmp; - for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) { - if (!kvm->arch.adapters[i]) - continue; - list_for_each_entry_safe(map, tmp, - &kvm->arch.adapters[i]->maps, list) { - list_del(&map->list); - put_page(map->page); - kfree(map); - } + for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) kfree(kvm->arch.adapters[i]); - } } static int modify_io_adapter(struct kvm_device *dev, @@ -2456,11 +2517,14 @@ static int modify_io_adapter(struct kvm_device *dev, if (ret > 0) ret = 0; break; + /* + * The following operations are no longer needed and therefore no-ops. + * The gpa to hva translation is done when an IRQ route is set up. The + * set_irq code uses get_user_pages_remote() to do the actual write. + */ case KVM_S390_IO_ADAPTER_MAP: - ret = kvm_s390_adapter_map(dev->kvm, req.id, req.addr); - break; case KVM_S390_IO_ADAPTER_UNMAP: - ret = kvm_s390_adapter_unmap(dev->kvm, req.id, req.addr); + ret = 0; break; default: ret = -EINVAL; @@ -2699,19 +2763,15 @@ static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap) return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit; } -static struct s390_map_info *get_map_info(struct s390_io_adapter *adapter, - u64 addr) +static struct page *get_map_page(struct kvm *kvm, u64 uaddr) { - struct s390_map_info *map; + struct page *page = NULL; - if (!adapter) - return NULL; - - list_for_each_entry(map, &adapter->maps, list) { - if (map->guest_addr == addr) - return map; - } - return NULL; + down_read(&kvm->mm->mmap_sem); + get_user_pages_remote(NULL, kvm->mm, uaddr, 1, FOLL_WRITE, + &page, NULL, NULL); + up_read(&kvm->mm->mmap_sem); + return page; } static int adapter_indicators_set(struct kvm *kvm, @@ -2720,30 +2780,35 @@ static int adapter_indicators_set(struct kvm *kvm, { unsigned long bit; int summary_set, idx; - struct s390_map_info *info; + struct page *ind_page, *summary_page; void *map; - info = get_map_info(adapter, adapter_int->ind_addr); - if (!info) + ind_page = get_map_page(kvm, adapter_int->ind_addr); + if (!ind_page) return -1; - map = page_address(info->page); - bit = get_ind_bit(info->addr, adapter_int->ind_offset, adapter->swap); - set_bit(bit, map); - idx = srcu_read_lock(&kvm->srcu); - mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT); - set_page_dirty_lock(info->page); - info = get_map_info(adapter, adapter_int->summary_addr); - if (!info) { - srcu_read_unlock(&kvm->srcu, idx); + summary_page = get_map_page(kvm, adapter_int->summary_addr); + if (!summary_page) { + put_page(ind_page); return -1; } - map = page_address(info->page); - bit = get_ind_bit(info->addr, adapter_int->summary_offset, - adapter->swap); + + idx = srcu_read_lock(&kvm->srcu); + map = page_address(ind_page); + bit = get_ind_bit(adapter_int->ind_addr, + adapter_int->ind_offset, adapter->swap); + set_bit(bit, map); + mark_page_dirty(kvm, adapter_int->ind_addr >> PAGE_SHIFT); + set_page_dirty_lock(ind_page); + map = page_address(summary_page); + bit = get_ind_bit(adapter_int->summary_addr, + adapter_int->summary_offset, adapter->swap); summary_set = test_and_set_bit(bit, map); - mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT); - set_page_dirty_lock(info->page); + mark_page_dirty(kvm, adapter_int->summary_addr >> PAGE_SHIFT); + set_page_dirty_lock(summary_page); srcu_read_unlock(&kvm->srcu, idx); + + put_page(ind_page); + put_page(summary_page); return summary_set ? 0 : 1; } @@ -2765,9 +2830,7 @@ static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e, adapter = get_io_adapter(kvm, e->adapter.adapter_id); if (!adapter) return -1; - down_read(&adapter->maps_lock); ret = adapter_indicators_set(kvm, adapter, &e->adapter); - up_read(&adapter->maps_lock); if ((ret > 0) && !adapter->masked) { ret = kvm_s390_inject_airq(kvm, adapter); if (ret == 0) @@ -2818,23 +2881,27 @@ int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { - int ret; + u64 uaddr; switch (ue->type) { + /* we store the userspace addresses instead of the guest addresses */ case KVM_IRQ_ROUTING_S390_ADAPTER: e->set = set_adapter_int; - e->adapter.summary_addr = ue->u.adapter.summary_addr; - e->adapter.ind_addr = ue->u.adapter.ind_addr; + uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr); + if (uaddr == -EFAULT) + return -EFAULT; + e->adapter.summary_addr = uaddr; + uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.ind_addr); + if (uaddr == -EFAULT) + return -EFAULT; + e->adapter.ind_addr = uaddr; e->adapter.summary_offset = ue->u.adapter.summary_offset; e->adapter.ind_offset = ue->u.adapter.ind_offset; e->adapter.adapter_id = ue->u.adapter.adapter_id; - ret = 0; - break; + return 0; default: - ret = -EINVAL; + return -EINVAL; } - - return ret; } int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index c2e6d4ba4e23..19a81024fe16 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2,7 +2,7 @@ /* * hosting IBM Z kernel virtual machines (s390x) * - * Copyright IBM Corp. 2008, 2018 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -44,6 +44,7 @@ #include <asm/cpacf.h> #include <asm/timex.h> #include <asm/ap.h> +#include <asm/uv.h> #include "kvm-s390.h" #include "gaccess.h" @@ -184,6 +185,11 @@ static u8 halt_poll_max_steal = 10; module_param(halt_poll_max_steal, byte, 0644); MODULE_PARM_DESC(halt_poll_max_steal, "Maximum percentage of steal time to allow polling"); +/* if set to true, the GISA will be initialized and used if available */ +static bool use_gisa = true; +module_param(use_gisa, bool, 0644); +MODULE_PARM_DESC(use_gisa, "Use the GISA if the host supports it."); + /* * For now we handle at most 16 double words as this is what the s390 base * kernel handles and stores in the prefix page. If we ever need to go beyond @@ -220,6 +226,7 @@ static struct kvm_s390_vm_cpu_subfunc kvm_s390_available_subfunc; static struct gmap_notifier gmap_notifier; static struct gmap_notifier vsie_gmap_notifier; debug_info_t *kvm_s390_dbf; +debug_info_t *kvm_s390_dbf_uv; /* Section: not file related */ int kvm_arch_hardware_enable(void) @@ -228,13 +235,15 @@ int kvm_arch_hardware_enable(void) return 0; } -int kvm_arch_check_processor_compat(void) +int kvm_arch_check_processor_compat(void *opaque) { return 0; } +/* forward declarations */ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end); +static int sca_switch_to_extended(struct kvm *kvm); static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta) { @@ -293,7 +302,7 @@ static struct notifier_block kvm_clock_notifier = { .notifier_call = kvm_clock_sync, }; -int kvm_arch_hardware_setup(void) +int kvm_arch_hardware_setup(void *opaque) { gmap_notifier.notifier_call = kvm_gmap_notifier; gmap_register_pte_notifier(&gmap_notifier); @@ -460,7 +469,12 @@ int kvm_arch_init(void *opaque) if (!kvm_s390_dbf) return -ENOMEM; - if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) + kvm_s390_dbf_uv = debug_register("kvm-uv", 32, 1, 7 * sizeof(long)); + if (!kvm_s390_dbf_uv) + goto out; + + if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view) || + debug_register_view(kvm_s390_dbf_uv, &debug_sprintf_view)) goto out; kvm_s390_cpu_feat_init(); @@ -487,6 +501,7 @@ void kvm_arch_exit(void) { kvm_s390_gib_destroy(); debug_unregister(kvm_s390_dbf); + debug_unregister(kvm_s390_dbf_uv); } /* Section: device related */ @@ -564,14 +579,16 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_BPB: r = test_facility(82); break; + case KVM_CAP_S390_PROTECTED: + r = is_prot_virt_host(); + break; default: r = 0; } return r; } -static void kvm_s390_sync_dirty_log(struct kvm *kvm, - struct kvm_memory_slot *memslot) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { int i; gfn_t cur_gfn, last_gfn; @@ -612,9 +629,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, { int r; unsigned long n; - struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int is_dirty = 0; + int is_dirty; if (kvm_is_ucontrol(kvm)) return -EINVAL; @@ -625,14 +641,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, if (log->slot >= KVM_USER_MEM_SLOTS) goto out; - slots = kvm_memslots(kvm); - memslot = id_to_memslot(slots, log->slot); - r = -ENOENT; - if (!memslot->dirty_bitmap) - goto out; - - kvm_s390_sync_dirty_log(kvm, memslot); - r = kvm_get_dirty_log(kvm, log, &is_dirty); + r = kvm_get_dirty_log(kvm, log, &is_dirty, &memslot); if (r) goto out; @@ -1993,6 +2002,9 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *ms; + if (unlikely(!slots->used_slots)) + return 0; + cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn); ms = gfn_to_memslot(kvm, cur_gfn); args->count = 0; @@ -2158,6 +2170,194 @@ out: return r; } +static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) +{ + struct kvm_vcpu *vcpu; + u16 rc, rrc; + int ret = 0; + int i; + + /* + * We ignore failures and try to destroy as many CPUs as possible. + * At the same time we must not free the assigned resources when + * this fails, as the ultravisor has still access to that memory. + * So kvm_s390_pv_destroy_cpu can leave a "wanted" memory leak + * behind. + * We want to return the first failure rc and rrc, though. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + mutex_lock(&vcpu->mutex); + if (kvm_s390_pv_destroy_cpu(vcpu, &rc, &rrc) && !ret) { + *rcp = rc; + *rrcp = rrc; + ret = -EIO; + } + mutex_unlock(&vcpu->mutex); + } + return ret; +} + +static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + int i, r = 0; + u16 dummy; + + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + mutex_lock(&vcpu->mutex); + r = kvm_s390_pv_create_cpu(vcpu, rc, rrc); + mutex_unlock(&vcpu->mutex); + if (r) + break; + } + if (r) + kvm_s390_cpus_from_pv(kvm, &dummy, &dummy); + return r; +} + +static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) +{ + int r = 0; + u16 dummy; + void __user *argp = (void __user *)cmd->data; + + switch (cmd->cmd) { + case KVM_PV_ENABLE: { + r = -EINVAL; + if (kvm_s390_pv_is_protected(kvm)) + break; + + /* + * FMT 4 SIE needs esca. As we never switch back to bsca from + * esca, we need no cleanup in the error cases below + */ + r = sca_switch_to_extended(kvm); + if (r) + break; + + down_write(¤t->mm->mmap_sem); + r = gmap_mark_unmergeable(); + up_write(¤t->mm->mmap_sem); + if (r) + break; + + r = kvm_s390_pv_init_vm(kvm, &cmd->rc, &cmd->rrc); + if (r) + break; + + r = kvm_s390_cpus_to_pv(kvm, &cmd->rc, &cmd->rrc); + if (r) + kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy); + + /* we need to block service interrupts from now on */ + set_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs); + break; + } + case KVM_PV_DISABLE: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = kvm_s390_cpus_from_pv(kvm, &cmd->rc, &cmd->rrc); + /* + * If a CPU could not be destroyed, destroy VM will also fail. + * There is no point in trying to destroy it. Instead return + * the rc and rrc from the first CPU that failed destroying. + */ + if (r) + break; + r = kvm_s390_pv_deinit_vm(kvm, &cmd->rc, &cmd->rrc); + + /* no need to block service interrupts any more */ + clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs); + break; + } + case KVM_PV_SET_SEC_PARMS: { + struct kvm_s390_pv_sec_parm parms = {}; + void *hdr; + + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = -EFAULT; + if (copy_from_user(&parms, argp, sizeof(parms))) + break; + + /* Currently restricted to 8KB */ + r = -EINVAL; + if (parms.length > PAGE_SIZE * 2) + break; + + r = -ENOMEM; + hdr = vmalloc(parms.length); + if (!hdr) + break; + + r = -EFAULT; + if (!copy_from_user(hdr, (void __user *)parms.origin, + parms.length)) + r = kvm_s390_pv_set_sec_parms(kvm, hdr, parms.length, + &cmd->rc, &cmd->rrc); + + vfree(hdr); + break; + } + case KVM_PV_UNPACK: { + struct kvm_s390_pv_unp unp = {}; + + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = -EFAULT; + if (copy_from_user(&unp, argp, sizeof(unp))) + break; + + r = kvm_s390_pv_unpack(kvm, unp.addr, unp.size, unp.tweak, + &cmd->rc, &cmd->rrc); + break; + } + case KVM_PV_VERIFY: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_VERIFY_IMG, &cmd->rc, &cmd->rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT VERIFY: rc %x rrc %x", cmd->rc, + cmd->rrc); + break; + } + case KVM_PV_PREP_RESET: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_PREPARE_RESET, &cmd->rc, &cmd->rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT PREP RESET: rc %x rrc %x", + cmd->rc, cmd->rrc); + break; + } + case KVM_PV_UNSHARE_ALL: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_SET_UNSHARE_ALL, &cmd->rc, &cmd->rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT UNSHARE: rc %x rrc %x", + cmd->rc, cmd->rrc); + break; + } + default: + r = -ENOTTY; + } + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2255,6 +2455,33 @@ long kvm_arch_vm_ioctl(struct file *filp, mutex_unlock(&kvm->slots_lock); break; } + case KVM_S390_PV_COMMAND: { + struct kvm_pv_cmd args; + + /* protvirt means user sigp */ + kvm->arch.user_cpu_state_ctrl = 1; + r = 0; + if (!is_prot_virt_host()) { + r = -EINVAL; + break; + } + if (copy_from_user(&args, argp, sizeof(args))) { + r = -EFAULT; + break; + } + if (args.flags) { + r = -EINVAL; + break; + } + mutex_lock(&kvm->lock); + r = kvm_s390_handle_pv(kvm, &args); + mutex_unlock(&kvm->lock); + if (copy_to_user(argp, &args, sizeof(args))) { + r = -EFAULT; + break; + } + break; + } default: r = -ENOTTY; } @@ -2504,7 +2731,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.use_skf = sclp.has_skey; spin_lock_init(&kvm->arch.start_stop_lock); kvm_s390_vsie_init(kvm); - kvm_s390_gisa_init(kvm); + if (use_gisa) + kvm_s390_gisa_init(kvm); KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid); return 0; @@ -2518,6 +2746,8 @@ out_err: void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { + u16 rc, rrc; + VCPU_EVENT(vcpu, 3, "%s", "free cpu"); trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id); kvm_s390_clear_local_irqs(vcpu); @@ -2530,6 +2760,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) if (vcpu->kvm->arch.use_cmma) kvm_s390_vcpu_unsetup_cmma(vcpu); + /* We can not hold the vcpu mutex here, we are already dying */ + if (kvm_s390_pv_cpu_get_handle(vcpu)) + kvm_s390_pv_destroy_cpu(vcpu, &rc, &rrc); free_page((unsigned long)(vcpu->arch.sie_block)); } @@ -2551,10 +2784,20 @@ static void kvm_free_vcpus(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { + u16 rc, rrc; + kvm_free_vcpus(kvm); sca_dispose(kvm); - debug_unregister(kvm->arch.dbf); kvm_s390_gisa_destroy(kvm); + /* + * We are already at the end of life and kvm->lock is not taken. + * This is ok as the file descriptor is closed by now and nobody + * can mess with the pv state. To avoid lockdep_assert_held from + * complaining we do not use kvm_s390_pv_is_protected. + */ + if (kvm_s390_pv_get_handle(kvm)) + kvm_s390_pv_deinit_vm(kvm, &rc, &rrc); + debug_unregister(kvm->arch.dbf); free_page((unsigned long)kvm->arch.sie_page2); if (!kvm_is_ucontrol(kvm)) gmap_remove(kvm->arch.gmap); @@ -2650,6 +2893,9 @@ static int sca_switch_to_extended(struct kvm *kvm) unsigned int vcpu_idx; u32 scaol, scaoh; + if (kvm->arch.use_esca) + return 0; + new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO); if (!new_sca) return -ENOMEM; @@ -2901,6 +3147,7 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu) static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu) { int rc = 0; + u16 uvrc, uvrrc; atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM | @@ -2968,6 +3215,14 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu) kvm_s390_vcpu_crypto_setup(vcpu); + mutex_lock(&vcpu->kvm->lock); + if (kvm_s390_pv_is_protected(vcpu->kvm)) { + rc = kvm_s390_pv_create_cpu(vcpu, &uvrc, &uvrrc); + if (rc) + kvm_s390_vcpu_unsetup_cmma(vcpu); + } + mutex_unlock(&vcpu->kvm->lock); + return rc; } @@ -3277,7 +3532,6 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) kvm_s390_set_prefix(vcpu, 0); kvm_s390_set_cpu_timer(vcpu, 0); vcpu->arch.sie_block->ckc = 0; - vcpu->arch.sie_block->todpr = 0; memset(vcpu->arch.sie_block->gcr, 0, sizeof(vcpu->arch.sie_block->gcr)); vcpu->arch.sie_block->gcr[0] = CR0_INITIAL_MASK; vcpu->arch.sie_block->gcr[14] = CR14_INITIAL_MASK; @@ -3295,9 +3549,17 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) vcpu->run->s.regs.pp = 0; vcpu->run->s.regs.gbea = 1; vcpu->run->s.regs.fpc = 0; - vcpu->arch.sie_block->gbea = 1; - vcpu->arch.sie_block->pp = 0; - vcpu->arch.sie_block->fpf &= ~FPF_BPBC; + /* + * Do not reset these registers in the protected case, as some of + * them are overlayed and they are not accessible in this case + * anyway. + */ + if (!kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->gbea = 1; + vcpu->arch.sie_block->pp = 0; + vcpu->arch.sie_block->fpf &= ~FPF_BPBC; + vcpu->arch.sie_block->todpr = 0; + } } static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu) @@ -3487,14 +3749,20 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, switch (mp_state->mp_state) { case KVM_MP_STATE_STOPPED: - kvm_s390_vcpu_stop(vcpu); + rc = kvm_s390_vcpu_stop(vcpu); break; case KVM_MP_STATE_OPERATING: - kvm_s390_vcpu_start(vcpu); + rc = kvm_s390_vcpu_start(vcpu); break; case KVM_MP_STATE_LOAD: + if (!kvm_s390_pv_cpu_is_protected(vcpu)) { + rc = -ENXIO; + break; + } + rc = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_OPR_LOAD); + break; case KVM_MP_STATE_CHECK_STOP: - /* fall through - CHECK_STOP and LOAD are not supported yet */ + fallthrough; /* CHECK_STOP and LOAD are not supported yet */ default: rc = -ENXIO; } @@ -3844,9 +4112,11 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) return vcpu_post_run_fault_in_sie(vcpu); } +#define PSW_INT_MASK (PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_MCHECK) static int __vcpu_run(struct kvm_vcpu *vcpu) { int rc, exit_reason; + struct sie_page *sie_page = (struct sie_page *)vcpu->arch.sie_block; /* * We try to hold kvm->srcu during most of vcpu_run (except when run- @@ -3868,8 +4138,28 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) guest_enter_irqoff(); __disable_cpu_timer_accounting(vcpu); local_irq_enable(); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy(sie_page->pv_grregs, + vcpu->run->s.regs.gprs, + sizeof(sie_page->pv_grregs)); + } exit_reason = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy(vcpu->run->s.regs.gprs, + sie_page->pv_grregs, + sizeof(sie_page->pv_grregs)); + /* + * We're not allowed to inject interrupts on intercepts + * that leave the guest state in an "in-between" state + * where the next SIE entry will do a continuation. + * Fence interrupts in our "internal" PSW. + */ + if (vcpu->arch.sie_block->icptcode == ICPT_PV_INSTR || + vcpu->arch.sie_block->icptcode == ICPT_PV_PREF) { + vcpu->arch.sie_block->gpsw.mask &= ~PSW_INT_MASK; + } + } local_irq_disable(); __enable_cpu_timer_accounting(vcpu); guest_exit_irqoff(); @@ -3883,7 +4173,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) return rc; } -static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void sync_regs_fmt2(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct runtime_instr_cb *riccb; struct gs_cb *gscb; @@ -3892,16 +4182,7 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) gscb = (struct gs_cb *) &kvm_run->s.regs.gscb; vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask; vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr; - if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) - kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix); - if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) { - memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128); - /* some control register changes require a tlb flush */ - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - } if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) { - kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm); - vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc; vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr; vcpu->arch.sie_block->pp = kvm_run->s.regs.pp; vcpu->arch.sie_block->gbea = kvm_run->s.regs.gbea; @@ -3942,6 +4223,36 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.sie_block->fpf &= ~FPF_BPBC; vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0; } + if (MACHINE_HAS_GS) { + preempt_disable(); + __ctl_set_bit(2, 4); + if (current->thread.gs_cb) { + vcpu->arch.host_gscb = current->thread.gs_cb; + save_gs_cb(vcpu->arch.host_gscb); + } + if (vcpu->arch.gs_enabled) { + current->thread.gs_cb = (struct gs_cb *) + &vcpu->run->s.regs.gscb; + restore_gs_cb(current->thread.gs_cb); + } + preempt_enable(); + } + /* SIE will load etoken directly from SDNX and therefore kvm_run */ +} + +static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) + kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix); + if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) { + memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128); + /* some control register changes require a tlb flush */ + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + } + if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) { + kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm); + vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc; + } save_access_regs(vcpu->arch.host_acrs); restore_access_regs(vcpu->run->s.regs.acrs); /* save host (userspace) fprs/vrs */ @@ -3956,23 +4267,47 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (test_fp_ctl(current->thread.fpu.fpc)) /* User space provided an invalid FPC, let's clear it */ current->thread.fpu.fpc = 0; + + /* Sync fmt2 only data */ + if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) { + sync_regs_fmt2(vcpu, kvm_run); + } else { + /* + * In several places we have to modify our internal view to + * not do things that are disallowed by the ultravisor. For + * example we must not inject interrupts after specific exits + * (e.g. 112 prefix page not secure). We do this by turning + * off the machine check, external and I/O interrupt bits + * of our PSW copy. To avoid getting validity intercepts, we + * do only accept the condition code from userspace. + */ + vcpu->arch.sie_block->gpsw.mask &= ~PSW_MASK_CC; + vcpu->arch.sie_block->gpsw.mask |= kvm_run->psw_mask & + PSW_MASK_CC; + } + + kvm_run->kvm_dirty_regs = 0; +} + +static void store_regs_fmt2(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr; + kvm_run->s.regs.pp = vcpu->arch.sie_block->pp; + kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea; + kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC; if (MACHINE_HAS_GS) { - preempt_disable(); __ctl_set_bit(2, 4); - if (current->thread.gs_cb) { - vcpu->arch.host_gscb = current->thread.gs_cb; - save_gs_cb(vcpu->arch.host_gscb); - } - if (vcpu->arch.gs_enabled) { - current->thread.gs_cb = (struct gs_cb *) - &vcpu->run->s.regs.gscb; - restore_gs_cb(current->thread.gs_cb); - } + if (vcpu->arch.gs_enabled) + save_gs_cb(current->thread.gs_cb); + preempt_disable(); + current->thread.gs_cb = vcpu->arch.host_gscb; + restore_gs_cb(vcpu->arch.host_gscb); preempt_enable(); + if (!vcpu->arch.host_gscb) + __ctl_clear_bit(2, 4); + vcpu->arch.host_gscb = NULL; } - /* SIE will load etoken directly from SDNX and therefore kvm_run */ - - kvm_run->kvm_dirty_regs = 0; + /* SIE will save etoken directly into SDNX and therefore kvm_run */ } static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -3983,13 +4318,9 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128); kvm_run->s.regs.cputm = kvm_s390_get_cpu_timer(vcpu); kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc; - kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr; - kvm_run->s.regs.pp = vcpu->arch.sie_block->pp; - kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea; kvm_run->s.regs.pft = vcpu->arch.pfault_token; kvm_run->s.regs.pfs = vcpu->arch.pfault_select; kvm_run->s.regs.pfc = vcpu->arch.pfault_compare; - kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); /* Save guest register state */ @@ -3998,19 +4329,8 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) /* Restore will be done lazily at return */ current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc; current->thread.fpu.regs = vcpu->arch.host_fpregs.regs; - if (MACHINE_HAS_GS) { - __ctl_set_bit(2, 4); - if (vcpu->arch.gs_enabled) - save_gs_cb(current->thread.gs_cb); - preempt_disable(); - current->thread.gs_cb = vcpu->arch.host_gscb; - restore_gs_cb(vcpu->arch.host_gscb); - preempt_enable(); - if (!vcpu->arch.host_gscb) - __ctl_clear_bit(2, 4); - vcpu->arch.host_gscb = NULL; - } - /* SIE will save etoken directly into SDNX and therefore kvm_run */ + if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) + store_regs_fmt2(vcpu, kvm_run); } int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -4034,6 +4354,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_sigset_activate(vcpu); + /* + * no need to check the return value of vcpu_start as it can only have + * an error for protvirt, but protvirt means user cpu state + */ if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) { kvm_s390_vcpu_start(vcpu); } else if (is_vcpu_stopped(vcpu)) { @@ -4171,18 +4495,27 @@ static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu) kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu); } -void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) +int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) { - int i, online_vcpus, started_vcpus = 0; + int i, online_vcpus, r = 0, started_vcpus = 0; if (!is_vcpu_stopped(vcpu)) - return; + return 0; trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1); /* Only one cpu at a time may enter/leave the STOPPED state. */ spin_lock(&vcpu->kvm->arch.start_stop_lock); online_vcpus = atomic_read(&vcpu->kvm->online_vcpus); + /* Let's tell the UV that we want to change into the operating state */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_OPR); + if (r) { + spin_unlock(&vcpu->kvm->arch.start_stop_lock); + return r; + } + } + for (i = 0; i < online_vcpus; i++) { if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) started_vcpus++; @@ -4202,27 +4535,43 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) kvm_s390_clear_cpuflags(vcpu, CPUSTAT_STOPPED); /* + * The real PSW might have changed due to a RESTART interpreted by the + * ultravisor. We block all interrupts and let the next sie exit + * refresh our view. + */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) + vcpu->arch.sie_block->gpsw.mask &= ~PSW_INT_MASK; + /* * Another VCPU might have used IBS while we were offline. * Let's play safe and flush the VCPU at startup. */ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); spin_unlock(&vcpu->kvm->arch.start_stop_lock); - return; + return 0; } -void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) +int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) { - int i, online_vcpus, started_vcpus = 0; + int i, online_vcpus, r = 0, started_vcpus = 0; struct kvm_vcpu *started_vcpu = NULL; if (is_vcpu_stopped(vcpu)) - return; + return 0; trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0); /* Only one cpu at a time may enter/leave the STOPPED state. */ spin_lock(&vcpu->kvm->arch.start_stop_lock); online_vcpus = atomic_read(&vcpu->kvm->online_vcpus); + /* Let's tell the UV that we want to change into the stopped state */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_STP); + if (r) { + spin_unlock(&vcpu->kvm->arch.start_stop_lock); + return r; + } + } + /* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */ kvm_s390_clear_stop_irq(vcpu); @@ -4245,7 +4594,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) } spin_unlock(&vcpu->kvm->arch.start_stop_lock); - return; + return 0; } static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, @@ -4272,12 +4621,40 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return r; } +static long kvm_s390_guest_sida_op(struct kvm_vcpu *vcpu, + struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + int r = 0; + + if (mop->flags || !mop->size) + return -EINVAL; + if (mop->size + mop->sida_offset < mop->size) + return -EINVAL; + if (mop->size + mop->sida_offset > sida_size(vcpu->arch.sie_block)) + return -E2BIG; + + switch (mop->op) { + case KVM_S390_MEMOP_SIDA_READ: + if (copy_to_user(uaddr, (void *)(sida_origin(vcpu->arch.sie_block) + + mop->sida_offset), mop->size)) + r = -EFAULT; + + break; + case KVM_S390_MEMOP_SIDA_WRITE: + if (copy_from_user((void *)(sida_origin(vcpu->arch.sie_block) + + mop->sida_offset), uaddr, mop->size)) + r = -EFAULT; + break; + } + return r; +} static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, struct kvm_s390_mem_op *mop) { void __user *uaddr = (void __user *)mop->buf; void *tmpbuf = NULL; - int r, srcu_idx; + int r = 0; const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION | KVM_S390_MEMOP_F_CHECK_ONLY; @@ -4287,14 +4664,15 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, if (mop->size > MEM_OP_MAX_SIZE) return -E2BIG; + if (kvm_s390_pv_cpu_is_protected(vcpu)) + return -EINVAL; + if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) { tmpbuf = vmalloc(mop->size); if (!tmpbuf) return -ENOMEM; } - srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - switch (mop->op) { case KVM_S390_MEMOP_LOGICAL_READ: if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { @@ -4320,12 +4698,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, } r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); break; - default: - r = -EINVAL; } - srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); - if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0) kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); @@ -4333,6 +4707,31 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, return r; } +static long kvm_s390_guest_memsida_op(struct kvm_vcpu *vcpu, + struct kvm_s390_mem_op *mop) +{ + int r, srcu_idx; + + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + switch (mop->op) { + case KVM_S390_MEMOP_LOGICAL_READ: + case KVM_S390_MEMOP_LOGICAL_WRITE: + r = kvm_s390_guest_mem_op(vcpu, mop); + break; + case KVM_S390_MEMOP_SIDA_READ: + case KVM_S390_MEMOP_SIDA_WRITE: + /* we are locked against sida going away by the vcpu->mutex */ + r = kvm_s390_guest_sida_op(vcpu, mop); + break; + default: + r = -EINVAL; + } + + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); + return r; +} + long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4368,6 +4767,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int idx; long r; + u16 rc, rrc; vcpu_load(vcpu); @@ -4389,18 +4789,40 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_S390_CLEAR_RESET: r = 0; kvm_arch_vcpu_ioctl_clear_reset(vcpu); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_CPU_RESET_CLEAR, &rc, &rrc); + VCPU_EVENT(vcpu, 3, "PROTVIRT RESET CLEAR VCPU: rc %x rrc %x", + rc, rrc); + } break; case KVM_S390_INITIAL_RESET: r = 0; kvm_arch_vcpu_ioctl_initial_reset(vcpu); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_CPU_RESET_INITIAL, + &rc, &rrc); + VCPU_EVENT(vcpu, 3, "PROTVIRT RESET INITIAL VCPU: rc %x rrc %x", + rc, rrc); + } break; case KVM_S390_NORMAL_RESET: r = 0; kvm_arch_vcpu_ioctl_normal_reset(vcpu); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_CPU_RESET, &rc, &rrc); + VCPU_EVENT(vcpu, 3, "PROTVIRT RESET NORMAL VCPU: rc %x rrc %x", + rc, rrc); + } break; case KVM_SET_ONE_REG: case KVM_GET_ONE_REG: { struct kvm_one_reg reg; + r = -EINVAL; + if (kvm_s390_pv_cpu_is_protected(vcpu)) + break; r = -EFAULT; if (copy_from_user(®, argp, sizeof(reg))) break; @@ -4463,7 +4885,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_s390_mem_op mem_op; if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0) - r = kvm_s390_guest_mem_op(vcpu, &mem_op); + r = kvm_s390_guest_memsida_op(vcpu, &mem_op); else r = -EFAULT; break; @@ -4523,12 +4945,6 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) -{ - return 0; -} - /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, @@ -4549,12 +4965,15 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit) return -EINVAL; + /* When we are protected, we should not change the memory slots */ + if (kvm_s390_pv_get_handle(kvm)) + return -EINVAL; return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { @@ -4570,7 +4989,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, old->npages * PAGE_SIZE); if (rc) break; - /* FALLTHROUGH */ + fallthrough; case KVM_MR_CREATE: rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, mem->guest_phys_addr, mem->memory_size); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 6d9448dbd052..79dcd647b378 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -2,7 +2,7 @@ /* * definition for kvm on s390 * - * Copyright IBM Corp. 2008, 2009 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -15,6 +15,7 @@ #include <linux/hrtimer.h> #include <linux/kvm.h> #include <linux/kvm_host.h> +#include <linux/lockdep.h> #include <asm/facility.h> #include <asm/processor.h> #include <asm/sclp.h> @@ -25,6 +26,17 @@ #define IS_ITDB_VALID(vcpu) ((*(char *)vcpu->arch.sie_block->itdba == TDB_FORMAT1)) extern debug_info_t *kvm_s390_dbf; +extern debug_info_t *kvm_s390_dbf_uv; + +#define KVM_UV_EVENT(d_kvm, d_loglevel, d_string, d_args...)\ +do { \ + debug_sprintf_event((d_kvm)->arch.dbf, d_loglevel, d_string "\n", \ + d_args); \ + debug_sprintf_event(kvm_s390_dbf_uv, d_loglevel, \ + "%d: " d_string "\n", (d_kvm)->userspace_pid, \ + d_args); \ +} while (0) + #define KVM_EVENT(d_loglevel, d_string, d_args...)\ do { \ debug_sprintf_event(kvm_s390_dbf, d_loglevel, d_string "\n", \ @@ -196,6 +208,39 @@ static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm) return kvm->arch.user_cpu_state_ctrl != 0; } +/* implemented in pv.c */ +int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); +int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); +int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc); +int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc); +int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, + u16 *rrc); +int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, + unsigned long tweak, u16 *rc, u16 *rrc); +int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state); + +static inline u64 kvm_s390_pv_get_handle(struct kvm *kvm) +{ + return kvm->arch.pv.handle; +} + +static inline u64 kvm_s390_pv_cpu_get_handle(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.pv.handle; +} + +static inline bool kvm_s390_pv_is_protected(struct kvm *kvm) +{ + lockdep_assert_held(&kvm->lock); + return !!kvm_s390_pv_get_handle(kvm); +} + +static inline bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu) +{ + lockdep_assert_held(&vcpu->mutex); + return !!kvm_s390_pv_cpu_get_handle(vcpu); +} + /* implemented in interrupt.c */ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu); @@ -286,8 +331,8 @@ void kvm_s390_set_tod_clock(struct kvm *kvm, long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); -void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); -void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); +int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); +int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu); bool kvm_s390_vcpu_sie_inhibited(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index ed52ffa8d5d4..69a824f9ef0b 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -2,7 +2,7 @@ /* * handling privileged instructions * - * Copyright IBM Corp. 2008, 2018 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -872,7 +872,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); - if (operand2 & 0xfff) + if (!kvm_s390_pv_cpu_is_protected(vcpu) && (operand2 & 0xfff)) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); switch (fc) { @@ -893,8 +893,13 @@ static int handle_stsi(struct kvm_vcpu *vcpu) handle_stsi_3_2_2(vcpu, (void *) mem); break; } - - rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy((void *)sida_origin(vcpu->arch.sie_block), (void *)mem, + PAGE_SIZE); + rc = 0; + } else { + rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); + } if (rc) { rc = kvm_s390_inject_prog_cond(vcpu, rc); goto out; diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c new file mode 100644 index 000000000000..63e330109b63 --- /dev/null +++ b/arch/s390/kvm/pv.c @@ -0,0 +1,303 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hosting Protected Virtual Machines + * + * Copyright IBM Corp. 2019, 2020 + * Author(s): Janosch Frank <frankja@linux.ibm.com> + */ +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/pagemap.h> +#include <linux/sched/signal.h> +#include <asm/pgalloc.h> +#include <asm/gmap.h> +#include <asm/uv.h> +#include <asm/mman.h> +#include "kvm-s390.h" + +int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) +{ + int cc = 0; + + if (kvm_s390_pv_cpu_get_handle(vcpu)) { + cc = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_DESTROY_SEC_CPU, rc, rrc); + + KVM_UV_EVENT(vcpu->kvm, 3, + "PROTVIRT DESTROY VCPU %d: rc %x rrc %x", + vcpu->vcpu_id, *rc, *rrc); + WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x", + *rc, *rrc); + } + /* Intended memory leak for something that should never happen. */ + if (!cc) + free_pages(vcpu->arch.pv.stor_base, + get_order(uv_info.guest_cpu_stor_len)); + + free_page(sida_origin(vcpu->arch.sie_block)); + vcpu->arch.sie_block->pv_handle_cpu = 0; + vcpu->arch.sie_block->pv_handle_config = 0; + memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv)); + vcpu->arch.sie_block->sdf = 0; + /* + * The sidad field (for sdf == 2) is now the gbea field (for sdf == 0). + * Use the reset value of gbea to avoid leaking the kernel pointer of + * the just freed sida. + */ + vcpu->arch.sie_block->gbea = 1; + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + + return cc ? EIO : 0; +} + +int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) +{ + struct uv_cb_csc uvcb = { + .header.cmd = UVC_CMD_CREATE_SEC_CPU, + .header.len = sizeof(uvcb), + }; + int cc; + + if (kvm_s390_pv_cpu_get_handle(vcpu)) + return -EINVAL; + + vcpu->arch.pv.stor_base = __get_free_pages(GFP_KERNEL, + get_order(uv_info.guest_cpu_stor_len)); + if (!vcpu->arch.pv.stor_base) + return -ENOMEM; + + /* Input */ + uvcb.guest_handle = kvm_s390_pv_get_handle(vcpu->kvm); + uvcb.num = vcpu->arch.sie_block->icpua; + uvcb.state_origin = (u64)vcpu->arch.sie_block; + uvcb.stor_origin = (u64)vcpu->arch.pv.stor_base; + + /* Alloc Secure Instruction Data Area Designation */ + vcpu->arch.sie_block->sidad = __get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!vcpu->arch.sie_block->sidad) { + free_pages(vcpu->arch.pv.stor_base, + get_order(uv_info.guest_cpu_stor_len)); + return -ENOMEM; + } + + cc = uv_call(0, (u64)&uvcb); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + KVM_UV_EVENT(vcpu->kvm, 3, + "PROTVIRT CREATE VCPU: cpu %d handle %llx rc %x rrc %x", + vcpu->vcpu_id, uvcb.cpu_handle, uvcb.header.rc, + uvcb.header.rrc); + + if (cc) { + u16 dummy; + + kvm_s390_pv_destroy_cpu(vcpu, &dummy, &dummy); + return -EIO; + } + + /* Output */ + vcpu->arch.pv.handle = uvcb.cpu_handle; + vcpu->arch.sie_block->pv_handle_cpu = uvcb.cpu_handle; + vcpu->arch.sie_block->pv_handle_config = kvm_s390_pv_get_handle(vcpu->kvm); + vcpu->arch.sie_block->sdf = 2; + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + return 0; +} + +/* only free resources when the destroy was successful */ +static void kvm_s390_pv_dealloc_vm(struct kvm *kvm) +{ + vfree(kvm->arch.pv.stor_var); + free_pages(kvm->arch.pv.stor_base, + get_order(uv_info.guest_base_stor_len)); + memset(&kvm->arch.pv, 0, sizeof(kvm->arch.pv)); +} + +static int kvm_s390_pv_alloc_vm(struct kvm *kvm) +{ + unsigned long base = uv_info.guest_base_stor_len; + unsigned long virt = uv_info.guest_virt_var_stor_len; + unsigned long npages = 0, vlen = 0; + struct kvm_memory_slot *memslot; + + kvm->arch.pv.stor_var = NULL; + kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL, get_order(base)); + if (!kvm->arch.pv.stor_base) + return -ENOMEM; + + /* + * Calculate current guest storage for allocation of the + * variable storage, which is based on the length in MB. + * + * Slots are sorted by GFN + */ + mutex_lock(&kvm->slots_lock); + memslot = kvm_memslots(kvm)->memslots; + npages = memslot->base_gfn + memslot->npages; + mutex_unlock(&kvm->slots_lock); + + kvm->arch.pv.guest_len = npages * PAGE_SIZE; + + /* Allocate variable storage */ + vlen = ALIGN(virt * ((npages * PAGE_SIZE) / HPAGE_SIZE), PAGE_SIZE); + vlen += uv_info.guest_virt_base_stor_len; + kvm->arch.pv.stor_var = vzalloc(vlen); + if (!kvm->arch.pv.stor_var) + goto out_err; + return 0; + +out_err: + kvm_s390_pv_dealloc_vm(kvm); + return -ENOMEM; +} + +/* this should not fail, but if it does, we must not free the donated memory */ +int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + int cc; + + /* make all pages accessible before destroying the guest */ + s390_reset_acc(kvm->mm); + + cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_DESTROY_SEC_CONF, rc, rrc); + WRITE_ONCE(kvm->arch.gmap->guest_handle, 0); + atomic_set(&kvm->mm->context.is_protected, 0); + KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc); + WARN_ONCE(cc, "protvirt destroy vm failed rc %x rrc %x", *rc, *rrc); + /* Inteded memory leak on "impossible" error */ + if (!cc) + kvm_s390_pv_dealloc_vm(kvm); + return cc ? -EIO : 0; +} + +int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + struct uv_cb_cgc uvcb = { + .header.cmd = UVC_CMD_CREATE_SEC_CONF, + .header.len = sizeof(uvcb) + }; + int cc, ret; + u16 dummy; + + ret = kvm_s390_pv_alloc_vm(kvm); + if (ret) + return ret; + + /* Inputs */ + uvcb.guest_stor_origin = 0; /* MSO is 0 for KVM */ + uvcb.guest_stor_len = kvm->arch.pv.guest_len; + uvcb.guest_asce = kvm->arch.gmap->asce; + uvcb.guest_sca = (unsigned long)kvm->arch.sca; + uvcb.conf_base_stor_origin = (u64)kvm->arch.pv.stor_base; + uvcb.conf_virt_stor_origin = (u64)kvm->arch.pv.stor_var; + + cc = uv_call(0, (u64)&uvcb); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + KVM_UV_EVENT(kvm, 3, "PROTVIRT CREATE VM: handle %llx len %llx rc %x rrc %x", + uvcb.guest_handle, uvcb.guest_stor_len, *rc, *rrc); + + /* Outputs */ + kvm->arch.pv.handle = uvcb.guest_handle; + + if (cc) { + if (uvcb.header.rc & UVC_RC_NEED_DESTROY) + kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy); + else + kvm_s390_pv_dealloc_vm(kvm); + return -EIO; + } + kvm->arch.gmap->guest_handle = uvcb.guest_handle; + atomic_set(&kvm->mm->context.is_protected, 1); + return 0; +} + +int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, + u16 *rrc) +{ + struct uv_cb_ssc uvcb = { + .header.cmd = UVC_CMD_SET_SEC_CONF_PARAMS, + .header.len = sizeof(uvcb), + .sec_header_origin = (u64)hdr, + .sec_header_len = length, + .guest_handle = kvm_s390_pv_get_handle(kvm), + }; + int cc = uv_call(0, (u64)&uvcb); + + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x", + *rc, *rrc); + return cc ? -EINVAL : 0; +} + +static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak, + u64 offset, u16 *rc, u16 *rrc) +{ + struct uv_cb_unp uvcb = { + .header.cmd = UVC_CMD_UNPACK_IMG, + .header.len = sizeof(uvcb), + .guest_handle = kvm_s390_pv_get_handle(kvm), + .gaddr = addr, + .tweak[0] = tweak, + .tweak[1] = offset, + }; + int ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb); + + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + + if (ret && ret != -EAGAIN) + KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x", + uvcb.gaddr, *rc, *rrc); + return ret; +} + +int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, + unsigned long tweak, u16 *rc, u16 *rrc) +{ + u64 offset = 0; + int ret = 0; + + if (addr & ~PAGE_MASK || !size || size & ~PAGE_MASK) + return -EINVAL; + + KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: start addr %lx size %lx", + addr, size); + + while (offset < size) { + ret = unpack_one(kvm, addr, tweak, offset, rc, rrc); + if (ret == -EAGAIN) { + cond_resched(); + if (fatal_signal_pending(current)) + break; + continue; + } + if (ret) + break; + addr += PAGE_SIZE; + offset += PAGE_SIZE; + } + if (!ret) + KVM_UV_EVENT(kvm, 3, "%s", "PROTVIRT VM UNPACK: successful"); + return ret; +} + +int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state) +{ + struct uv_cb_cpu_set_state uvcb = { + .header.cmd = UVC_CMD_CPU_SET_STATE, + .header.len = sizeof(uvcb), + .cpu_handle = kvm_s390_pv_cpu_get_handle(vcpu), + .state = state, + }; + int cc; + + cc = uv_call(0, (u64)&uvcb); + KVM_UV_EVENT(vcpu->kvm, 3, "PROTVIRT SET CPU %d STATE %d rc %x rrc %x", + vcpu->vcpu_id, state, uvcb.header.rc, uvcb.header.rrc); + if (cc) + return -EINVAL; + return 0; +} diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index aeccdb30899a..09bf7f2121ac 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -38,6 +38,7 @@ #include <asm/irq.h> #include <asm/mmu_context.h> #include <asm/facility.h> +#include <asm/uv.h> #include "../kernel/entry.h" #define __FAIL_ADDR_MASK -4096L @@ -812,3 +813,80 @@ out_extint: early_initcall(pfault_irq_init); #endif /* CONFIG_PFAULT */ + +#if IS_ENABLED(CONFIG_PGSTE) +void do_secure_storage_access(struct pt_regs *regs) +{ + unsigned long addr = regs->int_parm_long & __FAIL_ADDR_MASK; + struct vm_area_struct *vma; + struct mm_struct *mm; + struct page *page; + int rc; + + switch (get_fault_type(regs)) { + case USER_FAULT: + mm = current->mm; + down_read(&mm->mmap_sem); + vma = find_vma(mm, addr); + if (!vma) { + up_read(&mm->mmap_sem); + do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP); + break; + } + page = follow_page(vma, addr, FOLL_WRITE | FOLL_GET); + if (IS_ERR_OR_NULL(page)) { + up_read(&mm->mmap_sem); + break; + } + if (arch_make_page_accessible(page)) + send_sig(SIGSEGV, current, 0); + put_page(page); + up_read(&mm->mmap_sem); + break; + case KERNEL_FAULT: + page = phys_to_page(addr); + if (unlikely(!try_get_page(page))) + break; + rc = arch_make_page_accessible(page); + put_page(page); + if (rc) + BUG(); + break; + case VDSO_FAULT: + /* fallthrough */ + case GMAP_FAULT: + /* fallthrough */ + default: + do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP); + WARN_ON_ONCE(1); + } +} +NOKPROBE_SYMBOL(do_secure_storage_access); + +void do_non_secure_storage_access(struct pt_regs *regs) +{ + unsigned long gaddr = regs->int_parm_long & __FAIL_ADDR_MASK; + struct gmap *gmap = (struct gmap *)S390_lowcore.gmap; + + if (get_fault_type(regs) != GMAP_FAULT) { + do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP); + WARN_ON_ONCE(1); + return; + } + + if (gmap_convert_to_secure(gmap, gaddr) == -EINVAL) + send_sig(SIGSEGV, current, 0); +} +NOKPROBE_SYMBOL(do_non_secure_storage_access); + +#else +void do_secure_storage_access(struct pt_regs *regs) +{ + default_trap_handler(regs); +} + +void do_non_secure_storage_access(struct pt_regs *regs) +{ + default_trap_handler(regs); +} +#endif diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index edcdca97e85e..2fbece47ef6f 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -804,7 +804,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap, if (*table & _REGION_ENTRY_INVALID) return NULL; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); - /* Fallthrough */ + fallthrough; case _ASCE_TYPE_REGION2: table += (gaddr & _REGION2_INDEX) >> _REGION2_SHIFT; if (level == 3) @@ -812,7 +812,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap, if (*table & _REGION_ENTRY_INVALID) return NULL; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); - /* Fallthrough */ + fallthrough; case _ASCE_TYPE_REGION3: table += (gaddr & _REGION3_INDEX) >> _REGION3_SHIFT; if (level == 2) @@ -820,7 +820,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap, if (*table & _REGION_ENTRY_INVALID) return NULL; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); - /* Fallthrough */ + fallthrough; case _ASCE_TYPE_SEGMENT: table += (gaddr & _SEGMENT_INDEX) >> _SEGMENT_SHIFT; if (level == 1) @@ -2548,6 +2548,23 @@ int s390_enable_sie(void) } EXPORT_SYMBOL_GPL(s390_enable_sie); +int gmap_mark_unmergeable(void) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + int ret; + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + ret = ksm_madvise(vma, vma->vm_start, vma->vm_end, + MADV_UNMERGEABLE, &vma->vm_flags); + if (ret) + return ret; + } + mm->def_flags &= ~VM_MERGEABLE; + return 0; +} +EXPORT_SYMBOL_GPL(gmap_mark_unmergeable); + /* * Enable storage key handling from now on and initialize the storage * keys with the default key. @@ -2593,7 +2610,6 @@ static const struct mm_walk_ops enable_skey_walk_ops = { int s390_enable_skey(void) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; int rc = 0; down_write(&mm->mmap_sem); @@ -2601,16 +2617,11 @@ int s390_enable_skey(void) goto out_up; mm->context.uses_skeys = 1; - for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (ksm_madvise(vma, vma->vm_start, vma->vm_end, - MADV_UNMERGEABLE, &vma->vm_flags)) { - mm->context.uses_skeys = 0; - rc = -ENOMEM; - goto out_up; - } + rc = gmap_mark_unmergeable(); + if (rc) { + mm->context.uses_skeys = 0; + goto out_up; } - mm->def_flags &= ~VM_MERGEABLE; - walk_page_range(mm, 0, TASK_SIZE, &enable_skey_walk_ops, NULL); out_up: @@ -2640,3 +2651,38 @@ void s390_reset_cmma(struct mm_struct *mm) up_write(&mm->mmap_sem); } EXPORT_SYMBOL_GPL(s390_reset_cmma); + +/* + * make inaccessible pages accessible again + */ +static int __s390_reset_acc(pte_t *ptep, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t pte = READ_ONCE(*ptep); + + if (pte_present(pte)) + WARN_ON_ONCE(uv_convert_from_secure(pte_val(pte) & PAGE_MASK)); + return 0; +} + +static const struct mm_walk_ops reset_acc_walk_ops = { + .pte_entry = __s390_reset_acc, +}; + +#include <linux/sched/mm.h> +void s390_reset_acc(struct mm_struct *mm) +{ + /* + * we might be called during + * reset: we walk the pages and clear + * close of all kvm file descriptors: we walk the pages and clear + * exit of process on fd closure: vma already gone, do nothing + */ + if (!mmget_not_zero(mm)) + return; + down_read(&mm->mmap_sem); + walk_page_range(mm, 0, TASK_SIZE, &reset_acc_walk_ops, NULL); + up_read(&mm->mmap_sem); + mmput(mm); +} +EXPORT_SYMBOL_GPL(s390_reset_acc); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 98959e8cd448..42a2d0d3984a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -49,13 +49,16 @@ #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS +#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ + KVM_DIRTY_LOG_INITIALLY_SET) + /* x86-specific vcpu->requests bit members */ #define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0) #define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1) #define KVM_REQ_TRIPLE_FAULT KVM_ARCH_REQ(2) #define KVM_REQ_MMU_SYNC KVM_ARCH_REQ(3) #define KVM_REQ_CLOCK_UPDATE KVM_ARCH_REQ(4) -#define KVM_REQ_LOAD_CR3 KVM_ARCH_REQ(5) +#define KVM_REQ_LOAD_MMU_PGD KVM_ARCH_REQ(5) #define KVM_REQ_EVENT KVM_ARCH_REQ(6) #define KVM_REQ_APF_HALT KVM_ARCH_REQ(7) #define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(8) @@ -182,7 +185,10 @@ enum exit_fastpath_completion { EXIT_FASTPATH_SKIP_EMUL_INS, }; -#include <asm/kvm_emulate.h> +struct x86_emulate_ctxt; +struct x86_exception; +enum x86_intercept; +enum x86_intercept_stage; #define KVM_NR_MEM_OBJS 40 @@ -297,7 +303,6 @@ union kvm_mmu_extended_role { unsigned int cr4_pke:1; unsigned int cr4_smap:1; unsigned int cr4_smep:1; - unsigned int cr4_la57:1; unsigned int maxphyaddr:6; }; }; @@ -382,8 +387,7 @@ struct kvm_mmu_root_info { * current mmu mode. */ struct kvm_mmu { - void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); - unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); + unsigned long (*get_guest_pgd)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err, bool prefault); @@ -678,7 +682,7 @@ struct kvm_vcpu_arch { /* emulate context */ - struct x86_emulate_ctxt emulate_ctxt; + struct x86_emulate_ctxt *emulate_ctxt; bool emulate_regs_need_sync_to_vcpu; bool emulate_regs_need_sync_from_vcpu; int (*complete_userspace_io)(struct kvm_vcpu *vcpu); @@ -808,10 +812,6 @@ struct kvm_vcpu_arch { int pending_ioapic_eoi; int pending_external_vector; - /* GPA available */ - bool gpa_available; - gpa_t gpa_val; - /* be preempted when it's in kernel-mode(cpl=0) */ bool preempted_in_kernel; @@ -890,6 +890,7 @@ enum kvm_irqchip_mode { #define APICV_INHIBIT_REASON_NESTED 2 #define APICV_INHIBIT_REASON_IRQWIN 3 #define APICV_INHIBIT_REASON_PIT_REINJ 4 +#define APICV_INHIBIT_REASON_X2APIC 5 struct kvm_arch { unsigned long n_used_mmu_pages; @@ -920,6 +921,7 @@ struct kvm_arch { atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; struct kvm_apic_map *apic_map; + bool apic_map_dirty; bool apic_access_page_done; unsigned long apicv_inhibit_reasons; @@ -1052,19 +1054,14 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) } struct kvm_x86_ops { - int (*cpu_has_kvm_support)(void); /* __init */ - int (*disabled_by_bios)(void); /* __init */ int (*hardware_enable)(void); void (*hardware_disable)(void); - int (*check_processor_compatibility)(void);/* __init */ - int (*hardware_setup)(void); /* __init */ - void (*hardware_unsetup)(void); /* __exit */ + void (*hardware_unsetup)(void); bool (*cpu_has_accelerated_tpr)(void); bool (*has_emulated_msr)(int index); void (*cpuid_update)(struct kvm_vcpu *vcpu); - struct kvm *(*vm_alloc)(void); - void (*vm_free)(struct kvm *); + unsigned int vm_size; int (*vm_init)(struct kvm *kvm); void (*vm_destroy)(struct kvm *kvm); @@ -1090,7 +1087,6 @@ struct kvm_x86_ops { void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu); void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu); void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); - void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); int (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); @@ -1153,13 +1149,8 @@ struct kvm_x86_ops { int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); int (*get_tdp_level)(struct kvm_vcpu *vcpu); u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); - int (*get_lpage_level)(void); - bool (*rdtscp_supported)(void); - bool (*invpcid_supported)(void); - - void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); - void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry); + void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, unsigned long cr3); bool (*has_wbinvd_exit)(void); @@ -1171,16 +1162,12 @@ struct kvm_x86_ops { int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, - enum x86_intercept_stage stage); + enum x86_intercept_stage stage, + struct x86_exception *exception); void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion *exit_fastpath); - bool (*mpx_supported)(void); - bool (*xsaves_supported)(void); - bool (*umip_emulated)(void); - bool (*pt_supported)(void); - bool (*pku_supported)(void); - int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); + int (*check_nested_events)(struct kvm_vcpu *vcpu); void (*request_immediate_exit)(struct kvm_vcpu *vcpu); void (*sched_in)(struct kvm_vcpu *kvm, int cpu); @@ -1269,6 +1256,15 @@ struct kvm_x86_ops { int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu); }; +struct kvm_x86_init_ops { + int (*cpu_has_kvm_support)(void); + int (*disabled_by_bios)(void); + int (*check_processor_compatibility)(void); + int (*hardware_setup)(void); + + struct kvm_x86_ops *runtime_ops; +}; + struct kvm_arch_async_pf { u32 token; gfn_t gfn; @@ -1276,25 +1272,24 @@ struct kvm_arch_async_pf { bool direct_map; }; -extern struct kvm_x86_ops *kvm_x86_ops; +extern u64 __read_mostly host_efer; + +extern struct kvm_x86_ops kvm_x86_ops; extern struct kmem_cache *x86_fpu_cache; #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { - return kvm_x86_ops->vm_alloc(); -} - -static inline void kvm_arch_free_vm(struct kvm *kvm) -{ - return kvm_x86_ops->vm_free(kvm); + return __vmalloc(kvm_x86_ops.vm_size, + GFP_KERNEL_ACCOUNT | __GFP_ZERO, PAGE_KERNEL); } +void kvm_arch_free_vm(struct kvm *kvm); #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) { - if (kvm_x86_ops->tlb_remote_flush && - !kvm_x86_ops->tlb_remote_flush(kvm)) + if (kvm_x86_ops.tlb_remote_flush && + !kvm_x86_ops.tlb_remote_flush(kvm)) return 0; else return -ENOTSUPP; @@ -1313,7 +1308,8 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot); + struct kvm_memory_slot *memslot, + int start_level); void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, @@ -1379,10 +1375,11 @@ extern u64 kvm_mce_cap_supported; * * EMULTYPE_SKIP - Set when emulating solely to skip an instruction, i.e. to * decode the instruction length. For use *only* by - * kvm_x86_ops->skip_emulated_instruction() implementations. + * kvm_x86_ops.skip_emulated_instruction() implementations. * - * EMULTYPE_ALLOW_RETRY - Set when the emulator should resume the guest to - * retry native execution under certain conditions. + * EMULTYPE_ALLOW_RETRY_PF - Set when the emulator should resume the guest to + * retry native execution under certain conditions, + * Can only be set in conjunction with EMULTYPE_PF. * * EMULTYPE_TRAP_UD_FORCED - Set when emulating an intercepted #UD that was * triggered by KVM's magic "force emulation" prefix, @@ -1395,13 +1392,18 @@ extern u64 kvm_mce_cap_supported; * backdoor emulation, which is opt in via module param. * VMware backoor emulation handles select instructions * and reinjects the #GP for all other cases. + * + * EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which + * case the CR2/GPA value pass on the stack is valid. */ #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) -#define EMULTYPE_ALLOW_RETRY (1 << 3) +#define EMULTYPE_ALLOW_RETRY_PF (1 << 3) #define EMULTYPE_TRAP_UD_FORCED (1 << 4) #define EMULTYPE_VMWARE_GP (1 << 5) +#define EMULTYPE_PF (1 << 6) + int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len); @@ -1414,8 +1416,6 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data); int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu); int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu); -struct x86_emulate_ctxt; - int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); @@ -1512,8 +1512,7 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush); -void kvm_enable_tdp(void); -void kvm_disable_tdp(void); +void kvm_configure_mmu(bool enable_tdp, int tdp_page_level); static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception) @@ -1670,14 +1669,14 @@ static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops->vcpu_blocking) - kvm_x86_ops->vcpu_blocking(vcpu); + if (kvm_x86_ops.vcpu_blocking) + kvm_x86_ops.vcpu_blocking(vcpu); } static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops->vcpu_unblocking) - kvm_x86_ops->vcpu_unblocking(vcpu); + if (kvm_x86_ops.vcpu_unblocking) + kvm_x86_ops.vcpu_unblocking(vcpu); } static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 172f9749dbb2..87bd6025d91d 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -49,8 +49,7 @@ struct kvm_page_track_notifier_node { void kvm_page_track_init(struct kvm *kvm); void kvm_page_track_cleanup(struct kvm *kvm); -void kvm_page_track_free_memslot(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont); +void kvm_page_track_free_memslot(struct kvm_memory_slot *slot); int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 8521af3fef27..5e090d1f03f8 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -500,6 +500,18 @@ enum vmcs_field { VMX_EPT_EXECUTABLE_MASK) #define VMX_EPT_MT_MASK (7ull << VMX_EPT_MT_EPTE_SHIFT) +static inline u8 vmx_eptp_page_walk_level(u64 eptp) +{ + u64 encoded_level = eptp & VMX_EPTP_PWL_MASK; + + if (encoded_level == VMX_EPTP_PWL_5) + return 5; + + /* @eptp must be pre-validated by the caller. */ + WARN_ON_ONCE(encoded_level != VMX_EPTP_PWL_4); + return 4; +} + /* The mask to use to trigger an EPT Misconfiguration in order to track MMIO */ #define VMX_EPT_MISCONFIG_WX_VALUE (VMX_EPT_WRITABLE_MASK | \ VMX_EPT_EXECUTABLE_MASK) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b1c469446b07..901cd1fdecd9 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -24,6 +24,13 @@ #include "trace.h" #include "pmu.h" +/* + * Unlike "struct cpuinfo_x86.x86_capability", kvm_cpu_caps doesn't need to be + * aligned to sizeof(unsigned long) because it's not accessed via bitops. + */ +u32 kvm_cpu_caps[NCAPINTS] __read_mostly; +EXPORT_SYMBOL_GPL(kvm_cpu_caps); + static u32 xstate_required_size(u64 xstate_bv, bool compacted) { int feature_bit = 0; @@ -45,23 +52,6 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted) return ret; } -bool kvm_mpx_supported(void) -{ - return ((host_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) - && kvm_x86_ops->mpx_supported()); -} -EXPORT_SYMBOL_GPL(kvm_mpx_supported); - -u64 kvm_supported_xcr0(void) -{ - u64 xcr0 = KVM_SUPPORTED_XCR0 & host_xcr0; - - if (!kvm_mpx_supported()) - xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); - - return xcr0; -} - #define F feature_bit int kvm_update_cpuid(struct kvm_vcpu *vcpu) @@ -74,32 +64,24 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) return 0; /* Update OSXSAVE bit */ - if (boot_cpu_has(X86_FEATURE_XSAVE) && best->function == 0x1) { - best->ecx &= ~F(OSXSAVE); - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) - best->ecx |= F(OSXSAVE); - } + if (boot_cpu_has(X86_FEATURE_XSAVE) && best->function == 0x1) + cpuid_entry_change(best, X86_FEATURE_OSXSAVE, + kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)); - best->edx &= ~F(APIC); - if (vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE) - best->edx |= F(APIC); + cpuid_entry_change(best, X86_FEATURE_APIC, + vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE); if (apic) { - if (best->ecx & F(TSC_DEADLINE_TIMER)) + if (cpuid_entry_has(best, X86_FEATURE_TSC_DEADLINE_TIMER)) apic->lapic_timer.timer_mode_mask = 3 << 17; else apic->lapic_timer.timer_mode_mask = 1 << 17; } best = kvm_find_cpuid_entry(vcpu, 7, 0); - if (best) { - /* Update OSPKE bit */ - if (boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7) { - best->ecx &= ~F(OSPKE); - if (kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) - best->ecx |= F(OSPKE); - } - } + if (best && boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7) + cpuid_entry_change(best, X86_FEATURE_OSPKE, + kvm_read_cr4_bits(vcpu, X86_CR4_PKE)); best = kvm_find_cpuid_entry(vcpu, 0xD, 0); if (!best) { @@ -107,14 +89,14 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; } else { vcpu->arch.guest_supported_xcr0 = - (best->eax | ((u64)best->edx << 32)) & - kvm_supported_xcr0(); + (best->eax | ((u64)best->edx << 32)) & supported_xcr0; vcpu->arch.guest_xstate_size = best->ebx = xstate_required_size(vcpu->arch.xcr0, false); } best = kvm_find_cpuid_entry(vcpu, 0xD, 1); - if (best && (best->eax & (F(XSAVES) | F(XSAVEC)))) + if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) || + cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); /* @@ -136,12 +118,10 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { best = kvm_find_cpuid_entry(vcpu, 0x1, 0); - if (best) { - if (vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT) - best->ecx |= F(MWAIT); - else - best->ecx &= ~F(MWAIT); - } + if (best) + cpuid_entry_change(best, X86_FEATURE_MWAIT, + vcpu->arch.ia32_misc_enable_msr & + MSR_IA32_MISC_ENABLE_MWAIT); } /* Update physical-address width */ @@ -154,10 +134,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) static int is_efer_nx(void) { - unsigned long long efer = 0; - - rdmsrl_safe(MSR_EFER, &efer); - return efer & EFER_NX; + return host_efer & EFER_NX; } static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) @@ -173,8 +150,8 @@ static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) break; } } - if (entry && (entry->edx & F(NX)) && !is_efer_nx()) { - entry->edx &= ~F(NX); + if (entry && cpuid_entry_has(entry, X86_FEATURE_NX) && !is_efer_nx()) { + cpuid_entry_clear(entry, X86_FEATURE_NX); printk(KERN_INFO "kvm: guest NX capability removed\n"); } } @@ -232,7 +209,7 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, vcpu->arch.cpuid_nent = cpuid->nent; cpuid_fix_nx_cap(vcpu); kvm_apic_set_version(vcpu); - kvm_x86_ops->cpuid_update(vcpu); + kvm_x86_ops.cpuid_update(vcpu); r = kvm_update_cpuid(vcpu); out: @@ -255,7 +232,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, goto out; vcpu->arch.cpuid_nent = cpuid->nent; kvm_apic_set_version(vcpu); - kvm_x86_ops->cpuid_update(vcpu); + kvm_x86_ops.cpuid_update(vcpu); r = kvm_update_cpuid(vcpu); out: return r; @@ -281,15 +258,189 @@ out: return r; } -static __always_inline void cpuid_mask(u32 *word, int wordnum) +static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) { - reverse_cpuid_check(wordnum); - *word &= boot_cpu_data.x86_capability[wordnum]; + const struct cpuid_reg cpuid = x86_feature_cpuid(leaf * 32); + struct kvm_cpuid_entry2 entry; + + reverse_cpuid_check(leaf); + kvm_cpu_caps[leaf] &= mask; + + cpuid_count(cpuid.function, cpuid.index, + &entry.eax, &entry.ebx, &entry.ecx, &entry.edx); + + kvm_cpu_caps[leaf] &= *__cpuid_entry_get_reg(&entry, cpuid.reg); +} + +void kvm_set_cpu_caps(void) +{ + unsigned int f_nx = is_efer_nx() ? F(NX) : 0; +#ifdef CONFIG_X86_64 + unsigned int f_gbpages = F(GBPAGES); + unsigned int f_lm = F(LM); +#else + unsigned int f_gbpages = 0; + unsigned int f_lm = 0; +#endif + + BUILD_BUG_ON(sizeof(kvm_cpu_caps) > + sizeof(boot_cpu_data.x86_capability)); + + memcpy(&kvm_cpu_caps, &boot_cpu_data.x86_capability, + sizeof(kvm_cpu_caps)); + + kvm_cpu_cap_mask(CPUID_1_ECX, + /* + * NOTE: MONITOR (and MWAIT) are emulated as NOP, but *not* + * advertised to guests via CPUID! + */ + F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | + 0 /* DS-CPL, VMX, SMX, EST */ | + 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | + F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ | + F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) | + F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | + 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | + F(F16C) | F(RDRAND) + ); + /* KVM emulates x2apic in software irrespective of host support. */ + kvm_cpu_cap_set(X86_FEATURE_X2APIC); + + kvm_cpu_cap_mask(CPUID_1_EDX, + F(FPU) | F(VME) | F(DE) | F(PSE) | + F(TSC) | F(MSR) | F(PAE) | F(MCE) | + F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) | + F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | + F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLUSH) | + 0 /* Reserved, DS, ACPI */ | F(MMX) | + F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) | + 0 /* HTT, TM, Reserved, PBE */ + ); + + kvm_cpu_cap_mask(CPUID_7_0_EBX, + F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | + F(BMI2) | F(ERMS) | 0 /*INVPCID*/ | F(RTM) | 0 /*MPX*/ | F(RDSEED) | + F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) | + F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | + F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/ + ); + + kvm_cpu_cap_mask(CPUID_7_ECX, + F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(RDPID) | + 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*/ + ); + /* Set LA57 based on hardware capability. */ + if (cpuid_ecx(7) & F(LA57)) + kvm_cpu_cap_set(X86_FEATURE_LA57); + + kvm_cpu_cap_mask(CPUID_7_EDX, + F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | + F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | + F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) + ); + + /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ + kvm_cpu_cap_set(X86_FEATURE_TSC_ADJUST); + kvm_cpu_cap_set(X86_FEATURE_ARCH_CAPABILITIES); + + if (boot_cpu_has(X86_FEATURE_IBPB) && boot_cpu_has(X86_FEATURE_IBRS)) + kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + kvm_cpu_cap_set(X86_FEATURE_INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_AMD_SSBD)) + kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); + + kvm_cpu_cap_mask(CPUID_7_1_EAX, + F(AVX512_BF16) + ); + + kvm_cpu_cap_mask(CPUID_D_1_EAX, + F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) + ); + + kvm_cpu_cap_mask(CPUID_8000_0001_ECX, + F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | + F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | + F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | + 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | + F(TOPOEXT) | F(PERFCTR_CORE) + ); + + kvm_cpu_cap_mask(CPUID_8000_0001_EDX, + F(FPU) | F(VME) | F(DE) | F(PSE) | + F(TSC) | F(MSR) | F(PAE) | F(MCE) | + F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | + F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | + F(PAT) | F(PSE36) | 0 /* Reserved */ | + f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | + F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) | + 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW) + ); + + if (!tdp_enabled && IS_ENABLED(CONFIG_X86_64)) + kvm_cpu_cap_set(X86_FEATURE_GBPAGES); + + kvm_cpu_cap_mask(CPUID_8000_0008_EBX, + F(CLZERO) | F(XSAVEERPTR) | + F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | + F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) + ); + + /* + * AMD has separate bits for each SPEC_CTRL bit. + * arch/x86/kernel/cpu/bugs.c is kind enough to + * record that in cpufeatures so use them. + */ + if (boot_cpu_has(X86_FEATURE_IBPB)) + kvm_cpu_cap_set(X86_FEATURE_AMD_IBPB); + if (boot_cpu_has(X86_FEATURE_IBRS)) + kvm_cpu_cap_set(X86_FEATURE_AMD_IBRS); + if (boot_cpu_has(X86_FEATURE_STIBP)) + kvm_cpu_cap_set(X86_FEATURE_AMD_STIBP); + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) + kvm_cpu_cap_set(X86_FEATURE_AMD_SSBD); + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + kvm_cpu_cap_set(X86_FEATURE_AMD_SSB_NO); + /* + * The preference is to use SPEC CTRL MSR instead of the + * VIRT_SPEC MSR. + */ + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) && + !boot_cpu_has(X86_FEATURE_AMD_SSBD)) + kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); + + /* + * Hide all SVM features by default, SVM will set the cap bits for + * features it emulates and/or exposes for L1. + */ + kvm_cpu_cap_mask(CPUID_8000_000A_EDX, 0); + + kvm_cpu_cap_mask(CPUID_C000_0001_EDX, + F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | + F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | + F(PMM) | F(PMM_EN) + ); } +EXPORT_SYMBOL_GPL(kvm_set_cpu_caps); -static void do_host_cpuid(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index) +struct kvm_cpuid_array { + struct kvm_cpuid_entry2 *entries; + const int maxnent; + int nent; +}; + +static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, + u32 function, u32 index) { + struct kvm_cpuid_entry2 *entry; + + if (array->nent >= array->maxnent) + return NULL; + + entry = &array->entries[array->nent++]; + entry->function = function; entry->index = index; entry->flags = 0; @@ -298,9 +449,6 @@ static void do_host_cpuid(struct kvm_cpuid_entry2 *entry, u32 function, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); switch (function) { - case 2: - entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; - break; case 4: case 7: case 0xb: @@ -316,11 +464,18 @@ static void do_host_cpuid(struct kvm_cpuid_entry2 *entry, u32 function, entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; break; } + + return entry; } -static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, - u32 func, int *nent, int maxnent) +static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) { + struct kvm_cpuid_entry2 *entry; + + if (array->nent >= array->maxnent) + return -E2BIG; + + entry = &array->entries[array->nent]; entry->function = func; entry->index = 0; entry->flags = 0; @@ -328,17 +483,17 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, switch (func) { case 0: entry->eax = 7; - ++*nent; + ++array->nent; break; case 1: entry->ecx = F(MOVBE); - ++*nent; + ++array->nent; break; case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; entry->eax = 0; entry->ecx = F(RDPID); - ++*nent; + ++array->nent; default: break; } @@ -346,223 +501,60 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, return 0; } -static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) +static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) { - unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0; - unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0; - unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; - unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; - unsigned f_la57; - unsigned f_pku = kvm_x86_ops->pku_supported() ? F(PKU) : 0; - - /* cpuid 7.0.ebx */ - const u32 kvm_cpuid_7_0_ebx_x86_features = - F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | - F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) | - F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) | - F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | - F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | f_intel_pt; - - /* cpuid 7.0.ecx*/ - const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(RDPID) | - 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*/; - - /* cpuid 7.0.edx*/ - const u32 kvm_cpuid_7_0_edx_x86_features = - F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | - F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | - F(MD_CLEAR); - - /* cpuid 7.1.eax */ - const u32 kvm_cpuid_7_1_eax_x86_features = - F(AVX512_BF16); - - switch (index) { - case 0: - entry->eax = min(entry->eax, 1u); - entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_7_0_EBX); - /* TSC_ADJUST is emulated */ - entry->ebx |= F(TSC_ADJUST); - - entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; - f_la57 = entry->ecx & F(LA57); - cpuid_mask(&entry->ecx, CPUID_7_ECX); - /* Set LA57 based on hardware capability. */ - entry->ecx |= f_la57; - entry->ecx |= f_umip; - entry->ecx |= f_pku; - /* PKU is not yet implemented for shadow paging. */ - if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) - entry->ecx &= ~F(PKU); - - entry->edx &= kvm_cpuid_7_0_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_7_EDX); - if (boot_cpu_has(X86_FEATURE_IBPB) && boot_cpu_has(X86_FEATURE_IBRS)) - entry->edx |= F(SPEC_CTRL); - if (boot_cpu_has(X86_FEATURE_STIBP)) - entry->edx |= F(INTEL_STIBP); - if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - boot_cpu_has(X86_FEATURE_AMD_SSBD)) - entry->edx |= F(SPEC_CTRL_SSBD); - /* - * We emulate ARCH_CAPABILITIES in software even - * if the host doesn't support it. - */ - entry->edx |= F(ARCH_CAPABILITIES); - break; - case 1: - entry->eax &= kvm_cpuid_7_1_eax_x86_features; - entry->ebx = 0; - entry->ecx = 0; - entry->edx = 0; - break; - default: - WARN_ON_ONCE(1); - entry->eax = 0; - entry->ebx = 0; - entry->ecx = 0; - entry->edx = 0; - break; - } -} - -static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, - int *nent, int maxnent) -{ - int r; - unsigned f_nx = is_efer_nx() ? F(NX) : 0; -#ifdef CONFIG_X86_64 - unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL) - ? F(GBPAGES) : 0; - unsigned f_lm = F(LM); -#else - unsigned f_gbpages = 0; - unsigned f_lm = 0; -#endif - unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0; - unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0; - unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; - - /* cpuid 1.edx */ - const u32 kvm_cpuid_1_edx_x86_features = - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLUSH) | - 0 /* Reserved, DS, ACPI */ | F(MMX) | - F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) | - 0 /* HTT, TM, Reserved, PBE */; - /* cpuid 0x80000001.edx */ - const u32 kvm_cpuid_8000_0001_edx_x86_features = - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* Reserved */ | - f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | - F(FXSR) | F(FXSR_OPT) | f_gbpages | f_rdtscp | - 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW); - /* cpuid 1.ecx */ - const u32 kvm_cpuid_1_ecx_x86_features = - /* NOTE: MONITOR (and MWAIT) are emulated as NOP, - * but *not* advertised to guests via CPUID ! */ - F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | - 0 /* DS-CPL, VMX, SMX, EST */ | - 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | - F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ | - F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) | - F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | - 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | - F(F16C) | F(RDRAND); - /* cpuid 0x80000001.ecx */ - const u32 kvm_cpuid_8000_0001_ecx_x86_features = - F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | - F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | - F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | - 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | - F(TOPOEXT) | F(PERFCTR_CORE); - - /* cpuid 0x80000008.ebx */ - const u32 kvm_cpuid_8000_0008_ebx_x86_features = - F(CLZERO) | F(XSAVEERPTR) | - F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | - F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON); - - /* cpuid 0xC0000001.edx */ - const u32 kvm_cpuid_C000_0001_edx_x86_features = - F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | - F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | - F(PMM) | F(PMM_EN); - - /* cpuid 0xD.1.eax */ - const u32 kvm_cpuid_D_1_eax_x86_features = - F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | f_xsaves; + struct kvm_cpuid_entry2 *entry; + int r, i, max_idx; /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); r = -E2BIG; - if (WARN_ON(*nent >= maxnent)) + entry = do_host_cpuid(array, function, 0); + if (!entry) goto out; - do_host_cpuid(entry, function, 0); - ++*nent; - switch (function) { case 0: /* Limited to the highest leaf implemented in KVM. */ entry->eax = min(entry->eax, 0x1fU); break; case 1: - entry->edx &= kvm_cpuid_1_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_1_EDX); - entry->ecx &= kvm_cpuid_1_ecx_x86_features; - cpuid_mask(&entry->ecx, CPUID_1_ECX); - /* we support x2apic emulation even if host does not support - * it since we emulate x2apic in software */ - entry->ecx |= F(X2APIC); + cpuid_entry_override(entry, CPUID_1_EDX); + cpuid_entry_override(entry, CPUID_1_ECX); break; - /* function 2 entries are STATEFUL. That is, repeated cpuid commands - * may return different values. This forces us to get_cpu() before - * issuing the first command, and also to emulate this annoying behavior - * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */ - case 2: { - int t, times = entry->eax & 0xff; - - entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - for (t = 1; t < times; ++t) { - if (*nent >= maxnent) - goto out; - - do_host_cpuid(&entry[t], function, 0); - ++*nent; - } + case 2: + /* + * On ancient CPUs, function 2 entries are STATEFUL. That is, + * CPUID(function=2, index=0) may return different results each + * time, with the least-significant byte in EAX enumerating the + * number of times software should do CPUID(2, 0). + * + * Modern CPUs, i.e. every CPU KVM has *ever* run on are less + * idiotic. Intel's SDM states that EAX & 0xff "will always + * return 01H. Software should ignore this value and not + * interpret it as an informational descriptor", while AMD's + * APM states that CPUID(2) is reserved. + * + * WARN if a frankenstein CPU that supports virtualization and + * a stateful CPUID.0x2 is encountered. + */ + WARN_ON_ONCE((entry->eax & 0xff) > 1); break; - } /* functions 4 and 0x8000001d have additional index. */ case 4: - case 0x8000001d: { - int i, cache_type; - - /* read more entries until cache_type is zero */ - for (i = 1; ; ++i) { - if (*nent >= maxnent) + case 0x8000001d: + /* + * Read entries until the cache type in the previous entry is + * zero, i.e. indicates an invalid entry. + */ + for (i = 1; entry->eax & 0x1f; ++i) { + entry = do_host_cpuid(array, function, i); + if (!entry) goto out; - - cache_type = entry[i - 1].eax & 0x1f; - if (!cache_type) - break; - do_host_cpuid(&entry[i], function, i); - ++*nent; } break; - } case 6: /* Thermal management */ entry->eax = 0x4; /* allow ARAT */ entry->ebx = 0; @@ -570,22 +562,24 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, entry->edx = 0; break; /* function 7 has additional index. */ - case 7: { - int i; - - for (i = 0; ; ) { - do_cpuid_7_mask(&entry[i], i); - if (i == entry->eax) - break; - if (*nent >= maxnent) + case 7: + entry->eax = min(entry->eax, 1u); + cpuid_entry_override(entry, CPUID_7_0_EBX); + cpuid_entry_override(entry, CPUID_7_ECX); + cpuid_entry_override(entry, CPUID_7_EDX); + + /* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */ + if (entry->eax == 1) { + entry = do_host_cpuid(array, function, 1); + if (!entry) goto out; - ++i; - do_host_cpuid(&entry[i], function, i); - ++*nent; + cpuid_entry_override(entry, CPUID_7_1_EAX); + entry->ebx = 0; + entry->ecx = 0; + entry->edx = 0; } break; - } case 9: break; case 0xa: { /* Architectural Performance Monitoring */ @@ -622,79 +616,81 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, * thus they can be handled by common code. */ case 0x1f: - case 0xb: { - int i; - + case 0xb: /* - * We filled in entry[0] for CPUID(EAX=<function>, - * ECX=00H) above. If its level type (ECX[15:8]) is - * zero, then the leaf is unimplemented, and we're - * done. Otherwise, continue to populate entries - * until the level type (ECX[15:8]) of the previously - * added entry is zero. + * Populate entries until the level type (ECX[15:8]) of the + * previous entry is zero. Note, CPUID EAX.{0x1f,0xb}.0 is + * the starting entry, filled by the primary do_host_cpuid(). */ - for (i = 1; entry[i - 1].ecx & 0xff00; ++i) { - if (*nent >= maxnent) + for (i = 1; entry->ecx & 0xff00; ++i) { + entry = do_host_cpuid(array, function, i); + if (!entry) goto out; - - do_host_cpuid(&entry[i], function, i); - ++*nent; } break; - } - case 0xd: { - int idx, i; - u64 supported = kvm_supported_xcr0(); - - entry->eax &= supported; - entry->ebx = xstate_required_size(supported, false); + case 0xd: + entry->eax &= supported_xcr0; + entry->ebx = xstate_required_size(supported_xcr0, false); entry->ecx = entry->ebx; - entry->edx &= supported >> 32; - if (!supported) + entry->edx &= supported_xcr0 >> 32; + if (!supported_xcr0) break; - for (idx = 1, i = 1; idx < 64; ++idx) { - u64 mask = ((u64)1 << idx); - if (*nent >= maxnent) + entry = do_host_cpuid(array, function, 1); + if (!entry) + goto out; + + cpuid_entry_override(entry, CPUID_D_1_EAX); + if (entry->eax & (F(XSAVES)|F(XSAVEC))) + entry->ebx = xstate_required_size(supported_xcr0 | supported_xss, + true); + else { + WARN_ON_ONCE(supported_xss != 0); + entry->ebx = 0; + } + entry->ecx &= supported_xss; + entry->edx &= supported_xss >> 32; + + for (i = 2; i < 64; ++i) { + bool s_state; + if (supported_xcr0 & BIT_ULL(i)) + s_state = false; + else if (supported_xss & BIT_ULL(i)) + s_state = true; + else + continue; + + entry = do_host_cpuid(array, function, i); + if (!entry) goto out; - do_host_cpuid(&entry[i], function, idx); - if (idx == 1) { - entry[i].eax &= kvm_cpuid_D_1_eax_x86_features; - cpuid_mask(&entry[i].eax, CPUID_D_1_EAX); - entry[i].ebx = 0; - if (entry[i].eax & (F(XSAVES)|F(XSAVEC))) - entry[i].ebx = - xstate_required_size(supported, - true); - } else { - if (entry[i].eax == 0 || !(supported & mask)) - continue; - if (WARN_ON_ONCE(entry[i].ecx & 1)) - continue; + /* + * The supported check above should have filtered out + * invalid sub-leafs. Only valid sub-leafs should + * reach this point, and they should have a non-zero + * save state size. Furthermore, check whether the + * processor agrees with supported_xcr0/supported_xss + * on whether this is an XCR0- or IA32_XSS-managed area. + */ + if (WARN_ON_ONCE(!entry->eax || (entry->ecx & 0x1) != s_state)) { + --array->nent; + continue; } - entry[i].ecx = 0; - entry[i].edx = 0; - ++*nent; - ++i; + entry->edx = 0; } break; - } /* Intel PT */ - case 0x14: { - int t, times = entry->eax; - - if (!f_intel_pt) + case 0x14: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; + } - for (t = 1; t <= times; ++t) { - if (*nent >= maxnent) + for (i = 1, max_idx = entry->eax; i <= max_idx; ++i) { + if (!do_host_cpuid(array, function, i)) goto out; - do_host_cpuid(&entry[t], function, t); - ++*nent; } break; - } case KVM_CPUID_SIGNATURE: { static const char signature[12] = "KVMKVMKVM\0\0"; const u32 *sigptr = (const u32 *)signature; @@ -729,10 +725,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, entry->eax = min(entry->eax, 0x8000001f); break; case 0x80000001: - entry->edx &= kvm_cpuid_8000_0001_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_8000_0001_EDX); - entry->ecx &= kvm_cpuid_8000_0001_ecx_x86_features; - cpuid_mask(&entry->ecx, CPUID_8000_0001_ECX); + cpuid_entry_override(entry, CPUID_8000_0001_EDX); + cpuid_entry_override(entry, CPUID_8000_0001_ECX); break; case 0x80000007: /* Advanced power management */ /* invariant TSC is CPUID.80000007H:EDX[8] */ @@ -750,33 +744,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; - entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); - /* - * AMD has separate bits for each SPEC_CTRL bit. - * arch/x86/kernel/cpu/bugs.c is kind enough to - * record that in cpufeatures so use them. - */ - if (boot_cpu_has(X86_FEATURE_IBPB)) - entry->ebx |= F(AMD_IBPB); - if (boot_cpu_has(X86_FEATURE_IBRS)) - entry->ebx |= F(AMD_IBRS); - if (boot_cpu_has(X86_FEATURE_STIBP)) - entry->ebx |= F(AMD_STIBP); - if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - boot_cpu_has(X86_FEATURE_AMD_SSBD)) - entry->ebx |= F(AMD_SSBD); - if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) - entry->ebx |= F(AMD_SSB_NO); - /* - * The preference is to use SPEC CTRL MSR instead of the - * VIRT_SPEC MSR. - */ - if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) && - !boot_cpu_has(X86_FEATURE_AMD_SSBD)) - entry->ebx |= F(VIRT_SSBD); + cpuid_entry_override(entry, CPUID_8000_0008_EBX); break; } + case 0x8000000A: + if (!kvm_cpu_cap_has(X86_FEATURE_SVM)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + entry->eax = 1; /* SVM revision 1 */ + entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper + ASID emulation to nested SVM */ + entry->ecx = 0; /* Reserved */ + cpuid_entry_override(entry, CPUID_8000_000A_EDX); + break; case 0x80000019: entry->ecx = entry->edx = 0; break; @@ -794,8 +775,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, entry->eax = min(entry->eax, 0xC0000004); break; case 0xC0000001: - entry->edx &= kvm_cpuid_C000_0001_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_C000_0001_EDX); + cpuid_entry_override(entry, CPUID_C000_0001_EDX); break; case 3: /* Processor serial number */ case 5: /* MONITOR/MWAIT */ @@ -807,8 +787,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, break; } - kvm_x86_ops->set_supported_cpuid(function, entry); - r = 0; out: @@ -817,26 +795,39 @@ out: return r; } -static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func, - int *nent, int maxnent, unsigned int type) +static int do_cpuid_func(struct kvm_cpuid_array *array, u32 func, + unsigned int type) { - if (*nent >= maxnent) - return -E2BIG; - if (type == KVM_GET_EMULATED_CPUID) - return __do_cpuid_func_emulated(entry, func, nent, maxnent); + return __do_cpuid_func_emulated(array, func); - return __do_cpuid_func(entry, func, nent, maxnent); + return __do_cpuid_func(array, func); } -struct kvm_cpuid_param { - u32 func; - bool (*qualifier)(const struct kvm_cpuid_param *param); -}; +#define CENTAUR_CPUID_SIGNATURE 0xC0000000 -static bool is_centaur_cpu(const struct kvm_cpuid_param *param) +static int get_cpuid_func(struct kvm_cpuid_array *array, u32 func, + unsigned int type) { - return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR; + u32 limit; + int r; + + if (func == CENTAUR_CPUID_SIGNATURE && + boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR) + return 0; + + r = do_cpuid_func(array, func, type); + if (r) + return r; + + limit = array->entries[array->nent - 1].eax; + for (func = func + 1; func <= limit; ++func) { + r = do_cpuid_func(array, func, type); + if (r) + break; + } + + return r; } static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries, @@ -870,157 +861,145 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries, unsigned int type) { - struct kvm_cpuid_entry2 *cpuid_entries; - int limit, nent = 0, r = -E2BIG, i; - u32 func; - static const struct kvm_cpuid_param param[] = { - { .func = 0 }, - { .func = 0x80000000 }, - { .func = 0xC0000000, .qualifier = is_centaur_cpu }, - { .func = KVM_CPUID_SIGNATURE }, + static const u32 funcs[] = { + 0, 0x80000000, CENTAUR_CPUID_SIGNATURE, KVM_CPUID_SIGNATURE, + }; + + struct kvm_cpuid_array array = { + .nent = 0, + .maxnent = cpuid->nent, }; + int r, i; if (cpuid->nent < 1) - goto out; + return -E2BIG; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) cpuid->nent = KVM_MAX_CPUID_ENTRIES; if (sanity_check_entries(entries, cpuid->nent, type)) return -EINVAL; - r = -ENOMEM; - cpuid_entries = vzalloc(array_size(sizeof(struct kvm_cpuid_entry2), + array.entries = vzalloc(array_size(sizeof(struct kvm_cpuid_entry2), cpuid->nent)); - if (!cpuid_entries) - goto out; - - r = 0; - for (i = 0; i < ARRAY_SIZE(param); i++) { - const struct kvm_cpuid_param *ent = ¶m[i]; - - if (ent->qualifier && !ent->qualifier(ent)) - continue; - - r = do_cpuid_func(&cpuid_entries[nent], ent->func, - &nent, cpuid->nent, type); - - if (r) - goto out_free; - - limit = cpuid_entries[nent - 1].eax; - for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) - r = do_cpuid_func(&cpuid_entries[nent], func, - &nent, cpuid->nent, type); + if (!array.entries) + return -ENOMEM; + for (i = 0; i < ARRAY_SIZE(funcs); i++) { + r = get_cpuid_func(&array, funcs[i], type); if (r) goto out_free; } + cpuid->nent = array.nent; - r = -EFAULT; - if (copy_to_user(entries, cpuid_entries, - nent * sizeof(struct kvm_cpuid_entry2))) - goto out_free; - cpuid->nent = nent; - r = 0; + if (copy_to_user(entries, array.entries, + array.nent * sizeof(struct kvm_cpuid_entry2))) + r = -EFAULT; out_free: - vfree(cpuid_entries); -out: + vfree(array.entries); return r; } -static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) -{ - struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; - struct kvm_cpuid_entry2 *ej; - int j = i; - int nent = vcpu->arch.cpuid_nent; - - e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; - /* when no next entry is found, the current entry[i] is reselected */ - do { - j = (j + 1) % nent; - ej = &vcpu->arch.cpuid_entries[j]; - } while (ej->function != e->function); - - ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - - return j; -} - -/* find an entry with matching function, matching index (if needed), and that - * should be read next (if it's stateful) */ -static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e, - u32 function, u32 index) -{ - if (e->function != function) - return 0; - if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index) - return 0; - if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) && - !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) - return 0; - return 1; -} - struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index) { + struct kvm_cpuid_entry2 *e; int i; - struct kvm_cpuid_entry2 *best = NULL; for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - struct kvm_cpuid_entry2 *e; - e = &vcpu->arch.cpuid_entries[i]; - if (is_matching_cpuid_entry(e, function, index)) { - if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) - move_to_next_stateful_cpuid_entry(vcpu, i); - best = e; - break; - } + + if (e->function == function && (e->index == index || + !(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX))) + return e; } - return best; + return NULL; } EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); /* - * If the basic or extended CPUID leaf requested is higher than the - * maximum supported basic or extended leaf, respectively, then it is - * out of range. + * Intel CPUID semantics treats any query for an out-of-range leaf as if the + * highest basic leaf (i.e. CPUID.0H:EAX) were requested. AMD CPUID semantics + * returns all zeroes for any undefined leaf, whether or not the leaf is in + * range. Centaur/VIA follows Intel semantics. + * + * A leaf is considered out-of-range if its function is higher than the maximum + * supported leaf of its associated class or if its associated class does not + * exist. + * + * There are three primary classes to be considered, with their respective + * ranges described as "<base> - <top>[,<base2> - <top2>] inclusive. A primary + * class exists if a guest CPUID entry for its <base> leaf exists. For a given + * class, CPUID.<base>.EAX contains the max supported leaf for the class. + * + * - Basic: 0x00000000 - 0x3fffffff, 0x50000000 - 0x7fffffff + * - Hypervisor: 0x40000000 - 0x4fffffff + * - Extended: 0x80000000 - 0xbfffffff + * - Centaur: 0xc0000000 - 0xcfffffff + * + * The Hypervisor class is further subdivided into sub-classes that each act as + * their own indepdent class associated with a 0x100 byte range. E.g. if Qemu + * is advertising support for both HyperV and KVM, the resulting Hypervisor + * CPUID sub-classes are: + * + * - HyperV: 0x40000000 - 0x400000ff + * - KVM: 0x40000100 - 0x400001ff */ -static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function) +static struct kvm_cpuid_entry2 * +get_out_of_range_cpuid_entry(struct kvm_vcpu *vcpu, u32 *fn_ptr, u32 index) { - struct kvm_cpuid_entry2 *max; + struct kvm_cpuid_entry2 *basic, *class; + u32 function = *fn_ptr; + + basic = kvm_find_cpuid_entry(vcpu, 0, 0); + if (!basic) + return NULL; + + if (is_guest_vendor_amd(basic->ebx, basic->ecx, basic->edx) || + is_guest_vendor_hygon(basic->ebx, basic->ecx, basic->edx)) + return NULL; - max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); - return max && function <= max->eax; + if (function >= 0x40000000 && function <= 0x4fffffff) + class = kvm_find_cpuid_entry(vcpu, function & 0xffffff00, 0); + else if (function >= 0xc0000000) + class = kvm_find_cpuid_entry(vcpu, 0xc0000000, 0); + else + class = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); + + if (class && function <= class->eax) + return NULL; + + /* + * Leaf specific adjustments are also applied when redirecting to the + * max basic entry, e.g. if the max basic leaf is 0xb but there is no + * entry for CPUID.0xb.index (see below), then the output value for EDX + * needs to be pulled from CPUID.0xb.1. + */ + *fn_ptr = basic->eax; + + /* + * The class does not exist or the requested function is out of range; + * the effective CPUID entry is the max basic leaf. Note, the index of + * the original requested leaf is observed! + */ + return kvm_find_cpuid_entry(vcpu, basic->eax, index); } bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, - u32 *ecx, u32 *edx, bool check_limit) + u32 *ecx, u32 *edx, bool exact_only) { - u32 function = *eax, index = *ecx; + u32 orig_function = *eax, function = *eax, index = *ecx; struct kvm_cpuid_entry2 *entry; - struct kvm_cpuid_entry2 *max; - bool found; + bool exact, used_max_basic = false; entry = kvm_find_cpuid_entry(vcpu, function, index); - found = entry; - /* - * Intel CPUID semantics treats any query for an out-of-range - * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were - * requested. AMD CPUID semantics returns all zeroes for any - * undefined leaf, whether or not the leaf is in range. - */ - if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) && - !cpuid_function_in_range(vcpu, function)) { - max = kvm_find_cpuid_entry(vcpu, 0, 0); - if (max) { - function = max->eax; - entry = kvm_find_cpuid_entry(vcpu, function, index); - } + exact = !!entry; + + if (!entry && !exact_only) { + entry = get_out_of_range_cpuid_entry(vcpu, &function, index); + used_max_basic = !!entry; } + if (entry) { *eax = entry->eax; *ebx = entry->ebx; @@ -1049,8 +1028,9 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, } } } - trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found); - return found; + trace_kvm_cpuid(orig_function, index, *eax, *ebx, *ecx, *edx, exact, + used_max_basic); + return exact; } EXPORT_SYMBOL_GPL(kvm_cpuid); @@ -1063,7 +1043,7 @@ int kvm_emulate_cpuid(struct kvm_vcpu *vcpu) eax = kvm_rax_read(vcpu); ecx = kvm_rcx_read(vcpu); - kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, true); + kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, false); kvm_rax_write(vcpu, eax); kvm_rbx_write(vcpu, ebx); kvm_rcx_write(vcpu, ecx); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 7366c618aa04..63a70f6a3df3 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -6,8 +6,10 @@ #include <asm/cpu.h> #include <asm/processor.h> +extern u32 kvm_cpu_caps[NCAPINTS] __read_mostly; +void kvm_set_cpu_caps(void); + int kvm_update_cpuid(struct kvm_vcpu *vcpu); -bool kvm_mpx_supported(void); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index); int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, @@ -23,7 +25,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, - u32 *ecx, u32 *edx, bool check_limit); + u32 *ecx, u32 *edx, bool exact_only); int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); @@ -64,7 +66,7 @@ static const struct cpuid_reg reverse_cpuid[] = { * and can't be used by KVM to query/control guest capabilities. And obviously * the leaf being queried must have an entry in the lookup table. */ -static __always_inline void reverse_cpuid_check(unsigned x86_leaf) +static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) { BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); @@ -88,24 +90,18 @@ static __always_inline u32 __feature_bit(int x86_feature) #define feature_bit(name) __feature_bit(X86_FEATURE_##name) -static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) +static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned int x86_feature) { - unsigned x86_leaf = x86_feature / 32; + unsigned int x86_leaf = x86_feature / 32; reverse_cpuid_check(x86_leaf); return reverse_cpuid[x86_leaf]; } -static __always_inline int *guest_cpuid_get_register(struct kvm_vcpu *vcpu, unsigned x86_feature) +static __always_inline u32 *__cpuid_entry_get_reg(struct kvm_cpuid_entry2 *entry, + u32 reg) { - struct kvm_cpuid_entry2 *entry; - const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature); - - entry = kvm_find_cpuid_entry(vcpu, cpuid.function, cpuid.index); - if (!entry) - return NULL; - - switch (cpuid.reg) { + switch (reg) { case CPUID_EAX: return &entry->eax; case CPUID_EBX: @@ -120,9 +116,86 @@ static __always_inline int *guest_cpuid_get_register(struct kvm_vcpu *vcpu, unsi } } -static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, unsigned x86_feature) +static __always_inline u32 *cpuid_entry_get_reg(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature) +{ + const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature); + + return __cpuid_entry_get_reg(entry, cpuid.reg); +} + +static __always_inline u32 cpuid_entry_get(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature) +{ + u32 *reg = cpuid_entry_get_reg(entry, x86_feature); + + return *reg & __feature_bit(x86_feature); +} + +static __always_inline bool cpuid_entry_has(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature) +{ + return cpuid_entry_get(entry, x86_feature); +} + +static __always_inline void cpuid_entry_clear(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature) +{ + u32 *reg = cpuid_entry_get_reg(entry, x86_feature); + + *reg &= ~__feature_bit(x86_feature); +} + +static __always_inline void cpuid_entry_set(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature) +{ + u32 *reg = cpuid_entry_get_reg(entry, x86_feature); + + *reg |= __feature_bit(x86_feature); +} + +static __always_inline void cpuid_entry_change(struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature, + bool set) +{ + u32 *reg = cpuid_entry_get_reg(entry, x86_feature); + + /* + * Open coded instead of using cpuid_entry_{clear,set}() to coerce the + * compiler into using CMOV instead of Jcc when possible. + */ + if (set) + *reg |= __feature_bit(x86_feature); + else + *reg &= ~__feature_bit(x86_feature); +} + +static __always_inline void cpuid_entry_override(struct kvm_cpuid_entry2 *entry, + enum cpuid_leafs leaf) +{ + u32 *reg = cpuid_entry_get_reg(entry, leaf * 32); + + BUILD_BUG_ON(leaf >= ARRAY_SIZE(kvm_cpu_caps)); + *reg = kvm_cpu_caps[leaf]; +} + +static __always_inline u32 *guest_cpuid_get_register(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { - int *reg; + const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature); + struct kvm_cpuid_entry2 *entry; + + entry = kvm_find_cpuid_entry(vcpu, cpuid.function, cpuid.index); + if (!entry) + return NULL; + + return __cpuid_entry_get_reg(entry, cpuid.reg); +} + +static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, + unsigned int x86_feature) +{ + u32 *reg; reg = guest_cpuid_get_register(vcpu, x86_feature); if (!reg) @@ -131,21 +204,24 @@ static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, unsigned x86_ return *reg & __feature_bit(x86_feature); } -static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x86_feature) +static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { - int *reg; + u32 *reg; reg = guest_cpuid_get_register(vcpu, x86_feature); if (reg) *reg &= ~__feature_bit(x86_feature); } -static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu) +static inline bool guest_cpuid_is_amd_or_hygon(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; best = kvm_find_cpuid_entry(vcpu, 0, 0); - return best && best->ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx; + return best && + (is_guest_vendor_amd(best->ebx, best->ecx, best->edx) || + is_guest_vendor_hygon(best->ebx, best->ecx, best->edx)); } static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) @@ -192,4 +268,39 @@ static inline bool cpuid_fault_enabled(struct kvm_vcpu *vcpu) MSR_MISC_FEATURES_ENABLES_CPUID_FAULT; } +static __always_inline void kvm_cpu_cap_clear(unsigned int x86_feature) +{ + unsigned int x86_leaf = x86_feature / 32; + + reverse_cpuid_check(x86_leaf); + kvm_cpu_caps[x86_leaf] &= ~__feature_bit(x86_feature); +} + +static __always_inline void kvm_cpu_cap_set(unsigned int x86_feature) +{ + unsigned int x86_leaf = x86_feature / 32; + + reverse_cpuid_check(x86_leaf); + kvm_cpu_caps[x86_leaf] |= __feature_bit(x86_feature); +} + +static __always_inline u32 kvm_cpu_cap_get(unsigned int x86_feature) +{ + unsigned int x86_leaf = x86_feature / 32; + + reverse_cpuid_check(x86_leaf); + return kvm_cpu_caps[x86_leaf] & __feature_bit(x86_feature); +} + +static __always_inline bool kvm_cpu_cap_has(unsigned int x86_feature) +{ + return !!kvm_cpu_cap_get(x86_feature); +} + +static __always_inline void kvm_cpu_cap_check_and_set(unsigned int x86_feature) +{ + if (boot_cpu_has(x86_feature)) + kvm_cpu_cap_set(x86_feature); +} + #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index bc00642e5d3b..bddaba9c68dd 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -20,7 +20,7 @@ #include <linux/kvm_host.h> #include "kvm_cache_regs.h" -#include <asm/kvm_emulate.h> +#include "kvm_emulate.h" #include <linux/stringify.h> #include <asm/fpu/api.h> #include <asm/debugreg.h> @@ -665,6 +665,17 @@ static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector, ctxt->ops->set_segment(ctxt, selector, &desc, base3, seg); } +static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt) +{ + return (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_LA57) ? 57 : 48; +} + +static inline bool emul_is_noncanonical_address(u64 la, + struct x86_emulate_ctxt *ctxt) +{ + return get_canonical(la, ctxt_virt_addr_bits(ctxt)) != la; +} + /* * x86 defines three classes of vector instructions: explicitly * aligned, explicitly unaligned, and the rest, which change behaviour @@ -2711,10 +2722,8 @@ static bool vendor_intel(struct x86_emulate_ctxt *ctxt) u32 eax, ebx, ecx, edx; eax = ecx = 0; - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); - return ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx - && ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx - && edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx; + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true); + return is_guest_vendor_intel(ebx, ecx, edx); } static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt) @@ -2731,36 +2740,18 @@ static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt) eax = 0x00000000; ecx = 0x00000000; - ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); + ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true); /* - * Intel ("GenuineIntel") - * remark: Intel CPUs only support "syscall" in 64bit - * longmode. Also an 64bit guest with a - * 32bit compat-app running will #UD !! While this - * behaviour can be fixed (by emulating) into AMD - * response - CPUs of AMD can't behave like Intel. + * remark: Intel CPUs only support "syscall" in 64bit longmode. Also a + * 64bit guest with a 32bit compat-app running will #UD !! While this + * behaviour can be fixed (by emulating) into AMD response - CPUs of + * AMD can't behave like Intel. */ - if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && - ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && - edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx) + if (is_guest_vendor_intel(ebx, ecx, edx)) return false; - /* AMD ("AuthenticAMD") */ - if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx && - ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx && - edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) - return true; - - /* AMD ("AMDisbetter!") */ - if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx && - ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx && - edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx) - return true; - - /* Hygon ("HygonGenuine") */ - if (ebx == X86EMUL_CPUID_VENDOR_HygonGenuine_ebx && - ecx == X86EMUL_CPUID_VENDOR_HygonGenuine_ecx && - edx == X86EMUL_CPUID_VENDOR_HygonGenuine_edx) + if (is_guest_vendor_amd(ebx, ecx, edx) || + is_guest_vendor_hygon(ebx, ecx, edx)) return true; /* @@ -3980,7 +3971,7 @@ static int em_cpuid(struct x86_emulate_ctxt *ctxt) eax = reg_read(ctxt, VCPU_REGS_RAX); ecx = reg_read(ctxt, VCPU_REGS_RCX); - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true); + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); *reg_write(ctxt, VCPU_REGS_RAX) = eax; *reg_write(ctxt, VCPU_REGS_RBX) = ebx; *reg_write(ctxt, VCPU_REGS_RCX) = ecx; @@ -4250,7 +4241,7 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt) eax = 0x80000008; ecx = 0; if (ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, - &edx, false)) + &edx, true)) maxphyaddr = eax & 0xff; else maxphyaddr = 36; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index a86fda7a1d03..bcefa9d4e57e 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1022,7 +1022,7 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) return 1; - kvm_x86_ops->patch_hypercall(vcpu, instructions); + kvm_x86_ops.patch_hypercall(vcpu, instructions); ((unsigned char *)instructions)[3] = 0xc3; /* ret */ if (__copy_to_user((void __user *)addr, instructions, 4)) return 1; @@ -1607,7 +1607,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) * hypercall generates UD from non zero cpl and real mode * per HYPER-V spec */ - if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { + if (kvm_x86_ops.get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -1800,8 +1800,8 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, }; int i, nent = ARRAY_SIZE(cpuid_entries); - if (kvm_x86_ops->nested_get_evmcs_version) - evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu); + if (kvm_x86_ops.nested_get_evmcs_version) + evmcs_ver = kvm_x86_ops.nested_get_evmcs_version(vcpu); /* Skip NESTED_FEATURES if eVMCS is not supported */ if (!evmcs_ver) diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index b24c606ac04b..febca334c320 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -367,7 +367,7 @@ static void pit_load_count(struct kvm_pit *pit, int channel, u32 val) { struct kvm_kpit_state *ps = &pit->pit_state; - pr_debug("load_count val is %d, channel is %d\n", val, channel); + pr_debug("load_count val is %u, channel is %d\n", val, channel); /* * The largest possible initial count is 0; this is equivalent diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 58767020de41..62558b9bdda7 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -68,7 +68,7 @@ static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg) return 0; if (!kvm_register_is_available(vcpu, reg)) - kvm_x86_ops->cache_reg(vcpu, reg); + kvm_x86_ops.cache_reg(vcpu, reg); return vcpu->arch.regs[reg]; } @@ -108,7 +108,7 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) might_sleep(); /* on svm */ if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) - kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR); + kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_PDPTR); return vcpu->arch.walk_mmu->pdptrs[index]; } @@ -117,7 +117,7 @@ static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS; if (tmask & vcpu->arch.cr0_guest_owned_bits) - kvm_x86_ops->decache_cr0_guest_bits(vcpu); + kvm_x86_ops.decache_cr0_guest_bits(vcpu); return vcpu->arch.cr0 & mask; } @@ -130,14 +130,14 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR4_GUEST_BITS; if (tmask & vcpu->arch.cr4_guest_owned_bits) - kvm_x86_ops->decache_cr4_guest_bits(vcpu); + kvm_x86_ops.decache_cr4_guest_bits(vcpu); return vcpu->arch.cr4 & mask; } static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu) { if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) - kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_CR3); + kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_CR3); return vcpu->arch.cr3; } diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index c06e8353efd3..43c93ffa76ed 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -221,7 +221,7 @@ struct x86_emulate_ops { enum x86_intercept_stage stage); bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx, - u32 *ecx, u32 *edx, bool check_limit); + u32 *ecx, u32 *edx, bool exact_only); bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt); bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt); bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt); @@ -301,6 +301,7 @@ struct fastop; typedef void (*fastop_t)(struct fastop *); struct x86_emulate_ctxt { + void *vcpu; const struct x86_emulate_ops *ops; /* Register state before/after emulation. */ @@ -319,6 +320,10 @@ struct x86_emulate_ctxt { bool have_exception; struct x86_exception exception; + /* GPA available */ + bool gpa_available; + gpa_t gpa_val; + /* * decode cache */ @@ -329,9 +334,6 @@ struct x86_emulate_ctxt { u8 intercept; u8 op_bytes; u8 ad_bytes; - struct operand src; - struct operand src2; - struct operand dst; union { int (*execute)(struct x86_emulate_ctxt *ctxt); fastop_t fop; @@ -359,6 +361,11 @@ struct x86_emulate_ctxt { u8 seg_override; u64 d; unsigned long _eip; + + /* Here begins the usercopy section. */ + struct operand src; + struct operand src2; + struct operand dst; struct operand memop; unsigned long _regs[NR_VCPU_REGS]; struct operand *memopp; @@ -388,6 +395,34 @@ struct x86_emulate_ctxt { #define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e #define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69 +#define X86EMUL_CPUID_VENDOR_CentaurHauls_ebx 0x746e6543 +#define X86EMUL_CPUID_VENDOR_CentaurHauls_ecx 0x736c7561 +#define X86EMUL_CPUID_VENDOR_CentaurHauls_edx 0x48727561 + +static inline bool is_guest_vendor_intel(u32 ebx, u32 ecx, u32 edx) +{ + return ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && + ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && + edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx; +} + +static inline bool is_guest_vendor_amd(u32 ebx, u32 ecx, u32 edx) +{ + return (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx && + ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx && + edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) || + (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx && + ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx && + edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx); +} + +static inline bool is_guest_vendor_hygon(u32 ebx, u32 ecx, u32 edx) +{ + return ebx == X86EMUL_CPUID_VENDOR_HygonGenuine_ebx && + ecx == X86EMUL_CPUID_VENDOR_HygonGenuine_ecx && + edx == X86EMUL_CPUID_VENDOR_HygonGenuine_edx; +} + enum x86_intercept_stage { X86_ICTP_NONE = 0, /* Allow zero-init to not match anything */ X86_ICPT_PRE_EXCEPT, diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 7356a56e6282..ca80daf8f878 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -164,14 +164,28 @@ static void kvm_apic_map_free(struct rcu_head *rcu) kvfree(map); } -static void recalculate_apic_map(struct kvm *kvm) +void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; int i; u32 max_id = 255; /* enough space for any xAPIC ID */ + if (!kvm->arch.apic_map_dirty) { + /* + * Read kvm->arch.apic_map_dirty before + * kvm->arch.apic_map + */ + smp_rmb(); + return; + } + mutex_lock(&kvm->arch.apic_map_lock); + if (!kvm->arch.apic_map_dirty) { + /* Someone else has updated the map. */ + mutex_unlock(&kvm->arch.apic_map_lock); + return; + } kvm_for_each_vcpu(i, vcpu, kvm) if (kvm_apic_present(vcpu)) @@ -236,6 +250,12 @@ out: old = rcu_dereference_protected(kvm->arch.apic_map, lockdep_is_held(&kvm->arch.apic_map_lock)); rcu_assign_pointer(kvm->arch.apic_map, new); + /* + * Write kvm->arch.apic_map before + * clearing apic->apic_map_dirty + */ + smp_wmb(); + kvm->arch.apic_map_dirty = false; mutex_unlock(&kvm->arch.apic_map_lock); if (old) @@ -257,20 +277,20 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) else static_key_slow_inc(&apic_sw_disabled.key); - recalculate_apic_map(apic->vcpu->kvm); + apic->vcpu->kvm->arch.apic_map_dirty = true; } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) { kvm_lapic_set_reg(apic, APIC_ID, id << 24); - recalculate_apic_map(apic->vcpu->kvm); + apic->vcpu->kvm->arch.apic_map_dirty = true; } static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) { kvm_lapic_set_reg(apic, APIC_LDR, id); - recalculate_apic_map(apic->vcpu->kvm); + apic->vcpu->kvm->arch.apic_map_dirty = true; } static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) @@ -286,7 +306,7 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) kvm_lapic_set_reg(apic, APIC_ID, id); kvm_lapic_set_reg(apic, APIC_LDR, ldr); - recalculate_apic_map(apic->vcpu->kvm); + apic->vcpu->kvm->arch.apic_map_dirty = true; } static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) @@ -294,11 +314,6 @@ static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) return !(kvm_lapic_get_reg(apic, lvt_type) & APIC_LVT_MASKED); } -static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type) -{ - return kvm_lapic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK; -} - static inline int apic_lvtt_oneshot(struct kvm_lapic *apic) { return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_ONESHOT; @@ -448,7 +463,7 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) if (unlikely(vcpu->arch.apicv_active)) { /* need to update RVI */ kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); - kvm_x86_ops->hwapic_irr_update(vcpu, + kvm_x86_ops.hwapic_irr_update(vcpu, apic_find_highest_irr(apic)); } else { apic->irr_pending = false; @@ -473,7 +488,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) * just set SVI. */ if (unlikely(vcpu->arch.apicv_active)) - kvm_x86_ops->hwapic_isr_update(vcpu, vec); + kvm_x86_ops.hwapic_isr_update(vcpu, vec); else { ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -521,7 +536,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) * and must be left alone. */ if (unlikely(vcpu->arch.apicv_active)) - kvm_x86_ops->hwapic_isr_update(vcpu, + kvm_x86_ops.hwapic_isr_update(vcpu, apic_find_highest_isr(apic)); else { --apic->isr_count; @@ -659,7 +674,7 @@ static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) { int highest_irr; if (apic->vcpu->arch.apicv_active) - highest_irr = kvm_x86_ops->sync_pir_to_irr(apic->vcpu); + highest_irr = kvm_x86_ops.sync_pir_to_irr(apic->vcpu); else highest_irr = apic_find_highest_irr(apic); if (highest_irr == -1 || (highest_irr & 0xF0) <= ppr) @@ -1048,7 +1063,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic->regs + APIC_TMR); } - if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) { + if (kvm_x86_ops.deliver_posted_interrupt(vcpu, vector)) { kvm_lapic_set_irr(vector, apic); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); @@ -1226,7 +1241,7 @@ void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector) } EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated); -static void apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high) +void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high) { struct kvm_lapic_irq irq; @@ -1737,7 +1752,7 @@ static void cancel_hv_timer(struct kvm_lapic *apic) { WARN_ON(preemptible()); WARN_ON(!apic->lapic_timer.hv_timer_in_use); - kvm_x86_ops->cancel_hv_timer(apic->vcpu); + kvm_x86_ops.cancel_hv_timer(apic->vcpu); apic->lapic_timer.hv_timer_in_use = false; } @@ -1748,13 +1763,13 @@ static bool start_hv_timer(struct kvm_lapic *apic) bool expired; WARN_ON(preemptible()); - if (!kvm_x86_ops->set_hv_timer) + if (!kvm_x86_ops.set_hv_timer) return false; if (!ktimer->tscdeadline) return false; - if (kvm_x86_ops->set_hv_timer(vcpu, ktimer->tscdeadline, &expired)) + if (kvm_x86_ops.set_hv_timer(vcpu, ktimer->tscdeadline, &expired)) return false; ktimer->hv_timer_in_use = true; @@ -1917,7 +1932,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_DFR: if (!apic_x2apic_mode(apic)) { kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); - recalculate_apic_map(apic->vcpu->kvm); + apic->vcpu->kvm->arch.apic_map_dirty = true; } else ret = 1; break; @@ -1946,7 +1961,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_ICR: /* No delay here, so we always clear the pending bit */ val &= ~(1 << 12); - apic_send_ipi(apic, val, kvm_lapic_get_reg(apic, APIC_ICR2)); + kvm_apic_send_ipi(apic, val, kvm_lapic_get_reg(apic, APIC_ICR2)); kvm_lapic_set_reg(apic, APIC_ICR, val); break; @@ -2023,6 +2038,8 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) break; } + kvm_recalculate_apic_map(apic->vcpu->kvm); + return ret; } EXPORT_SYMBOL_GPL(kvm_lapic_reg_write); @@ -2171,7 +2188,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) static_key_slow_dec_deferred(&apic_hw_disabled); } else { static_key_slow_inc(&apic_hw_disabled.key); - recalculate_apic_map(vcpu->kvm); + vcpu->kvm->arch.apic_map_dirty = true; } } @@ -2179,7 +2196,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) - kvm_x86_ops->set_virtual_apic_mode(vcpu); + kvm_x86_ops.set_virtual_apic_mode(vcpu); apic->base_address = apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_BASE; @@ -2212,6 +2229,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) if (!apic) return; + vcpu->kvm->arch.apic_map_dirty = false; /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); @@ -2256,13 +2274,15 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.pv_eoi.msr_val = 0; apic_update_ppr(apic); if (vcpu->arch.apicv_active) { - kvm_x86_ops->apicv_post_state_restore(vcpu); - kvm_x86_ops->hwapic_irr_update(vcpu, -1); - kvm_x86_ops->hwapic_isr_update(vcpu, -1); + kvm_x86_ops.apicv_post_state_restore(vcpu); + kvm_x86_ops.hwapic_irr_update(vcpu, -1); + kvm_x86_ops.hwapic_isr_update(vcpu, -1); } vcpu->arch.apic_arb_prio = 0; vcpu->arch.apic_attention = 0; + + kvm_recalculate_apic_map(vcpu->kvm); } /* @@ -2484,17 +2504,18 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) struct kvm_lapic *apic = vcpu->arch.apic; int r; - kvm_lapic_set_base(vcpu, vcpu->arch.apic_base); /* set SPIV separately to get count of SW disabled APICs right */ apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV))); r = kvm_apic_state_fixup(vcpu, s, true); - if (r) + if (r) { + kvm_recalculate_apic_map(vcpu->kvm); return r; + } memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s)); - recalculate_apic_map(vcpu->kvm); + kvm_recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); apic_update_ppr(apic); @@ -2506,10 +2527,10 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) kvm_apic_update_apicv(vcpu); apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { - kvm_x86_ops->apicv_post_state_restore(vcpu); - kvm_x86_ops->hwapic_irr_update(vcpu, + kvm_x86_ops.apicv_post_state_restore(vcpu); + kvm_x86_ops.hwapic_irr_update(vcpu, apic_find_highest_irr(apic)); - kvm_x86_ops->hwapic_isr_update(vcpu, + kvm_x86_ops.hwapic_isr_update(vcpu, apic_find_highest_isr(apic)); } kvm_make_request(KVM_REQ_EVENT, vcpu); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index ec6fbfe325cf..40ed6ed22751 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -78,6 +78,7 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); +void kvm_recalculate_apic_map(struct kvm *kvm); void kvm_apic_set_version(struct kvm_vcpu *vcpu); int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val); int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, @@ -95,6 +96,7 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu); bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map); +void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high); u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index a647601c9e1c..8a3b1bce722a 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -95,11 +95,11 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu) return kvm_get_pcid(vcpu, kvm_read_cr3(vcpu)); } -static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu) +static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) { if (VALID_PAGE(vcpu->arch.mmu->root_hpa)) - vcpu->arch.mmu->set_cr3(vcpu, vcpu->arch.mmu->root_hpa | - kvm_get_active_pcid(vcpu)); + kvm_x86_ops.load_mmu_pgd(vcpu, vcpu->arch.mmu->root_hpa | + kvm_get_active_pcid(vcpu)); } int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, @@ -170,8 +170,8 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned pte_access, unsigned pte_pkey, unsigned pfec) { - int cpl = kvm_x86_ops->get_cpl(vcpu); - unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); + int cpl = kvm_x86_ops.get_cpl(vcpu); + unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); /* * If CPL < 3, SMAP prevention are disabled if EFLAGS.AC = 1. diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 87e9ba27ada1..8071952e9cf2 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -19,6 +19,7 @@ #include "mmu.h" #include "x86.h" #include "kvm_cache_regs.h" +#include "kvm_emulate.h" #include "cpuid.h" #include <linux/kvm_host.h> @@ -86,6 +87,8 @@ __MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); */ bool tdp_enabled = false; +static int max_page_level __read_mostly; + enum { AUDIT_PRE_PAGE_FAULT, AUDIT_POST_PAGE_FAULT, @@ -215,17 +218,6 @@ struct kvm_shadow_walk_iterator { unsigned index; }; -static const union kvm_mmu_page_role mmu_base_role_mask = { - .cr0_wp = 1, - .gpte_is_8_bytes = 1, - .nxe = 1, - .smep_andnot_wp = 1, - .smap_andnot_wp = 1, - .smm = 1, - .guest_mode = 1, - .ad_disabled = 1, -}; - #define for_each_shadow_entry_using_root(_vcpu, _root, _addr, _walker) \ for (shadow_walk_init_using_root(&(_walker), (_vcpu), \ (_root), (_addr)); \ @@ -313,7 +305,7 @@ kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu); static inline bool kvm_available_flush_tlb_with_range(void) { - return kvm_x86_ops->tlb_remote_flush_with_range; + return kvm_x86_ops.tlb_remote_flush_with_range; } static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm, @@ -321,8 +313,8 @@ static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm, { int ret = -ENOTSUPP; - if (range && kvm_x86_ops->tlb_remote_flush_with_range) - ret = kvm_x86_ops->tlb_remote_flush_with_range(kvm, range); + if (range && kvm_x86_ops.tlb_remote_flush_with_range) + ret = kvm_x86_ops.tlb_remote_flush_with_range(kvm, range); if (ret) kvm_flush_remote_tlbs(kvm); @@ -1650,7 +1642,7 @@ static bool spte_set_dirty(u64 *sptep) rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep); /* - * Similar to the !kvm_x86_ops->slot_disable_log_dirty case, + * Similar to the !kvm_x86_ops.slot_disable_log_dirty case, * do not bother adding back write access to pages marked * SPTE_AD_WRPROT_ONLY_MASK. */ @@ -1739,8 +1731,8 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - if (kvm_x86_ops->enable_log_dirty_pt_masked) - kvm_x86_ops->enable_log_dirty_pt_masked(kvm, slot, gfn_offset, + if (kvm_x86_ops.enable_log_dirty_pt_masked) + kvm_x86_ops.enable_log_dirty_pt_masked(kvm, slot, gfn_offset, mask); else kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); @@ -1755,8 +1747,8 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, */ int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops->write_log_dirty) - return kvm_x86_ops->write_log_dirty(vcpu); + if (kvm_x86_ops.write_log_dirty) + return kvm_x86_ops.write_log_dirty(vcpu); return 0; } @@ -3044,7 +3036,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (level > PT_PAGE_TABLE_LEVEL) spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) - spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn, + spte |= kvm_x86_ops.get_mt_mask(vcpu, gfn, kvm_is_mmio_pfn(pfn)); if (host_writable) @@ -3292,7 +3284,7 @@ static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, if (!slot) return PT_PAGE_TABLE_LEVEL; - max_level = min(max_level, kvm_x86_ops->get_lpage_level()); + max_level = min(max_level, max_page_level); for ( ; max_level > PT_PAGE_TABLE_LEVEL; max_level--) { linfo = lpage_info_slot(gfn, slot, max_level); if (!linfo->disallow_lpage) @@ -3568,8 +3560,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * write-protected for dirty-logging or access tracking. */ if ((error_code & PFERR_WRITE_MASK) && - spte_can_locklessly_be_made_writable(spte)) - { + spte_can_locklessly_be_made_writable(spte)) { new_spte |= PT_WRITABLE_MASK; /* @@ -3731,7 +3722,9 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root); } else BUG(); - vcpu->arch.mmu->root_cr3 = vcpu->arch.mmu->get_cr3(vcpu); + + /* root_cr3 is ignored for direct MMUs. */ + vcpu->arch.mmu->root_cr3 = 0; return 0; } @@ -3743,7 +3736,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) gfn_t root_gfn, root_cr3; int i; - root_cr3 = vcpu->arch.mmu->get_cr3(vcpu); + root_cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); root_gfn = root_cr3 >> PAGE_SHIFT; if (mmu_check_root(vcpu, root_gfn)) @@ -4080,7 +4073,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; arch.gfn = gfn; arch.direct_map = vcpu->arch.mmu->direct_map; - arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu); + arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); return kvm_setup_async_pf(vcpu, cr2_or_gpa, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); @@ -4252,6 +4245,14 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu, context->nx = false; } +static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t cr3, + union kvm_mmu_page_role role) +{ + return (role.direct || cr3 == root->cr3) && + VALID_PAGE(root->hpa) && page_header(root->hpa) && + role.word == page_header(root->hpa)->role.word; +} + /* * Find out if a previously cached root matching the new CR3/role is available. * The current root is also inserted into the cache. @@ -4270,12 +4271,13 @@ static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3, root.cr3 = mmu->root_cr3; root.hpa = mmu->root_hpa; + if (is_root_usable(&root, new_cr3, new_role)) + return true; + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { swap(root, mmu->prev_roots[i]); - if (new_cr3 == root.cr3 && VALID_PAGE(root.hpa) && - page_header(root.hpa) != NULL && - new_role.word == page_header(root.hpa)->role.word) + if (is_root_usable(&root, new_cr3, new_role)) break; } @@ -4309,7 +4311,7 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3, * accompanied by KVM_REQ_MMU_RELOAD, which will free * the root set here and allocate a new one. */ - kvm_make_request(KVM_REQ_LOAD_CR3, vcpu); + kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); if (!skip_tlb_flush) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); @@ -4508,7 +4510,8 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, cpuid_maxphyaddr(vcpu), context->root_level, context->nx, guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), - is_pse(vcpu), guest_cpuid_is_amd(vcpu)); + is_pse(vcpu), + guest_cpuid_is_amd_or_hygon(vcpu)); } static void @@ -4874,7 +4877,6 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu) 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.cr4_la57 = !!kvm_read_cr4_bits(vcpu, X86_CR4_LA57); ext.maxphyaddr = cpuid_maxphyaddr(vcpu); ext.valid = 1; @@ -4907,7 +4909,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only); role.base.ad_disabled = (shadow_accessed_mask == 0); - role.base.level = kvm_x86_ops->get_tdp_level(vcpu); + role.base.level = kvm_x86_ops.get_tdp_level(vcpu); role.base.direct = true; role.base.gpte_is_8_bytes = true; @@ -4920,7 +4922,6 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) union kvm_mmu_role new_role = kvm_calc_tdp_mmu_root_page_role(vcpu, false); - new_role.base.word &= mmu_base_role_mask.word; if (new_role.as_u64 == context->mmu_role.as_u64) return; @@ -4929,10 +4930,9 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; context->update_pte = nonpaging_update_pte; - context->shadow_root_level = kvm_x86_ops->get_tdp_level(vcpu); + context->shadow_root_level = kvm_x86_ops.get_tdp_level(vcpu); context->direct_map = true; - context->set_cr3 = kvm_x86_ops->set_tdp_cr3; - context->get_cr3 = get_cr3; + context->get_guest_pgd = get_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; @@ -4992,7 +4992,6 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) union kvm_mmu_role new_role = kvm_calc_shadow_mmu_root_page_role(vcpu, false); - new_role.base.word &= mmu_base_role_mask.word; if (new_role.as_u64 == context->mmu_role.as_u64) return; @@ -5012,14 +5011,14 @@ EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); static union kvm_mmu_role kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, - bool execonly) + bool execonly, u8 level) { union kvm_mmu_role role = {0}; /* SMM flag is inherited from root_mmu */ role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm; - role.base.level = PT64_ROOT_4LEVEL; + role.base.level = level; role.base.gpte_is_8_bytes = true; role.base.direct = false; role.base.ad_disabled = !accessed_dirty; @@ -5043,17 +5042,17 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool accessed_dirty, gpa_t new_eptp) { struct kvm_mmu *context = vcpu->arch.mmu; + u8 level = vmx_eptp_page_walk_level(new_eptp); union kvm_mmu_role new_role = kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty, - execonly); + execonly, level); __kvm_mmu_new_cr3(vcpu, new_eptp, new_role.base, false); - new_role.base.word &= mmu_base_role_mask.word; if (new_role.as_u64 == context->mmu_role.as_u64) return; - context->shadow_root_level = PT64_ROOT_4LEVEL; + context->shadow_root_level = level; context->nx = true; context->ept_ad = accessed_dirty; @@ -5062,7 +5061,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->sync_page = ept_sync_page; context->invlpg = ept_invlpg; context->update_pte = ept_update_pte; - context->root_level = PT64_ROOT_4LEVEL; + context->root_level = level; context->direct_map = false; context->mmu_role.as_u64 = new_role.as_u64; @@ -5079,8 +5078,7 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu) struct kvm_mmu *context = vcpu->arch.mmu; kvm_init_shadow_mmu(vcpu); - context->set_cr3 = kvm_x86_ops->set_cr3; - context->get_cr3 = get_cr3; + context->get_guest_pgd = get_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; } @@ -5090,12 +5088,11 @@ 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 *g_context = &vcpu->arch.nested_mmu; - new_role.base.word &= mmu_base_role_mask.word; if (new_role.as_u64 == g_context->mmu_role.as_u64) return; g_context->mmu_role.as_u64 = new_role.as_u64; - g_context->get_cr3 = get_cr3; + g_context->get_guest_pgd = get_cr3; g_context->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault; @@ -5185,8 +5182,8 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) kvm_mmu_sync_roots(vcpu); if (r) goto out; - kvm_mmu_load_cr3(vcpu); - kvm_x86_ops->tlb_flush(vcpu, true); + kvm_mmu_load_pgd(vcpu); + kvm_x86_ops.tlb_flush(vcpu, true); out: return r; } @@ -5329,6 +5326,22 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) return spte; } +/* + * Ignore various flags when determining if a SPTE can be immediately + * overwritten for the current MMU. + * - level: explicitly checked in mmu_pte_write_new_pte(), and will never + * match the current MMU role, as MMU's level tracks the root level. + * - access: updated based on the new guest PTE + * - quadrant: handled by get_written_sptes() + * - invalid: always false (loop only walks valid shadow pages) + */ +static const union kvm_mmu_page_role role_ign = { + .level = 0xf, + .access = 0x7, + .quadrant = 0x3, + .invalid = 0x1, +}; + static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes, struct kvm_page_track_notifier_node *node) @@ -5384,8 +5397,8 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, entry = *spte; mmu_page_zap_pte(vcpu->kvm, sp, spte); if (gentry && - !((sp->role.word ^ base_role) - & mmu_base_role_mask.word) && rmap_can_add(vcpu)) + !((sp->role.word ^ base_role) & ~role_ign.word) && + rmap_can_add(vcpu)) mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); if (need_remote_flush(entry, *spte)) remote_flush = true; @@ -5416,18 +5429,12 @@ EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { - int r, emulation_type = 0; + int r, emulation_type = EMULTYPE_PF; bool direct = vcpu->arch.mmu->direct_map; if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) return RET_PF_RETRY; - /* With shadow page tables, fault_address contains a GVA or nGPA. */ - if (vcpu->arch.mmu->direct_map) { - vcpu->arch.gpa_available = true; - vcpu->arch.gpa_val = cr2_or_gpa; - } - r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); @@ -5471,7 +5478,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, * for L1 isn't going to magically fix whatever issue cause L2 to fail. */ if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) - emulation_type = EMULTYPE_ALLOW_RETRY; + emulation_type |= EMULTYPE_ALLOW_RETRY_PF; emulate: /* * On AMD platforms, under certain conditions insn_len may be zero on #NPF. @@ -5481,7 +5488,7 @@ emulate: * guest, with the exception of AMD Erratum 1096 which is unrecoverable. */ if (unlikely(insn && !insn_len)) { - if (!kvm_x86_ops->need_emulation_on_page_fault(vcpu)) + if (!kvm_x86_ops.need_emulation_on_page_fault(vcpu)) return 1; } @@ -5516,7 +5523,7 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) if (VALID_PAGE(mmu->prev_roots[i].hpa)) mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); - kvm_x86_ops->tlb_flush_gva(vcpu, gva); + kvm_x86_ops.tlb_flush_gva(vcpu, gva); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); @@ -5541,7 +5548,7 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) } if (tlb_flush) - kvm_x86_ops->tlb_flush_gva(vcpu, gva); + kvm_x86_ops.tlb_flush_gva(vcpu, gva); ++vcpu->stat.invlpg; @@ -5553,18 +5560,25 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) } EXPORT_SYMBOL_GPL(kvm_mmu_invpcid_gva); -void kvm_enable_tdp(void) +void kvm_configure_mmu(bool enable_tdp, int tdp_page_level) { - tdp_enabled = true; -} -EXPORT_SYMBOL_GPL(kvm_enable_tdp); + tdp_enabled = enable_tdp; -void kvm_disable_tdp(void) -{ - tdp_enabled = false; + /* + * max_page_level reflects the capabilities of KVM's MMU irrespective + * of kernel support, e.g. KVM may be capable of using 1GB pages when + * the kernel is not. But, KVM never creates a page size greater than + * what is used by the kernel for any given HVA, i.e. the kernel's + * capabilities are ultimately consulted by kvm_mmu_hugepage_adjust(). + */ + if (tdp_enabled) + max_page_level = tdp_page_level; + else if (boot_cpu_has(X86_FEATURE_GBPAGES)) + max_page_level = PT_PDPE_LEVEL; + else + max_page_level = PT_DIRECTORY_LEVEL; } -EXPORT_SYMBOL_GPL(kvm_disable_tdp); - +EXPORT_SYMBOL_GPL(kvm_configure_mmu); /* The return value indicates if tlb flush on all vcpus is needed. */ typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); @@ -5658,7 +5672,7 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) * SVM's 32-bit NPT support, TDP paging doesn't use PAE paging and can * skip allocating the PDP table. */ - if (tdp_enabled && kvm_x86_ops->get_tdp_level(vcpu) > PT32E_ROOT_LEVEL) + if (tdp_enabled && kvm_x86_ops.get_tdp_level(vcpu) > PT32E_ROOT_LEVEL) return 0; page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_DMA32); @@ -5860,23 +5874,17 @@ static bool slot_rmap_write_protect(struct kvm *kvm, } void kvm_mmu_slot_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot) + struct kvm_memory_slot *memslot, + int start_level) { bool flush; spin_lock(&kvm->mmu_lock); - flush = slot_handle_all_level(kvm, memslot, slot_rmap_write_protect, - false); + flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, + start_level, PT_MAX_HUGEPAGE_LEVEL, false); spin_unlock(&kvm->mmu_lock); /* - * kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log() - * which do tlb flush out of mmu-lock should be serialized by - * kvm->slots_lock otherwise tlb flush would be missed. - */ - lockdep_assert_held(&kvm->slots_lock); - - /* * We can flush all the TLBs out of the mmu lock without TLB * corruption since we just change the spte from writable to * readonly so that we only need to care the case of changing @@ -5888,8 +5896,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, * on PT_WRITABLE_MASK anymore. */ if (flush) - kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, - memslot->npages); + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, @@ -5941,6 +5948,21 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, spin_unlock(&kvm->mmu_lock); } +void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + /* + * All current use cases for flushing the TLBs for a specific memslot + * are related to dirty logging, and do the TLB flush out of mmu_lock. + * The interaction between the various operations on memslot must be + * serialized by slots_locks to ensure the TLB flush from one operation + * is observed by any other operation on the same memslot. + */ + lockdep_assert_held(&kvm->slots_lock); + kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, + memslot->npages); +} + void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { @@ -5950,8 +5972,6 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false); spin_unlock(&kvm->mmu_lock); - lockdep_assert_held(&kvm->slots_lock); - /* * It's also safe to flush TLBs out of mmu lock here as currently this * function is only used for dirty logging, in which case flushing TLB @@ -5959,8 +5979,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, * dirty_bitmap. */ if (flush) - kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, - memslot->npages); + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty); @@ -5974,12 +5993,8 @@ void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, false); spin_unlock(&kvm->mmu_lock); - /* see kvm_mmu_slot_remove_write_access */ - lockdep_assert_held(&kvm->slots_lock); - if (flush) - kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, - memslot->npages); + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access); @@ -5992,12 +6007,8 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm, flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false); spin_unlock(&kvm->mmu_lock); - lockdep_assert_held(&kvm->slots_lock); - - /* see kvm_mmu_slot_leaf_clear_dirty */ if (flush) - kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, - memslot->npages); + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty); diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 3521e2d176f2..ddc1ec3bdacd 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -14,22 +14,18 @@ #include <linux/kvm_host.h> #include <linux/rculist.h> -#include <asm/kvm_host.h> #include <asm/kvm_page_track.h> #include "mmu.h" -void kvm_page_track_free_memslot(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) { int i; - for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) - if (!dont || free->arch.gfn_track[i] != - dont->arch.gfn_track[i]) { - kvfree(free->arch.gfn_track[i]); - free->arch.gfn_track[i] = NULL; - } + for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { + kvfree(slot->arch.gfn_track[i]); + slot->arch.gfn_track[i] = NULL; + } } int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, @@ -48,7 +44,7 @@ int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, return 0; track_free: - kvm_page_track_free_memslot(slot, NULL); + kvm_page_track_free_memslot(slot); return -ENOMEM; } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 21a3320f166a..9bdf9b7d9a96 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -66,7 +66,7 @@ #define PT_GUEST_ACCESSED_SHIFT 8 #define PT_HAVE_ACCESSED_DIRTY(mmu) ((mmu)->ept_ad) #define CMPXCHG cmpxchg64 - #define PT_MAX_FULL_LEVELS 4 + #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL #else #error Invalid PTTYPE value #endif @@ -333,7 +333,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, trace_kvm_mmu_pagetable_walk(addr, access); retry_walk: walker->level = mmu->root_level; - pte = mmu->get_cr3(vcpu); + pte = mmu->get_guest_pgd(vcpu); have_ad = PT_HAVE_ACCESSED_DIRTY(mmu); #if PTTYPE == 64 diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index bcc6a73d6628..a5078841bdac 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -111,7 +111,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, .config = config, }; - attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc); + attr.sample_period = get_sample_period(pmc, pmc->counter); if (in_tx) attr.config |= HSW_IN_TX; @@ -158,7 +158,7 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) /* recalibrate sample period and check if it's accepted by perf core */ if (perf_event_period(pmc->perf_event, - (-pmc->counter) & pmc_bitmask(pmc))) + get_sample_period(pmc, pmc->counter))) return false; /* reuse perf_event to serve as pmc_reprogram_counter() does*/ @@ -211,7 +211,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) ARCH_PERFMON_EVENTSEL_CMASK | HSW_IN_TX | HSW_IN_TX_CHECKPOINTED))) { - config = kvm_x86_ops->pmu_ops->find_arch_event(pmc_to_pmu(pmc), + config = kvm_x86_ops.pmu_ops->find_arch_event(pmc_to_pmu(pmc), event_select, unit_mask); if (config != PERF_COUNT_HW_MAX) @@ -265,7 +265,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) pmc->current_config = (u64)ctrl; pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE, - kvm_x86_ops->pmu_ops->find_fixed_event(idx), + kvm_x86_ops.pmu_ops->find_fixed_event(idx), !(en_field & 0x2), /* exclude user */ !(en_field & 0x1), /* exclude kernel */ pmi, false, false); @@ -274,7 +274,7 @@ EXPORT_SYMBOL_GPL(reprogram_fixed_counter); void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx) { - struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx); + struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx); if (!pmc) return; @@ -296,7 +296,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) int bit; for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) { - struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit); + struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, bit); if (unlikely(!pmc || !pmc->perf_event)) { clear_bit(bit, pmu->reprogram_pmi); @@ -318,7 +318,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) /* check if idx is a valid index to access PMU */ int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { - return kvm_x86_ops->pmu_ops->is_valid_rdpmc_ecx(vcpu, idx); + return kvm_x86_ops.pmu_ops->is_valid_rdpmc_ecx(vcpu, idx); } bool is_vmware_backdoor_pmc(u32 pmc_idx) @@ -368,7 +368,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) if (is_vmware_backdoor_pmc(idx)) return kvm_pmu_rdpmc_vmware(vcpu, idx, data); - pmc = kvm_x86_ops->pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask); + pmc = kvm_x86_ops.pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask); if (!pmc) return 1; @@ -384,14 +384,14 @@ void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { - return kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr) || - kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr); + return kvm_x86_ops.pmu_ops->msr_idx_to_pmc(vcpu, msr) || + kvm_x86_ops.pmu_ops->is_valid_msr(vcpu, msr); } static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr); + struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->msr_idx_to_pmc(vcpu, msr); if (pmc) __set_bit(pmc->idx, pmu->pmc_in_use); @@ -399,13 +399,13 @@ static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr) int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) { - return kvm_x86_ops->pmu_ops->get_msr(vcpu, msr, data); + return kvm_x86_ops.pmu_ops->get_msr(vcpu, msr, data); } int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index); - return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info); + return kvm_x86_ops.pmu_ops->set_msr(vcpu, msr_info); } /* refresh PMU settings. This function generally is called when underlying @@ -414,7 +414,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { - kvm_x86_ops->pmu_ops->refresh(vcpu); + kvm_x86_ops.pmu_ops->refresh(vcpu); } void kvm_pmu_reset(struct kvm_vcpu *vcpu) @@ -422,7 +422,7 @@ void kvm_pmu_reset(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); irq_work_sync(&pmu->irq_work); - kvm_x86_ops->pmu_ops->reset(vcpu); + kvm_x86_ops.pmu_ops->reset(vcpu); } void kvm_pmu_init(struct kvm_vcpu *vcpu) @@ -430,7 +430,7 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); memset(pmu, 0, sizeof(*pmu)); - kvm_x86_ops->pmu_ops->init(vcpu); + kvm_x86_ops.pmu_ops->init(vcpu); init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); pmu->event_count = 0; pmu->need_cleanup = false; @@ -462,7 +462,7 @@ void kvm_pmu_cleanup(struct kvm_vcpu *vcpu) pmu->pmc_in_use, X86_PMC_IDX_MAX); for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) { - pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, i); + pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, i); if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc)) pmc_stop_counter(pmc); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 13332984b6d5..a6c78a797cb1 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -88,7 +88,7 @@ static inline bool pmc_is_fixed(struct kvm_pmc *pmc) static inline bool pmc_is_enabled(struct kvm_pmc *pmc) { - return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc); + return kvm_x86_ops.pmu_ops->pmc_is_enabled(pmc); } static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu, @@ -129,6 +129,15 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) return NULL; } +static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) +{ + u64 sample_period = (-counter_value) & pmc_bitmask(pmc); + + if (!sample_period) + sample_period = pmc_bitmask(pmc) + 1; + return sample_period; +} + void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel); void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx); void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 216364cb65a3..851e9cc79930 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -522,10 +522,31 @@ static void recalc_intercepts(struct vcpu_svm *svm) h = &svm->nested.hsave->control; g = &svm->nested; - c->intercept_cr = h->intercept_cr | g->intercept_cr; - c->intercept_dr = h->intercept_dr | g->intercept_dr; - c->intercept_exceptions = h->intercept_exceptions | g->intercept_exceptions; - c->intercept = h->intercept | g->intercept; + c->intercept_cr = h->intercept_cr; + c->intercept_dr = h->intercept_dr; + c->intercept_exceptions = h->intercept_exceptions; + c->intercept = h->intercept; + + if (svm->vcpu.arch.hflags & HF_VINTR_MASK) { + /* We only want the cr8 intercept bits of L1 */ + c->intercept_cr &= ~(1U << INTERCEPT_CR8_READ); + c->intercept_cr &= ~(1U << INTERCEPT_CR8_WRITE); + + /* + * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not + * affect any interrupt we may want to inject; therefore, + * interrupt window vmexits are irrelevant to L0. + */ + c->intercept &= ~(1ULL << INTERCEPT_VINTR); + } + + /* We don't want to see VMMCALLs from a nested guest */ + c->intercept &= ~(1ULL << INTERCEPT_VMMCALL); + + c->intercept_cr |= g->intercept_cr; + c->intercept_dr |= g->intercept_dr; + c->intercept_exceptions |= g->intercept_exceptions; + c->intercept |= g->intercept; } static inline struct vmcb *get_host_vmcb(struct vcpu_svm *svm) @@ -630,6 +651,11 @@ static inline void clr_intercept(struct vcpu_svm *svm, int bit) recalc_intercepts(svm); } +static inline bool is_intercept(struct vcpu_svm *svm, int bit) +{ + return (svm->vmcb->control.intercept & (1ULL << bit)) != 0; +} + static inline bool vgif_enabled(struct vcpu_svm *svm) { return !!(svm->vmcb->control.int_ctl & V_GIF_ENABLE_MASK); @@ -1209,6 +1235,7 @@ static int avic_ga_log_notifier(u32 ga_tag) u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag); pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id); + trace_kvm_avic_ga_log(vm_id, vcpu_id); spin_lock_irqsave(&svm_vm_data_hash_lock, flags); hash_for_each_possible(svm_vm_data_hash, kvm_svm, hnode, vm_id) { @@ -1370,6 +1397,29 @@ static void svm_hardware_teardown(void) iopm_base = 0; } +static __init void svm_set_cpu_caps(void) +{ + kvm_set_cpu_caps(); + + supported_xss = 0; + + /* CPUID 0x80000001 and 0x8000000A (SVM features) */ + if (nested) { + kvm_cpu_cap_set(X86_FEATURE_SVM); + + if (nrips) + kvm_cpu_cap_set(X86_FEATURE_NRIPS); + + if (npt_enabled) + kvm_cpu_cap_set(X86_FEATURE_NPT); + } + + /* CPUID 0x80000008 */ + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1388,6 +1438,8 @@ static __init int svm_hardware_setup(void) init_msrpm_offsets(); + supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); + if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); @@ -1435,16 +1487,11 @@ static __init int svm_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_NPT)) npt_enabled = false; - if (npt_enabled && !npt) { - printk(KERN_INFO "kvm: Nested Paging disabled\n"); + if (npt_enabled && !npt) npt_enabled = false; - } - if (npt_enabled) { - printk(KERN_INFO "kvm: Nested Paging enabled\n"); - kvm_enable_tdp(); - } else - kvm_disable_tdp(); + kvm_configure_mmu(npt_enabled, PT_PDPE_LEVEL); + pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); if (nrips) { if (!boot_cpu_has(X86_FEATURE_NRIPS)) @@ -1480,6 +1527,8 @@ static __init int svm_hardware_setup(void) pr_info("Virtual GIF supported\n"); } + svm_set_cpu_caps(); + return 0; err: @@ -1939,19 +1988,6 @@ static void __unregister_enc_region_locked(struct kvm *kvm, kfree(region); } -static struct kvm *svm_vm_alloc(void) -{ - struct kvm_svm *kvm_svm = __vmalloc(sizeof(struct kvm_svm), - GFP_KERNEL_ACCOUNT | __GFP_ZERO, - PAGE_KERNEL); - return &kvm_svm->kvm; -} - -static void svm_vm_free(struct kvm *kvm) -{ - vfree(to_kvm_svm(kvm)); -} - static void sev_vm_destroy(struct kvm *kvm) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; @@ -2186,7 +2222,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) } init_vmcb(svm); - kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, true); + kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, false); kvm_rdx_write(vcpu, eax); if (kvm_vcpu_apicv_active(vcpu) && !init_event) @@ -2420,14 +2456,38 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } +static inline void svm_enable_vintr(struct vcpu_svm *svm) +{ + struct vmcb_control_area *control; + + /* The following fields are ignored when AVIC is enabled */ + WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu)); + + /* + * This is just a dummy VINTR to actually cause a vmexit to happen. + * Actual injection of virtual interrupts happens through EVENTINJ. + */ + control = &svm->vmcb->control; + control->int_vector = 0x0; + control->int_ctl &= ~V_INTR_PRIO_MASK; + control->int_ctl |= V_IRQ_MASK | + ((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT); + mark_dirty(svm->vmcb, VMCB_INTR); +} + static void svm_set_vintr(struct vcpu_svm *svm) { set_intercept(svm, INTERCEPT_VINTR); + if (is_intercept(svm, INTERCEPT_VINTR)) + svm_enable_vintr(svm); } static void svm_clear_vintr(struct vcpu_svm *svm) { clr_intercept(svm, INTERCEPT_VINTR); + + svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; + mark_dirty(svm->vmcb, VMCB_INTR); } static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg) @@ -2983,15 +3043,6 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) return pdpte; } -static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, - unsigned long root) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - svm->vmcb->control.nested_cr3 = __sme_set(root); - mark_dirty(svm->vmcb, VMCB_NPT); -} - static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, struct x86_exception *fault) { @@ -3027,8 +3078,7 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu = &vcpu->arch.guest_mmu; kvm_init_shadow_mmu(vcpu); - vcpu->arch.mmu->set_cr3 = nested_svm_set_tdp_cr3; - vcpu->arch.mmu->get_cr3 = nested_svm_get_tdp_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; vcpu->arch.mmu->shadow_root_level = get_npt_level(vcpu); @@ -3089,43 +3139,36 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, return vmexit; } -/* This function returns true if it is save to enable the irq window */ -static inline bool nested_svm_intr(struct vcpu_svm *svm) +static void nested_svm_intr(struct vcpu_svm *svm) { - if (!is_guest_mode(&svm->vcpu)) - return true; - - if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) - return true; - - if (!(svm->vcpu.arch.hflags & HF_HIF_MASK)) - return false; - - /* - * if vmexit was already requested (by intercepted exception - * for instance) do not overwrite it with "external interrupt" - * vmexit. - */ - if (svm->nested.exit_required) - return false; - svm->vmcb->control.exit_code = SVM_EXIT_INTR; svm->vmcb->control.exit_info_1 = 0; svm->vmcb->control.exit_info_2 = 0; - if (svm->nested.intercept & 1ULL) { - /* - * The #vmexit can't be emulated here directly because this - * code path runs with irqs and preemption disabled. A - * #vmexit emulation might sleep. Only signal request for - * the #vmexit here. - */ - svm->nested.exit_required = true; - trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); - return false; + /* nested_svm_vmexit this gets called afterwards from handle_exit */ + svm->nested.exit_required = true; + trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); +} + +static bool nested_exit_on_intr(struct vcpu_svm *svm) +{ + return (svm->nested.intercept & 1ULL); +} + +static int svm_check_nested_events(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + bool block_nested_events = + kvm_event_needs_reinjection(vcpu) || svm->nested.exit_required; + + if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(svm)) { + if (block_nested_events) + return -EBUSY; + nested_svm_intr(svm); + return 0; } - return true; + return 0; } /* This function returns true if it is save to enable the nmi window */ @@ -3244,9 +3287,6 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) return NESTED_EXIT_CONTINUE; } -/* - * If this function returns true, this #vmexit was already handled - */ static int nested_svm_intercept(struct vcpu_svm *svm) { u32 exit_code = svm->vmcb->control.exit_code; @@ -3521,6 +3561,9 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) static bool nested_vmcb_checks(struct vmcb *vmcb) { + if ((vmcb->save.efer & EFER_SVME) == 0) + return false; + if ((vmcb->control.intercept & (1ULL << INTERCEPT_VMRUN)) == 0) return false; @@ -3537,6 +3580,10 @@ static bool nested_vmcb_checks(struct vmcb *vmcb) static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, struct vmcb *nested_vmcb, struct kvm_host_map *map) { + bool evaluate_pending_interrupts = + is_intercept(svm, INTERCEPT_VINTR) || + is_intercept(svm, INTERCEPT_IRET); + if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF) svm->vcpu.arch.hflags |= HF_HIF_MASK; else @@ -3596,15 +3643,6 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, else svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; - if (svm->vcpu.arch.hflags & HF_VINTR_MASK) { - /* We only want the cr8 intercept bits of the guest */ - clr_cr_intercept(svm, INTERCEPT_CR8_READ); - clr_cr_intercept(svm, INTERCEPT_CR8_WRITE); - } - - /* We don't want to see VMMCALLs from a nested guest */ - clr_intercept(svm, INTERCEPT_VMMCALL); - svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset; svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset; @@ -3632,7 +3670,21 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, svm->nested.vmcb = vmcb_gpa; + /* + * If L1 had a pending IRQ/NMI before executing VMRUN, + * which wasn't delivered because it was disallowed (e.g. + * interrupts disabled), L0 needs to evaluate if this pending + * event should cause an exit from L2 to L1 or be delivered + * directly to L2. + * + * Usually this would be handled by the processor noticing an + * IRQ/NMI window request. However, VMRUN can unblock interrupts + * by implicitly setting GIF, so force L0 to perform pending event + * evaluation by requesting a KVM_REQ_EVENT. + */ enable_gif(svm); + if (unlikely(evaluate_pending_interrupts)) + kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); mark_all_dirty(svm->vmcb); } @@ -3834,11 +3886,8 @@ static int clgi_interception(struct vcpu_svm *svm) disable_gif(svm); /* After a CLGI no interrupts should come */ - if (!kvm_vcpu_apicv_active(&svm->vcpu)) { + if (!kvm_vcpu_apicv_active(&svm->vcpu)) svm_clear_vintr(svm); - svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; - mark_dirty(svm->vmcb, VMCB_INTR); - } return ret; } @@ -5124,19 +5173,6 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) ++vcpu->stat.nmi_injections; } -static inline void svm_inject_irq(struct vcpu_svm *svm, int irq) -{ - struct vmcb_control_area *control; - - /* The following fields are ignored when AVIC is enabled */ - control = &svm->vmcb->control; - control->int_vector = irq; - control->int_ctl &= ~V_INTR_PRIO_MASK; - control->int_ctl |= V_IRQ_MASK | - ((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT); - mark_dirty(svm->vmcb, VMCB_INTR); -} - static void svm_set_irq(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -5525,18 +5561,15 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - int ret; if (!gif_set(svm) || (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)) return 0; - ret = !!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF); - - if (is_guest_mode(vcpu)) - return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK); - - return ret; + if (is_guest_mode(vcpu) && (svm->vcpu.arch.hflags & HF_VINTR_MASK)) + return !!(svm->vcpu.arch.hflags & HF_HIF_MASK); + else + return !!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF); } static void enable_irq_window(struct kvm_vcpu *vcpu) @@ -5551,7 +5584,7 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) * enabled, the STGI interception will not occur. Enable the irq * window under the assumption that the hardware will set the GIF. */ - if ((vgif_enabled(svm) || gif_set(svm)) && nested_svm_intr(svm)) { + if (vgif_enabled(svm) || gif_set(svm)) { /* * IRQ window is not needed when AVIC is enabled, * unless we have pending ExtINT since it cannot be injected @@ -5560,7 +5593,6 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) */ svm_toggle_avic_for_irq_window(vcpu, false); svm_set_vintr(svm); - svm_inject_irq(svm, 0x0); } } @@ -5946,24 +5978,30 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) } STACK_FRAME_NON_STANDARD(svm_vcpu_run); -static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) +static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); + bool update_guest_cr3 = true; + unsigned long cr3; - svm->vmcb->save.cr3 = __sme_set(root); - mark_dirty(svm->vmcb, VMCB_CR); -} - -static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) -{ - struct vcpu_svm *svm = to_svm(vcpu); + cr3 = __sme_set(root); + if (npt_enabled) { + svm->vmcb->control.nested_cr3 = cr3; + mark_dirty(svm->vmcb, VMCB_NPT); - svm->vmcb->control.nested_cr3 = __sme_set(root); - mark_dirty(svm->vmcb, VMCB_NPT); + /* Loading L2's CR3 is handled by enter_svm_guest_mode. */ + if (is_guest_mode(vcpu)) + update_guest_cr3 = false; + else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + cr3 = vcpu->arch.cr3; + else /* CR3 is already up-to-date. */ + update_guest_cr3 = false; + } - /* Also sync guest cr3 here in case we live migrate */ - svm->vmcb->save.cr3 = kvm_read_cr3(vcpu); - mark_dirty(svm->vmcb, VMCB_CR); + if (update_guest_cr3) { + svm->vmcb->save.cr3 = cr3; + mark_dirty(svm->vmcb, VMCB_CR); + } } static int is_disabled(void) @@ -6025,12 +6063,19 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) boot_cpu_has(X86_FEATURE_XSAVES); /* Update nrips enabled cache */ - svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS); + svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) && + guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS); if (!kvm_vcpu_apicv_active(vcpu)) return; - guest_cpuid_clear(vcpu, X86_FEATURE_X2APIC); + /* + * AVIC does not work with an x2APIC mode guest. If the X2APIC feature + * is exposed to the guest, disable AVIC. + */ + if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC)) + kvm_request_apicv_update(vcpu->kvm, false, + APICV_INHIBIT_REASON_X2APIC); /* * Currently, AVIC does not work with nested virtualization. @@ -6041,88 +6086,11 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) APICV_INHIBIT_REASON_NESTED); } -#define F feature_bit - -static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) -{ - switch (func) { - case 0x1: - if (avic) - entry->ecx &= ~F(X2APIC); - break; - case 0x80000001: - if (nested) - entry->ecx |= (1 << 2); /* Set SVM bit */ - break; - case 0x80000008: - if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) || - boot_cpu_has(X86_FEATURE_AMD_SSBD)) - entry->ebx |= F(VIRT_SSBD); - break; - case 0x8000000A: - entry->eax = 1; /* SVM revision 1 */ - entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper - ASID emulation to nested SVM */ - entry->ecx = 0; /* Reserved */ - entry->edx = 0; /* Per default do not support any - additional features */ - - /* Support next_rip if host supports it */ - if (boot_cpu_has(X86_FEATURE_NRIPS)) - entry->edx |= F(NRIPS); - - /* Support NPT for the guest if enabled */ - if (npt_enabled) - entry->edx |= F(NPT); - - } -} - -static int svm_get_lpage_level(void) -{ - return PT_PDPE_LEVEL; -} - -static bool svm_rdtscp_supported(void) -{ - return boot_cpu_has(X86_FEATURE_RDTSCP); -} - -static bool svm_invpcid_supported(void) -{ - return false; -} - -static bool svm_mpx_supported(void) -{ - return false; -} - -static bool svm_xsaves_supported(void) -{ - return boot_cpu_has(X86_FEATURE_XSAVES); -} - -static bool svm_umip_emulated(void) -{ - return false; -} - -static bool svm_pt_supported(void) -{ - return false; -} - static bool svm_has_wbinvd_exit(void) { return true; } -static bool svm_pku_supported(void) -{ - return false; -} - #define PRE_EX(exit) { .exit_code = (exit), \ .stage = X86_ICPT_PRE_EXCEPT, } #define POST_EX(exit) { .exit_code = (exit), \ @@ -6189,7 +6157,8 @@ static const struct __x86_intercept { static int svm_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, - enum x86_intercept_stage stage) + enum x86_intercept_stage stage, + struct x86_exception *exception) { struct vcpu_svm *svm = to_svm(vcpu); int vmexit, ret = X86EMUL_CONTINUE; @@ -7371,7 +7340,7 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) * TODO: Last condition latch INIT signals on vCPU when * vCPU is in guest-mode and vmcb12 defines intercept on INIT. * To properly emulate the INIT intercept, SVM should implement - * kvm_x86_ops->check_nested_events() and call nested_svm_vmexit() + * kvm_x86_ops.check_nested_events() and call nested_svm_vmexit() * there if an INIT signal is pending. */ return !gif_set(svm) || @@ -7384,7 +7353,8 @@ static bool svm_check_apicv_inhibit_reasons(ulong bit) BIT(APICV_INHIBIT_REASON_HYPERV) | BIT(APICV_INHIBIT_REASON_NESTED) | BIT(APICV_INHIBIT_REASON_IRQWIN) | - BIT(APICV_INHIBIT_REASON_PIT_REINJ); + BIT(APICV_INHIBIT_REASON_PIT_REINJ) | + BIT(APICV_INHIBIT_REASON_X2APIC); return supported & BIT(bit); } @@ -7394,12 +7364,8 @@ static void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate) avic_update_access_page(kvm, activate); } -static struct kvm_x86_ops svm_x86_ops __ro_after_init = { - .cpu_has_kvm_support = has_svm, - .disabled_by_bios = is_disabled, - .hardware_setup = svm_hardware_setup, +static struct kvm_x86_ops svm_x86_ops __initdata = { .hardware_unsetup = svm_hardware_teardown, - .check_processor_compatibility = svm_check_processor_compat, .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, .cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr, @@ -7409,8 +7375,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .vcpu_free = svm_free_vcpu, .vcpu_reset = svm_vcpu_reset, - .vm_alloc = svm_vm_alloc, - .vm_free = svm_vm_free, + .vm_size = sizeof(struct kvm_svm), .vm_init = svm_vm_init, .vm_destroy = svm_vm_destroy, @@ -7432,7 +7397,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .decache_cr0_guest_bits = svm_decache_cr0_guest_bits, .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, .set_cr0 = svm_set_cr0, - .set_cr3 = svm_set_cr3, .set_cr4 = svm_set_cr4, .set_efer = svm_set_efer, .get_idt = svm_get_idt, @@ -7485,26 +7449,14 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_exit_info = svm_get_exit_info, - .get_lpage_level = svm_get_lpage_level, - .cpuid_update = svm_cpuid_update, - .rdtscp_supported = svm_rdtscp_supported, - .invpcid_supported = svm_invpcid_supported, - .mpx_supported = svm_mpx_supported, - .xsaves_supported = svm_xsaves_supported, - .umip_emulated = svm_umip_emulated, - .pt_supported = svm_pt_supported, - .pku_supported = svm_pku_supported, - - .set_supported_cpuid = svm_set_supported_cpuid, - .has_wbinvd_exit = svm_has_wbinvd_exit, .read_l1_tsc_offset = svm_read_l1_tsc_offset, .write_l1_tsc_offset = svm_write_l1_tsc_offset, - .set_tdp_cr3 = set_tdp_cr3, + .load_mmu_pgd = svm_load_mmu_pgd, .check_intercept = svm_check_intercept, .handle_exit_irqoff = svm_handle_exit_irqoff, @@ -7534,11 +7486,22 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .need_emulation_on_page_fault = svm_need_emulation_on_page_fault, .apic_init_signal_blocked = svm_apic_init_signal_blocked, + + .check_nested_events = svm_check_nested_events, +}; + +static struct kvm_x86_init_ops svm_init_ops __initdata = { + .cpu_has_kvm_support = has_svm, + .disabled_by_bios = is_disabled, + .hardware_setup = svm_hardware_setup, + .check_processor_compatibility = svm_check_processor_compat, + + .runtime_ops = &svm_x86_ops, }; static int __init svm_init(void) { - return kvm_init(&svm_x86_ops, sizeof(struct vcpu_svm), + return kvm_init(&svm_init_ops, sizeof(struct vcpu_svm), __alignof__(struct vcpu_svm), THIS_MODULE); } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index cef5a344fedb..249062f24b94 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -151,32 +151,38 @@ TRACE_EVENT(kvm_fast_mmio, * Tracepoint for cpuid. */ TRACE_EVENT(kvm_cpuid, - TP_PROTO(unsigned int function, unsigned long rax, unsigned long rbx, - unsigned long rcx, unsigned long rdx, bool found), - TP_ARGS(function, rax, rbx, rcx, rdx, found), + TP_PROTO(unsigned int function, unsigned int index, unsigned long rax, + unsigned long rbx, unsigned long rcx, unsigned long rdx, + bool found, bool used_max_basic), + TP_ARGS(function, index, rax, rbx, rcx, rdx, found, used_max_basic), TP_STRUCT__entry( __field( unsigned int, function ) + __field( unsigned int, index ) __field( unsigned long, rax ) __field( unsigned long, rbx ) __field( unsigned long, rcx ) __field( unsigned long, rdx ) __field( bool, found ) + __field( bool, used_max_basic ) ), TP_fast_assign( __entry->function = function; + __entry->index = index; __entry->rax = rax; __entry->rbx = rbx; __entry->rcx = rcx; __entry->rdx = rdx; __entry->found = found; + __entry->used_max_basic = used_max_basic; ), - TP_printk("func %x rax %lx rbx %lx rcx %lx rdx %lx, cpuid entry %s", - __entry->function, __entry->rax, + TP_printk("func %x idx %x rax %lx rbx %lx rcx %lx rdx %lx, cpuid entry %s%s", + __entry->function, __entry->index, __entry->rax, __entry->rbx, __entry->rcx, __entry->rdx, - __entry->found ? "found" : "not found") + __entry->found ? "found" : "not found", + __entry->used_max_basic ? ", used max basic" : "") ); #define AREG(x) { APIC_##x, "APIC_" #x } @@ -240,7 +246,7 @@ TRACE_EVENT(kvm_exit, __entry->guest_rip = kvm_rip_read(vcpu); __entry->isa = isa; __entry->vcpu_id = vcpu->vcpu_id; - kvm_x86_ops->get_exit_info(vcpu, &__entry->info1, + kvm_x86_ops.get_exit_info(vcpu, &__entry->info1, &__entry->info2); ), @@ -744,14 +750,14 @@ TRACE_EVENT(kvm_emulate_insn, ), TP_fast_assign( - __entry->csbase = kvm_x86_ops->get_segment_base(vcpu, VCPU_SREG_CS); - __entry->len = vcpu->arch.emulate_ctxt.fetch.ptr - - vcpu->arch.emulate_ctxt.fetch.data; - __entry->rip = vcpu->arch.emulate_ctxt._eip - __entry->len; + __entry->csbase = kvm_x86_ops.get_segment_base(vcpu, VCPU_SREG_CS); + __entry->len = vcpu->arch.emulate_ctxt->fetch.ptr + - vcpu->arch.emulate_ctxt->fetch.data; + __entry->rip = vcpu->arch.emulate_ctxt->_eip - __entry->len; memcpy(__entry->insn, - vcpu->arch.emulate_ctxt.fetch.data, + vcpu->arch.emulate_ctxt->fetch.data, 15); - __entry->flags = kei_decode_mode(vcpu->arch.emulate_ctxt.mode); + __entry->flags = kei_decode_mode(vcpu->arch.emulate_ctxt->mode); __entry->failed = failed; ), @@ -1367,6 +1373,24 @@ TRACE_EVENT(kvm_avic_unaccelerated_access, __entry->vec) ); +TRACE_EVENT(kvm_avic_ga_log, + TP_PROTO(u32 vmid, u32 vcpuid), + TP_ARGS(vmid, vcpuid), + + TP_STRUCT__entry( + __field(u32, vmid) + __field(u32, vcpuid) + ), + + TP_fast_assign( + __entry->vmid = vmid; + __entry->vcpuid = vcpuid; + ), + + TP_printk("vmid=%u, vcpuid=%u", + __entry->vmid, __entry->vcpuid) +); + TRACE_EVENT(kvm_hv_timer_state, TP_PROTO(unsigned int vcpu_id, unsigned int hv_timer_in_use), TP_ARGS(vcpu_id, hv_timer_in_use), diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index f486e2606247..8903475f751e 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -101,7 +101,7 @@ static inline bool cpu_has_load_perf_global_ctrl(void) (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL); } -static inline bool vmx_mpx_supported(void) +static inline bool cpu_has_vmx_mpx(void) { return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) && (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_BNDCFGS); @@ -146,11 +146,6 @@ static inline bool vmx_umip_emulated(void) SECONDARY_EXEC_DESC; } -static inline bool vmx_pku_supported(void) -{ - return boot_cpu_has(X86_FEATURE_PKU); -} - static inline bool cpu_has_vmx_rdtscp(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -354,4 +349,22 @@ static inline bool cpu_has_vmx_intel_pt(void) (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL); } +/* + * Processor Trace can operate in one of three modes: + * a. system-wide: trace both host/guest and output to host buffer + * b. host-only: only trace host and output to host buffer + * c. host-guest: trace host and guest simultaneously and output to their + * respective buffer + * + * KVM currently only supports (a) and (c). + */ +static inline bool vmx_pt_mode_is_system(void) +{ + return pt_mode == PT_MODE_SYSTEM; +} +static inline bool vmx_pt_mode_is_host_guest(void) +{ + return pt_mode == PT_MODE_HOST_GUEST; +} + #endif /* __KVM_X86_VMX_CAPS_H */ diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index 6de47f2569c9..e5f7a7ebf27d 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -198,6 +198,13 @@ static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {} static inline void evmcs_touch_msr_bitmap(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ +enum nested_evmptrld_status { + EVMPTRLD_DISABLED, + EVMPTRLD_SUCCEEDED, + EVMPTRLD_VMFAIL, + EVMPTRLD_ERROR, +}; + bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa); uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); int nested_enable_evmcs(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 9750e590c89d..de232306561a 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -353,9 +353,8 @@ static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) to_vmx(vcpu)->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT, nested_ept_ad_enabled(vcpu), - nested_ept_get_cr3(vcpu)); - vcpu->arch.mmu->set_cr3 = vmx_set_cr3; - vcpu->arch.mmu->get_cr3 = nested_ept_get_cr3; + nested_ept_get_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; @@ -1910,18 +1909,18 @@ static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) * This is an equivalent of the nested hypervisor executing the vmptrld * instruction. */ -static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, - bool from_launch) +static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( + struct kvm_vcpu *vcpu, bool from_launch) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool evmcs_gpa_changed = false; u64 evmcs_gpa; if (likely(!vmx->nested.enlightened_vmcs_enabled)) - return 1; + return EVMPTRLD_DISABLED; if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) - return 1; + return EVMPTRLD_DISABLED; if (unlikely(!vmx->nested.hv_evmcs || evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { @@ -1932,7 +1931,7 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, if (kvm_vcpu_map(vcpu, gpa_to_gfn(evmcs_gpa), &vmx->nested.hv_evmcs_map)) - return 0; + return EVMPTRLD_ERROR; vmx->nested.hv_evmcs = vmx->nested.hv_evmcs_map.hva; @@ -1961,7 +1960,7 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, if ((vmx->nested.hv_evmcs->revision_id != KVM_EVMCS_VERSION) && (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION)) { nested_release_evmcs(vcpu); - return 0; + return EVMPTRLD_VMFAIL; } vmx->nested.dirty_vmcs12 = true; @@ -1990,21 +1989,13 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, vmx->nested.hv_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; - return 1; + return EVMPTRLD_SUCCEEDED; } void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * hv_evmcs may end up being not mapped after migration (when - * L2 was running), map it here to make sure vmcs12 changes are - * properly reflected. - */ - if (vmx->nested.enlightened_vmcs_enabled && !vmx->nested.hv_evmcs) - nested_vmx_handle_enlightened_vmptrld(vcpu, false); - if (vmx->nested.hv_evmcs) { copy_vmcs12_to_enlightened(vmx); /* All fields are clean */ @@ -2475,9 +2466,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * If L1 use EPT, then L0 needs to execute INVEPT on * EPTP02 instead of EPTP01. Therefore, delay TLB * flush until vmcs02->eptp is fully updated by - * KVM_REQ_LOAD_CR3. Note that this assumes + * KVM_REQ_LOAD_MMU_PGD. Note that this assumes * KVM_REQ_TLB_FLUSH is evaluated after - * KVM_REQ_LOAD_CR3 in vcpu_enter_guest(). + * KVM_REQ_LOAD_MMU_PGD in vcpu_enter_guest(). */ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } @@ -2522,7 +2513,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, /* * Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12 * on nested VM-Exit, which can occur without actually running L2 and - * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with + * thus without hitting vmx_load_mmu_pgd(), e.g. if L1 is entering L2 with * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the * transition to HLT instead of running L2. */ @@ -2564,13 +2555,13 @@ static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12) return 0; } -static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address) +static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp) { struct vcpu_vmx *vmx = to_vmx(vcpu); int maxphyaddr = cpuid_maxphyaddr(vcpu); /* Check for memory type validity */ - switch (address & VMX_EPTP_MT_MASK) { + switch (new_eptp & VMX_EPTP_MT_MASK) { case VMX_EPTP_MT_UC: if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT))) return false; @@ -2583,16 +2574,26 @@ static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address) return false; } - /* only 4 levels page-walk length are valid */ - if (CC((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4)) + /* Page-walk levels validity. */ + switch (new_eptp & VMX_EPTP_PWL_MASK) { + case VMX_EPTP_PWL_5: + if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_5_BIT))) + return false; + break; + case VMX_EPTP_PWL_4: + if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_4_BIT))) + return false; + break; + default: return false; + } /* Reserved bits should not be set */ - if (CC(address >> maxphyaddr || ((address >> 7) & 0x1f))) + if (CC(new_eptp >> maxphyaddr || ((new_eptp >> 7) & 0x1f))) return false; /* AD, if set, should be supported */ - if (address & VMX_EPTP_AD_ENABLE_BIT) { + if (new_eptp & VMX_EPTP_AD_ENABLE_BIT) { if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT))) return false; } @@ -2641,7 +2642,7 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, return -EINVAL; if (nested_cpu_has_ept(vmcs12) && - CC(!valid_ept_address(vcpu, vmcs12->ept_pointer))) + CC(!nested_vmx_check_eptp(vcpu, vmcs12->ept_pointer))) return -EINVAL; if (nested_cpu_has_vmfunc(vmcs12)) { @@ -2961,7 +2962,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) /* * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS, * which is reserved to '1' by hardware. GUEST_RFLAGS is guaranteed to - * be written (by preparve_vmcs02()) before the "real" VMEnter, i.e. + * be written (by prepare_vmcs02()) before the "real" VMEnter, i.e. * there is no need to preserve other bits or save/restore the field. */ vmcs_writel(GUEST_RFLAGS, 0); @@ -3053,6 +3054,27 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) struct page *page; u64 hpa; + /* + * hv_evmcs may end up being not mapped after migration (when + * L2 was running), map it here to make sure vmcs12 changes are + * properly reflected. + */ + if (vmx->nested.enlightened_vmcs_enabled && !vmx->nested.hv_evmcs) { + 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; + return false; + } + } + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { /* * Translate L1 physical address to host physical @@ -3316,12 +3338,18 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) enum nvmx_vmentry_status status; struct vcpu_vmx *vmx = to_vmx(vcpu); u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu); + enum nested_evmptrld_status evmptrld_status; if (!nested_vmx_check_permission(vcpu)) return 1; - if (!nested_vmx_handle_enlightened_vmptrld(vcpu, launch)) + evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, launch); + if (evmptrld_status == EVMPTRLD_ERROR) { + kvm_queue_exception(vcpu, UD_VECTOR); return 1; + } else if (evmptrld_status == EVMPTRLD_VMFAIL) { + return nested_vmx_failInvalid(vcpu); + } if (!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull) return nested_vmx_failInvalid(vcpu); @@ -3499,7 +3527,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, } -static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) +void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); gfn_t gfn; @@ -3604,7 +3632,7 @@ static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu) vcpu->arch.exception.payload); } -static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) +static int vmx_check_nested_events(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qual; @@ -3680,8 +3708,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } - if ((kvm_cpu_has_interrupt(vcpu) || external_intr) && - nested_exit_on_intr(vcpu)) { + if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) { if (block_nested_events) return -EBUSY; nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); @@ -4024,7 +4051,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * * If vmcs12 uses EPT, we need to execute this flush on EPTP01 * and therefore we request the TLB flush to happen only after VMCS EPTP - * has been set by KVM_REQ_LOAD_CR3. + * has been set by KVM_REQ_LOAD_MMU_PGD. */ if (enable_vpid && (!nested_cpu_has_vpid(vmcs12) || !nested_has_guest_tlb_tag(vcpu))) { @@ -4329,17 +4356,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (likely(!vmx->fail)) { - /* - * TODO: SDM says that with acknowledge interrupt on - * exit, bit 31 of the VM-exit interrupt information - * (valid interrupt) is always set to 1 on - * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't - * need kvm_cpu_has_interrupt(). See the commit - * message for details. - */ - if (nested_exit_intr_ack_set(vcpu) && - exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && - kvm_cpu_has_interrupt(vcpu)) { + if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && + nested_exit_intr_ack_set(vcpu)) { int irq = kvm_cpu_get_interrupt(vcpu); WARN_ON(irq < 0); vmcs12->vm_exit_intr_info = irq | @@ -4383,7 +4401,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, * Decode the memory-address operand of a vmx instruction, as recorded on an * exit caused by such an instruction (run by a guest hypervisor). * On success, returns 0. When the operand is invalid, returns 1 and throws - * #UD or #GP. + * #UD, #GP, or #SS. */ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret) @@ -4424,7 +4442,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, if (base_is_valid) off += kvm_register_read(vcpu, base_reg); if (index_is_valid) - off += kvm_register_read(vcpu, index_reg)<<scaling; + off += kvm_register_read(vcpu, index_reg) << scaling; vmx_get_segment(vcpu, &s, seg_reg); /* @@ -4517,7 +4535,7 @@ void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu) return; vmx = to_vmx(vcpu); - if (kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) { + if (kvm_x86_ops.pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) { vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; vmx->nested.msrs.exit_ctls_high |= @@ -4603,7 +4621,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) vmx->nested.vmcs02_initialized = false; vmx->nested.vmxon = true; - if (pt_mode == PT_MODE_HOST_GUEST) { + if (vmx_pt_mode_is_host_guest()) { vmx->pt_desc.guest.ctl = 0; pt_update_intercept_for_msr(vmx); } @@ -5235,7 +5253,7 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { u32 index = kvm_rcx_read(vcpu); - u64 address; + u64 new_eptp; bool accessed_dirty; struct kvm_mmu *mmu = vcpu->arch.walk_mmu; @@ -5248,23 +5266,23 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu, if (kvm_vcpu_read_guest_page(vcpu, vmcs12->eptp_list_address >> PAGE_SHIFT, - &address, index * 8, 8)) + &new_eptp, index * 8, 8)) return 1; - accessed_dirty = !!(address & VMX_EPTP_AD_ENABLE_BIT); + 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 */ - if (vmcs12->ept_pointer != address) { - if (!valid_ept_address(vcpu, address)) + if (vmcs12->ept_pointer != new_eptp) { + if (!nested_vmx_check_eptp(vcpu, new_eptp)) return 1; kvm_mmu_unload(vcpu); mmu->ept_ad = accessed_dirty; mmu->mmu_role.base.ad_disabled = !accessed_dirty; - vmcs12->ept_pointer = address; + vmcs12->ept_pointer = new_eptp; /* * TODO: Check what's the correct approach in case * mmu reload fails. Currently, we just let the next @@ -5525,8 +5543,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - if (vmx->nested.nested_run_pending) - return false; + WARN_ON_ONCE(vmx->nested.nested_run_pending); if (unlikely(vmx->fail)) { trace_kvm_nested_vmenter_failed( @@ -5535,19 +5552,6 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) return true; } - /* - * The host physical addresses of some pages of guest memory - * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC - * Page). The CPU may write to these pages via their host - * physical address while L2 is running, bypassing any - * address-translation-based dirty tracking (e.g. EPT write - * protection). - * - * Mark them dirty on every exit from L2 to prevent them from - * getting out of sync with dirty tracking. - */ - nested_mark_vmcs12_pages_dirty(vcpu); - trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason, vmcs_readl(EXIT_QUALIFICATION), vmx->idt_vectoring_info, @@ -5628,7 +5632,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); case EXIT_REASON_MONITOR_TRAP_FLAG: - return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG); + return nested_cpu_has_mtf(vmcs12); case EXIT_REASON_MONITOR_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING); case EXIT_REASON_PAUSE_INSTRUCTION: @@ -5905,10 +5909,12 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa); } else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) { /* - * Sync eVMCS upon entry as we may not have - * HV_X64_MSR_VP_ASSIST_PAGE set up yet. + * nested_vmx_handle_enlightened_vmptrld() cannot be called + * directly from here as HV_X64_MSR_VP_ASSIST_PAGE may not be + * restored yet. EVMCS will be mapped from + * nested_get_vmcs12_pages(). */ - vmx->nested.need_vmcs12_to_shadow_sync = true; + kvm_make_request(KVM_REQ_GET_VMCS12_PAGES, vcpu); } else { return -EINVAL; } @@ -6130,11 +6136,13 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) /* nested EPT: emulate EPT also to L1 */ msrs->secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT; - msrs->ept_caps = VMX_EPT_PAGE_WALK_4_BIT | - VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT; - if (cpu_has_vmx_ept_execute_only()) - msrs->ept_caps |= - VMX_EPT_EXECUTE_ONLY_BIT; + msrs->ept_caps = + VMX_EPT_PAGE_WALK_4_BIT | + VMX_EPT_PAGE_WALK_5_BIT | + VMX_EPTP_WB_BIT | + VMX_EPT_INVEPT_BIT | + VMX_EPT_EXECUTE_ONLY_BIT; + msrs->ept_caps &= ept_caps; msrs->ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT | VMX_EPT_EXTENT_CONTEXT_BIT | VMX_EPT_2MB_PAGE_BIT | @@ -6233,7 +6241,8 @@ void nested_vmx_hardware_unsetup(void) } } -__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) +__init int nested_vmx_hardware_setup(struct kvm_x86_ops *ops, + int (*exit_handlers[])(struct kvm_vcpu *)) { int i; @@ -6269,12 +6278,12 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid; exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc; - kvm_x86_ops->check_nested_events = vmx_check_nested_events; - kvm_x86_ops->get_nested_state = vmx_get_nested_state; - kvm_x86_ops->set_nested_state = vmx_set_nested_state; - kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages; - kvm_x86_ops->nested_enable_evmcs = nested_enable_evmcs; - kvm_x86_ops->nested_get_evmcs_version = nested_get_evmcs_version; + ops->check_nested_events = vmx_check_nested_events; + ops->get_nested_state = vmx_get_nested_state; + ops->set_nested_state = vmx_set_nested_state; + ops->get_vmcs12_pages = nested_get_vmcs12_pages; + ops->nested_enable_evmcs = nested_enable_evmcs; + ops->nested_get_evmcs_version = nested_get_evmcs_version; return 0; } diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 9aeda46f473e..ac56aefa49e3 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -19,7 +19,8 @@ enum nvmx_vmentry_status { void vmx_leave_nested(struct kvm_vcpu *vcpu); void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps); void nested_vmx_hardware_unsetup(void); -__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); +__init int nested_vmx_hardware_setup(struct kvm_x86_ops *ops, + int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, @@ -33,6 +34,7 @@ int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret); void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu); +void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu); bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, int size); @@ -60,7 +62,7 @@ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu) vmx->nested.hv_evmcs; } -static inline unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) +static inline unsigned long nested_ept_get_eptp(struct kvm_vcpu *vcpu) { /* return the page table to be shadowed - in our case, EPT12 */ return get_vmcs12(vcpu)->ept_pointer; @@ -68,7 +70,7 @@ static inline unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) static inline bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu) { - return nested_ept_get_cr3(vcpu) & VMX_EPTP_AD_ENABLE_BIT; + return nested_ept_get_eptp(vcpu) & VMX_EPTP_AD_ENABLE_BIT; } /* diff --git a/arch/x86/kvm/vmx/ops.h b/arch/x86/kvm/vmx/ops.h index 45eaedee2ac0..19717d0a1100 100644 --- a/arch/x86/kvm/vmx/ops.h +++ b/arch/x86/kvm/vmx/ops.h @@ -13,6 +13,8 @@ #define __ex(x) __kvm_handle_fault_on_reboot(x) asmlinkage void vmread_error(unsigned long field, bool fault); +__attribute__((regparm(0))) void vmread_error_trampoline(unsigned long field, + bool fault); void vmwrite_error(unsigned long field, unsigned long value); void vmclear_error(struct vmcs *vmcs, u64 phys_addr); void vmptrld_error(struct vmcs *vmcs, u64 phys_addr); @@ -70,15 +72,28 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) asm volatile("1: vmread %2, %1\n\t" ".byte 0x3e\n\t" /* branch taken hint */ "ja 3f\n\t" - "mov %2, %%" _ASM_ARG1 "\n\t" - "xor %%" _ASM_ARG2 ", %%" _ASM_ARG2 "\n\t" - "2: call vmread_error\n\t" - "xor %k1, %k1\n\t" + + /* + * VMREAD failed. Push '0' for @fault, push the failing + * @field, and bounce through the trampoline to preserve + * volatile registers. + */ + "push $0\n\t" + "push %2\n\t" + "2:call vmread_error_trampoline\n\t" + + /* + * Unwind the stack. Note, the trampoline zeros out the + * memory for @fault so that the result is '0' on error. + */ + "pop %2\n\t" + "pop %1\n\t" "3:\n\t" + /* VMREAD faulted. As above, except push '1' for @fault. */ ".pushsection .fixup, \"ax\"\n\t" - "4: mov %2, %%" _ASM_ARG1 "\n\t" - "mov $1, %%" _ASM_ARG2 "\n\t" + "4: push $1\n\t" + "push %2\n\t" "jmp 2b\n\t" ".popsection\n\t" _ASM_EXTABLE(1b, 4b) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index fd21cdb10b79..7c857737b438 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -263,9 +263,15 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated) data = (s64)(s32)data; pmc->counter += data - pmc_read_counter(pmc); + if (pmc->perf_event) + perf_event_period(pmc->perf_event, + get_sample_period(pmc, data)); return 0; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc->counter += data - pmc_read_counter(pmc); + if (pmc->perf_event) + perf_event_period(pmc->perf_event, + get_sample_period(pmc, data)); return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) @@ -329,7 +335,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->global_ovf_ctrl_mask = pmu->global_ctrl_mask & ~(MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF | MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD); - if (kvm_x86_ops->pt_supported()) + if (vmx_pt_mode_is_host_guest()) pmu->global_ovf_ctrl_mask &= ~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 81ada2ce99e7..9651ba388ba9 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -135,12 +135,12 @@ SYM_FUNC_START(__vmx_vcpu_run) cmpb $0, %bl /* Load guest registers. Don't clobber flags. */ - mov VCPU_RBX(%_ASM_AX), %_ASM_BX mov VCPU_RCX(%_ASM_AX), %_ASM_CX mov VCPU_RDX(%_ASM_AX), %_ASM_DX + mov VCPU_RBX(%_ASM_AX), %_ASM_BX + mov VCPU_RBP(%_ASM_AX), %_ASM_BP mov VCPU_RSI(%_ASM_AX), %_ASM_SI mov VCPU_RDI(%_ASM_AX), %_ASM_DI - mov VCPU_RBP(%_ASM_AX), %_ASM_BP #ifdef CONFIG_X86_64 mov VCPU_R8 (%_ASM_AX), %r8 mov VCPU_R9 (%_ASM_AX), %r9 @@ -168,12 +168,12 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Save all guest registers, including RAX from the stack */ __ASM_SIZE(pop) VCPU_RAX(%_ASM_AX) - mov %_ASM_BX, VCPU_RBX(%_ASM_AX) mov %_ASM_CX, VCPU_RCX(%_ASM_AX) mov %_ASM_DX, VCPU_RDX(%_ASM_AX) + mov %_ASM_BX, VCPU_RBX(%_ASM_AX) + mov %_ASM_BP, VCPU_RBP(%_ASM_AX) mov %_ASM_SI, VCPU_RSI(%_ASM_AX) mov %_ASM_DI, VCPU_RDI(%_ASM_AX) - mov %_ASM_BP, VCPU_RBP(%_ASM_AX) #ifdef CONFIG_X86_64 mov %r8, VCPU_R8 (%_ASM_AX) mov %r9, VCPU_R9 (%_ASM_AX) @@ -197,12 +197,12 @@ SYM_FUNC_START(__vmx_vcpu_run) * free. RSP and RAX are exempt as RSP is restored by hardware during * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail. */ -1: xor %ebx, %ebx - xor %ecx, %ecx +1: xor %ecx, %ecx xor %edx, %edx + xor %ebx, %ebx + xor %ebp, %ebp xor %esi, %esi xor %edi, %edi - xor %ebp, %ebp #ifdef CONFIG_X86_64 xor %r8d, %r8d xor %r9d, %r9d @@ -234,3 +234,61 @@ SYM_FUNC_START(__vmx_vcpu_run) 2: mov $1, %eax jmp 1b SYM_FUNC_END(__vmx_vcpu_run) + +/** + * vmread_error_trampoline - Trampoline from inline asm to vmread_error() + * @field: VMCS field encoding that failed + * @fault: %true if the VMREAD faulted, %false if it failed + + * Save and restore volatile registers across a call to vmread_error(). Note, + * all parameters are passed on the stack. + */ +SYM_FUNC_START(vmread_error_trampoline) + push %_ASM_BP + mov %_ASM_SP, %_ASM_BP + + push %_ASM_AX + push %_ASM_CX + push %_ASM_DX +#ifdef CONFIG_X86_64 + push %rdi + push %rsi + push %r8 + push %r9 + push %r10 + push %r11 +#endif +#ifdef CONFIG_X86_64 + /* Load @field and @fault to arg1 and arg2 respectively. */ + mov 3*WORD_SIZE(%rbp), %_ASM_ARG2 + mov 2*WORD_SIZE(%rbp), %_ASM_ARG1 +#else + /* Parameters are passed on the stack for 32-bit (see asmlinkage). */ + push 3*WORD_SIZE(%ebp) + push 2*WORD_SIZE(%ebp) +#endif + + call vmread_error + +#ifndef CONFIG_X86_64 + add $8, %esp +#endif + + /* Zero out @fault, which will be popped into the result register. */ + _ASM_MOV $0, 3*WORD_SIZE(%_ASM_BP) + +#ifdef CONFIG_X86_64 + pop %r11 + pop %r10 + pop %r9 + pop %r8 + pop %rsi + pop %rdi +#endif + pop %_ASM_DX + pop %_ASM_CX + pop %_ASM_AX + pop %_ASM_BP + + ret +SYM_FUNC_END(vmread_error_trampoline) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 458e684dfbdc..91749f1254e8 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -437,7 +437,6 @@ static const struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; -u64 host_efer; static unsigned long host_idt_base; /* @@ -658,53 +657,16 @@ static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, return ret; } -void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) -{ - vmcs_clear(loaded_vmcs->vmcs); - if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) - vmcs_clear(loaded_vmcs->shadow_vmcs); - loaded_vmcs->cpu = -1; - loaded_vmcs->launched = 0; -} - #ifdef CONFIG_KEXEC_CORE -/* - * This bitmap is used to indicate whether the vmclear - * operation is enabled on all cpus. All disabled by - * default. - */ -static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE; - -static inline void crash_enable_local_vmclear(int cpu) -{ - cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline void crash_disable_local_vmclear(int cpu) -{ - cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline int crash_local_vmclear_enabled(int cpu) -{ - return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - static void crash_vmclear_local_loaded_vmcss(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; - if (!crash_local_vmclear_enabled(cpu)) - return; - list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), loaded_vmcss_on_cpu_link) vmcs_clear(v->vmcs); } -#else -static inline void crash_enable_local_vmclear(int cpu) { } -static inline void crash_disable_local_vmclear(int cpu) { } #endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) @@ -716,19 +678,24 @@ static void __loaded_vmcs_clear(void *arg) return; /* vcpu migration can race with cpu offline */ if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) per_cpu(current_vmcs, cpu) = NULL; - crash_disable_local_vmclear(cpu); + + vmcs_clear(loaded_vmcs->vmcs); + if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) + vmcs_clear(loaded_vmcs->shadow_vmcs); + list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); /* - * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link - * is before setting loaded_vmcs->vcpu to -1 which is done in - * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist - * then adds the vmcs into percpu list before it is deleted. + * Ensure all writes to loaded_vmcs, including deleting it from its + * current percpu list, complete before setting loaded_vmcs->vcpu to + * -1, otherwise a different cpu can see vcpu == -1 first and add + * loaded_vmcs to its percpu list before it's deleted from this cpu's + * list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs(). */ smp_wmb(); - loaded_vmcs_init(loaded_vmcs); - crash_enable_local_vmclear(cpu); + loaded_vmcs->cpu = -1; + loaded_vmcs->launched = 0; } void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) @@ -812,7 +779,7 @@ void update_exception_bitmap(struct kvm_vcpu *vcpu) if (to_vmx(vcpu)->rmode.vm86_active) eb = ~0; if (enable_ept) - eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */ + eb &= ~(1u << PF_VECTOR); /* When we are running a nested L2 guest and L1 specified for it a * certain exception bitmap, we must trap the same exceptions and pass @@ -1063,7 +1030,7 @@ static unsigned long segment_base(u16 selector) static inline bool pt_can_write_msr(struct vcpu_vmx *vmx) { - return (pt_mode == PT_MODE_HOST_GUEST) && + return vmx_pt_mode_is_host_guest() && !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN); } @@ -1097,7 +1064,7 @@ static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range) static void pt_guest_enter(struct vcpu_vmx *vmx) { - if (pt_mode == PT_MODE_SYSTEM) + if (vmx_pt_mode_is_system()) return; /* @@ -1114,7 +1081,7 @@ static void pt_guest_enter(struct vcpu_vmx *vmx) static void pt_guest_exit(struct vcpu_vmx *vmx) { - if (pt_mode == PT_MODE_SYSTEM) + if (vmx_pt_mode_is_system()) return; if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { @@ -1347,18 +1314,17 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) if (!already_loaded) { loaded_vmcs_clear(vmx->loaded_vmcs); local_irq_disable(); - crash_disable_local_vmclear(cpu); /* - * Read loaded_vmcs->cpu should be before fetching - * loaded_vmcs->loaded_vmcss_on_cpu_link. - * See the comments in __loaded_vmcs_clear(). + * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to + * this cpu's percpu list, otherwise it may not yet be deleted + * from its previous cpu's percpu list. Pairs with the + * smb_wmb() in __loaded_vmcs_clear(). */ smp_rmb(); list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, &per_cpu(loaded_vmcss_on_cpu, cpu)); - crash_enable_local_vmclear(cpu); local_irq_enable(); } @@ -1691,16 +1657,6 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) vmx_clear_hlt(vcpu); } -static bool vmx_rdtscp_supported(void) -{ - return cpu_has_vmx_rdtscp(); -} - -static bool vmx_invpcid_supported(void) -{ - return cpu_has_vmx_invpcid(); -} - /* * Swap MSR entry in host/guest MSR entry array. */ @@ -1908,24 +1864,24 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) &msr_info->data); break; case MSR_IA32_RTIT_CTL: - if (pt_mode != PT_MODE_HOST_GUEST) + if (!vmx_pt_mode_is_host_guest()) return 1; msr_info->data = vmx->pt_desc.guest.ctl; break; case MSR_IA32_RTIT_STATUS: - if (pt_mode != PT_MODE_HOST_GUEST) + if (!vmx_pt_mode_is_host_guest()) return 1; msr_info->data = vmx->pt_desc.guest.status; break; case MSR_IA32_RTIT_CR3_MATCH: - if ((pt_mode != PT_MODE_HOST_GUEST) || + if (!vmx_pt_mode_is_host_guest() || !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering)) return 1; msr_info->data = vmx->pt_desc.guest.cr3_match; break; case MSR_IA32_RTIT_OUTPUT_BASE: - if ((pt_mode != PT_MODE_HOST_GUEST) || + if (!vmx_pt_mode_is_host_guest() || (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, @@ -1934,7 +1890,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmx->pt_desc.guest.output_base; break; case MSR_IA32_RTIT_OUTPUT_MASK: - if ((pt_mode != PT_MODE_HOST_GUEST) || + if (!vmx_pt_mode_is_host_guest() || (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, @@ -1944,7 +1900,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; - if ((pt_mode != PT_MODE_HOST_GUEST) || + if (!vmx_pt_mode_is_host_guest() || (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_num_address_ranges))) return 1; @@ -2150,7 +2106,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_RTIT_CTL: - if ((pt_mode != PT_MODE_HOST_GUEST) || + if (!vmx_pt_mode_is_host_guest() || vmx_rtit_ctl_check(vcpu, data) || vmx->nested.vmxon) return 1; @@ -2266,18 +2222,33 @@ static __init int vmx_disabled_by_bios(void) !boot_cpu_has(X86_FEATURE_VMX); } -static void kvm_cpu_vmxon(u64 addr) +static int kvm_cpu_vmxon(u64 vmxon_pointer) { + u64 msr; + cr4_set_bits(X86_CR4_VMXE); intel_pt_handle_vmx(1); - asm volatile ("vmxon %0" : : "m"(addr)); + asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" + _ASM_EXTABLE(1b, %l[fault]) + : : [vmxon_pointer] "m"(vmxon_pointer) + : : fault); + return 0; + +fault: + WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", + rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); + intel_pt_handle_vmx(0); + cr4_clear_bits(X86_CR4_VMXE); + + return -EFAULT; } static int hardware_enable(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); + int r; if (cr4_read_shadow() & X86_CR4_VMXE) return -EBUSY; @@ -2294,18 +2265,10 @@ static int hardware_enable(void) INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); - /* - * Now we can enable the vmclear operation in kdump - * since the loaded_vmcss_on_cpu list on this cpu - * has been initialized. - * - * Though the cpu is not in VMX operation now, there - * is no problem to enable the vmclear operation - * for the loaded_vmcss_on_cpu list is empty! - */ - crash_enable_local_vmclear(cpu); + r = kvm_cpu_vmxon(phys_addr); + if (r) + return r; - kvm_cpu_vmxon(phys_addr); if (enable_ept) ept_sync_global(); @@ -2617,9 +2580,12 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) if (!loaded_vmcs->vmcs) return -ENOMEM; + vmcs_clear(loaded_vmcs->vmcs); + loaded_vmcs->shadow_vmcs = NULL; loaded_vmcs->hv_timer_soft_disabled = false; - loaded_vmcs_init(loaded_vmcs); + loaded_vmcs->cpu = -1; + loaded_vmcs->launched = 0; if (cpu_has_vmx_msr_bitmap()) { loaded_vmcs->msr_bitmap = (unsigned long *) @@ -3001,9 +2967,8 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) static int get_ept_level(struct kvm_vcpu *vcpu) { - /* Nested EPT currently only supports 4-level walks. */ if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu))) - return 4; + return vmx_eptp_page_walk_level(nested_ept_get_eptp(vcpu)); if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) return 5; return 4; @@ -3023,7 +2988,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) return eptp; } -void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long cr3) { struct kvm *kvm = vcpu->kvm; bool update_guest_cr3 = true; @@ -3035,7 +3000,7 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) eptp = construct_eptp(vcpu, cr3); vmcs_write64(EPT_POINTER, eptp); - if (kvm_x86_ops->tlb_remote_flush) { + if (kvm_x86_ops.tlb_remote_flush) { spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock); to_vmx(vcpu)->ept_pointer = eptp; to_kvm_vmx(kvm)->ept_pointers_match @@ -4040,7 +4005,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; - if (pt_mode == PT_MODE_SYSTEM) + if (vmx_pt_mode_is_system()) exec_control &= ~(SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX); if (!cpu_need_virtualize_apic_accesses(vcpu)) exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; @@ -4095,7 +4060,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) } } - if (vmx_rdtscp_supported()) { + if (cpu_has_vmx_rdtscp()) { bool rdtscp_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP); if (!rdtscp_enabled) exec_control &= ~SECONDARY_EXEC_RDTSCP; @@ -4110,7 +4075,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) } } - if (vmx_invpcid_supported()) { + if (cpu_has_vmx_invpcid()) { /* Exposing INVPCID only when PCID is exposed */ bool invpcid_enabled = guest_cpuid_has(vcpu, X86_FEATURE_INVPCID) && @@ -4281,7 +4246,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) if (cpu_has_vmx_encls_vmexit()) vmcs_write64(ENCLS_EXITING_BITMAP, -1ull); - if (pt_mode == PT_MODE_HOST_GUEST) { + if (vmx_pt_mode_is_host_guest()) { memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc)); /* Bit[6~0] are forced to 1, writes are ignored. */ vmx->pt_desc.guest.output_mask = 0x7F; @@ -4509,8 +4474,13 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { - return (!to_vmx(vcpu)->nested.nested_run_pending && - vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && + if (to_vmx(vcpu)->nested.nested_run_pending) + return false; + + if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) + return true; + + return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); } @@ -4566,7 +4536,6 @@ static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) case GP_VECTOR: case MF_VECTOR: return true; - break; } return false; } @@ -5343,7 +5312,6 @@ static void vmx_enable_tdp(void) VMX_EPT_RWX_MASK, 0ull); ept_set_mmio_spte_mask(); - kvm_enable_tdp(); } /* @@ -5876,8 +5844,23 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, if (vmx->emulation_required) return handle_invalid_guest_state(vcpu); - if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason)) - return nested_vmx_reflect_vmexit(vcpu, exit_reason); + if (is_guest_mode(vcpu)) { + /* + * The host physical addresses of some pages of guest memory + * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC + * Page). The CPU may write to these pages via their host + * physical address while L2 is running, bypassing any + * address-translation-based dirty tracking (e.g. EPT write + * protection). + * + * Mark them dirty on every exit from L2 to prevent them from + * getting out of sync with dirty tracking. + */ + nested_mark_vmcs12_pages_dirty(vcpu); + + if (nested_vmx_exit_reflected(vcpu, exit_reason)) + return nested_vmx_reflect_vmexit(vcpu, exit_reason); + } if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { dump_vmcs(); @@ -6237,15 +6220,13 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); /* if exit due to PF check for async PF */ - if (is_page_fault(vmx->exit_intr_info)) + if (is_page_fault(vmx->exit_intr_info)) { vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); - /* Handle machine checks before interrupts are enabled */ - if (is_machine_check(vmx->exit_intr_info)) + } else if (is_machine_check(vmx->exit_intr_info)) { kvm_machine_check(); - /* We need to handle NMIs before interrupts are enabled */ - if (is_nmi(vmx->exit_intr_info)) { + } else if (is_nmi(vmx->exit_intr_info)) { kvm_before_interrupt(&vmx->vcpu); asm("int $2"); kvm_after_interrupt(&vmx->vcpu); @@ -6331,11 +6312,6 @@ static bool vmx_has_emulated_msr(int index) } } -static bool vmx_pt_supported(void) -{ - return pt_mode == PT_MODE_HOST_GUEST; -} - static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -6581,7 +6557,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) pt_guest_enter(vmx); - atomic_switch_perf_msrs(vmx); + if (vcpu_to_pmu(vcpu)->version) + atomic_switch_perf_msrs(vmx); atomic_switch_umwait_control_msr(vmx); if (enable_preemption_timer) @@ -6698,20 +6675,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_complete_interrupts(vmx); } -static struct kvm *vmx_vm_alloc(void) -{ - struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx), - GFP_KERNEL_ACCOUNT | __GFP_ZERO, - PAGE_KERNEL); - return &kvm_vmx->kvm; -} - -static void vmx_vm_free(struct kvm *kvm) -{ - kfree(kvm->arch.hyperv.hv_pa_pg); - vfree(to_kvm_vmx(kvm)); -} - static void vmx_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6914,17 +6877,24 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) u8 cache; u64 ipat = 0; - /* For VT-d and EPT combination - * 1. MMIO: always map as UC - * 2. EPT with VT-d: - * a. VT-d without snooping control feature: can't guarantee the - * result, try to trust guest. - * b. VT-d with snooping control feature: snooping control feature of - * VT-d engine can guarantee the cache correctness. Just set it - * to WB to keep consistent with host. So the same as item 3. - * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep - * consistent with host MTRR + /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in + * memory aliases with conflicting memory types and sometimes MCEs. + * We have to be careful as to what are honored and when. + * + * For MMIO, guest CD/MTRR are ignored. The EPT memory type is set to + * UC. The effective memory type is UC or WC depending on guest PAT. + * This was historically the source of MCEs and we want to be + * conservative. + * + * When there is no need to deal with noncoherent DMA (e.g., no VT-d + * or VT-d has snoop control), guest CD/MTRR/PAT are all ignored. The + * EPT memory type is set to WB. The effective memory type is forced + * WB. + * + * Otherwise, we trust guest. Guest CD/MTRR/PAT are all honored. The + * EPT memory type is used to emulate guest CD/MTRR. */ + if (is_mmio) { cache = MTRR_TYPE_UNCACHABLE; goto exit; @@ -6951,15 +6921,6 @@ exit: return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; } -static int vmx_get_lpage_level(void) -{ - if (enable_ept && !cpu_has_vmx_ept_1g_page()) - return PT_DIRECTORY_LEVEL; - else - /* For shadow and EPT supported 1GB page */ - return PT_PDPE_LEVEL; -} - static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx) { /* @@ -7150,10 +7111,37 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) } } -static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) +static __init void vmx_set_cpu_caps(void) { - if (func == 1 && nested) - entry->ecx |= feature_bit(VMX); + kvm_set_cpu_caps(); + + /* CPUID 0x1 */ + if (nested) + kvm_cpu_cap_set(X86_FEATURE_VMX); + + /* CPUID 0x7 */ + if (kvm_mpx_supported()) + kvm_cpu_cap_check_and_set(X86_FEATURE_MPX); + if (cpu_has_vmx_invpcid()) + kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID); + if (vmx_pt_mode_is_host_guest()) + kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT); + + /* PKU is not yet implemented for shadow paging. */ + if (enable_ept && boot_cpu_has(X86_FEATURE_OSPKE)) + kvm_cpu_cap_check_and_set(X86_FEATURE_PKU); + + if (vmx_umip_emulated()) + kvm_cpu_cap_set(X86_FEATURE_UMIP); + + /* CPUID 0xD.1 */ + supported_xss = 0; + if (!vmx_xsaves_supported()) + kvm_cpu_cap_clear(X86_FEATURE_XSAVES); + + /* CPUID 0x80000001 */ + if (!cpu_has_vmx_rdtscp()) + kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); } static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) @@ -7197,10 +7185,10 @@ static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, - enum x86_intercept_stage stage) + enum x86_intercept_stage stage, + struct x86_exception *exception) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; switch (info->intercept) { /* @@ -7209,8 +7197,8 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, */ case x86_intercept_rdtscp: if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { - ctxt->exception.vector = UD_VECTOR; - ctxt->exception.error_code_valid = false; + exception->vector = UD_VECTOR; + exception->error_code_valid = false; return X86EMUL_PROPAGATE_FAULT; } break; @@ -7321,7 +7309,8 @@ static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) static void vmx_slot_enable_log_dirty(struct kvm *kvm, struct kvm_memory_slot *slot) { - kvm_mmu_slot_leaf_clear_dirty(kvm, slot); + if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) + kvm_mmu_slot_leaf_clear_dirty(kvm, slot); kvm_mmu_slot_largepage_remove_write_access(kvm, slot); } @@ -7504,7 +7493,7 @@ static void pi_post_block(struct kvm_vcpu *vcpu) static void vmx_post_block(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops->set_hv_timer) + if (kvm_x86_ops.set_hv_timer) kvm_lapic_switch_to_hv_timer(vcpu); pi_post_block(vcpu); @@ -7671,13 +7660,164 @@ static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) return to_vmx(vcpu)->nested.vmxon; } +static void hardware_unsetup(void) +{ + if (nested) + nested_vmx_hardware_unsetup(); + + free_kvm_area(); +} + +static bool vmx_check_apicv_inhibit_reasons(ulong bit) +{ + ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_HYPERV); + + return supported & BIT(bit); +} + +static struct kvm_x86_ops vmx_x86_ops __initdata = { + .hardware_unsetup = hardware_unsetup, + + .hardware_enable = hardware_enable, + .hardware_disable = hardware_disable, + .cpu_has_accelerated_tpr = report_flexpriority, + .has_emulated_msr = vmx_has_emulated_msr, + + .vm_size = sizeof(struct kvm_vmx), + .vm_init = vmx_vm_init, + + .vcpu_create = vmx_create_vcpu, + .vcpu_free = vmx_free_vcpu, + .vcpu_reset = vmx_vcpu_reset, + + .prepare_guest_switch = vmx_prepare_switch_to_guest, + .vcpu_load = vmx_vcpu_load, + .vcpu_put = vmx_vcpu_put, + + .update_bp_intercept = update_exception_bitmap, + .get_msr_feature = vmx_get_msr_feature, + .get_msr = vmx_get_msr, + .set_msr = vmx_set_msr, + .get_segment_base = vmx_get_segment_base, + .get_segment = vmx_get_segment, + .set_segment = vmx_set_segment, + .get_cpl = vmx_get_cpl, + .get_cs_db_l_bits = vmx_get_cs_db_l_bits, + .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits, + .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, + .set_cr0 = vmx_set_cr0, + .set_cr4 = vmx_set_cr4, + .set_efer = vmx_set_efer, + .get_idt = vmx_get_idt, + .set_idt = vmx_set_idt, + .get_gdt = vmx_get_gdt, + .set_gdt = vmx_set_gdt, + .get_dr6 = vmx_get_dr6, + .set_dr6 = vmx_set_dr6, + .set_dr7 = vmx_set_dr7, + .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, + .cache_reg = vmx_cache_reg, + .get_rflags = vmx_get_rflags, + .set_rflags = vmx_set_rflags, + + .tlb_flush = vmx_flush_tlb, + .tlb_flush_gva = vmx_flush_tlb_gva, + + .run = vmx_vcpu_run, + .handle_exit = vmx_handle_exit, + .skip_emulated_instruction = vmx_skip_emulated_instruction, + .update_emulated_instruction = vmx_update_emulated_instruction, + .set_interrupt_shadow = vmx_set_interrupt_shadow, + .get_interrupt_shadow = vmx_get_interrupt_shadow, + .patch_hypercall = vmx_patch_hypercall, + .set_irq = vmx_inject_irq, + .set_nmi = vmx_inject_nmi, + .queue_exception = vmx_queue_exception, + .cancel_injection = vmx_cancel_injection, + .interrupt_allowed = vmx_interrupt_allowed, + .nmi_allowed = vmx_nmi_allowed, + .get_nmi_mask = vmx_get_nmi_mask, + .set_nmi_mask = vmx_set_nmi_mask, + .enable_nmi_window = enable_nmi_window, + .enable_irq_window = enable_irq_window, + .update_cr8_intercept = update_cr8_intercept, + .set_virtual_apic_mode = vmx_set_virtual_apic_mode, + .set_apic_access_page_addr = vmx_set_apic_access_page_addr, + .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, + .load_eoi_exitmap = vmx_load_eoi_exitmap, + .apicv_post_state_restore = vmx_apicv_post_state_restore, + .check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons, + .hwapic_irr_update = vmx_hwapic_irr_update, + .hwapic_isr_update = vmx_hwapic_isr_update, + .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, + .sync_pir_to_irr = vmx_sync_pir_to_irr, + .deliver_posted_interrupt = vmx_deliver_posted_interrupt, + .dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt, + + .set_tss_addr = vmx_set_tss_addr, + .set_identity_map_addr = vmx_set_identity_map_addr, + .get_tdp_level = get_ept_level, + .get_mt_mask = vmx_get_mt_mask, + + .get_exit_info = vmx_get_exit_info, + + .cpuid_update = vmx_cpuid_update, + + .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, + + .read_l1_tsc_offset = vmx_read_l1_tsc_offset, + .write_l1_tsc_offset = vmx_write_l1_tsc_offset, + + .load_mmu_pgd = vmx_load_mmu_pgd, + + .check_intercept = vmx_check_intercept, + .handle_exit_irqoff = vmx_handle_exit_irqoff, + + .request_immediate_exit = vmx_request_immediate_exit, + + .sched_in = vmx_sched_in, + + .slot_enable_log_dirty = vmx_slot_enable_log_dirty, + .slot_disable_log_dirty = vmx_slot_disable_log_dirty, + .flush_log_dirty = vmx_flush_log_dirty, + .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, + .write_log_dirty = vmx_write_pml_buffer, + + .pre_block = vmx_pre_block, + .post_block = vmx_post_block, + + .pmu_ops = &intel_pmu_ops, + + .update_pi_irte = vmx_update_pi_irte, + +#ifdef CONFIG_X86_64 + .set_hv_timer = vmx_set_hv_timer, + .cancel_hv_timer = vmx_cancel_hv_timer, +#endif + + .setup_mce = vmx_setup_mce, + + .smi_allowed = vmx_smi_allowed, + .pre_enter_smm = vmx_pre_enter_smm, + .pre_leave_smm = vmx_pre_leave_smm, + .enable_smi_window = enable_smi_window, + + .check_nested_events = NULL, + .get_nested_state = NULL, + .set_nested_state = NULL, + .get_vmcs12_pages = NULL, + .nested_enable_evmcs = NULL, + .nested_get_evmcs_version = NULL, + .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, + .apic_init_signal_blocked = vmx_apic_init_signal_blocked, +}; + static __init int hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; - int r, i; - - rdmsrl_safe(MSR_EFER, &host_efer); + int r, i, ept_lpage_level; store_idt(&dt); host_idt_base = dt.address; @@ -7696,6 +7836,10 @@ static __init int hardware_setup(void) WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); } + if (!cpu_has_vmx_mpx()) + supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | + XFEATURE_MASK_BNDCSR); + if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; @@ -7724,19 +7868,16 @@ static __init int hardware_setup(void) * using the APIC_ACCESS_ADDR VMCS field. */ if (!flexpriority_enabled) - kvm_x86_ops->set_apic_access_page_addr = NULL; + vmx_x86_ops.set_apic_access_page_addr = NULL; if (!cpu_has_vmx_tpr_shadow()) - kvm_x86_ops->update_cr8_intercept = NULL; - - if (enable_ept && !cpu_has_vmx_ept_2m_page()) - kvm_disable_largepages(); + vmx_x86_ops.update_cr8_intercept = NULL; #if IS_ENABLED(CONFIG_HYPERV) if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH && enable_ept) { - kvm_x86_ops->tlb_remote_flush = hv_remote_flush_tlb; - kvm_x86_ops->tlb_remote_flush_with_range = + vmx_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; + vmx_x86_ops.tlb_remote_flush_with_range = hv_remote_flush_tlb_with_range; } #endif @@ -7751,7 +7892,7 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_apicv()) { enable_apicv = 0; - kvm_x86_ops->sync_pir_to_irr = NULL; + vmx_x86_ops.sync_pir_to_irr = NULL; } if (cpu_has_vmx_tsc_scaling()) { @@ -7764,8 +7905,16 @@ static __init int hardware_setup(void) if (enable_ept) vmx_enable_tdp(); + + if (!enable_ept) + ept_lpage_level = 0; + else if (cpu_has_vmx_ept_1g_page()) + ept_lpage_level = PT_PDPE_LEVEL; + else if (cpu_has_vmx_ept_2m_page()) + ept_lpage_level = PT_DIRECTORY_LEVEL; else - kvm_disable_tdp(); + ept_lpage_level = PT_PAGE_TABLE_LEVEL; + kvm_configure_mmu(enable_ept, ept_lpage_level); /* * Only enable PML when hardware supports PML feature, and both EPT @@ -7775,10 +7924,10 @@ static __init int hardware_setup(void) enable_pml = 0; if (!enable_pml) { - kvm_x86_ops->slot_enable_log_dirty = NULL; - kvm_x86_ops->slot_disable_log_dirty = NULL; - kvm_x86_ops->flush_log_dirty = NULL; - kvm_x86_ops->enable_log_dirty_pt_masked = NULL; + vmx_x86_ops.slot_enable_log_dirty = NULL; + vmx_x86_ops.slot_disable_log_dirty = NULL; + vmx_x86_ops.flush_log_dirty = NULL; + vmx_x86_ops.enable_log_dirty_pt_masked = NULL; } if (!cpu_has_vmx_preemption_timer()) @@ -7806,9 +7955,9 @@ static __init int hardware_setup(void) } if (!enable_preemption_timer) { - kvm_x86_ops->set_hv_timer = NULL; - kvm_x86_ops->cancel_hv_timer = NULL; - kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit; + vmx_x86_ops.set_hv_timer = NULL; + vmx_x86_ops.cancel_hv_timer = NULL; + vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit; } kvm_set_posted_intr_wakeup_handler(wakeup_handler); @@ -7824,185 +7973,27 @@ static __init int hardware_setup(void) nested_vmx_setup_ctls_msrs(&vmcs_config.nested, vmx_capability.ept); - r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); + r = nested_vmx_hardware_setup(&vmx_x86_ops, + kvm_vmx_exit_handlers); if (r) return r; } + vmx_set_cpu_caps(); + r = alloc_kvm_area(); if (r) nested_vmx_hardware_unsetup(); return r; } -static __exit void hardware_unsetup(void) -{ - if (nested) - nested_vmx_hardware_unsetup(); - - free_kvm_area(); -} - -static bool vmx_check_apicv_inhibit_reasons(ulong bit) -{ - ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_HYPERV); - - return supported & BIT(bit); -} - -static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { +static struct kvm_x86_init_ops vmx_init_ops __initdata = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, - .hardware_setup = hardware_setup, - .hardware_unsetup = hardware_unsetup, .check_processor_compatibility = vmx_check_processor_compat, - .hardware_enable = hardware_enable, - .hardware_disable = hardware_disable, - .cpu_has_accelerated_tpr = report_flexpriority, - .has_emulated_msr = vmx_has_emulated_msr, - - .vm_init = vmx_vm_init, - .vm_alloc = vmx_vm_alloc, - .vm_free = vmx_vm_free, - - .vcpu_create = vmx_create_vcpu, - .vcpu_free = vmx_free_vcpu, - .vcpu_reset = vmx_vcpu_reset, - - .prepare_guest_switch = vmx_prepare_switch_to_guest, - .vcpu_load = vmx_vcpu_load, - .vcpu_put = vmx_vcpu_put, - - .update_bp_intercept = update_exception_bitmap, - .get_msr_feature = vmx_get_msr_feature, - .get_msr = vmx_get_msr, - .set_msr = vmx_set_msr, - .get_segment_base = vmx_get_segment_base, - .get_segment = vmx_get_segment, - .set_segment = vmx_set_segment, - .get_cpl = vmx_get_cpl, - .get_cs_db_l_bits = vmx_get_cs_db_l_bits, - .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits, - .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, - .set_cr0 = vmx_set_cr0, - .set_cr3 = vmx_set_cr3, - .set_cr4 = vmx_set_cr4, - .set_efer = vmx_set_efer, - .get_idt = vmx_get_idt, - .set_idt = vmx_set_idt, - .get_gdt = vmx_get_gdt, - .set_gdt = vmx_set_gdt, - .get_dr6 = vmx_get_dr6, - .set_dr6 = vmx_set_dr6, - .set_dr7 = vmx_set_dr7, - .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, - .cache_reg = vmx_cache_reg, - .get_rflags = vmx_get_rflags, - .set_rflags = vmx_set_rflags, - - .tlb_flush = vmx_flush_tlb, - .tlb_flush_gva = vmx_flush_tlb_gva, - - .run = vmx_vcpu_run, - .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = vmx_skip_emulated_instruction, - .update_emulated_instruction = vmx_update_emulated_instruction, - .set_interrupt_shadow = vmx_set_interrupt_shadow, - .get_interrupt_shadow = vmx_get_interrupt_shadow, - .patch_hypercall = vmx_patch_hypercall, - .set_irq = vmx_inject_irq, - .set_nmi = vmx_inject_nmi, - .queue_exception = vmx_queue_exception, - .cancel_injection = vmx_cancel_injection, - .interrupt_allowed = vmx_interrupt_allowed, - .nmi_allowed = vmx_nmi_allowed, - .get_nmi_mask = vmx_get_nmi_mask, - .set_nmi_mask = vmx_set_nmi_mask, - .enable_nmi_window = enable_nmi_window, - .enable_irq_window = enable_irq_window, - .update_cr8_intercept = update_cr8_intercept, - .set_virtual_apic_mode = vmx_set_virtual_apic_mode, - .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, - .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_post_state_restore = vmx_apicv_post_state_restore, - .check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons, - .hwapic_irr_update = vmx_hwapic_irr_update, - .hwapic_isr_update = vmx_hwapic_isr_update, - .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, - .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_posted_interrupt = vmx_deliver_posted_interrupt, - .dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt, - - .set_tss_addr = vmx_set_tss_addr, - .set_identity_map_addr = vmx_set_identity_map_addr, - .get_tdp_level = get_ept_level, - .get_mt_mask = vmx_get_mt_mask, - - .get_exit_info = vmx_get_exit_info, - - .get_lpage_level = vmx_get_lpage_level, - - .cpuid_update = vmx_cpuid_update, - - .rdtscp_supported = vmx_rdtscp_supported, - .invpcid_supported = vmx_invpcid_supported, - - .set_supported_cpuid = vmx_set_supported_cpuid, - - .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - - .read_l1_tsc_offset = vmx_read_l1_tsc_offset, - .write_l1_tsc_offset = vmx_write_l1_tsc_offset, - - .set_tdp_cr3 = vmx_set_cr3, - - .check_intercept = vmx_check_intercept, - .handle_exit_irqoff = vmx_handle_exit_irqoff, - .mpx_supported = vmx_mpx_supported, - .xsaves_supported = vmx_xsaves_supported, - .umip_emulated = vmx_umip_emulated, - .pt_supported = vmx_pt_supported, - .pku_supported = vmx_pku_supported, - - .request_immediate_exit = vmx_request_immediate_exit, - - .sched_in = vmx_sched_in, - - .slot_enable_log_dirty = vmx_slot_enable_log_dirty, - .slot_disable_log_dirty = vmx_slot_disable_log_dirty, - .flush_log_dirty = vmx_flush_log_dirty, - .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, - .write_log_dirty = vmx_write_pml_buffer, - - .pre_block = vmx_pre_block, - .post_block = vmx_post_block, - - .pmu_ops = &intel_pmu_ops, - - .update_pi_irte = vmx_update_pi_irte, - -#ifdef CONFIG_X86_64 - .set_hv_timer = vmx_set_hv_timer, - .cancel_hv_timer = vmx_cancel_hv_timer, -#endif - - .setup_mce = vmx_setup_mce, - - .smi_allowed = vmx_smi_allowed, - .pre_enter_smm = vmx_pre_enter_smm, - .pre_leave_smm = vmx_pre_leave_smm, - .enable_smi_window = enable_smi_window, + .hardware_setup = hardware_setup, - .check_nested_events = NULL, - .get_nested_state = NULL, - .set_nested_state = NULL, - .get_vmcs12_pages = NULL, - .nested_enable_evmcs = NULL, - .nested_get_evmcs_version = NULL, - .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, - .apic_init_signal_blocked = vmx_apic_init_signal_blocked, + .runtime_ops = &vmx_x86_ops, }; static void vmx_cleanup_l1d_flush(void) @@ -8089,7 +8080,7 @@ static int __init vmx_init(void) } #endif - r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), + r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), THIS_MODULE); if (r) return r; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 0695ea177e22..aab9df55336e 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -12,7 +12,6 @@ #include "vmcs.h" extern const u32 vmx_msr_index[]; -extern u64 host_efer; #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 @@ -333,9 +332,9 @@ u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu); void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask); void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer); void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); void set_cr4_guest_host_mask(struct vcpu_vmx *vmx); +void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long cr3); void ept_save_pdptrs(struct kvm_vcpu *vcpu); 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); @@ -450,7 +449,7 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static inline u32 vmx_vmentry_ctrl(void) { u32 vmentry_ctrl = vmcs_config.vmentry_ctrl; - if (pt_mode == PT_MODE_SYSTEM) + if (vmx_pt_mode_is_system()) vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ @@ -461,7 +460,7 @@ static inline u32 vmx_vmentry_ctrl(void) static inline u32 vmx_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; - if (pt_mode == PT_MODE_SYSTEM) + if (vmx_pt_mode_is_system()) vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | VM_EXIT_CLEAR_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ @@ -491,7 +490,6 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags); void free_vmcs(struct vmcs *vmcs); int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); -void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs); void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs); static inline struct vmcs *alloc_vmcs(bool shadow) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bf8564d73fc3..b8124b562dea 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -22,6 +22,7 @@ #include "i8254.h" #include "tss.h" #include "kvm_cache_regs.h" +#include "kvm_emulate.h" #include "x86.h" #include "cpuid.h" #include "pmu.h" @@ -81,7 +82,7 @@ u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P; EXPORT_SYMBOL_GPL(kvm_mce_cap_supported); #define emul_to_vcpu(ctxt) \ - container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt) + ((struct kvm_vcpu *)(ctxt)->vcpu) /* EFER defaults: * - enable syscall per default because its emulated by KVM @@ -109,7 +110,7 @@ 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); -struct kvm_x86_ops *kvm_x86_ops __read_mostly; +struct kvm_x86_ops kvm_x86_ops __read_mostly; EXPORT_SYMBOL_GPL(kvm_x86_ops); static bool __read_mostly ignore_msrs = 0; @@ -180,7 +181,17 @@ struct kvm_shared_msrs { static struct kvm_shared_msrs_global __read_mostly shared_msrs_global; static struct kvm_shared_msrs __percpu *shared_msrs; +#define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ + | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ + | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \ + | XFEATURE_MASK_PKRU) + +u64 __read_mostly host_efer; +EXPORT_SYMBOL_GPL(host_efer); + static u64 __read_mostly host_xss; +u64 __read_mostly supported_xss; +EXPORT_SYMBOL_GPL(supported_xss); struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, @@ -226,10 +237,25 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { }; u64 __read_mostly host_xcr0; +u64 __read_mostly supported_xcr0; +EXPORT_SYMBOL_GPL(supported_xcr0); struct kmem_cache *x86_fpu_cache; EXPORT_SYMBOL_GPL(x86_fpu_cache); +static struct kmem_cache *x86_emulator_cache; + +static struct kmem_cache *kvm_alloc_emulator_cache(void) +{ + unsigned int useroffset = offsetof(struct x86_emulate_ctxt, src); + unsigned int size = sizeof(struct x86_emulate_ctxt); + + return kmem_cache_create_usercopy("x86_emulator", size, + __alignof__(struct x86_emulate_ctxt), + SLAB_ACCOUNT, useroffset, + size - useroffset, NULL); +} + static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) @@ -350,6 +376,7 @@ int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } kvm_lapic_set_base(vcpu, msr_info->data); + kvm_recalculate_apic_map(vcpu->kvm); return 0; } EXPORT_SYMBOL_GPL(kvm_set_apic_base); @@ -619,7 +646,7 @@ EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); */ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) { - if (kvm_x86_ops->get_cpl(vcpu) <= required_cpl) + if (kvm_x86_ops.get_cpl(vcpu) <= required_cpl) return true; kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return false; @@ -760,7 +787,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!is_pae(vcpu)) return 1; - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); if (cs_l) return 1; } else @@ -773,7 +800,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) return 1; - kvm_x86_ops->set_cr0(vcpu, cr0); + kvm_x86_ops.set_cr0(vcpu, cr0); if ((cr0 ^ old_cr0) & X86_CR0_PG) { kvm_clear_async_pf_completion_queue(vcpu); @@ -869,7 +896,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { - if (kvm_x86_ops->get_cpl(vcpu) != 0 || + if (kvm_x86_ops.get_cpl(vcpu) != 0 || __kvm_set_xcr(vcpu, index, xcr)) { kvm_inject_gp(vcpu, 0); return 1; @@ -903,10 +930,10 @@ static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) { u64 reserved_bits = __cr4_reserved_bits(cpu_has, c); - if (cpuid_ecx(0x7) & feature_bit(LA57)) + if (kvm_cpu_cap_has(X86_FEATURE_LA57)) reserved_bits &= ~X86_CR4_LA57; - if (kvm_x86_ops->umip_emulated()) + if (kvm_cpu_cap_has(X86_FEATURE_UMIP)) reserved_bits &= ~X86_CR4_UMIP; return reserved_bits; @@ -950,7 +977,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; } - if (kvm_x86_ops->set_cr4(vcpu, cr4)) + if (kvm_x86_ops.set_cr4(vcpu, cr4)) return 1; if (((cr4 ^ old_cr4) & pdptr_bits) || @@ -1034,7 +1061,7 @@ static void kvm_update_dr0123(struct kvm_vcpu *vcpu) static void kvm_update_dr6(struct kvm_vcpu *vcpu) { if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) - kvm_x86_ops->set_dr6(vcpu, vcpu->arch.dr6); + kvm_x86_ops.set_dr6(vcpu, vcpu->arch.dr6); } static void kvm_update_dr7(struct kvm_vcpu *vcpu) @@ -1045,7 +1072,7 @@ static void kvm_update_dr7(struct kvm_vcpu *vcpu) dr7 = vcpu->arch.guest_debug_dr7; else dr7 = vcpu->arch.dr7; - kvm_x86_ops->set_dr7(vcpu, dr7); + kvm_x86_ops.set_dr7(vcpu, dr7); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED; if (dr7 & DR7_BP_EN_MASK) vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED; @@ -1115,7 +1142,7 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) *val = vcpu->arch.dr6; else - *val = kvm_x86_ops->get_dr6(vcpu); + *val = kvm_x86_ops.get_dr6(vcpu); break; case 5: /* fall through */ @@ -1350,7 +1377,7 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr) rdmsrl_safe(msr->index, &msr->data); break; default: - if (kvm_x86_ops->get_msr_feature(msr)) + if (kvm_x86_ops.get_msr_feature(msr)) return 1; } return 0; @@ -1418,7 +1445,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) efer &= ~EFER_LMA; efer |= vcpu->arch.efer & EFER_LMA; - kvm_x86_ops->set_efer(vcpu, efer); + kvm_x86_ops.set_efer(vcpu, efer); /* Update reserved bits */ if ((efer ^ old_efer) & EFER_NX) @@ -1474,7 +1501,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, msr.index = index; msr.host_initiated = host_initiated; - return kvm_x86_ops->set_msr(vcpu, &msr); + return kvm_x86_ops.set_msr(vcpu, &msr); } /* @@ -1492,7 +1519,7 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, msr.index = index; msr.host_initiated = host_initiated; - ret = kvm_x86_ops->get_msr(vcpu, &msr); + ret = kvm_x86_ops.get_msr(vcpu, &msr); if (!ret) *data = msr.data; return ret; @@ -1561,8 +1588,12 @@ static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) && ((data & APIC_MODE_MASK) == APIC_DM_FIXED)) { + data &= ~(1 << 12); + kvm_apic_send_ipi(vcpu->arch.apic, (u32)data, (u32)(data >> 32)); kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR2, (u32)(data >> 32)); - return kvm_lapic_reg_write(vcpu->arch.apic, APIC_ICR, (u32)data); + kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR, (u32)data); + trace_kvm_apic_write(APIC_ICR, (u32)data); + return 0; } return 1; @@ -1571,11 +1602,12 @@ static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) { u32 msr = kvm_rcx_read(vcpu); - u64 data = kvm_read_edx_eax(vcpu); + u64 data; int ret = 0; switch (msr) { case APIC_BASE_MSR + (APIC_ICR >> 4): + data = kvm_read_edx_eax(vcpu); ret = handle_fastpath_set_x2apic_icr_irqoff(vcpu, data); break; default: @@ -1876,7 +1908,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) { - u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + u64 curr_offset = kvm_x86_ops.read_l1_tsc_offset(vcpu); vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; } @@ -1918,7 +1950,7 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { - u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + u64 tsc_offset = kvm_x86_ops.read_l1_tsc_offset(vcpu); return tsc_offset + kvm_scale_tsc(vcpu, host_tsc); } @@ -1926,7 +1958,7 @@ EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { - vcpu->arch.tsc_offset = kvm_x86_ops->write_l1_tsc_offset(vcpu, offset); + vcpu->arch.tsc_offset = kvm_x86_ops.write_l1_tsc_offset(vcpu, offset); } static inline bool kvm_check_tsc_unstable(void) @@ -2050,7 +2082,7 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc); static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { - u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + u64 tsc_offset = kvm_x86_ops.read_l1_tsc_offset(vcpu); kvm_vcpu_write_tsc_offset(vcpu, tsc_offset + adjustment); } @@ -2525,7 +2557,7 @@ static void kvmclock_sync_fn(struct work_struct *work) static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ - if (guest_cpuid_is_amd(vcpu)) + if (guest_cpuid_is_amd_or_hygon(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; @@ -2647,7 +2679,7 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu) static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) { ++vcpu->stat.tlb_flush; - kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa); + kvm_x86_ops.tlb_flush(vcpu, invalidate_gpa); } static void record_steal_time(struct kvm_vcpu *vcpu) @@ -2800,12 +2832,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) return 1; /* - * We do support PT if kvm_x86_ops->pt_supported(), but we do - * not support IA32_XSS[bit 8]. Guests will have to use - * RDMSR/WRMSR rather than XSAVES/XRSTORS to save/restore PT - * MSRs. + * KVM supports exposing PT to the guest, but does not support + * IA32_XSS[bit 8]. Guests have to use RDMSR/WRMSR rather than + * XSAVES/XRSTORS to save/restore PT MSRs. */ - if (data != 0) + if (data & ~supported_xss) return 1; vcpu->arch.ia32_xss = data; break; @@ -3079,7 +3110,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); - break; case MSR_IA32_TSCDEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); break; @@ -3162,7 +3192,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); - break; case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current * silicon. It is however accessed by winxp in very narrow @@ -3367,10 +3396,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * fringe case that is not enabled except via specific settings * of the module parameters. */ - r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE); + r = kvm_x86_ops.has_emulated_msr(MSR_IA32_SMBASE); break; case KVM_CAP_VAPIC: - r = !kvm_x86_ops->cpu_has_accelerated_tpr(); + r = !kvm_x86_ops.cpu_has_accelerated_tpr(); break; case KVM_CAP_NR_VCPUS: r = KVM_SOFT_MAX_VCPUS; @@ -3397,14 +3426,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_X2APIC_API_VALID_FLAGS; break; case KVM_CAP_NESTED_STATE: - r = kvm_x86_ops->get_nested_state ? - kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0; + r = kvm_x86_ops.get_nested_state ? + kvm_x86_ops.get_nested_state(NULL, NULL, 0) : 0; break; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: - r = kvm_x86_ops->enable_direct_tlbflush != NULL; + r = kvm_x86_ops.enable_direct_tlbflush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - r = kvm_x86_ops->nested_enable_evmcs != NULL; + r = kvm_x86_ops.nested_enable_evmcs != NULL; break; default: break; @@ -3466,7 +3495,7 @@ long kvm_arch_dev_ioctl(struct file *filp, r = 0; break; } - case KVM_X86_GET_MCE_CAP_SUPPORTED: { + case KVM_X86_GET_MCE_CAP_SUPPORTED: r = -EFAULT; if (copy_to_user(argp, &kvm_mce_cap_supported, sizeof(kvm_mce_cap_supported))) @@ -3498,9 +3527,9 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_MSRS: r = msr_io(NULL, argp, do_get_msr_feature, 1); break; - } default: r = -EINVAL; + break; } out: return r; @@ -3520,14 +3549,14 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Address WBINVD may be executed by guest */ if (need_emulate_wbinvd(vcpu)) { - if (kvm_x86_ops->has_wbinvd_exit()) + if (kvm_x86_ops.has_wbinvd_exit()) cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); else if (vcpu->cpu != -1 && vcpu->cpu != cpu) smp_call_function_single(vcpu->cpu, wbinvd_ipi, NULL, 1); } - kvm_x86_ops->vcpu_load(vcpu, cpu); + kvm_x86_ops.vcpu_load(vcpu, cpu); /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { @@ -3594,7 +3623,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) int idx; if (vcpu->preempted) - vcpu->arch.preempted_in_kernel = !kvm_x86_ops->get_cpl(vcpu); + vcpu->arch.preempted_in_kernel = !kvm_x86_ops.get_cpl(vcpu); /* * Disable page faults because we're in atomic context here. @@ -3613,7 +3642,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) kvm_steal_time_set_preempted(vcpu); srcu_read_unlock(&vcpu->kvm->srcu, idx); pagefault_enable(); - kvm_x86_ops->vcpu_put(vcpu); + kvm_x86_ops.vcpu_put(vcpu); vcpu->arch.last_host_tsc = rdtsc(); /* * If userspace has set any breakpoints or watchpoints, dr6 is restored @@ -3627,7 +3656,7 @@ static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { if (vcpu->arch.apicv_active) - kvm_x86_ops->sync_pir_to_irr(vcpu); + kvm_x86_ops.sync_pir_to_irr(vcpu); return kvm_apic_get_state(vcpu, s); } @@ -3735,7 +3764,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, for (bank = 0; bank < bank_num; bank++) vcpu->arch.mce_banks[bank*4] = ~(u64)0; - kvm_x86_ops->setup_mce(vcpu); + kvm_x86_ops.setup_mce(vcpu); out: return r; } @@ -3839,11 +3868,11 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; events->interrupt.soft = 0; - events->interrupt.shadow = kvm_x86_ops->get_interrupt_shadow(vcpu); + events->interrupt.shadow = kvm_x86_ops.get_interrupt_shadow(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = vcpu->arch.nmi_pending != 0; - events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); + events->nmi.masked = kvm_x86_ops.get_nmi_mask(vcpu); events->nmi.pad = 0; events->sipi_vector = 0; /* never valid when reporting to user space */ @@ -3910,13 +3939,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.nr = events->interrupt.nr; vcpu->arch.interrupt.soft = events->interrupt.soft; if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) - kvm_x86_ops->set_interrupt_shadow(vcpu, + kvm_x86_ops.set_interrupt_shadow(vcpu, events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) vcpu->arch.nmi_pending = events->nmi.pending; - kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); + kvm_x86_ops.set_nmi_mask(vcpu, events->nmi.masked); if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && lapic_in_kernel(vcpu)) @@ -4103,8 +4132,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility * with old userspace. */ - if (xstate_bv & ~kvm_supported_xcr0() || - mxcsr & ~mxcsr_feature_mask) + if (xstate_bv & ~supported_xcr0 || mxcsr & ~mxcsr_feature_mask) return -EINVAL; load_xsave(vcpu, (u8 *)guest_xsave->region); } else { @@ -4191,9 +4219,9 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return kvm_hv_activate_synic(vcpu, cap->cap == KVM_CAP_HYPERV_SYNIC2); case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - if (!kvm_x86_ops->nested_enable_evmcs) + if (!kvm_x86_ops.nested_enable_evmcs) return -ENOTTY; - r = kvm_x86_ops->nested_enable_evmcs(vcpu, &vmcs_version); + r = kvm_x86_ops.nested_enable_evmcs(vcpu, &vmcs_version); if (!r) { user_ptr = (void __user *)(uintptr_t)cap->args[0]; if (copy_to_user(user_ptr, &vmcs_version, @@ -4202,10 +4230,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, } return r; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: - if (!kvm_x86_ops->enable_direct_tlbflush) + if (!kvm_x86_ops.enable_direct_tlbflush) return -ENOTTY; - return kvm_x86_ops->enable_direct_tlbflush(vcpu); + return kvm_x86_ops.enable_direct_tlbflush(vcpu); default: return -EINVAL; @@ -4508,7 +4536,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, u32 user_data_size; r = -EINVAL; - if (!kvm_x86_ops->get_nested_state) + if (!kvm_x86_ops.get_nested_state) break; BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size)); @@ -4516,7 +4544,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (get_user(user_data_size, &user_kvm_nested_state->size)) break; - r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state, + r = kvm_x86_ops.get_nested_state(vcpu, user_kvm_nested_state, user_data_size); if (r < 0) break; @@ -4538,7 +4566,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, int idx; r = -EINVAL; - if (!kvm_x86_ops->set_nested_state) + if (!kvm_x86_ops.set_nested_state) break; r = -EFAULT; @@ -4560,7 +4588,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); + r = kvm_x86_ops.set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } @@ -4604,14 +4632,14 @@ static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) if (addr > (unsigned int)(-3 * PAGE_SIZE)) return -EINVAL; - ret = kvm_x86_ops->set_tss_addr(kvm, addr); + ret = kvm_x86_ops.set_tss_addr(kvm, addr); return ret; } static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { - return kvm_x86_ops->set_identity_map_addr(kvm, ident_addr); + return kvm_x86_ops.set_identity_map_addr(kvm, ident_addr); } static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, @@ -4763,77 +4791,13 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, return 0; } -/** - * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot - * @kvm: kvm instance - * @log: slot id and address to which we copy the log - * - * Steps 1-4 below provide general overview of dirty page logging. See - * kvm_get_dirty_log_protect() function description for additional details. - * - * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we - * always flush the TLB (step 4) even if previous step failed and the dirty - * bitmap may be corrupt. Regardless of previous outcome the KVM logging API - * does not preclude user space subsequent dirty log read. Flushing TLB ensures - * writes will be marked dirty for next log read. - * - * 1. Take a snapshot of the bit and clear it if needed. - * 2. Write protect the corresponding page. - * 3. Copy the snapshot to the userspace. - * 4. Flush TLB's if needed. - */ -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { - bool flush = false; - int r; - - mutex_lock(&kvm->slots_lock); - /* * Flush potentially hardware-cached dirty pages to dirty_bitmap. */ - if (kvm_x86_ops->flush_log_dirty) - kvm_x86_ops->flush_log_dirty(kvm); - - r = kvm_get_dirty_log_protect(kvm, log, &flush); - - /* - * All the TLBs can be flushed out of mmu lock, see the comments in - * kvm_mmu_slot_remove_write_access(). - */ - lockdep_assert_held(&kvm->slots_lock); - if (flush) - kvm_flush_remote_tlbs(kvm); - - mutex_unlock(&kvm->slots_lock); - return r; -} - -int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) -{ - bool flush = false; - int r; - - mutex_lock(&kvm->slots_lock); - - /* - * Flush potentially hardware-cached dirty pages to dirty_bitmap. - */ - if (kvm_x86_ops->flush_log_dirty) - kvm_x86_ops->flush_log_dirty(kvm); - - r = kvm_clear_dirty_log_protect(kvm, log, &flush); - - /* - * All the TLBs can be flushed out of mmu lock, see the comments in - * kvm_mmu_slot_remove_write_access(). - */ - lockdep_assert_held(&kvm->slots_lock); - if (flush) - kvm_flush_remote_tlbs(kvm); - - mutex_unlock(&kvm->slots_lock); - return r; + if (kvm_x86_ops.flush_log_dirty) + kvm_x86_ops.flush_log_dirty(kvm); } int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, @@ -5186,8 +5150,8 @@ set_identity_unlock: } case KVM_MEMORY_ENCRYPT_OP: { r = -ENOTTY; - if (kvm_x86_ops->mem_enc_op) - r = kvm_x86_ops->mem_enc_op(kvm, argp); + if (kvm_x86_ops.mem_enc_op) + r = kvm_x86_ops.mem_enc_op(kvm, argp); break; } case KVM_MEMORY_ENCRYPT_REG_REGION: { @@ -5198,8 +5162,8 @@ set_identity_unlock: goto out; r = -ENOTTY; - if (kvm_x86_ops->mem_enc_reg_region) - r = kvm_x86_ops->mem_enc_reg_region(kvm, ®ion); + if (kvm_x86_ops.mem_enc_reg_region) + r = kvm_x86_ops.mem_enc_reg_region(kvm, ®ion); break; } case KVM_MEMORY_ENCRYPT_UNREG_REGION: { @@ -5210,8 +5174,8 @@ set_identity_unlock: goto out; r = -ENOTTY; - if (kvm_x86_ops->mem_enc_unreg_region) - r = kvm_x86_ops->mem_enc_unreg_region(kvm, ®ion); + if (kvm_x86_ops.mem_enc_unreg_region) + r = kvm_x86_ops.mem_enc_unreg_region(kvm, ®ion); break; } case KVM_HYPERV_EVENTFD: { @@ -5262,28 +5226,28 @@ static void kvm_init_msr_list(void) continue; break; case MSR_TSC_AUX: - if (!kvm_x86_ops->rdtscp_supported()) + if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) continue; break; case MSR_IA32_RTIT_CTL: case MSR_IA32_RTIT_STATUS: - if (!kvm_x86_ops->pt_supported()) + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) continue; break; case MSR_IA32_RTIT_CR3_MATCH: - if (!kvm_x86_ops->pt_supported() || + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) continue; break; case MSR_IA32_RTIT_OUTPUT_BASE: case MSR_IA32_RTIT_OUTPUT_MASK: - if (!kvm_x86_ops->pt_supported() || + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) continue; break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: { - if (!kvm_x86_ops->pt_supported() || + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >= intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; @@ -5306,7 +5270,7 @@ static void kvm_init_msr_list(void) } for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { - if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i])) + if (!kvm_x86_ops.has_emulated_msr(emulated_msrs_all[i])) continue; emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; @@ -5369,13 +5333,13 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) static void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - kvm_x86_ops->set_segment(vcpu, var, seg); + kvm_x86_ops.set_segment(vcpu, var, seg); } void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - kvm_x86_ops->get_segment(vcpu, var, seg); + kvm_x86_ops.get_segment(vcpu, var, seg); } gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, @@ -5395,14 +5359,14 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_FETCH_MASK; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } @@ -5410,7 +5374,7 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } @@ -5459,7 +5423,7 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; @@ -5484,7 +5448,7 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; /* * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED @@ -5505,7 +5469,7 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt, struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u32 access = 0; - if (!system && kvm_x86_ops->get_cpl(vcpu) == 3) + if (!system && kvm_x86_ops.get_cpl(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); @@ -5558,7 +5522,7 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u32 access = PFERR_WRITE_MASK; - if (!system && kvm_x86_ops->get_cpl(vcpu) == 3) + if (!system && kvm_x86_ops.get_cpl(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, @@ -5621,7 +5585,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { - u32 access = ((kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0) + u32 access = ((kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); /* @@ -5740,7 +5704,7 @@ static int emulator_read_write_onepage(unsigned long addr, void *val, int handled, ret; bool write = ops->write; struct kvm_mmio_fragment *frag; - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; /* * If the exit was due to a NPF we may already have a GPA. @@ -5749,10 +5713,9 @@ static int emulator_read_write_onepage(unsigned long addr, void *val, * operation using rep will only have the initial GPA from the NPF * occurred. */ - if (vcpu->arch.gpa_available && - emulator_can_use_gpa(ctxt) && - (addr & ~PAGE_MASK) == (vcpu->arch.gpa_val & ~PAGE_MASK)) { - gpa = vcpu->arch.gpa_val; + if (ctxt->gpa_available && emulator_can_use_gpa(ctxt) && + (addr & ~PAGE_MASK) == (ctxt->gpa_val & ~PAGE_MASK)) { + gpa = ctxt->gpa_val; ret = vcpu_is_mmio_gpa(vcpu, addr, gpa, write); } else { ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); @@ -5972,11 +5935,9 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, return 0; } -static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, - int size, unsigned short port, void *val, - unsigned int count) +static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *val, unsigned int count) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int ret; if (vcpu->arch.pio.count) @@ -5996,20 +5957,33 @@ data_avail: return 0; } -static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, - int size, unsigned short port, - const void *val, unsigned int count) +static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, void *val, + unsigned int count) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + return emulator_pio_in(emul_to_vcpu(ctxt), size, port, val, count); + +} +static int emulator_pio_out(struct kvm_vcpu *vcpu, int size, + unsigned short port, const void *val, + unsigned int count) +{ memcpy(vcpu->arch.pio_data, val, size * count); trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); } +static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, + const void *val, unsigned int count) +{ + return emulator_pio_out(emul_to_vcpu(ctxt), size, port, val, count); +} + static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { - return kvm_x86_ops->get_segment_base(vcpu, seg); + return kvm_x86_ops.get_segment_base(vcpu, seg); } static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) @@ -6022,7 +5996,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; - if (kvm_x86_ops->has_wbinvd_exit()) { + if (kvm_x86_ops.has_wbinvd_exit()) { int cpu = get_cpu(); cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); @@ -6127,27 +6101,27 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { - return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt)); + return kvm_x86_ops.get_cpl(emul_to_vcpu(ctxt)); } static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops->get_gdt(emul_to_vcpu(ctxt), dt); + kvm_x86_ops.get_gdt(emul_to_vcpu(ctxt), dt); } static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops->get_idt(emul_to_vcpu(ctxt), dt); + kvm_x86_ops.get_idt(emul_to_vcpu(ctxt), dt); } static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops->set_gdt(emul_to_vcpu(ctxt), dt); + kvm_x86_ops.set_gdt(emul_to_vcpu(ctxt), dt); } static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops->set_idt(emul_to_vcpu(ctxt), dt); + kvm_x86_ops.set_idt(emul_to_vcpu(ctxt), dt); } static unsigned long emulator_get_cached_segment_base( @@ -6269,13 +6243,15 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage) { - return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage); + return kvm_x86_ops.check_intercept(emul_to_vcpu(ctxt), info, stage, + &ctxt->exception); } static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, - u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit) + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, + bool exact_only) { - return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, check_limit); + return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, exact_only); } static bool emulator_guest_has_long_mode(struct x86_emulate_ctxt *ctxt) @@ -6305,7 +6281,7 @@ static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulon static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) { - kvm_x86_ops->set_nmi_mask(emul_to_vcpu(ctxt), masked); + kvm_x86_ops.set_nmi_mask(emul_to_vcpu(ctxt), masked); } static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) @@ -6321,7 +6297,7 @@ static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_fla static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, const char *smstate) { - return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate); + return kvm_x86_ops.pre_leave_smm(emul_to_vcpu(ctxt), smstate); } static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) @@ -6383,7 +6359,7 @@ static const struct x86_emulate_ops emulate_ops = { static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) { - u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(vcpu); + u32 int_shadow = kvm_x86_ops.get_interrupt_shadow(vcpu); /* * an sti; sti; sequence only disable interrupts for the first * instruction. So, if the last instruction, be it emulated or @@ -6394,7 +6370,7 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) if (int_shadow & mask) mask = 0; if (unlikely(int_shadow || mask)) { - kvm_x86_ops->set_interrupt_shadow(vcpu, mask); + kvm_x86_ops.set_interrupt_shadow(vcpu, mask); if (!mask) kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -6402,7 +6378,7 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) static bool inject_emulated_exception(struct kvm_vcpu *vcpu) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; if (ctxt->exception.vector == PF_VECTOR) return kvm_propagate_fault(vcpu, &ctxt->exception); @@ -6414,13 +6390,31 @@ static bool inject_emulated_exception(struct kvm_vcpu *vcpu) return false; } +static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt; + + ctxt = kmem_cache_zalloc(x86_emulator_cache, GFP_KERNEL_ACCOUNT); + if (!ctxt) { + pr_err("kvm: failed to allocate vcpu's emulator\n"); + return NULL; + } + + ctxt->vcpu = vcpu; + ctxt->ops = &emulate_ops; + vcpu->arch.emulate_ctxt = ctxt; + + return ctxt; +} + static void init_emulate_ctxt(struct kvm_vcpu *vcpu) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int cs_db, cs_l; - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + ctxt->gpa_available = false; ctxt->eflags = kvm_get_rflags(vcpu); ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; @@ -6440,7 +6434,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); @@ -6479,7 +6473,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) kvm_queue_exception(vcpu, UD_VECTOR); - if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { + if (!is_guest_mode(vcpu) && kvm_x86_ops.get_cpl(vcpu) == 0) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; @@ -6496,10 +6490,11 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, gpa_t gpa = cr2_or_gpa; kvm_pfn_t pfn; - if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) return false; - if (WARN_ON_ONCE(is_guest_mode(vcpu))) + if (WARN_ON_ONCE(is_guest_mode(vcpu)) || + WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) return false; if (!vcpu->arch.mmu->direct_map) { @@ -6587,10 +6582,11 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, */ vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; - if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) return false; - if (WARN_ON_ONCE(is_guest_mode(vcpu))) + if (WARN_ON_ONCE(is_guest_mode(vcpu)) || + WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) return false; if (x86_page_table_writing_insn(ctxt)) @@ -6658,10 +6654,10 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { - unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); + unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); int r; - r = kvm_x86_ops->skip_emulated_instruction(vcpu); + r = kvm_x86_ops.skip_emulated_instruction(vcpu); if (unlikely(!r)) return 0; @@ -6753,7 +6749,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len) { int r; - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; @@ -6843,8 +6839,19 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } restart: - /* Save the faulting GPA (cr2) in the address field */ - ctxt->exception.address = cr2_or_gpa; + if (emulation_type & EMULTYPE_PF) { + /* Save the faulting GPA (cr2) in the address field */ + ctxt->exception.address = cr2_or_gpa; + + /* With shadow page tables, cr2 contains a GVA or nGPA. */ + if (vcpu->arch.mmu->direct_map) { + ctxt->gpa_available = true; + ctxt->gpa_val = cr2_or_gpa; + } + } else { + /* Sanitize the address out of an abundance of paranoia. */ + ctxt->exception.address = 0; + } r = x86_emulate_insn(ctxt); @@ -6885,7 +6892,7 @@ restart: r = 1; if (writeback) { - unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); + unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; if (!ctxt->have_exception || @@ -6893,8 +6900,8 @@ restart: kvm_rip_write(vcpu, ctxt->eip); if (r && ctxt->tf) r = kvm_vcpu_do_singlestep(vcpu); - if (kvm_x86_ops->update_emulated_instruction) - kvm_x86_ops->update_emulated_instruction(vcpu); + if (kvm_x86_ops.update_emulated_instruction) + kvm_x86_ops.update_emulated_instruction(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } @@ -6945,8 +6952,8 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { unsigned long val = kvm_rax_read(vcpu); - int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt, - size, port, &val, 1); + int ret = emulator_pio_out(vcpu, size, port, &val, 1); + if (ret) return ret; @@ -6982,11 +6989,10 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu) val = (vcpu->arch.pio.size < 4) ? kvm_rax_read(vcpu) : 0; /* - * Since vcpu->arch.pio.count == 1 let emulator_pio_in_emulated perform + * Since vcpu->arch.pio.count == 1 let emulator_pio_in perform * the copy and tracing */ - emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, vcpu->arch.pio.size, - vcpu->arch.pio.port, &val, 1); + emulator_pio_in(vcpu, vcpu->arch.pio.size, vcpu->arch.pio.port, &val, 1); kvm_rax_write(vcpu, val); return kvm_skip_emulated_instruction(vcpu); @@ -7001,8 +7007,7 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, /* For size less than 4 we merge, else we zero extend */ val = (size < 4) ? kvm_rax_read(vcpu) : 0; - ret = emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, size, port, - &val, 1); + ret = emulator_pio_in(vcpu, size, port, &val, 1); if (ret) { kvm_rax_write(vcpu, val); return ret; @@ -7225,7 +7230,7 @@ static int kvm_is_user_mode(void) int user_mode = 3; if (__this_cpu_read(current_vcpu)) - user_mode = kvm_x86_ops->get_cpl(__this_cpu_read(current_vcpu)); + user_mode = kvm_x86_ops.get_cpl(__this_cpu_read(current_vcpu)); return user_mode != 0; } @@ -7302,10 +7307,10 @@ static struct notifier_block pvclock_gtod_notifier = { int kvm_arch_init(void *opaque) { + struct kvm_x86_init_ops *ops = opaque; int r; - struct kvm_x86_ops *ops = opaque; - if (kvm_x86_ops) { + if (kvm_x86_ops.hardware_enable) { printk(KERN_ERR "kvm: already loaded the other module\n"); r = -EEXIST; goto out; @@ -7342,18 +7347,22 @@ int kvm_arch_init(void *opaque) goto out; } + x86_emulator_cache = kvm_alloc_emulator_cache(); + if (!x86_emulator_cache) { + pr_err("kvm: failed to allocate cache for x86 emulator\n"); + goto out_free_x86_fpu_cache; + } + shared_msrs = alloc_percpu(struct kvm_shared_msrs); if (!shared_msrs) { printk(KERN_ERR "kvm: failed to allocate percpu kvm_shared_msrs\n"); - goto out_free_x86_fpu_cache; + goto out_free_x86_emulator_cache; } r = kvm_mmu_module_init(); if (r) goto out_free_percpu; - kvm_x86_ops = ops; - kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0, PT_PRESENT_MASK, 0, sme_me_mask); @@ -7361,8 +7370,10 @@ int kvm_arch_init(void *opaque) perf_register_guest_info_callbacks(&kvm_guest_cbs); - if (boot_cpu_has(X86_FEATURE_XSAVE)) + if (boot_cpu_has(X86_FEATURE_XSAVE)) { host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; + } kvm_lapic_init(); if (pi_inject_timer == -1) @@ -7378,6 +7389,8 @@ int kvm_arch_init(void *opaque) out_free_percpu: free_percpu(shared_msrs); +out_free_x86_emulator_cache: + kmem_cache_destroy(x86_emulator_cache); out_free_x86_fpu_cache: kmem_cache_destroy(x86_fpu_cache); out: @@ -7400,7 +7413,7 @@ void kvm_arch_exit(void) #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); #endif - kvm_x86_ops = NULL; + kvm_x86_ops.hardware_enable = NULL; kvm_mmu_module_exit(); free_percpu(shared_msrs); kmem_cache_destroy(x86_fpu_cache); @@ -7538,7 +7551,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a3 &= 0xFFFFFFFF; } - if (kvm_x86_ops->get_cpl(vcpu) != 0) { + if (kvm_x86_ops.get_cpl(vcpu) != 0) { ret = -KVM_EPERM; goto out; } @@ -7584,7 +7597,7 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) char instruction[3]; unsigned long rip = kvm_rip_read(vcpu); - kvm_x86_ops->patch_hypercall(vcpu, instruction); + kvm_x86_ops.patch_hypercall(vcpu, instruction); return emulator_write_emulated(ctxt, rip, instruction, 3, &ctxt->exception); @@ -7613,7 +7626,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) { int max_irr, tpr; - if (!kvm_x86_ops->update_cr8_intercept) + if (!kvm_x86_ops.update_cr8_intercept) return; if (!lapic_in_kernel(vcpu)) @@ -7632,17 +7645,17 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) tpr = kvm_lapic_get_cr8(vcpu); - kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); + kvm_x86_ops.update_cr8_intercept(vcpu, tpr, max_irr); } -static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) +static int inject_pending_event(struct kvm_vcpu *vcpu) { int r; /* try to reinject previous events if any */ if (vcpu->arch.exception.injected) - kvm_x86_ops->queue_exception(vcpu); + kvm_x86_ops.queue_exception(vcpu); /* * Do not inject an NMI or interrupt if there is a pending * exception. Exceptions and interrupts are recognized at @@ -7659,9 +7672,9 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) */ else if (!vcpu->arch.exception.pending) { if (vcpu->arch.nmi_injected) - kvm_x86_ops->set_nmi(vcpu); + kvm_x86_ops.set_nmi(vcpu); else if (vcpu->arch.interrupt.injected) - kvm_x86_ops->set_irq(vcpu); + kvm_x86_ops.set_irq(vcpu); } /* @@ -7670,8 +7683,8 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) * from L2 to L1 due to pending L1 events which require exit * from L2 to L1. */ - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + if (is_guest_mode(vcpu) && kvm_x86_ops.check_nested_events) { + r = kvm_x86_ops.check_nested_events(vcpu); if (r != 0) return r; } @@ -7708,7 +7721,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) } } - kvm_x86_ops->queue_exception(vcpu); + kvm_x86_ops.queue_exception(vcpu); } /* Don't consider new event if we re-injected an event */ @@ -7716,14 +7729,14 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) return 0; if (vcpu->arch.smi_pending && !is_smm(vcpu) && - kvm_x86_ops->smi_allowed(vcpu)) { + kvm_x86_ops.smi_allowed(vcpu)) { vcpu->arch.smi_pending = false; ++vcpu->arch.smi_count; enter_smm(vcpu); - } else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { + } else if (vcpu->arch.nmi_pending && kvm_x86_ops.nmi_allowed(vcpu)) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; - kvm_x86_ops->set_nmi(vcpu); + kvm_x86_ops.set_nmi(vcpu); } else if (kvm_cpu_has_injectable_intr(vcpu)) { /* * Because interrupts can be injected asynchronously, we are @@ -7732,15 +7745,15 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) * proposal and current concerns. Perhaps we should be setting * KVM_REQ_EVENT only on certain events and not unconditionally? */ - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + if (is_guest_mode(vcpu) && kvm_x86_ops.check_nested_events) { + r = kvm_x86_ops.check_nested_events(vcpu); if (r != 0) return r; } - if (kvm_x86_ops->interrupt_allowed(vcpu)) { + if (kvm_x86_ops.interrupt_allowed(vcpu)) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); - kvm_x86_ops->set_irq(vcpu); + kvm_x86_ops.set_irq(vcpu); } } @@ -7756,7 +7769,7 @@ static void process_nmi(struct kvm_vcpu *vcpu) * If an NMI is already in progress, limit further NMIs to just one. * Otherwise, allow two (and we'll inject the first one immediately). */ - if (kvm_x86_ops->get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) + if (kvm_x86_ops.get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) limit = 1; vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); @@ -7846,11 +7859,11 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7f7c, seg.limit); put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg)); - kvm_x86_ops->get_gdt(vcpu, &dt); + kvm_x86_ops.get_gdt(vcpu, &dt); put_smstate(u32, buf, 0x7f74, dt.address); put_smstate(u32, buf, 0x7f70, dt.size); - kvm_x86_ops->get_idt(vcpu, &dt); + kvm_x86_ops.get_idt(vcpu, &dt); put_smstate(u32, buf, 0x7f58, dt.address); put_smstate(u32, buf, 0x7f54, dt.size); @@ -7900,7 +7913,7 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7e94, seg.limit); put_smstate(u64, buf, 0x7e98, seg.base); - kvm_x86_ops->get_idt(vcpu, &dt); + kvm_x86_ops.get_idt(vcpu, &dt); put_smstate(u32, buf, 0x7e84, dt.size); put_smstate(u64, buf, 0x7e88, dt.address); @@ -7910,7 +7923,7 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7e74, seg.limit); put_smstate(u64, buf, 0x7e78, seg.base); - kvm_x86_ops->get_gdt(vcpu, &dt); + kvm_x86_ops.get_gdt(vcpu, &dt); put_smstate(u32, buf, 0x7e64, dt.size); put_smstate(u64, buf, 0x7e68, dt.address); @@ -7940,28 +7953,28 @@ static void enter_smm(struct kvm_vcpu *vcpu) * vCPU state (e.g. leave guest mode) after we've saved the state into * the SMM state-save area. */ - kvm_x86_ops->pre_enter_smm(vcpu, buf); + kvm_x86_ops.pre_enter_smm(vcpu, buf); vcpu->arch.hflags |= HF_SMM_MASK; kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); - if (kvm_x86_ops->get_nmi_mask(vcpu)) + if (kvm_x86_ops.get_nmi_mask(vcpu)) vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else - kvm_x86_ops->set_nmi_mask(vcpu, true); + kvm_x86_ops.set_nmi_mask(vcpu, true); kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0x8000); cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); - kvm_x86_ops->set_cr0(vcpu, cr0); + kvm_x86_ops.set_cr0(vcpu, cr0); vcpu->arch.cr0 = cr0; - kvm_x86_ops->set_cr4(vcpu, 0); + kvm_x86_ops.set_cr4(vcpu, 0); /* Undocumented: IDT limit is set to zero on entry to SMM. */ dt.address = dt.size = 0; - kvm_x86_ops->set_idt(vcpu, &dt); + kvm_x86_ops.set_idt(vcpu, &dt); __kvm_set_dr(vcpu, 7, DR7_FIXED_1); @@ -7992,7 +8005,7 @@ static void enter_smm(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - kvm_x86_ops->set_efer(vcpu, 0); + kvm_x86_ops.set_efer(vcpu, 0); #endif kvm_update_cpuid(vcpu); @@ -8030,7 +8043,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) vcpu->arch.apicv_active = kvm_apicv_activated(vcpu->kvm); kvm_apic_update_apicv(vcpu); - kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); + kvm_x86_ops.refresh_apicv_exec_ctrl(vcpu); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); @@ -8043,23 +8056,30 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); */ void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) { - if (!kvm_x86_ops->check_apicv_inhibit_reasons || - !kvm_x86_ops->check_apicv_inhibit_reasons(bit)) + unsigned long old, new, expected; + + if (!kvm_x86_ops.check_apicv_inhibit_reasons || + !kvm_x86_ops.check_apicv_inhibit_reasons(bit)) return; - if (activate) { - if (!test_and_clear_bit(bit, &kvm->arch.apicv_inhibit_reasons) || - !kvm_apicv_activated(kvm)) - return; - } else { - if (test_and_set_bit(bit, &kvm->arch.apicv_inhibit_reasons) || - kvm_apicv_activated(kvm)) - return; - } + old = READ_ONCE(kvm->arch.apicv_inhibit_reasons); + do { + expected = new = old; + if (activate) + __clear_bit(bit, &new); + else + __set_bit(bit, &new); + if (new == old) + break; + old = cmpxchg(&kvm->arch.apicv_inhibit_reasons, expected, new); + } while (old != expected); + + if (!!old == !!new) + return; trace_kvm_apicv_update_request(activate, bit); - if (kvm_x86_ops->pre_update_apicv_exec_ctrl) - kvm_x86_ops->pre_update_apicv_exec_ctrl(kvm, activate); + if (kvm_x86_ops.pre_update_apicv_exec_ctrl) + kvm_x86_ops.pre_update_apicv_exec_ctrl(kvm, activate); kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE); } EXPORT_SYMBOL_GPL(kvm_request_apicv_update); @@ -8075,7 +8095,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { if (vcpu->arch.apicv_active) - kvm_x86_ops->sync_pir_to_irr(vcpu); + kvm_x86_ops.sync_pir_to_irr(vcpu); if (ioapic_in_kernel(vcpu->kvm)) kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -8095,7 +8115,7 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, vcpu_to_synic(vcpu)->vec_bitmap, 256); - kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); + kvm_x86_ops.load_eoi_exitmap(vcpu, eoi_exit_bitmap); } int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, @@ -8122,13 +8142,13 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) if (!lapic_in_kernel(vcpu)) return; - if (!kvm_x86_ops->set_apic_access_page_addr) + if (!kvm_x86_ops.set_apic_access_page_addr) return; page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); if (is_error_page(page)) return; - kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page)); + kvm_x86_ops.set_apic_access_page_addr(vcpu, page_to_phys(page)); /* * Do not pin apic access page in memory, the MMU notifier @@ -8160,7 +8180,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) { - if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) { + if (unlikely(!kvm_x86_ops.get_vmcs12_pages(vcpu))) { r = 0; goto out; } @@ -8180,8 +8200,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) kvm_mmu_sync_roots(vcpu); - if (kvm_check_request(KVM_REQ_LOAD_CR3, vcpu)) - kvm_mmu_load_cr3(vcpu); + if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu)) + kvm_mmu_load_pgd(vcpu); if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) kvm_vcpu_flush_tlb(vcpu, true); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { @@ -8266,7 +8286,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } - if (inject_pending_event(vcpu, req_int_win) != 0) + if (inject_pending_event(vcpu) != 0) req_immediate_exit = true; else { /* Enable SMI/NMI/IRQ window open exits if needed. @@ -8284,12 +8304,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * SMI. */ if (vcpu->arch.smi_pending && !is_smm(vcpu)) - if (!kvm_x86_ops->enable_smi_window(vcpu)) + if (!kvm_x86_ops.enable_smi_window(vcpu)) req_immediate_exit = true; if (vcpu->arch.nmi_pending) - kvm_x86_ops->enable_nmi_window(vcpu); + kvm_x86_ops.enable_nmi_window(vcpu); if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) - kvm_x86_ops->enable_irq_window(vcpu); + kvm_x86_ops.enable_irq_window(vcpu); WARN_ON(vcpu->arch.exception.pending); } @@ -8306,7 +8326,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_disable(); - kvm_x86_ops->prepare_guest_switch(vcpu); + kvm_x86_ops.prepare_guest_switch(vcpu); /* * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt @@ -8337,7 +8357,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * notified with kvm_vcpu_kick. */ if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) - kvm_x86_ops->sync_pir_to_irr(vcpu); + kvm_x86_ops.sync_pir_to_irr(vcpu); if (vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || need_resched() || signal_pending(current)) { @@ -8352,7 +8372,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_x86_ops->request_immediate_exit(vcpu); + kvm_x86_ops.request_immediate_exit(vcpu); } trace_kvm_entry(vcpu->vcpu_id); @@ -8372,7 +8392,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } - kvm_x86_ops->run(vcpu); + kvm_x86_ops.run(vcpu); /* * Do this here before restoring debug registers on the host. And @@ -8382,7 +8402,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); - kvm_x86_ops->sync_dirty_debug_regs(vcpu); + kvm_x86_ops.sync_dirty_debug_regs(vcpu); kvm_update_dr0123(vcpu); kvm_update_dr6(vcpu); kvm_update_dr7(vcpu); @@ -8404,7 +8424,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_x86_ops->handle_exit_irqoff(vcpu, &exit_fastpath); + kvm_x86_ops.handle_exit_irqoff(vcpu, &exit_fastpath); /* * Consume any pending interrupts, including the possible source of @@ -8447,12 +8467,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); - vcpu->arch.gpa_available = false; - r = kvm_x86_ops->handle_exit(vcpu, exit_fastpath); + r = kvm_x86_ops.handle_exit(vcpu, exit_fastpath); return r; cancel_injection: - kvm_x86_ops->cancel_injection(vcpu); + kvm_x86_ops.cancel_injection(vcpu); if (unlikely(vcpu->arch.apic_attention)) kvm_lapic_sync_from_vapic(vcpu); out: @@ -8462,13 +8481,13 @@ out: static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { if (!kvm_arch_vcpu_runnable(vcpu) && - (!kvm_x86_ops->pre_block || kvm_x86_ops->pre_block(vcpu) == 0)) { + (!kvm_x86_ops.pre_block || kvm_x86_ops.pre_block(vcpu) == 0)) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - if (kvm_x86_ops->post_block) - kvm_x86_ops->post_block(vcpu); + if (kvm_x86_ops.post_block) + kvm_x86_ops.post_block(vcpu); if (!kvm_check_request(KVM_REQ_UNHALT, vcpu)) return 1; @@ -8488,15 +8507,14 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) break; default: return -EINTR; - break; } return 1; } static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) - kvm_x86_ops->check_nested_events(vcpu, false); + if (is_guest_mode(vcpu) && kvm_x86_ops.check_nested_events) + kvm_x86_ops.check_nested_events(vcpu); return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); @@ -8652,7 +8670,7 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) kvm_save_current_fpu(vcpu->arch.user_fpu); - /* PKRU is separately restored in kvm_x86_ops->run. */ + /* PKRU is separately restored in kvm_x86_ops.run. */ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, ~XFEATURE_MASK_PKRU); @@ -8757,7 +8775,7 @@ static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) * that usually, but some bad designed PV devices (vmware * backdoor interface) need this to work */ - emulator_writeback_register_cache(&vcpu->arch.emulate_ctxt); + emulator_writeback_register_cache(vcpu->arch.emulate_ctxt); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; } regs->rax = kvm_rax_read(vcpu); @@ -8855,10 +8873,10 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); - kvm_x86_ops->get_idt(vcpu, &dt); + kvm_x86_ops.get_idt(vcpu, &dt); sregs->idt.limit = dt.size; sregs->idt.base = dt.address; - kvm_x86_ops->get_gdt(vcpu, &dt); + kvm_x86_ops.get_gdt(vcpu, &dt); sregs->gdt.limit = dt.size; sregs->gdt.base = dt.address; @@ -8943,7 +8961,7 @@ out: int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); @@ -9005,10 +9023,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) dt.size = sregs->idt.limit; dt.address = sregs->idt.base; - kvm_x86_ops->set_idt(vcpu, &dt); + kvm_x86_ops.set_idt(vcpu, &dt); dt.size = sregs->gdt.limit; dt.address = sregs->gdt.base; - kvm_x86_ops->set_gdt(vcpu, &dt); + kvm_x86_ops.set_gdt(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; @@ -9018,16 +9036,16 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_set_cr8(vcpu, sregs->cr8); mmu_reset_needed |= vcpu->arch.efer != sregs->efer; - kvm_x86_ops->set_efer(vcpu, sregs->efer); + kvm_x86_ops.set_efer(vcpu, sregs->efer); mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; - kvm_x86_ops->set_cr0(vcpu, sregs->cr0); + kvm_x86_ops.set_cr0(vcpu, sregs->cr0); vcpu->arch.cr0 = sregs->cr0; mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)); - kvm_x86_ops->set_cr4(vcpu, sregs->cr4); + kvm_x86_ops.set_cr4(vcpu, sregs->cr4); if (cpuid_update_needed) kvm_update_cpuid(vcpu); @@ -9133,7 +9151,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, */ kvm_set_rflags(vcpu, rflags); - kvm_x86_ops->update_bp_intercept(vcpu); + kvm_x86_ops.update_bp_intercept(vcpu); r = 0; @@ -9275,7 +9293,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) struct page *page; int r; - vcpu->arch.emulate_ctxt.ops = &emulate_ops; if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else @@ -9313,11 +9330,14 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) GFP_KERNEL_ACCOUNT)) goto fail_free_mce_banks; + if (!alloc_emulate_ctxt(vcpu)) + goto free_wbinvd_dirty_mask; + vcpu->arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!vcpu->arch.user_fpu) { pr_err("kvm: failed to allocate userspace's fpu\n"); - goto free_wbinvd_dirty_mask; + goto free_emulate_ctxt; } vcpu->arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, @@ -9342,7 +9362,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_hv_vcpu_init(vcpu); - r = kvm_x86_ops->vcpu_create(vcpu); + r = kvm_x86_ops.vcpu_create(vcpu); if (r) goto free_guest_fpu; @@ -9359,6 +9379,8 @@ free_guest_fpu: kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); free_user_fpu: kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); +free_emulate_ctxt: + kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_wbinvd_dirty_mask: free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); fail_free_mce_banks: @@ -9393,11 +9415,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) mutex_unlock(&vcpu->mutex); - if (!kvmclock_periodic_sync) - return; - - schedule_delayed_work(&kvm->arch.kvmclock_sync_work, - KVMCLOCK_SYNC_PERIOD); + if (kvmclock_periodic_sync && vcpu->vcpu_idx == 0) + schedule_delayed_work(&kvm->arch.kvmclock_sync_work, + KVMCLOCK_SYNC_PERIOD); } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) @@ -9409,8 +9429,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvmclock_reset(vcpu); - kvm_x86_ops->vcpu_free(vcpu); + kvm_x86_ops.vcpu_free(vcpu); + kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); @@ -9496,7 +9517,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.ia32_xss = 0; - kvm_x86_ops->vcpu_reset(vcpu, init_event); + kvm_x86_ops.vcpu_reset(vcpu, init_event); } void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -9521,7 +9542,7 @@ int kvm_arch_hardware_enable(void) bool stable, backwards_tsc = false; kvm_shared_msr_cpu_online(); - ret = kvm_x86_ops->hardware_enable(); + ret = kvm_x86_ops.hardware_enable(); if (ret != 0) return ret; @@ -9603,18 +9624,29 @@ int kvm_arch_hardware_enable(void) void kvm_arch_hardware_disable(void) { - kvm_x86_ops->hardware_disable(); + kvm_x86_ops.hardware_disable(); drop_user_return_notifiers(); } -int kvm_arch_hardware_setup(void) +int kvm_arch_hardware_setup(void *opaque) { + struct kvm_x86_init_ops *ops = opaque; int r; - r = kvm_x86_ops->hardware_setup(); + rdmsrl_safe(MSR_EFER, &host_efer); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + rdmsrl(MSR_IA32_XSS, host_xss); + + r = ops->hardware_setup(); if (r != 0) return r; + memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); + + if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) + supported_xss = 0; + cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); if (kvm_has_tsc_control) { @@ -9631,28 +9663,26 @@ int kvm_arch_hardware_setup(void) kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; } - if (boot_cpu_has(X86_FEATURE_XSAVES)) - rdmsrl(MSR_IA32_XSS, host_xss); - kvm_init_msr_list(); return 0; } void kvm_arch_hardware_unsetup(void) { - kvm_x86_ops->hardware_unsetup(); + kvm_x86_ops.hardware_unsetup(); } -int kvm_arch_check_processor_compat(void) +int kvm_arch_check_processor_compat(void *opaque) { struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + struct kvm_x86_init_ops *ops = opaque; WARN_ON(!irqs_disabled()); if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits) return -EIO; - return kvm_x86_ops->check_processor_compatibility(); + return ops->check_processor_compatibility(); } bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) @@ -9678,9 +9708,16 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) pmu->need_cleanup = true; kvm_make_request(KVM_REQ_PMU, vcpu); } - kvm_x86_ops->sched_in(vcpu, cpu); + kvm_x86_ops.sched_in(vcpu, cpu); +} + +void kvm_arch_free_vm(struct kvm *kvm) +{ + kfree(kvm->arch.hyperv.hv_pa_pg); + vfree(kvm); } + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { if (type) @@ -9715,7 +9752,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); - return kvm_x86_ops->vm_init(kvm); + return kvm_x86_ops.vm_init(kvm); } int kvm_arch_post_init_vm(struct kvm *kvm) @@ -9763,9 +9800,9 @@ void kvm_arch_sync_events(struct kvm *kvm) int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) { int i, r; - unsigned long hva; + unsigned long hva, uninitialized_var(old_npages); struct kvm_memslots *slots = kvm_memslots(kvm); - struct kvm_memory_slot *slot, old; + struct kvm_memory_slot *slot; /* Called with kvm->slots_lock held. */ if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) @@ -9773,7 +9810,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) slot = id_to_memslot(slots, id); if (size) { - if (slot->npages) + if (slot && slot->npages) return -EEXIST; /* @@ -9785,13 +9822,18 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) if (IS_ERR((void *)hva)) return PTR_ERR((void *)hva); } else { - if (!slot->npages) + if (!slot || !slot->npages) return 0; - hva = 0; + /* + * Stuff a non-canonical value to catch use-after-delete. This + * ends up being 0 on 32-bit KVM, but there's no better + * alternative. + */ + hva = (unsigned long)(0xdeadull << 48); + old_npages = slot->npages; } - old = *slot; for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { struct kvm_userspace_memory_region m; @@ -9806,7 +9848,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) } if (!size) - vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); + vm_munmap(hva, old_npages * PAGE_SIZE); return 0; } @@ -9833,8 +9875,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm) __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); mutex_unlock(&kvm->slots_lock); } - if (kvm_x86_ops->vm_destroy) - kvm_x86_ops->vm_destroy(kvm); + if (kvm_x86_ops.vm_destroy) + kvm_x86_ops.vm_destroy(kvm); kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); kvm_free_vcpus(kvm); @@ -9845,34 +9887,36 @@ 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 *free, - struct kvm_memory_slot *dont) +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) { - kvfree(free->arch.rmap[i]); - free->arch.rmap[i] = NULL; - } + kvfree(slot->arch.rmap[i]); + slot->arch.rmap[i] = NULL; + if (i == 0) continue; - if (!dont || free->arch.lpage_info[i - 1] != - dont->arch.lpage_info[i - 1]) { - kvfree(free->arch.lpage_info[i - 1]); - free->arch.lpage_info[i - 1] = NULL; - } + kvfree(slot->arch.lpage_info[i - 1]); + slot->arch.lpage_info[i - 1] = NULL; } - kvm_page_track_free_memslot(free, dont); + kvm_page_track_free_memslot(slot); } -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) +static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, + unsigned long npages) { int i; + /* + * 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 + * the new memslot is successful. + */ + memset(&slot->arch, 0, sizeof(slot->arch)); + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { struct kvm_lpage_info *linfo; unsigned long ugfn; @@ -9903,11 +9947,9 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, ugfn = slot->userspace_addr >> PAGE_SHIFT; /* * If the gfn and userspace address are not aligned wrt each - * other, or if explicitly asked to, disable large page - * support for this slot + * other, disable large page support for this slot. */ - if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) || - !kvm_largepages_enabled()) { + if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1)) { unsigned long j; for (j = 0; j < lpages; ++j) @@ -9954,6 +9996,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { + if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) + return kvm_alloc_memslot_metadata(memslot, + mem->memory_size >> PAGE_SHIFT); return 0; } @@ -9962,14 +10007,14 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, { /* Still write protect RO slot */ if (new->flags & KVM_MEM_READONLY) { - kvm_mmu_slot_remove_write_access(kvm, new); + kvm_mmu_slot_remove_write_access(kvm, new, PT_PAGE_TABLE_LEVEL); return; } /* * Call kvm_x86_ops dirty logging hooks when they are valid. * - * kvm_x86_ops->slot_disable_log_dirty is called when: + * kvm_x86_ops.slot_disable_log_dirty is called when: * * - KVM_MR_CREATE with dirty logging is disabled * - KVM_MR_FLAGS_ONLY with dirty logging is disabled in new flag @@ -9981,7 +10026,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * any additional overhead from PML when guest is running with dirty * logging disabled for memory slots. * - * kvm_x86_ops->slot_enable_log_dirty is called when switching new slot + * kvm_x86_ops.slot_enable_log_dirty is called when switching new slot * to dirty logging mode. * * If kvm_x86_ops dirty logging hooks are invalid, use write protect. @@ -9997,19 +10042,32 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * See the comments in fast_page_fault(). */ if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { - if (kvm_x86_ops->slot_enable_log_dirty) - kvm_x86_ops->slot_enable_log_dirty(kvm, new); - else - kvm_mmu_slot_remove_write_access(kvm, new); + if (kvm_x86_ops.slot_enable_log_dirty) { + kvm_x86_ops.slot_enable_log_dirty(kvm, new); + } else { + int level = + kvm_dirty_log_manual_protect_and_init_set(kvm) ? + PT_DIRECTORY_LEVEL : PT_PAGE_TABLE_LEVEL; + + /* + * 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. + */ + kvm_mmu_slot_remove_write_access(kvm, new, level); + } } else { - if (kvm_x86_ops->slot_disable_log_dirty) - kvm_x86_ops->slot_disable_log_dirty(kvm, new); + if (kvm_x86_ops.slot_disable_log_dirty) + kvm_x86_ops.slot_disable_log_dirty(kvm, new); } } void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { @@ -10051,6 +10109,10 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, */ if (change != KVM_MR_DELETE) kvm_mmu_slot_apply_flags(kvm, (struct kvm_memory_slot *) new); + + /* Free the arrays associated with the old memslot. */ + if (change == KVM_MR_MOVE) + kvm_arch_free_memslot(kvm, old); } void kvm_arch_flush_shadow_all(struct kvm *kvm) @@ -10067,8 +10129,8 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { return (is_guest_mode(vcpu) && - kvm_x86_ops->guest_apic_has_interrupt && - kvm_x86_ops->guest_apic_has_interrupt(vcpu)); + kvm_x86_ops.guest_apic_has_interrupt && + kvm_x86_ops.guest_apic_has_interrupt(vcpu)); } static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) @@ -10087,7 +10149,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_NMI, vcpu) || (vcpu->arch.nmi_pending && - kvm_x86_ops->nmi_allowed(vcpu))) + kvm_x86_ops.nmi_allowed(vcpu))) return true; if (kvm_test_request(KVM_REQ_SMI, vcpu) || @@ -10120,7 +10182,7 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) kvm_test_request(KVM_REQ_EVENT, vcpu)) return true; - if (vcpu->arch.apicv_active && kvm_x86_ops->dy_apicv_has_pending_interrupt(vcpu)) + if (vcpu->arch.apicv_active && kvm_x86_ops.dy_apicv_has_pending_interrupt(vcpu)) return true; return false; @@ -10138,7 +10200,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) { - return kvm_x86_ops->interrupt_allowed(vcpu); + return kvm_x86_ops.interrupt_allowed(vcpu); } unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu) @@ -10160,7 +10222,7 @@ unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags; - rflags = kvm_x86_ops->get_rflags(vcpu); + rflags = kvm_x86_ops.get_rflags(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) rflags &= ~X86_EFLAGS_TF; return rflags; @@ -10172,7 +10234,7 @@ static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) rflags |= X86_EFLAGS_TF; - kvm_x86_ops->set_rflags(vcpu, rflags); + kvm_x86_ops.set_rflags(vcpu, rflags); } void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) @@ -10195,7 +10257,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) return; if (!vcpu->arch.mmu->direct_map && - work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu)) + work->arch.cr3 != vcpu->arch.mmu->get_guest_pgd(vcpu)) return; kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); @@ -10283,7 +10345,7 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) || (vcpu->arch.apf.send_user_only && - kvm_x86_ops->get_cpl(vcpu) == 0)) + kvm_x86_ops.get_cpl(vcpu) == 0)) return false; return true; @@ -10303,7 +10365,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) * If interrupts are off we cannot even use an artificial * halt state. */ - return kvm_x86_ops->interrupt_allowed(vcpu); + return kvm_x86_ops.interrupt_allowed(vcpu); } void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, @@ -10432,7 +10494,7 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, irqfd->producer = prod; - return kvm_x86_ops->update_pi_irte(irqfd->kvm, + return kvm_x86_ops.update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 1); } @@ -10452,7 +10514,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, * when the irq is masked/disabled or the consumer side (KVM * int this case doesn't want to receive the interrupts. */ - ret = kvm_x86_ops->update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0); + ret = kvm_x86_ops.update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0); if (ret) printk(KERN_INFO "irq bypass consumer (token %p) unregistration" " fails: %d\n", irqfd->consumer.token, ret); @@ -10461,7 +10523,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set) { - return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set); + return kvm_x86_ops.update_pi_irte(kvm, host_irq, guest_irq, set); } bool kvm_vector_hashing_enabled(void) @@ -10518,4 +10580,5 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 3624665acee4..b968acc0516f 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -5,6 +5,7 @@ #include <linux/kvm_host.h> #include <asm/pvclock.h> #include "kvm_cache_regs.h" +#include "kvm_emulate.h" #define KVM_DEFAULT_PLE_GAP 128 #define KVM_VMX_DEFAULT_PLE_WINDOW 4096 @@ -96,7 +97,7 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu) if (!is_long_mode(vcpu)) return false; - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); return cs_l; } @@ -149,11 +150,6 @@ static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu) return kvm_read_cr4_bits(vcpu, X86_CR4_LA57) ? 57 : 48; } -static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt) -{ - return (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_LA57) ? 57 : 48; -} - static inline u64 get_canonical(u64 la, u8 vaddr_bits) { return ((int64_t)la << (64 - vaddr_bits)) >> (64 - vaddr_bits); @@ -164,12 +160,6 @@ static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu) return get_canonical(la, vcpu_virt_addr_bits(vcpu)) != la; } -static inline bool emul_is_noncanonical_address(u64 la, - struct x86_emulate_ctxt *ctxt) -{ - return get_canonical(la, ctxt_virt_addr_bits(ctxt)) != la; -} - static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, unsigned access) { @@ -247,7 +237,7 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) { - return is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu); + return is_smm(vcpu) || kvm_x86_ops.apic_init_signal_blocked(vcpu); } void kvm_set_pending_timer(struct kvm_vcpu *vcpu); @@ -280,13 +270,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); -#define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ - | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ - | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \ - | XFEATURE_MASK_PKRU) extern u64 host_xcr0; +extern u64 supported_xcr0; +extern u64 supported_xss; -extern u64 kvm_supported_xcr0(void); +static inline bool kvm_mpx_supported(void) +{ + return (supported_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) + == (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); +} extern unsigned int min_timer_period_us; diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 63457908c9c4..69f4164d6477 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -231,6 +231,9 @@ struct vgic_dist { /* distributor enabled */ bool enabled; + /* Wants SGIs without active state */ + bool nassgireq; + struct vgic_irq *spis; struct vgic_io_device dist_iodev; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bcb9b2ac0791..6d58beb65454 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -360,6 +360,10 @@ static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *mem return memslot->dirty_bitmap + len / sizeof(*memslot->dirty_bitmap); } +#ifndef KVM_DIRTY_LOG_MANUAL_CAPS +#define KVM_DIRTY_LOG_MANUAL_CAPS KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE +#endif + struct kvm_s390_adapter_int { u64 ind_addr; u64 summary_addr; @@ -431,11 +435,11 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) */ struct kvm_memslots { u64 generation; - struct kvm_memory_slot memslots[KVM_MEM_SLOTS_NUM]; /* The mapping table from slot id to the index in memslots[]. */ short id_to_index[KVM_MEM_SLOTS_NUM]; atomic_t lru_slot; int used_slots; + struct kvm_memory_slot memslots[]; }; struct kvm { @@ -493,7 +497,7 @@ struct kvm { #endif long tlbs_dirty; struct list_head devices; - bool manual_dirty_log_protect; + u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; struct kvm_stat_data **debugfs_stat_data; struct srcu_struct srcu; @@ -527,6 +531,11 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) +{ + return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); +} + static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) { return srcu_dereference_check(kvm->buses[idx], &kvm->srcu, @@ -572,10 +581,11 @@ static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) return vcpu->vcpu_idx; } -#define kvm_for_each_memslot(memslot, slots) \ - for (memslot = &slots->memslots[0]; \ - memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\ - memslot++) +#define kvm_for_each_memslot(memslot, slots) \ + for (memslot = &slots->memslots[0]; \ + memslot < slots->memslots + slots->used_slots; memslot++) \ + if (WARN_ON_ONCE(!memslot->npages)) { \ + } else void kvm_vcpu_destroy(struct kvm_vcpu *vcpu); @@ -635,12 +645,15 @@ static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) return __kvm_memslots(vcpu->kvm, as_id); } -static inline struct kvm_memory_slot * -id_to_memslot(struct kvm_memslots *slots, int id) +static inline +struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { int index = slots->id_to_index[id]; struct kvm_memory_slot *slot; + if (index < 0) + return NULL; + slot = &slots->memslots[index]; WARN_ON(slot->id != id); @@ -669,10 +682,7 @@ int kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem); int __kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem); -void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont); -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages); +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, @@ -680,11 +690,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); -bool kvm_largepages_enabled(void); -void kvm_disable_largepages(void); /* flush all memory translations */ void kvm_arch_flush_shadow_all(struct kvm *kvm); /* flush memory translations pointing to 'slot' */ @@ -704,7 +712,6 @@ void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); void kvm_set_page_accessed(struct page *page); -kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); @@ -819,23 +826,20 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf); int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext); -int kvm_get_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log, int *is_dirty); - -int kvm_get_dirty_log_protect(struct kvm *kvm, - struct kvm_dirty_log *log, bool *flush); -int kvm_clear_dirty_log_protect(struct kvm *kvm, - struct kvm_clear_dirty_log *log, bool *flush); - void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); - -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log); -int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, - struct kvm_clear_dirty_log *log); +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot); + +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT +void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot); +#else /* !CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); +int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, + int *is_dirty, struct kvm_memory_slot **memslot); +#endif int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status); @@ -882,9 +886,9 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu); int kvm_arch_hardware_enable(void); void kvm_arch_hardware_disable(void); -int kvm_arch_hardware_setup(void); +int kvm_arch_hardware_setup(void *opaque); void kvm_arch_hardware_unsetup(void); -int kvm_arch_check_processor_compat(void); +int kvm_arch_check_processor_compat(void *opaque); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); @@ -1018,6 +1022,8 @@ bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c. * gfn_to_memslot() itself isn't here as an inline because that would * bloat other code too much. + * + * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! */ static inline struct kvm_memory_slot * search_memslots(struct kvm_memslots *slots, gfn_t gfn) @@ -1026,6 +1032,9 @@ search_memslots(struct kvm_memslots *slots, gfn_t gfn) int slot = atomic_read(&slots->lru_slot); struct kvm_memory_slot *memslots = slots->memslots; + if (unlikely(!slots->used_slots)) + return NULL; + if (gfn >= memslots[slot].base_gfn && gfn < memslots[slot].base_gfn + memslots[slot].npages) return &memslots[slot]; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4b95f9a31a2f..428c7dde6b4b 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -474,12 +474,17 @@ struct kvm_s390_mem_op { __u32 size; /* amount of bytes */ __u32 op; /* type of operation */ __u64 buf; /* buffer in userspace */ - __u8 ar; /* the access register number */ - __u8 reserved[31]; /* should be set to 0 */ + union { + __u8 ar; /* the access register number */ + __u32 sida_offset; /* offset into the sida */ + __u8 reserved[32]; /* should be set to 0 */ + }; }; /* types for kvm_s390_mem_op->op */ #define KVM_S390_MEMOP_LOGICAL_READ 0 #define KVM_S390_MEMOP_LOGICAL_WRITE 1 +#define KVM_S390_MEMOP_SIDA_READ 2 +#define KVM_S390_MEMOP_SIDA_WRITE 3 /* flags for kvm_s390_mem_op->flags */ #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) @@ -1010,6 +1015,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_NISV_TO_USER 177 #define KVM_CAP_ARM_INJECT_EXT_DABT 178 #define KVM_CAP_S390_VCPU_RESETS 179 +#define KVM_CAP_S390_PROTECTED 180 +#define KVM_CAP_PPC_SECURE_GUEST 181 #ifdef KVM_CAP_IRQ_ROUTING @@ -1478,6 +1485,39 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) +struct kvm_s390_pv_sec_parm { + __u64 origin; + __u64 length; +}; + +struct kvm_s390_pv_unp { + __u64 addr; + __u64 size; + __u64 tweak; +}; + +enum pv_cmd_id { + KVM_PV_ENABLE, + KVM_PV_DISABLE, + KVM_PV_SET_SEC_PARMS, + KVM_PV_UNPACK, + KVM_PV_VERIFY, + KVM_PV_PREP_RESET, + KVM_PV_UNSHARE_ALL, +}; + +struct kvm_pv_cmd { + __u32 cmd; /* Command to be executed */ + __u16 rc; /* Ultravisor return code */ + __u16 rrc; /* Ultravisor return reason code */ + __u64 data; /* Data or address */ + __u32 flags; /* flags for future extensions. Must be 0 for now */ + __u32 reserved[3]; +}; + +/* Available with KVM_CAP_S390_PROTECTED */ +#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ @@ -1628,4 +1668,7 @@ struct kvm_hyperv_eventfd { #define KVM_HYPERV_CONN_ID_MASK 0x00ffffff #define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) +#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) +#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) + #endif /* __LINUX_KVM_H */ diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/asm/unistd_64.h index cb52a3a8b8fc..4205ed4158bf 100644 --- a/tools/arch/x86/include/asm/unistd_64.h +++ b/tools/arch/x86/include/asm/unistd_64.h @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NR_userfaultfd +#define __NR_userfaultfd 282 +#endif #ifndef __NR_perf_event_open # define __NR_perf_event_open 298 #endif diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 4cf93110c259..e83fc8e868f4 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -25,7 +25,7 @@ import sys import locale import os import time -import optparse +import argparse import ctypes import fcntl import resource @@ -33,6 +33,8 @@ import struct import re import subprocess from collections import defaultdict, namedtuple +from functools import reduce +from datetime import datetime VMX_EXIT_REASONS = { 'EXCEPTION_NMI': 0, @@ -873,7 +875,7 @@ class Stats(object): if options.debugfs: providers.append(DebugfsProvider(options.pid, options.fields, - options.dbgfs_include_past)) + options.debugfs_include_past)) if options.tracepoints or not providers: providers.append(TracepointProvider(options.pid, options.fields)) @@ -974,15 +976,17 @@ DELAY_DEFAULT = 3.0 MAX_GUEST_NAME_LEN = 48 MAX_REGEX_LEN = 44 SORT_DEFAULT = 0 +MIN_DELAY = 0.1 +MAX_DELAY = 25.5 class Tui(object): """Instruments curses to draw a nice text ui.""" - def __init__(self, stats): + def __init__(self, stats, opts): self.stats = stats self.screen = None self._delay_initial = 0.25 - self._delay_regular = DELAY_DEFAULT + self._delay_regular = opts.set_delay self._sorting = SORT_DEFAULT self._display_guests = 0 @@ -1183,7 +1187,7 @@ class Tui(object): if not self._is_running_guest(self.stats.pid_filter): if self._gname: - try: # ...to identify the guest by name in case it's back + try: # ...to identify the guest by name in case it's back pids = self.get_pid_from_gname(self._gname) if len(pids) == 1: self._refresh_header(pids[0]) @@ -1282,7 +1286,8 @@ class Tui(object): ' p filter by guest name/PID', ' q quit', ' r reset stats', - ' s set update interval', + ' s set delay between refreshs (value range: ' + '%s-%s secs)' % (MIN_DELAY, MAX_DELAY), ' x toggle reporting of stats for individual child trace' ' events', 'Any other key refreshes statistics immediately') @@ -1336,8 +1341,8 @@ class Tui(object): msg = '' while True: self.screen.erase() - self.screen.addstr(0, 0, 'Set update interval (defaults to %.1fs).' % - DELAY_DEFAULT, curses.A_BOLD) + self.screen.addstr(0, 0, 'Set update interval (defaults to %.1fs).' + % DELAY_DEFAULT, curses.A_BOLD) self.screen.addstr(4, 0, msg) self.screen.addstr(2, 0, 'Change delay from %.1fs to ' % self._delay_regular) @@ -1348,11 +1353,9 @@ class Tui(object): try: if len(val) > 0: delay = float(val) - if delay < 0.1: - msg = '"' + str(val) + '": Value must be >=0.1' - continue - if delay > 25.5: - msg = '"' + str(val) + '": Value must be <=25.5' + err = is_delay_valid(delay) + if err is not None: + msg = err continue else: delay = DELAY_DEFAULT @@ -1488,33 +1491,64 @@ def batch(stats): pass -def log(stats): - """Prints statistics as reiterating key block, multiple value blocks.""" - keys = sorted(stats.get().keys()) - - def banner(): +class StdFormat(object): + def __init__(self, keys): + self._banner = '' for key in keys: - print(key.split(' ')[0], end=' ') - print() + self._banner += key.split(' ')[0] + ' ' - def statline(): - s = stats.get() + def get_banner(self): + return self._banner + + @staticmethod + def get_statline(keys, s): + res = '' for key in keys: - print(' %9d' % s[key].delta, end=' ') - print() + res += ' %9d' % s[key].delta + return res + + +class CSVFormat(object): + def __init__(self, keys): + self._banner = 'timestamp' + self._banner += reduce(lambda res, key: "{},{!s}".format(res, + key.split(' ')[0]), keys, '') + + def get_banner(self): + return self._banner + + @staticmethod + def get_statline(keys, s): + return reduce(lambda res, key: "{},{!s}".format(res, s[key].delta), + keys, '') + + +def log(stats, opts, frmt, keys): + """Prints statistics as reiterating key block, multiple value blocks.""" line = 0 banner_repeat = 20 while True: try: - time.sleep(1) + time.sleep(opts.set_delay) if line % banner_repeat == 0: - banner() - statline() + print(frmt.get_banner()) + print(datetime.now().strftime("%Y-%m-%d %H:%M:%S") + + frmt.get_statline(keys, stats.get())) line += 1 except KeyboardInterrupt: break +def is_delay_valid(delay): + """Verify delay is in valid value range.""" + msg = None + if delay < MIN_DELAY: + msg = '"' + str(delay) + '": Delay must be >=%s' % MIN_DELAY + if delay > MAX_DELAY: + msg = '"' + str(delay) + '": Delay must be <=%s' % MAX_DELAY + return msg + + def get_options(): """Returns processed program arguments.""" description_text = """ @@ -1545,89 +1579,85 @@ Interactive Commands: p filter by PID q quit r reset stats - s set update interval + s set update interval (value range: 0.1-25.5 secs) x toggle reporting of stats for individual child trace events Press any other key to refresh statistics immediately. """ % (PATH_DEBUGFS_KVM, PATH_DEBUGFS_TRACING) - class PlainHelpFormatter(optparse.IndentedHelpFormatter): - def format_description(self, description): - if description: - return description + "\n" - else: - return "" - - def cb_guest_to_pid(option, opt, val, parser): - try: - pids = Tui.get_pid_from_gname(val) - except: - sys.exit('Error while searching for guest "{}". Use "-p" to ' - 'specify a pid instead?'.format(val)) - if len(pids) == 0: - sys.exit('Error: No guest by the name "{}" found'.format(val)) - if len(pids) > 1: - sys.exit('Error: Multiple processes found (pids: {}). Use "-p" ' - 'to specify the desired pid'.format(" ".join(pids))) - parser.values.pid = pids[0] - - optparser = optparse.OptionParser(description=description_text, - formatter=PlainHelpFormatter()) - optparser.add_option('-1', '--once', '--batch', - action='store_true', - default=False, - dest='once', - help='run in batch mode for one second', - ) - optparser.add_option('-i', '--debugfs-include-past', - action='store_true', - default=False, - dest='dbgfs_include_past', - help='include all available data on past events for ' - 'debugfs', - ) - optparser.add_option('-l', '--log', - action='store_true', - default=False, - dest='log', - help='run in logging mode (like vmstat)', - ) - optparser.add_option('-t', '--tracepoints', - action='store_true', - default=False, - dest='tracepoints', - help='retrieve statistics from tracepoints', - ) - optparser.add_option('-d', '--debugfs', - action='store_true', - default=False, - dest='debugfs', - help='retrieve statistics from debugfs', - ) - optparser.add_option('-f', '--fields', - action='store', - default='', - dest='fields', - help='''fields to display (regex) - "-f help" for a list of available events''', - ) - optparser.add_option('-p', '--pid', - action='store', - default=0, - type='int', - dest='pid', - help='restrict statistics to pid', - ) - optparser.add_option('-g', '--guest', - action='callback', - type='string', - dest='pid', - metavar='GUEST', - help='restrict statistics to guest by name', - callback=cb_guest_to_pid, - ) - options, unkn = optparser.parse_args(sys.argv) - if len(unkn) != 1: - sys.exit('Error: Extra argument(s): ' + ' '.join(unkn[1:])) + class Guest_to_pid(argparse.Action): + def __call__(self, parser, namespace, values, option_string=None): + try: + pids = Tui.get_pid_from_gname(values) + except: + sys.exit('Error while searching for guest "{}". Use "-p" to ' + 'specify a pid instead?'.format(values)) + if len(pids) == 0: + sys.exit('Error: No guest by the name "{}" found' + .format(values)) + if len(pids) > 1: + sys.exit('Error: Multiple processes found (pids: {}). Use "-p"' + ' to specify the desired pid'.format(" ".join(pids))) + namespace.pid = pids[0] + + argparser = argparse.ArgumentParser(description=description_text, + formatter_class=argparse + .RawTextHelpFormatter) + argparser.add_argument('-1', '--once', '--batch', + action='store_true', + default=False, + help='run in batch mode for one second', + ) + argparser.add_argument('-c', '--csv', + action='store_true', + default=False, + help='log in csv format - requires option -l/--log', + ) + argparser.add_argument('-d', '--debugfs', + action='store_true', + default=False, + help='retrieve statistics from debugfs', + ) + argparser.add_argument('-f', '--fields', + default='', + help='''fields to display (regex) +"-f help" for a list of available events''', + ) + argparser.add_argument('-g', '--guest', + type=str, + help='restrict statistics to guest by name', + action=Guest_to_pid, + ) + argparser.add_argument('-i', '--debugfs-include-past', + action='store_true', + default=False, + help='include all available data on past events for' + ' debugfs', + ) + argparser.add_argument('-l', '--log', + action='store_true', + default=False, + help='run in logging mode (like vmstat)', + ) + argparser.add_argument('-p', '--pid', + type=int, + default=0, + help='restrict statistics to pid', + ) + argparser.add_argument('-s', '--set-delay', + type=float, + default=DELAY_DEFAULT, + metavar='DELAY', + help='set delay between refreshs (value range: ' + '%s-%s secs)' % (MIN_DELAY, MAX_DELAY), + ) + argparser.add_argument('-t', '--tracepoints', + action='store_true', + default=False, + help='retrieve statistics from tracepoints', + ) + options = argparser.parse_args() + if options.csv and not options.log: + sys.exit('Error: Option -c/--csv requires -l/--log') try: # verify that we were passed a valid regex up front re.compile(options.fields) @@ -1693,6 +1723,10 @@ def main(): sys.stderr.write('Did you use a (unsupported) tid instead of a pid?\n') sys.exit('Specified pid does not exist.') + err = is_delay_valid(options.set_delay) + if err is not None: + sys.exit('Error: ' + err) + stats = Stats(options) if options.fields == 'help': @@ -1704,12 +1738,18 @@ def main(): sys.exit(0) if options.log: - log(stats) + keys = sorted(stats.get().keys()) + if options.csv: + frmt = CSVFormat(keys) + else: + frmt = StdFormat(keys) + log(stats, options, frmt, keys) elif not options.once: - with Tui(stats) as tui: + with Tui(stats, options) as tui: tui.show_stats() else: batch(stats) + if __name__ == "__main__": main() diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index c057ba52364e..a97ded2aedad 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -49,7 +49,7 @@ INTERACTIVE COMMANDS *r*:: reset stats -*s*:: set update interval +*s*:: set delay between refreshs *x*:: toggle reporting of stats for child trace events :: *Note*: The stats for the parents summarize the respective child trace @@ -64,37 +64,45 @@ OPTIONS --batch:: run in batch mode for one second --l:: ---log:: - run in logging mode (like vmstat) - --t:: ---tracepoints:: - retrieve statistics from tracepoints +-c:: +--csv=<file>:: + log in csv format - requires option -l/--log -d:: --debugfs:: retrieve statistics from debugfs +-f<fields>:: +--fields=<fields>:: + fields to display (regex), "-f help" for a list of available events + +-g<guest>:: +--guest=<guest_name>:: + limit statistics to one virtual machine (guest name) + +-h:: +--help:: + show help message + -i:: --debugfs-include-past:: include all available data on past events for debugfs +-l:: +--log:: + run in logging mode (like vmstat) + -p<pid>:: --pid=<pid>:: limit statistics to one virtual machine (pid) --g<guest>:: ---guest=<guest_name>:: - limit statistics to one virtual machine (guest name) +-s:: +--set-delay:: + set delay between refreshs (value range: 0.1-25.5 secs) --f<fields>:: ---fields=<fields>:: - fields to display (regex), "-f help" for a list of available events - --h:: ---help:: - show help message +-t:: +--tracepoints:: + retrieve statistics from tracepoints SEE ALSO -------- diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 30072c3f52fb..16877c3daabf 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,13 +1,16 @@ -/s390x/sync_regs_test /s390x/memop +/s390x/resets +/s390x/sync_regs_test /x86_64/cr4_cpuid_sync_test /x86_64/evmcs_test /x86_64/hyperv_cpuid /x86_64/mmio_warning_test /x86_64/platform_info_test +/x86_64/set_memory_region_test /x86_64/set_sregs_test /x86_64/smm_test /x86_64/state_test +/x86_64/svm_vmcall_test /x86_64/sync_regs_test /x86_64/vmx_close_while_nested_test /x86_64/vmx_dirty_log_test @@ -15,5 +18,7 @@ /x86_64/vmx_tsc_adjust_test /x86_64/xss_msr_test /clear_dirty_log_test +/demand_paging_test /dirty_log_test /kvm_create_max_vcpus +/steal_time diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index d91c53b726e6..712a2ddd2a27 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -7,7 +7,7 @@ top_srcdir = ../../../.. KSFT_KHDR_INSTALL := 1 UNAME_M := $(shell uname -m) -LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c +LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/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 LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c @@ -17,27 +17,33 @@ TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test +TEST_GEN_PROGS_x86_64 += x86_64/set_memory_region_test TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test TEST_GEN_PROGS_x86_64 += x86_64/smm_test TEST_GEN_PROGS_x86_64 += x86_64/state_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test 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/xss_msr_test -TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test +TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus +TEST_GEN_PROGS_x86_64 += steal_time TEST_GEN_PROGS_aarch64 += clear_dirty_log_test +TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus +TEST_GEN_PROGS_aarch64 += steal_time TEST_GEN_PROGS_s390x = s390x/memop -TEST_GEN_PROGS_s390x += s390x/sync_regs_test TEST_GEN_PROGS_s390x += s390x/resets +TEST_GEN_PROGS_s390x += s390x/sync_regs_test +TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += kvm_create_max_vcpus diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c index 749336937d37..11672ec6f74e 100644 --- a/tools/testing/selftests/kvm/clear_dirty_log_test.c +++ b/tools/testing/selftests/kvm/clear_dirty_log_test.c @@ -1,2 +1,6 @@ #define USE_CLEAR_DIRTY_LOG +#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) +#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) +#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ + KVM_DIRTY_LOG_INITIALLY_SET) #include "dirty_log_test.c" diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c new file mode 100644 index 000000000000..360cd3ea4cd6 --- /dev/null +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -0,0 +1,661 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KVM demand paging test + * Adapted from dirty_log_test.c + * + * Copyright (C) 2018, Red Hat, Inc. + * Copyright (C) 2019, Google, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_name */ + +#include <stdio.h> +#include <stdlib.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <asm/unistd.h> +#include <time.h> +#include <poll.h> +#include <pthread.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> +#include <linux/userfaultfd.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +#ifdef __NR_userfaultfd + +/* The memory slot index demand page */ +#define TEST_MEM_SLOT_INDEX 1 + +/* Default guest test virtual memory offset */ +#define DEFAULT_GUEST_TEST_MEM 0xc0000000 + +#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */ + +#ifdef PRINT_PER_PAGE_UPDATES +#define PER_PAGE_DEBUG(...) printf(__VA_ARGS__) +#else +#define PER_PAGE_DEBUG(...) _no_printf(__VA_ARGS__) +#endif + +#ifdef PRINT_PER_VCPU_UPDATES +#define PER_VCPU_DEBUG(...) printf(__VA_ARGS__) +#else +#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__) +#endif + +#define MAX_VCPUS 512 + +/* + * Guest/Host shared variables. Ensure addr_gva2hva() and/or + * sync_global_to/from_guest() are used when accessing from + * the host. READ/WRITE_ONCE() should also be used with anything + * that may change. + */ +static uint64_t host_page_size; +static uint64_t guest_page_size; + +static char *guest_data_prototype; + +/* + * Guest physical memory offset of the testing memory slot. + * This will be set to the topmost valid physical address minus + * the test memory size. + */ +static uint64_t guest_test_phys_mem; + +/* + * Guest virtual memory offset of the testing memory slot. + * Must not conflict with identity mapped test code. + */ +static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; + +struct vcpu_args { + uint64_t gva; + uint64_t pages; + + /* Only used by the host userspace part of the vCPU thread */ + int vcpu_id; + struct kvm_vm *vm; +}; + +static struct vcpu_args vcpu_args[MAX_VCPUS]; + +/* + * Continuously write to the first 8 bytes of each page in the demand paging + * memory region. + */ +static void guest_code(uint32_t vcpu_id) +{ + uint64_t gva; + uint64_t pages; + int i; + + /* Make sure vCPU args data structure is not corrupt. */ + GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id); + + gva = vcpu_args[vcpu_id].gva; + pages = vcpu_args[vcpu_id].pages; + + for (i = 0; i < pages; i++) { + uint64_t addr = gva + (i * guest_page_size); + + addr &= ~(host_page_size - 1); + *(uint64_t *)addr = 0x0123456789ABCDEF; + } + + GUEST_SYNC(1); +} + +static void *vcpu_worker(void *data) +{ + int ret; + struct vcpu_args *args = (struct vcpu_args *)data; + struct kvm_vm *vm = args->vm; + int vcpu_id = args->vcpu_id; + struct kvm_run *run; + struct timespec start, end, ts_diff; + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + run = vcpu_state(vm, vcpu_id); + + clock_gettime(CLOCK_MONOTONIC, &start); + + /* Let the guest access its memory */ + ret = _vcpu_run(vm, vcpu_id); + TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); + if (get_ucall(vm, vcpu_id, NULL) != UCALL_SYNC) { + TEST_ASSERT(false, + "Invalid guest sync status: exit_reason=%s\n", + exit_reason_str(run->exit_reason)); + } + + clock_gettime(CLOCK_MONOTONIC, &end); + ts_diff = timespec_sub(end, start); + PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id, + ts_diff.tv_sec, ts_diff.tv_nsec); + + return NULL; +} + +#define PAGE_SHIFT_4K 12 +#define PTES_PER_4K_PT 512 + +static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus, + uint64_t vcpu_memory_bytes) +{ + struct kvm_vm *vm; + uint64_t pages = DEFAULT_GUEST_PHY_PAGES; + + /* Account for a few pages per-vCPU for stacks */ + pages += DEFAULT_STACK_PGS * vcpus; + + /* + * Reserve twice the ammount of memory needed to map the test region and + * the page table / stacks region, at 4k, for page tables. Do the + * calculation with 4K page size: the smallest of all archs. (e.g., 64K + * page size guest will need even less memory for page tables). + */ + pages += (2 * pages) / PTES_PER_4K_PT; + pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) / + PTES_PER_4K_PT; + pages = vm_adjust_num_guest_pages(mode, pages); + + pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); + + vm = _vm_create(mode, pages, O_RDWR); + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); +#ifdef __x86_64__ + vm_create_irqchip(vm); +#endif + return vm; +} + +static int handle_uffd_page_request(int uffd, uint64_t addr) +{ + pid_t tid; + struct timespec start; + struct timespec end; + struct uffdio_copy copy; + int r; + + tid = syscall(__NR_gettid); + + copy.src = (uint64_t)guest_data_prototype; + copy.dst = addr; + copy.len = host_page_size; + copy.mode = 0; + + clock_gettime(CLOCK_MONOTONIC, &start); + + 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; + } + + clock_gettime(CLOCK_MONOTONIC, &end); + + PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid, + timespec_to_ns(timespec_sub(end, start))); + PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n", + host_page_size, addr, tid); + + return 0; +} + +bool quit_uffd_thread; + +struct uffd_handler_args { + int uffd; + int pipefd; + useconds_t delay; +}; + +static void *uffd_handler_thread_fn(void *arg) +{ + struct uffd_handler_args *uffd_args = (struct uffd_handler_args *)arg; + int uffd = uffd_args->uffd; + int pipefd = uffd_args->pipefd; + useconds_t delay = uffd_args->delay; + int64_t pages = 0; + struct timespec start, end, ts_diff; + + clock_gettime(CLOCK_MONOTONIC, &start); + while (!quit_uffd_thread) { + struct uffd_msg msg; + struct pollfd pollfd[2]; + char tmp_chr; + int r; + uint64_t addr; + + pollfd[0].fd = uffd; + pollfd[0].events = POLLIN; + pollfd[1].fd = pipefd; + pollfd[1].events = POLLIN; + + r = poll(pollfd, 2, -1); + switch (r) { + case -1: + pr_info("poll err"); + continue; + case 0: + continue; + case 1: + break; + default: + pr_info("Polling uffd returned %d", r); + return NULL; + } + + if (pollfd[0].revents & POLLERR) { + pr_info("uffd revents has POLLERR"); + return NULL; + } + + if (pollfd[1].revents & POLLIN) { + r = read(pollfd[1].fd, &tmp_chr, 1); + TEST_ASSERT(r == 1, + "Error reading pipefd in UFFD thread\n"); + return NULL; + } + + if (!pollfd[0].revents & POLLIN) + continue; + + r = read(uffd, &msg, sizeof(msg)); + if (r == -1) { + if (errno == EAGAIN) + continue; + pr_info("Read of uffd gor errno %d", errno); + return NULL; + } + + if (r != sizeof(msg)) { + pr_info("Read on uffd returned unexpected size: %d bytes", r); + return NULL; + } + + if (!(msg.event & UFFD_EVENT_PAGEFAULT)) + continue; + + if (delay) + usleep(delay); + addr = msg.arg.pagefault.address; + r = handle_uffd_page_request(uffd, addr); + if (r < 0) + return NULL; + pages++; + } + + clock_gettime(CLOCK_MONOTONIC, &end); + ts_diff = timespec_sub(end, start); + PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n", + pages, ts_diff.tv_sec, ts_diff.tv_nsec, + pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); + + 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) +{ + int uffd; + struct uffdio_api uffdio_api; + struct uffdio_register uffdio_register; + + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd == -1) { + pr_info("uffd creation failed\n"); + return -1; + } + + 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; + } + + 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; + } + + uffd_args->uffd = uffd; + uffd_args->pipefd = pipefd; + uffd_args->delay = uffd_delay; + pthread_create(uffd_handler_thread, NULL, uffd_handler_thread_fn, + uffd_args); + + PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n", + hva, hva + len); + + return 0; +} + +static void run_test(enum vm_guest_mode mode, bool use_uffd, + useconds_t uffd_delay, int vcpus, + uint64_t vcpu_memory_bytes) +{ + pthread_t *vcpu_threads; + pthread_t *uffd_handler_threads = NULL; + struct uffd_handler_args *uffd_args = NULL; + struct timespec start, end, ts_diff; + int *pipefds = NULL; + struct kvm_vm *vm; + uint64_t guest_num_pages; + int vcpu_id; + int r; + + vm = create_vm(mode, vcpus, vcpu_memory_bytes); + + guest_page_size = vm_get_page_size(vm); + + TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0, + "Guest memory size is not guest page size aligned."); + + guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size; + guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); + + /* + * If there should be more memory in the guest test region than there + * can be pages in the guest, it will definitely cause problems. + */ + 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_num_pages, vm_get_max_gfn(vm), vcpus, + vcpu_memory_bytes); + + host_page_size = getpagesize(); + TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0, + "Guest memory size is not host page size aligned."); + + guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * + guest_page_size; + guest_test_phys_mem &= ~(host_page_size - 1); + +#ifdef __s390x__ + /* Align to 1M (segment size) */ + guest_test_phys_mem &= ~((1 << 20) - 1); +#endif + + pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); + + /* Add an extra memory slot for testing demand paging */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + guest_test_phys_mem, + TEST_MEM_SLOT_INDEX, + 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); + + ucall_init(vm, NULL); + + guest_data_prototype = malloc(host_page_size); + TEST_ASSERT(guest_data_prototype, + "Failed to allocate buffer for guest data pattern"); + memset(guest_data_prototype, 0xAB, host_page_size); + + vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads)); + TEST_ASSERT(vcpu_threads, "Memory allocation failed"); + + if (use_uffd) { + uffd_handler_threads = + malloc(vcpus * sizeof(*uffd_handler_threads)); + TEST_ASSERT(uffd_handler_threads, "Memory allocation failed"); + + uffd_args = malloc(vcpus * sizeof(*uffd_args)); + TEST_ASSERT(uffd_args, "Memory allocation failed"); + + pipefds = malloc(sizeof(int) * vcpus * 2); + TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd"); + } + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + vm_paddr_t vcpu_gpa; + void *vcpu_hva; + + vm_vcpu_add_default(vm, vcpu_id, guest_code); + + vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes); + PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes); + + /* Cache the HVA pointer of the region */ + vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); + + if (use_uffd) { + /* + * Set up user fault fd to handle demand paging + * requests. + */ + r = pipe2(&pipefds[vcpu_id * 2], + 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], + uffd_delay, &uffd_args[vcpu_id], + vcpu_hva, vcpu_memory_bytes); + if (r < 0) + exit(-r); + } + +#ifdef __x86_64__ + vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid()); +#endif + + vcpu_args[vcpu_id].vm = vm; + vcpu_args[vcpu_id].vcpu_id = vcpu_id; + vcpu_args[vcpu_id].gva = guest_test_virt_mem + + (vcpu_id * vcpu_memory_bytes); + vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size; + } + + /* Export the shared variables to the guest */ + sync_global_to_guest(vm, host_page_size); + sync_global_to_guest(vm, guest_page_size); + sync_global_to_guest(vm, vcpu_args); + + pr_info("Finished creating vCPUs and starting uffd threads\n"); + + clock_gettime(CLOCK_MONOTONIC, &start); + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, + &vcpu_args[vcpu_id]); + } + + pr_info("Started all vCPUs\n"); + + /* Wait for the vcpu threads to quit */ + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + pthread_join(vcpu_threads[vcpu_id], NULL); + PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id); + } + + pr_info("All vCPU threads joined\n"); + + clock_gettime(CLOCK_MONOTONIC, &end); + + if (use_uffd) { + char c; + + /* Tell the user fault fd handler threads to quit */ + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + r = write(pipefds[vcpu_id * 2 + 1], &c, 1); + TEST_ASSERT(r == 1, "Unable to write to pipefd"); + + pthread_join(uffd_handler_threads[vcpu_id], NULL); + } + } + + ts_diff = timespec_sub(end, start); + pr_info("Total guest execution time: %ld.%.9lds\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + pr_info("Overall demand paging rate: %f pgs/sec\n", + guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); + + ucall_uninit(vm); + kvm_vm_free(vm); + + free(guest_data_prototype); + free(vcpu_threads); + if (use_uffd) { + free(uffd_handler_threads); + free(uffd_args); + free(pipefds); + } +} + +struct guest_mode { + bool supported; + bool enabled; +}; +static struct guest_mode guest_modes[NUM_VM_MODES]; + +#define guest_mode_init(mode, supported, enabled) ({ \ + guest_modes[mode] = (struct guest_mode){ supported, enabled }; \ +}) + +static void help(char *name) +{ + int i; + + puts(""); + printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n" + " [-b memory] [-v vcpus]\n", name); + printf(" -m: specify the guest mode ID to test\n" + " (default: test all supported modes)\n" + " This option may be used multiple times.\n" + " Guest mode IDs:\n"); + for (i = 0; i < NUM_VM_MODES; ++i) { + printf(" %d: %s%s\n", i, vm_guest_mode_string(i), + guest_modes[i].supported ? " (supported)" : ""); + } + printf(" -u: use User Fault FD to handle vCPU page\n" + " faults.\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(" -v: specify the number of vCPUs to run.\n"); + puts(""); + exit(0); +} + +int main(int argc, char *argv[]) +{ + bool mode_selected = false; + uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE; + int vcpus = 1; + unsigned int mode; + int opt, i; + bool use_uffd = false; + useconds_t uffd_delay = 0; + +#ifdef __x86_64__ + guest_mode_init(VM_MODE_PXXV48_4K, true, true); +#endif +#ifdef __aarch64__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); + guest_mode_init(VM_MODE_P40V48_64K, true, true); + { + unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); + + if (limit >= 52) + guest_mode_init(VM_MODE_P52V48_64K, true, true); + if (limit >= 48) { + guest_mode_init(VM_MODE_P48V48_4K, true, true); + guest_mode_init(VM_MODE_P48V48_64K, true, true); + } + } +#endif +#ifdef __s390x__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); +#endif + + while ((opt = getopt(argc, argv, "hm:ud:b:v:")) != -1) { + switch (opt) { + case 'm': + if (!mode_selected) { + for (i = 0; i < NUM_VM_MODES; ++i) + guest_modes[i].enabled = false; + mode_selected = true; + } + mode = strtoul(optarg, NULL, 10); + TEST_ASSERT(mode < NUM_VM_MODES, + "Guest mode ID %d too big", mode); + guest_modes[mode].enabled = true; + break; + case 'u': + use_uffd = true; + break; + case 'd': + uffd_delay = strtoul(optarg, NULL, 0); + TEST_ASSERT(uffd_delay >= 0, + "A negative UFFD delay is not supported."); + break; + case 'b': + vcpu_memory_bytes = parse_size(optarg); + break; + case 'v': + vcpus = atoi(optarg); + TEST_ASSERT(vcpus > 0, + "Must have a positive number of vCPUs"); + TEST_ASSERT(vcpus <= MAX_VCPUS, + "This test does not currently support\n" + "more than %d vCPUs.", MAX_VCPUS); + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + for (i = 0; i < NUM_VM_MODES; ++i) { + if (!guest_modes[i].enabled) + continue; + TEST_ASSERT(guest_modes[i].supported, + "Guest mode ID %d (%s) not supported.", + i, vm_guest_mode_string(i)); + run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes); + } + + return 0; +} + +#else /* __NR_userfaultfd */ + +#warning "missing __NR_userfaultfd definition" + +int main(void) +{ + print_skip("__NR_userfaultfd must be present for userfaultfd test"); + return KSFT_SKIP; +} + +#endif /* __NR_userfaultfd */ diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 5614222a6628..752ec158ac59 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -166,24 +166,22 @@ static void *vcpu_worker(void *data) pages_count += TEST_PAGES_PER_LOOP; generate_random_array(guest_array, TEST_PAGES_PER_LOOP); } else { - TEST_ASSERT(false, - "Invalid guest sync status: " - "exit_reason=%s\n", - exit_reason_str(run->exit_reason)); + TEST_FAIL("Invalid guest sync status: " + "exit_reason=%s\n", + exit_reason_str(run->exit_reason)); } } - DEBUG("Dirtied %"PRIu64" pages\n", pages_count); + pr_info("Dirtied %"PRIu64" pages\n", pages_count); return NULL; } -static void vm_dirty_log_verify(unsigned long *bmap) +static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap) { + uint64_t step = vm_num_host_pages(mode, 1); uint64_t page; uint64_t *value_ptr; - uint64_t step = host_page_size >= guest_page_size ? 1 : - guest_page_size / host_page_size; for (page = 0; page < host_num_pages; page += step) { value_ptr = host_test_mem + page * host_page_size; @@ -252,6 +250,8 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, struct kvm_vm *vm; uint64_t extra_pg_pages = extra_mem_pages / 512 * 2; + 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); #ifdef __x86_64__ @@ -264,6 +264,10 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, #define DIRTY_MEM_BITS 30 /* 1G */ #define PAGE_SHIFT_4K 12 +#ifdef USE_CLEAR_DIRTY_LOG +static u64 dirty_log_manual_caps; +#endif + static void run_test(enum vm_guest_mode mode, unsigned long iterations, unsigned long interval, uint64_t phys_offset) { @@ -289,14 +293,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, * case where the size is not aligned to 64 pages. */ guest_num_pages = (1ul << (DIRTY_MEM_BITS - - vm_get_page_shift(vm))) + 16; -#ifdef __s390x__ - /* Round up to multiple of 1M (segment size) */ - guest_num_pages = (guest_num_pages + 0xff) & ~0xffUL; -#endif + vm_get_page_shift(vm))) + 3; + guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); + host_page_size = getpagesize(); - host_num_pages = (guest_num_pages * guest_page_size) / host_page_size + - !!((guest_num_pages * guest_page_size) % host_page_size); + host_num_pages = vm_num_host_pages(mode, guest_num_pages); if (!phys_offset) { guest_test_phys_mem = (vm_get_max_gfn(vm) - @@ -311,7 +312,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, guest_test_phys_mem &= ~((1 << 20) - 1); #endif - DEBUG("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); + pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); bmap = bitmap_alloc(host_num_pages); host_bmap_track = bitmap_alloc(host_num_pages); @@ -320,7 +321,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, struct kvm_enable_cap cap = {}; cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; - cap.args[0] = 1; + cap.args[0] = dirty_log_manual_caps; vm_enable_cap(vm, &cap); #endif @@ -332,8 +333,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, 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 * guest_page_size, 0); + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); /* Cache the HVA pointer of the region */ host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem); @@ -341,9 +341,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, #ifdef __x86_64__ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); #endif -#ifdef __aarch64__ ucall_init(vm, NULL); -#endif /* Export the shared variables to the guest */ sync_global_to_guest(vm, host_page_size); @@ -369,7 +367,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, host_num_pages); #endif - vm_dirty_log_verify(bmap); + vm_dirty_log_verify(mode, bmap); iteration++; sync_global_to_guest(vm, iteration); } @@ -378,9 +376,9 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, host_quit = true; pthread_join(vcpu_thread, NULL); - DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), " - "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count, - host_track_next_count); + pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), " + "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count, + host_track_next_count); free(bmap); free(host_bmap_track); @@ -388,15 +386,14 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, kvm_vm_free(vm); } -struct vm_guest_mode_params { +struct guest_mode { bool supported; bool enabled; }; -struct vm_guest_mode_params vm_guest_mode_params[NUM_VM_MODES]; +static struct guest_mode guest_modes[NUM_VM_MODES]; -#define vm_guest_mode_params_init(mode, supported, enabled) \ -({ \ - vm_guest_mode_params[mode] = (struct vm_guest_mode_params){ supported, enabled }; \ +#define guest_mode_init(mode, supported, enabled) ({ \ + guest_modes[mode] = (struct guest_mode){ supported, enabled }; \ }) static void help(char *name) @@ -419,7 +416,7 @@ static void help(char *name) " Guest mode IDs:\n"); for (i = 0; i < NUM_VM_MODES; ++i) { printf(" %d: %s%s\n", i, vm_guest_mode_string(i), - vm_guest_mode_params[i].supported ? " (supported)" : ""); + guest_modes[i].supported ? " (supported)" : ""); } puts(""); exit(0); @@ -433,34 +430,38 @@ int main(int argc, char *argv[]) uint64_t phys_offset = 0; unsigned int mode; int opt, i; -#ifdef __aarch64__ - unsigned int host_ipa_limit; -#endif #ifdef USE_CLEAR_DIRTY_LOG - if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2)) { - fprintf(stderr, "KVM_CLEAR_DIRTY_LOG not available, skipping tests\n"); + dirty_log_manual_caps = + kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + if (!dirty_log_manual_caps) { + print_skip("KVM_CLEAR_DIRTY_LOG not available"); exit(KSFT_SKIP); } + dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); #endif #ifdef __x86_64__ - vm_guest_mode_params_init(VM_MODE_PXXV48_4K, true, true); + guest_mode_init(VM_MODE_PXXV48_4K, true, true); #endif #ifdef __aarch64__ - vm_guest_mode_params_init(VM_MODE_P40V48_4K, true, true); - vm_guest_mode_params_init(VM_MODE_P40V48_64K, true, true); - - host_ipa_limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); - if (host_ipa_limit >= 52) - vm_guest_mode_params_init(VM_MODE_P52V48_64K, true, true); - if (host_ipa_limit >= 48) { - vm_guest_mode_params_init(VM_MODE_P48V48_4K, true, true); - vm_guest_mode_params_init(VM_MODE_P48V48_64K, true, true); + guest_mode_init(VM_MODE_P40V48_4K, true, true); + guest_mode_init(VM_MODE_P40V48_64K, true, true); + + { + unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); + + if (limit >= 52) + guest_mode_init(VM_MODE_P52V48_64K, true, true); + if (limit >= 48) { + guest_mode_init(VM_MODE_P48V48_4K, true, true); + guest_mode_init(VM_MODE_P48V48_64K, true, true); + } } #endif #ifdef __s390x__ - vm_guest_mode_params_init(VM_MODE_P40V48_4K, true, true); + guest_mode_init(VM_MODE_P40V48_4K, true, true); #endif while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) { @@ -477,13 +478,13 @@ int main(int argc, char *argv[]) case 'm': if (!mode_selected) { for (i = 0; i < NUM_VM_MODES; ++i) - vm_guest_mode_params[i].enabled = false; + guest_modes[i].enabled = false; mode_selected = true; } mode = strtoul(optarg, NULL, 10); TEST_ASSERT(mode < NUM_VM_MODES, "Guest mode ID %d too big", mode); - vm_guest_mode_params[mode].enabled = true; + guest_modes[mode].enabled = true; break; case 'h': default: @@ -495,15 +496,15 @@ int main(int argc, char *argv[]) TEST_ASSERT(iterations > 2, "Iterations must be greater than two"); TEST_ASSERT(interval > 0, "Interval must be greater than zero"); - DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n", - iterations, interval); + pr_info("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n", + iterations, interval); srandom(time(0)); for (i = 0; i < NUM_VM_MODES; ++i) { - if (!vm_guest_mode_params[i].enabled) + if (!guest_modes[i].enabled) continue; - TEST_ASSERT(vm_guest_mode_params[i].supported, + TEST_ASSERT(guest_modes[i].supported, "Guest mode ID %d (%s) not supported.", i, vm_guest_mode_string(i)); run_test(i, iterations, interval, phys_offset); diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h index 4912d23844bc..d8f4d6bfe05d 100644 --- a/tools/testing/selftests/kvm/include/evmcs.h +++ b/tools/testing/selftests/kvm/include/evmcs.h @@ -16,6 +16,8 @@ #define u32 uint32_t #define u64 uint64_t +#define EVMCS_VERSION 1 + extern bool enable_evmcs; struct hv_vp_assist_page { diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index ae0d14c2540a..a99b875f50d2 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -16,7 +16,8 @@ #include "sparsebit.h" -/* Callers of kvm_util only have an incomplete/opaque description of the +/* + * Callers of kvm_util only have an incomplete/opaque description of the * structure kvm_util is using to maintain the state of a VM. */ struct kvm_vm; @@ -24,12 +25,6 @@ struct kvm_vm; typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ -#ifndef NDEBUG -#define DEBUG(...) printf(__VA_ARGS__); -#else -#define DEBUG(...) -#endif - /* Minimum allocated guest virtual and physical addresses */ #define KVM_UTIL_MIN_VADDR 0x2000 @@ -84,6 +79,23 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename, uint32_t data_memslot, uint32_t pgd_memslot); void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); + +/* + * VM VCPU Dump + * + * Input Args: + * stream - Output FILE stream + * vm - Virtual Machine + * vcpuid - VCPU ID + * indent - Left margin indent amount + * + * Output Args: None + * + * Return: None + * + * Dumps the current state of the VCPU specified by @vcpuid, within the VM + * given by @vm, to the FILE stream given by @stream. + */ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent); @@ -100,14 +112,31 @@ int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, void *arg); void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); 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_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); void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - size_t size, uint32_t pgd_memslot); + unsigned int npages, uint32_t pgd_memslot); 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); + +/* + * Address Guest Virtual to Guest Physical + * + * Input Args: + * vm - Virtual Machine + * gva - VM virtual address + * + * Output Args: None + * + * Return: + * Equivalent VM physical address + * + * Returns the VM physical address of the translated VM virtual + * address given by @gva. + */ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); @@ -118,7 +147,27 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_mp_state *mp_state); void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); + +/* + * VM VCPU Args Set + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * num - number of arguments + * ... - arguments, each of type uint64_t + * + * Output Args: None + * + * Return: None + * + * Sets the first @num function input registers of the VCPU with @vcpuid, + * per the C calling convention of the architecture, to the values given + * as variable args. Each of the variable args is expected to be of type + * uint64_t. The maximum @num can be is specific to the architecture. + */ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...); + void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs); void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, @@ -147,15 +196,57 @@ int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid, const char *exit_reason_str(unsigned int exit_reason); void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot); + +/* + * VM Virtual Page Map + * + * Input Args: + * vm - Virtual Machine + * vaddr - VM Virtual Address + * paddr - VM Physical Address + * memslot - Memory region slot for new virtual translation tables + * + * Output Args: None + * + * Return: None + * + * 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 pgd_memslot); + uint32_t memslot); + 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); -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_size, +/* + * Create a VM with reasonable defaults + * + * Input Args: + * vcpuid - The id of the single VCPU to add to the VM. + * extra_mem_pages - The number of extra pages to add (this will + * decide how much extra space we will need to + * setup the page tables using memslot 0) + * guest_code - The vCPU's entry point + * + * Output Args: None + * + * Return: + * Pointer to opaque structure that describes the created VM. + */ +struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, void *guest_code); + +/* + * Adds a vCPU with reasonable defaults (e.g. a stack) + * + * Input Args: + * vm - Virtual Machine + * vcpuid - The id of the VCPU to add to the VM. + * guest_code - The vCPU's entry point + */ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code); bool vm_is_unrestricted_guest(struct kvm_vm *vm); @@ -164,6 +255,21 @@ 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); +unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); +unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages); +unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages); +static inline unsigned int +vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) +{ + unsigned int n; + n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages)); +#ifdef __s390x__ + /* s390 requires 1M aligned guest sizes */ + n = (n + 255) & ~255; +#endif + return n; +} + struct kvm_userspace_memory_region * kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end); diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index a41db6fb7e24..5eb01bf51b86 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -19,12 +19,28 @@ #include <fcntl.h> #include "kselftest.h" +static inline int _no_printf(const char *format, ...) { return 0; } + +#ifdef DEBUG +#define pr_debug(...) printf(__VA_ARGS__) +#else +#define pr_debug(...) _no_printf(__VA_ARGS__) +#endif +#ifndef QUIET +#define pr_info(...) printf(__VA_ARGS__) +#else +#define pr_info(...) _no_printf(__VA_ARGS__) +#endif + +void print_skip(const char *fmt, ...) __attribute__((format(printf, 1, 2))); + ssize_t test_write(int fd, const void *buf, size_t count); ssize_t test_read(int fd, void *buf, size_t count); int test_seq_read(const char *path, char **bufp, size_t *sizep); void test_assert(bool exp, const char *exp_str, - const char *file, unsigned int line, const char *fmt, ...); + const char *file, unsigned int line, const char *fmt, ...) + __attribute__((format(printf, 5, 6))); #define TEST_ASSERT(e, fmt, ...) \ test_assert((e), #e, __FILE__, __LINE__, fmt, ##__VA_ARGS__) @@ -39,4 +55,14 @@ void test_assert(bool exp, const char *exp_str, #a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \ } while (0) +#define TEST_FAIL(fmt, ...) \ + TEST_ASSERT(false, fmt, ##__VA_ARGS__) + +size_t parse_size(const char *size); + +int64_t timespec_to_ns(struct timespec ts); +struct timespec timespec_add_ns(struct timespec ts, int64_t ns); +struct timespec timespec_add(struct timespec ts1, struct timespec ts2); +struct timespec timespec_sub(struct timespec ts1, struct timespec ts2); + #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c index 6f38c3dc0d56..0299cd81b8ba 100644 --- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c +++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c @@ -24,8 +24,8 @@ void test_vcpu_creation(int first_vcpu_id, int num_vcpus) struct kvm_vm *vm; int i; - printf("Testing creating %d vCPUs, with IDs %d...%d.\n", - num_vcpus, first_vcpu_id, first_vcpu_id + num_vcpus - 1); + pr_info("Testing creating %d vCPUs, with IDs %d...%d.\n", + num_vcpus, first_vcpu_id, first_vcpu_id + num_vcpus - 1); vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); @@ -41,8 +41,8 @@ int main(int argc, char *argv[]) int kvm_max_vcpu_id = kvm_check_cap(KVM_CAP_MAX_VCPU_ID); int kvm_max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); - printf("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id); - printf("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus); + pr_info("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id); + pr_info("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus); /* * Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID. diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 86036a59a668..2afa6618b396 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -130,7 +130,7 @@ void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8; break; default: - TEST_ASSERT(false, "Page table levels must be 2, 3, or 4"); + TEST_FAIL("Page table levels must be 2, 3, or 4"); } *ptep = paddr | 3; @@ -173,20 +173,19 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) goto unmapped_gva; break; default: - TEST_ASSERT(false, "Page table levels must be 2, 3, or 4"); + TEST_FAIL("Page table levels must be 2, 3, or 4"); } return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1)); unmapped_gva: - TEST_ASSERT(false, "No mapping for vm virtual address, " - "gva: 0x%lx", gva); + TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva); exit(1); } static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level) { -#ifdef DEBUG_VM +#ifdef DEBUG static const char * const type[] = { "", "pud", "pmd", "pte" }; uint64_t pte, *ptep; @@ -197,7 +196,7 @@ static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t p ptep = addr_gpa2hva(vm, pte); if (!*ptep) continue; - printf("%*s%s: %lx: %lx at %p\n", indent, "", type[level], pte, *ptep, ptep); + fprintf(stream, "%*s%s: %lx: %lx at %p\n", indent, "", type[level], pte, *ptep, ptep); pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level + 1); } #endif @@ -215,7 +214,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) ptep = addr_gpa2hva(vm, pgd); if (!*ptep) continue; - printf("%*spgd: %lx: %lx at %p\n", indent, "", pgd, *ptep, ptep); + fprintf(stream, "%*spgd: %lx: %lx at %p\n", indent, "", pgd, *ptep, ptep); pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level); } } @@ -262,11 +261,11 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini switch (vm->mode) { case VM_MODE_P52V48_4K: - TEST_ASSERT(false, "AArch64 does not support 4K sized pages " - "with 52-bit physical address ranges"); + TEST_FAIL("AArch64 does not support 4K sized pages " + "with 52-bit physical address ranges"); case VM_MODE_PXXV48_4K: - TEST_ASSERT(false, "AArch64 does not support 4K sized pages " - "with ANY-bit physical address ranges"); + TEST_FAIL("AArch64 does not support 4K sized pages " + "with ANY-bit physical address ranges"); case VM_MODE_P52V48_64K: tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ @@ -288,7 +287,7 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini tcr_el1 |= 2ul << 32; /* IPS = 40 bits */ break; default: - TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode); + TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); } sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */; @@ -333,3 +332,21 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) { aarch64_vcpu_add_default(vm, vcpuid, NULL, guest_code); } + +void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) +{ + va_list ap; + int i; + + TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n" + " num: %u\n", num); + + va_start(ap, num); + + for (i = 0; i < num; i++) { + set_reg(vm, vcpuid, ARM64_CORE_REG(regs.regs[i]), + va_arg(ap, uint64_t)); + } + + va_end(ap); +} diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index 6cd91970fbad..c8e0ec20d3bf 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -62,7 +62,7 @@ void ucall_init(struct kvm_vm *vm, void *arg) if (ucall_mmio_init(vm, start + offset)) return; } - TEST_ASSERT(false, "Can't find a ucall mmio address"); + TEST_FAIL("Can't find a ucall mmio address"); } void ucall_uninit(struct kvm_vm *vm) diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c index d1cf9f6e0e6b..5ebbd0d6b472 100644 --- a/tools/testing/selftests/kvm/lib/assert.c +++ b/tools/testing/selftests/kvm/lib/assert.c @@ -82,8 +82,10 @@ test_assert(bool exp, const char *exp_str, } va_end(ap); - if (errno == EACCES) - ksft_exit_skip("Access denied - Exiting.\n"); + if (errno == EACCES) { + print_skip("Access denied - Exiting"); + exit(KSFT_SKIP); + } exit(254); } diff --git a/tools/testing/selftests/kvm/lib/io.c b/tools/testing/selftests/kvm/lib/io.c index eaf351cc7e7f..fedb2a741f0b 100644 --- a/tools/testing/selftests/kvm/lib/io.c +++ b/tools/testing/selftests/kvm/lib/io.c @@ -61,9 +61,9 @@ ssize_t test_write(int fd, const void *buf, size_t count) continue; case 0: - TEST_ASSERT(false, "Unexpected EOF,\n" - " rc: %zi num_written: %zi num_left: %zu", - rc, num_written, num_left); + TEST_FAIL("Unexpected EOF,\n" + " rc: %zi num_written: %zi num_left: %zu", + rc, num_written, num_left); break; default: @@ -138,9 +138,9 @@ ssize_t test_read(int fd, void *buf, size_t count) break; case 0: - TEST_ASSERT(false, "Unexpected EOF,\n" - " rc: %zi num_read: %zi num_left: %zu", - rc, num_read, num_left); + TEST_FAIL("Unexpected EOF,\n" + " rc: %zi num_read: %zi num_left: %zu", + rc, num_read, num_left); break; default: diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index a6dd0401eb50..8a3523d4434f 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -92,7 +92,7 @@ static void vm_open(struct kvm_vm *vm, int perm) exit(KSFT_SKIP); if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { - fprintf(stderr, "immediate_exit not available, skipping test\n"); + print_skip("immediate_exit not available"); exit(KSFT_SKIP); } @@ -113,6 +113,25 @@ const char * const vm_guest_mode_string[] = { _Static_assert(sizeof(vm_guest_mode_string)/sizeof(char *) == NUM_VM_MODES, "Missing new mode strings?"); +struct vm_guest_mode_params { + unsigned int pa_bits; + unsigned int va_bits; + unsigned int page_size; + unsigned int page_shift; +}; + +static const struct vm_guest_mode_params vm_guest_mode_params[] = { + { 52, 48, 0x1000, 12 }, + { 52, 48, 0x10000, 16 }, + { 48, 48, 0x1000, 12 }, + { 48, 48, 0x10000, 16 }, + { 40, 48, 0x1000, 12 }, + { 40, 48, 0x10000, 16 }, + { 0, 0, 0x1000, 12 }, +}; +_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, + "Missing new mode params?"); + /* * VM Create * @@ -136,7 +155,8 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) { struct kvm_vm *vm; - DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode)); + pr_debug("%s: mode='%s' pages='%ld' perm='%d'\n", __func__, + vm_guest_mode_string(mode), phy_pages, perm); vm = calloc(1, sizeof(*vm)); TEST_ASSERT(vm != NULL, "Insufficient Memory"); @@ -144,67 +164,45 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) vm->mode = mode; vm->type = 0; + vm->pa_bits = vm_guest_mode_params[mode].pa_bits; + vm->va_bits = vm_guest_mode_params[mode].va_bits; + vm->page_size = vm_guest_mode_params[mode].page_size; + vm->page_shift = vm_guest_mode_params[mode].page_shift; + /* Setup mode specific traits. */ switch (vm->mode) { case VM_MODE_P52V48_4K: vm->pgtable_levels = 4; - vm->pa_bits = 52; - vm->va_bits = 48; - vm->page_size = 0x1000; - vm->page_shift = 12; break; case VM_MODE_P52V48_64K: vm->pgtable_levels = 3; - vm->pa_bits = 52; - vm->va_bits = 48; - vm->page_size = 0x10000; - vm->page_shift = 16; break; case VM_MODE_P48V48_4K: vm->pgtable_levels = 4; - vm->pa_bits = 48; - vm->va_bits = 48; - vm->page_size = 0x1000; - vm->page_shift = 12; break; case VM_MODE_P48V48_64K: vm->pgtable_levels = 3; - vm->pa_bits = 48; - vm->va_bits = 48; - vm->page_size = 0x10000; - vm->page_shift = 16; break; case VM_MODE_P40V48_4K: vm->pgtable_levels = 4; - vm->pa_bits = 40; - vm->va_bits = 48; - vm->page_size = 0x1000; - vm->page_shift = 12; break; case VM_MODE_P40V48_64K: vm->pgtable_levels = 3; - vm->pa_bits = 40; - vm->va_bits = 48; - vm->page_size = 0x10000; - vm->page_shift = 16; break; case VM_MODE_PXXV48_4K: #ifdef __x86_64__ kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits); TEST_ASSERT(vm->va_bits == 48, "Linear address width " "(%d bits) not supported", vm->va_bits); + pr_debug("Guest physical address width detected: %d\n", + vm->pa_bits); vm->pgtable_levels = 4; - vm->page_size = 0x1000; - vm->page_shift = 12; - DEBUG("Guest physical address width detected: %d\n", - vm->pa_bits); #else - TEST_ASSERT(false, "VM_MODE_PXXV48_4K not supported on " - "non-x86 platforms"); + TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms"); #endif break; default: - TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode); + TEST_FAIL("Unknown guest mode, mode: 0x%x", mode); } #ifdef __aarch64__ @@ -266,7 +264,7 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm) TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" " slot: %u flags: 0x%x\n" - " guest_phys_addr: 0x%lx size: 0x%lx", + " guest_phys_addr: 0x%llx size: 0x%llx", ret, errno, region->region.slot, region->region.flags, region->region.guest_phys_addr, @@ -281,7 +279,7 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) ret = ioctl(vm->fd, KVM_GET_DIRTY_LOG, &args); TEST_ASSERT(ret == 0, "%s: KVM_GET_DIRTY_LOG failed: %s", - strerror(-ret)); + __func__, strerror(-ret)); } void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, @@ -294,7 +292,7 @@ void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args); TEST_ASSERT(ret == 0, "%s: KVM_CLEAR_DIRTY_LOG failed: %s", - strerror(-ret)); + __func__, strerror(-ret)); } /* @@ -582,6 +580,10 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, size_t huge_page_size = KVM_UTIL_PGS_PER_HUGEPG * vm->page_size; size_t alignment; + TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages, + "Number of guest pages is not compatible with the host. " + "Try npages=%d", vm_adjust_num_guest_pages(vm->mode, npages)); + TEST_ASSERT((guest_paddr % vm->page_size) == 0, "Guest physical " "address not on a page boundary.\n" " guest_paddr: 0x%lx vm->page_size: 0x%x", @@ -600,7 +602,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, region = (struct userspace_mem_region *) userspace_mem_region_find( vm, guest_paddr, (guest_paddr + npages * vm->page_size) - 1); if (region != NULL) - TEST_ASSERT(false, "overlapping userspace_mem_region already " + TEST_FAIL("overlapping userspace_mem_region already " "exists\n" " requested guest_paddr: 0x%lx npages: 0x%lx " "page_size: 0x%x\n" @@ -616,7 +618,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, break; } if (region != NULL) - TEST_ASSERT(false, "A mem region with the requested slot " + TEST_FAIL("A mem region with the requested slot " "already exists.\n" " requested slot: %u paddr: 0x%lx npages: 0x%lx\n" " existing slot: %u paddr: 0x%lx size: 0x%lx", @@ -720,7 +722,7 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot) " requested slot: %u\n", memslot); fputs("---- vm dump ----\n", stderr); vm_dump(stderr, vm, 2); - TEST_ASSERT(false, "Mem region not found"); + TEST_FAIL("Mem region not found"); } return region; @@ -757,6 +759,36 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags) } /* + * VM Memory Region Move + * + * Input Args: + * vm - Virtual Machine + * slot - Slot of the memory region to move + * new_gpa - Starting guest physical address + * + * Output Args: None + * + * Return: None + * + * Change the gpa of a memory region. + */ +void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) +{ + struct userspace_mem_region *region; + int ret; + + region = memslot2region(vm, slot); + + region->region.guest_phys_addr = new_gpa; + + ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); + + TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed\n" + "ret: %i errno: %i slot: %u new_gpa: 0x%lx", + ret, errno, slot, new_gpa); +} + +/* * VCPU mmap Size * * Input Args: None @@ -808,7 +840,7 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid) /* Confirm a vcpu with the specified id doesn't already exist. */ vcpu = vcpu_find(vm, vcpuid); if (vcpu != NULL) - TEST_ASSERT(false, "vcpu with the specified id " + TEST_FAIL("vcpu with the specified id " "already exists,\n" " requested vcpuid: %u\n" " existing vcpuid: %u state: %p", @@ -901,8 +933,7 @@ static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, } while (pgidx_start != 0); no_va_found: - TEST_ASSERT(false, "No vaddr of specified pages available, " - "pages: 0x%lx", pages); + TEST_FAIL("No vaddr of specified pages available, pages: 0x%lx", pages); /* NOT REACHED */ return -1; @@ -982,21 +1013,21 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, * vm - Virtual Machine * vaddr - Virtuall address to map * paddr - VM Physical Address - * size - The size of the range to map + * npages - The number of pages to map * pgd_memslot - Memory region slot for new virtual translation tables * * Output Args: None * * Return: None * - * Within the VM given by vm, creates a virtual translation for the - * page range starting at vaddr to the page range starting at paddr. + * Within the VM given by @vm, creates a virtual translation for + * @npages starting at @vaddr to the page range starting at @paddr. */ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - size_t size, uint32_t pgd_memslot) + unsigned int npages, uint32_t pgd_memslot) { size_t page_size = vm->page_size; - size_t npages = size / page_size; + size_t size = npages * page_size; TEST_ASSERT(vaddr + size > vaddr, "Vaddr overflow"); TEST_ASSERT(paddr + size > paddr, "Paddr overflow"); @@ -1037,7 +1068,7 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) + (gpa - region->region.guest_phys_addr)); } - TEST_ASSERT(false, "No vm physical memory at 0x%lx", gpa); + TEST_FAIL("No vm physical memory at 0x%lx", gpa); return NULL; } @@ -1071,8 +1102,7 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) + (hva - (uintptr_t) region->host_mem)); } - TEST_ASSERT(false, "No mapping to a guest physical address, " - "hva: %p", hva); + TEST_FAIL("No mapping to a guest physical address, hva: %p", hva); return -1; } @@ -1703,3 +1733,43 @@ unsigned int vm_get_max_gfn(struct kvm_vm *vm) { return vm->max_gfn; } + +static unsigned int vm_calc_num_pages(unsigned int num_pages, + unsigned int page_shift, + unsigned int new_page_shift, + bool ceil) +{ + unsigned int n = 1 << (new_page_shift - page_shift); + + if (page_shift >= new_page_shift) + return num_pages * (1 << (page_shift - new_page_shift)); + + return num_pages / n + !!(ceil && num_pages % n); +} + +static inline int getpageshift(void) +{ + return __builtin_ffs(getpagesize()) - 1; +} + +unsigned int +vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) +{ + return vm_calc_num_pages(num_guest_pages, + vm_guest_mode_params[mode].page_shift, + getpageshift(), true); +} + +unsigned int +vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages) +{ + return vm_calc_num_pages(num_host_pages, getpageshift(), + vm_guest_mode_params[mode].page_shift, false); +} + +unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size) +{ + unsigned int n; + n = DIV_ROUND_UP(size, vm_guest_mode_params[mode].page_size); + return vm_adjust_num_guest_pages(mode, n); +} diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index ac50c42750cf..ca56a0133127 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -12,17 +12,6 @@ #define KVM_DEV_PATH "/dev/kvm" -#ifndef BITS_PER_BYTE -#define BITS_PER_BYTE 8 -#endif - -#ifndef BITS_PER_LONG -#define BITS_PER_LONG (BITS_PER_BYTE * sizeof(long)) -#endif - -#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) -#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_LONG) - struct userspace_mem_region { struct userspace_mem_region *next, *prev; struct kvm_userspace_memory_region region; @@ -64,8 +53,56 @@ struct kvm_vm { }; struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid); + +/* + * Virtual Translation Tables Dump + * + * Input Args: + * stream - Output FILE stream + * vm - Virtual Machine + * indent - Left margin indent amount + * + * Output Args: None + * + * Return: None + * + * Dumps to the FILE stream given by @stream, the contents of all the + * virtual translation tables for the VM given by @vm. + */ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); + +/* + * Register Dump + * + * Input Args: + * stream - Output FILE stream + * regs - Registers + * indent - Left margin indent amount + * + * Output Args: None + * + * Return: None + * + * Dumps the state of the registers given by @regs, to the FILE stream + * given by @stream. + */ void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent); + +/* + * System Register Dump + * + * Input Args: + * stream - Output FILE stream + * sregs - System registers + * indent - Left margin indent amount + * + * Output Args: None + * + * Return: None + * + * Dumps the state of the system registers given by @sregs, to the FILE stream + * given by @stream. + */ void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent); struct userspace_mem_region * diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index 32a02360b1eb..8d94961bd046 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -51,22 +51,6 @@ 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); } -/* - * VM Virtual Page Map - * - * Input Args: - * vm - Virtual Machine - * gva - VM Virtual Address - * gpa - VM Physical Address - * memslot - Memory region slot for new virtual translation tables - * - * Output Args: None - * - * Return: None - * - * Within the VM given by 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 gva, uint64_t gpa, uint32_t memslot) { @@ -107,26 +91,6 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa, entry[idx] = gpa; } -/* - * Address Guest Virtual to Guest Physical - * - * Input Args: - * vm - Virtual Machine - * gpa - VM virtual address - * - * Output Args: None - * - * Return: - * Equivalent VM physical address - * - * Translates the VM virtual address given by gva to a VM physical - * address and then locates the memory region containing the VM - * physical address, within the VM given by vm. When found, the host - * virtual address providing the memory to the vm physical address is - * returned. - * A TEST_ASSERT failure occurs if no region containing translated - * VM virtual address exists. - */ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { int ri, idx; @@ -196,21 +160,6 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) virt_dump_region(stream, vm, indent, vm->pgd); } -/* - * Create a VM with reasonable defaults - * - * Input Args: - * vcpuid - The id of the single VCPU to add to the VM. - * extra_mem_pages - The size of extra memories to add (this will - * decide how much extra space we will need to - * setup the page tables using mem slot 0) - * guest_code - The vCPU's entry point - * - * Output Args: None - * - * Return: - * Pointer to opaque structure that describes the created VM. - */ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, void *guest_code) { @@ -231,13 +180,6 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, return vm; } -/* - * Adds a vCPU with reasonable defaults (i.e. a stack and initial PSW) - * - * Input Args: - * vcpuid - The id of the VCPU to add to the VM. - * guest_code - The vCPU's entry point - */ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) { size_t stack_size = DEFAULT_STACK_PGS * getpagesize(); @@ -269,6 +211,26 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) run->psw_addr = (uintptr_t)guest_code; } +void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) +{ + va_list ap; + struct kvm_regs regs; + int i; + + TEST_ASSERT(num >= 1 && num <= 5, "Unsupported number of args,\n" + " num: %u\n", + num); + + va_start(ap, num); + vcpu_regs_get(vm, vcpuid, ®s); + + for (i = 0; i < num; i++) + regs.gprs[i + 2] = va_arg(ap, uint64_t); + + vcpu_regs_set(vm, vcpuid, ®s); + va_end(ap); +} + void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) { struct vcpu *vcpu = vm->vcpu_head; diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c new file mode 100644 index 000000000000..689e97c27ee2 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * tools/testing/selftests/kvm/lib/test_util.c + * + * Copyright (C) 2020, Google LLC. + */ +#include <stdlib.h> +#include <ctype.h> +#include <limits.h> +#include <assert.h> +#include "test_util.h" + +/* + * Parses "[0-9]+[kmgt]?". + */ +size_t parse_size(const char *size) +{ + size_t base; + char *scale; + int shift = 0; + + TEST_ASSERT(size && isdigit(size[0]), "Need at least one digit in '%s'", size); + + base = strtoull(size, &scale, 0); + + TEST_ASSERT(base != ULLONG_MAX, "Overflow parsing size!"); + + switch (tolower(*scale)) { + case 't': + shift = 40; + break; + case 'g': + shift = 30; + break; + case 'm': + shift = 20; + break; + case 'k': + shift = 10; + break; + case 'b': + case '\0': + shift = 0; + break; + default: + TEST_ASSERT(false, "Unknown size letter %c", *scale); + } + + TEST_ASSERT((base << shift) >> shift == base, "Overflow scaling size!"); + + return base << shift; +} + +int64_t timespec_to_ns(struct timespec ts) +{ + return (int64_t)ts.tv_nsec + 1000000000LL * (int64_t)ts.tv_sec; +} + +struct timespec timespec_add_ns(struct timespec ts, int64_t ns) +{ + struct timespec res; + + res.tv_nsec = ts.tv_nsec + ns; + res.tv_sec = ts.tv_sec + res.tv_nsec / 1000000000LL; + res.tv_nsec %= 1000000000LL; + + return res; +} + +struct timespec timespec_add(struct timespec ts1, struct timespec ts2) +{ + int64_t ns1 = timespec_to_ns(ts1); + int64_t ns2 = timespec_to_ns(ts2); + return timespec_add_ns((struct timespec){0}, ns1 + ns2); +} + +struct timespec timespec_sub(struct timespec ts1, struct timespec ts2) +{ + int64_t ns1 = timespec_to_ns(ts1); + int64_t ns2 = timespec_to_ns(ts2); + return timespec_add_ns((struct timespec){0}, ns1 - ns2); +} + +void print_skip(const char *fmt, ...) +{ + va_list ap; + + assert(fmt); + va_start(ap, fmt); + vprintf(fmt, ap); + va_end(ap); + puts(", skipping test"); +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 683d3bdb8f6a..f6eb34eaa0d2 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -77,20 +77,6 @@ struct pageTableEntry { uint64_t execute_disable:1; }; -/* Register Dump - * - * Input Args: - * indent - Left margin indent amount - * regs - register - * - * Output Args: - * stream - Output FILE stream - * - * Return: None - * - * Dumps the state of the registers given by regs, to the FILE stream - * given by steam. - */ void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) { @@ -115,19 +101,20 @@ void regs_dump(FILE *stream, struct kvm_regs *regs, regs->rip, regs->rflags); } -/* Segment Dump +/* + * Segment Dump * * Input Args: - * indent - Left margin indent amount + * stream - Output FILE stream * segment - KVM segment + * indent - Left margin indent amount * - * Output Args: - * stream - Output FILE stream + * Output Args: None * * Return: None * - * Dumps the state of the KVM segment given by segment, to the FILE stream - * given by steam. + * Dumps the state of the KVM segment given by @segment, to the FILE stream + * given by @stream. */ static void segment_dump(FILE *stream, struct kvm_segment *segment, uint8_t indent) @@ -146,19 +133,20 @@ static void segment_dump(FILE *stream, struct kvm_segment *segment, segment->unusable, segment->padding); } -/* dtable Dump +/* + * dtable Dump * * Input Args: - * indent - Left margin indent amount + * stream - Output FILE stream * dtable - KVM dtable + * indent - Left margin indent amount * - * Output Args: - * stream - Output FILE stream + * Output Args: None * * Return: None * - * Dumps the state of the KVM dtable given by dtable, to the FILE stream - * given by steam. + * Dumps the state of the KVM dtable given by @dtable, to the FILE stream + * given by @stream. */ static void dtable_dump(FILE *stream, struct kvm_dtable *dtable, uint8_t indent) @@ -169,20 +157,6 @@ static void dtable_dump(FILE *stream, struct kvm_dtable *dtable, dtable->padding[0], dtable->padding[1], dtable->padding[2]); } -/* System Register Dump - * - * Input Args: - * indent - Left margin indent amount - * sregs - System registers - * - * Output Args: - * stream - Output FILE stream - * - * Return: None - * - * Dumps the state of the system registers given by sregs, to the FILE stream - * given by steam. - */ void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent) { @@ -240,21 +214,6 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot) } } -/* VM Virtual Page Map - * - * Input Args: - * vm - Virtual Machine - * vaddr - VM Virtual Address - * paddr - VM Physical Address - * pgd_memslot - Memory region slot for new virtual translation tables - * - * Output Args: None - * - * Return: None - * - * Within the VM given by 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 pgd_memslot) { @@ -326,20 +285,6 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, pte[index[0]].present = 1; } -/* Virtual Translation Tables Dump - * - * Input Args: - * vm - Virtual Machine - * indent - Left margin indent amount - * - * Output Args: - * stream - Output FILE stream - * - * Return: None - * - * Dumps to the FILE stream given by stream, the contents of all the - * virtual translation tables for the VM given by vm. - */ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { struct pageMapL4Entry *pml4e, *pml4e_start; @@ -421,7 +366,8 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) } } -/* Set Unusable Segment +/* + * Set Unusable Segment * * Input Args: None * @@ -430,7 +376,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) * * Return: None * - * Sets the segment register pointed to by segp to an unusable state. + * Sets the segment register pointed to by @segp to an unusable state. */ static void kvm_seg_set_unusable(struct kvm_segment *segp) { @@ -460,7 +406,8 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) } -/* Set Long Mode Flat Kernel Code Segment +/* + * Set Long Mode Flat Kernel Code Segment * * Input Args: * vm - VM whose GDT is being filled, or NULL to only write segp @@ -471,8 +418,8 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) * * Return: None * - * Sets up the KVM segment pointed to by segp, to be a code segment - * with the selector value given by selector. + * Sets up the KVM segment pointed to by @segp, to be a code segment + * with the selector value given by @selector. */ static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector, struct kvm_segment *segp) @@ -491,7 +438,8 @@ static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector, kvm_seg_fill_gdt_64bit(vm, segp); } -/* Set Long Mode Flat Kernel Data Segment +/* + * Set Long Mode Flat Kernel Data Segment * * Input Args: * vm - VM whose GDT is being filled, or NULL to only write segp @@ -502,8 +450,8 @@ static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector, * * Return: None * - * Sets up the KVM segment pointed to by segp, to be a data segment - * with the selector value given by selector. + * Sets up the KVM segment pointed to by @segp, to be a data segment + * with the selector value given by @selector. */ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, struct kvm_segment *segp) @@ -521,24 +469,6 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, kvm_seg_fill_gdt_64bit(vm, segp); } -/* Address Guest Virtual to Guest Physical - * - * Input Args: - * vm - Virtual Machine - * gpa - VM virtual address - * - * Output Args: None - * - * Return: - * Equivalent VM physical address - * - * Translates the VM virtual address given by gva to a VM physical - * address and then locates the memory region containing the VM - * physical address, within the VM given by vm. When found, the host - * virtual address providing the memory to the vm physical address is returned. - * A TEST_ASSERT failure occurs if no region containing translated - * VM virtual address exists. - */ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { uint16_t index[4]; @@ -576,8 +506,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) return (pte[index[0]].address * vm->page_size) + (gva & 0xfffu); unmapped_gva: - TEST_ASSERT(false, "No mapping for vm virtual address, " - "gva: 0x%lx", gva); + TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva); exit(EXIT_FAILURE); } @@ -634,18 +563,13 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m break; default: - TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode); + TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); } sregs.cr3 = vm->pgd; vcpu_sregs_set(vm, vcpuid, &sregs); } -/* Adds a vCPU with reasonable defaults (i.e., a stack) - * - * Input Args: - * vcpuid - The id of the VCPU to add to the VM. - * guest_code - The vCPU's entry point - */ + void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) { struct kvm_mp_state mp_state; @@ -670,7 +594,8 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) vcpu_set_mp_state(vm, vcpuid, &mp_state); } -/* Allocate an instance of struct kvm_cpuid2 +/* + * Allocate an instance of struct kvm_cpuid2 * * Input Args: None * @@ -703,7 +628,8 @@ static struct kvm_cpuid2 *allocate_kvm_cpuid2(void) return cpuid; } -/* KVM Supported CPUID Get +/* + * KVM Supported CPUID Get * * Input Args: None * @@ -735,11 +661,12 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void) return cpuid; } -/* Locate a cpuid entry. +/* + * Locate a cpuid entry. * * Input Args: - * cpuid: The cpuid. * function: The function of the cpuid entry to find. + * index: The index of the cpuid entry. * * Output Args: None * @@ -766,7 +693,8 @@ kvm_get_supported_cpuid_index(uint32_t function, uint32_t index) return entry; } -/* VM VCPU CPUID Set +/* + * VM VCPU CPUID Set * * Input Args: * vm - Virtual Machine @@ -793,20 +721,6 @@ void vcpu_set_cpuid(struct kvm_vm *vm, } -/* Create a VM with reasonable defaults - * - * Input Args: - * vcpuid - The id of the single VCPU to add to the VM. - * extra_mem_pages - The size of extra memories to add (this will - * decide how much extra space we will need to - * setup the page tables using mem slot 0) - * guest_code - The vCPU's entry point - * - * Output Args: None - * - * Return: - * Pointer to opaque structure that describes the created VM. - */ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, void *guest_code) { @@ -837,7 +751,8 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, return vm; } -/* VCPU Get MSR +/* + * VCPU Get MSR * * Input Args: * vm - Virtual Machine @@ -869,7 +784,8 @@ uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index) return buffer.entry.data; } -/* _VCPU Set MSR +/* + * _VCPU Set MSR * * Input Args: * vm - Virtual Machine @@ -902,7 +818,8 @@ int _vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, return r; } -/* VCPU Set MSR +/* + * VCPU Set MSR * * Input Args: * vm - Virtual Machine @@ -926,22 +843,6 @@ void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, " rc: %i errno: %i", r, errno); } -/* VM VCPU Args Set - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * num - number of arguments - * ... - arguments, each of type uint64_t - * - * Output Args: None - * - * Return: None - * - * Sets the first num function input arguments to the values - * given as variable args. Each of the variable args is expected to - * be of type uint64_t. - */ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) { va_list ap; @@ -976,22 +877,6 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) va_end(ap); } -/* - * VM VCPU Dump - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * indent - Left margin indent amount - * - * Output Args: - * stream - Output FILE stream - * - * Return: None - * - * Dumps the current state of the VCPU specified by vcpuid, within the VM - * given by vm, to the FILE stream given by stream. - */ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) { struct kvm_regs regs; diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c index 6e05a8fc3fe0..c42401068373 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/svm.c +++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c @@ -154,7 +154,7 @@ void nested_svm_check_supported(void) kvm_get_supported_cpuid_entry(0x80000001); if (!(entry->ecx & CPUID_SVM)) { - fprintf(stderr, "nested SVM not enabled, skipping test\n"); + print_skip("nested SVM not enabled"); exit(KSFT_SKIP); } } diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 7aaa99ca4dbc..6f17f69394be 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -191,7 +191,7 @@ bool load_vmcs(struct vmx_pages *vmx) if (evmcs_vmptrld(vmx->enlightened_vmcs_gpa, vmx->enlightened_vmcs)) return false; - current_evmcs->revision_id = vmcs_revision(); + current_evmcs->revision_id = EVMCS_VERSION; } return true; @@ -381,7 +381,7 @@ void nested_vmx_check_supported(void) struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); if (!(entry->ecx & CPUID_VMX)) { - fprintf(stderr, "nested VMX not enabled, skipping test\n"); + print_skip("nested VMX not enabled"); exit(KSFT_SKIP); } } diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index 9edaa9a134ce..9f49ead380ab 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -40,7 +40,7 @@ int main(int argc, char *argv[]) maxsize = kvm_check_cap(KVM_CAP_S390_MEM_OP); if (!maxsize) { - fprintf(stderr, "CAP_S390_MEM_OP not supported -> skip test\n"); + print_skip("CAP_S390_MEM_OP not supported"); exit(KSFT_SKIP); } if (maxsize > sizeof(mem1)) diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390x/resets.c index 1485bc6c8999..b143db6d8693 100644 --- a/tools/testing/selftests/kvm/s390x/resets.c +++ b/tools/testing/selftests/kvm/s390x/resets.c @@ -20,29 +20,42 @@ struct kvm_s390_irq buf[VCPU_ID + LOCAL_IRQS]; struct kvm_vm *vm; struct kvm_run *run; -struct kvm_sync_regs *regs; -static uint64_t regs_null[16]; - -static uint64_t crs[16] = { 0x40000ULL, - 0x42000ULL, - 0, 0, 0, 0, 0, - 0x43000ULL, - 0, 0, 0, 0, 0, - 0x44000ULL, - 0, 0 -}; +struct kvm_sync_regs *sync_regs; +static uint8_t regs_null[512]; static void guest_code_initial(void) { - /* Round toward 0 */ - uint32_t fpc = 0x11; + /* set several CRs to "safe" value */ + unsigned long cr2_59 = 0x10; /* enable guarded storage */ + unsigned long cr8_63 = 0x1; /* monitor mask = 1 */ + unsigned long cr10 = 1; /* PER START */ + unsigned long cr11 = -1; /* PER END */ + /* Dirty registers */ asm volatile ( - " lctlg 0,15,%0\n" - " sfpc %1\n" - : : "Q" (crs), "d" (fpc)); - GUEST_SYNC(0); + " lghi 2,0x11\n" /* Round toward 0 */ + " sfpc 2\n" /* set fpc to !=0 */ + " lctlg 2,2,%0\n" + " lctlg 8,8,%1\n" + " lctlg 10,10,%2\n" + " lctlg 11,11,%3\n" + /* now clobber some general purpose regs */ + " llihh 0,0xffff\n" + " llihl 1,0x5555\n" + " llilh 2,0xaaaa\n" + " llill 3,0x0000\n" + /* now clobber a floating point reg */ + " lghi 4,0x1\n" + " cdgbr 0,4\n" + /* now clobber an access reg */ + " sar 9,4\n" + /* We embed diag 501 here to control register content */ + " diag 0,0,0x501\n" + : + : "m" (cr2_59), "m" (cr8_63), "m" (cr10), "m" (cr11) + /* no clobber list as this should not return */ + ); } static void test_one_reg(uint64_t id, uint64_t value) @@ -53,7 +66,7 @@ static void test_one_reg(uint64_t id, uint64_t value) reg.addr = (uintptr_t)&eval_reg; reg.id = id; vcpu_get_reg(vm, VCPU_ID, ®); - TEST_ASSERT(eval_reg == value, "value == %s", value); + TEST_ASSERT(eval_reg == value, "value == 0x%lx", value); } static void assert_noirq(void) @@ -87,6 +100,31 @@ static void assert_clear(void) vcpu_fpu_get(vm, VCPU_ID, &fpu); TEST_ASSERT(!memcmp(&fpu.fprs, regs_null, sizeof(fpu.fprs)), "fprs == 0"); + + /* sync regs */ + TEST_ASSERT(!memcmp(sync_regs->gprs, regs_null, sizeof(sync_regs->gprs)), + "gprs0-15 == 0 (sync_regs)"); + + TEST_ASSERT(!memcmp(sync_regs->acrs, regs_null, sizeof(sync_regs->acrs)), + "acrs0-15 == 0 (sync_regs)"); + + TEST_ASSERT(!memcmp(sync_regs->vrs, regs_null, sizeof(sync_regs->vrs)), + "vrs0-15 == 0 (sync_regs)"); +} + +static void assert_initial_noclear(void) +{ + TEST_ASSERT(sync_regs->gprs[0] == 0xffff000000000000UL, + "gpr0 == 0xffff000000000000 (sync_regs)"); + TEST_ASSERT(sync_regs->gprs[1] == 0x0000555500000000UL, + "gpr1 == 0x0000555500000000 (sync_regs)"); + TEST_ASSERT(sync_regs->gprs[2] == 0x00000000aaaa0000UL, + "gpr2 == 0x00000000aaaa0000 (sync_regs)"); + TEST_ASSERT(sync_regs->gprs[3] == 0x0000000000000000UL, + "gpr3 == 0x0000000000000000 (sync_regs)"); + TEST_ASSERT(sync_regs->fprs[0] == 0x3ff0000000000000UL, + "fpr0 == 0f1 (sync_regs)"); + TEST_ASSERT(sync_regs->acrs[9] == 1, "ar9 == 1 (sync_regs)"); } static void assert_initial(void) @@ -94,12 +132,32 @@ static void assert_initial(void) struct kvm_sregs sregs; struct kvm_fpu fpu; + /* KVM_GET_SREGS */ vcpu_sregs_get(vm, VCPU_ID, &sregs); - TEST_ASSERT(sregs.crs[0] == 0xE0UL, "cr0 == 0xE0"); - TEST_ASSERT(sregs.crs[14] == 0xC2000000UL, "cr14 == 0xC2000000"); + TEST_ASSERT(sregs.crs[0] == 0xE0UL, "cr0 == 0xE0 (KVM_GET_SREGS)"); + TEST_ASSERT(sregs.crs[14] == 0xC2000000UL, + "cr14 == 0xC2000000 (KVM_GET_SREGS)"); TEST_ASSERT(!memcmp(&sregs.crs[1], regs_null, sizeof(sregs.crs[1]) * 12), - "cr1-13 == 0"); - TEST_ASSERT(sregs.crs[15] == 0, "cr15 == 0"); + "cr1-13 == 0 (KVM_GET_SREGS)"); + TEST_ASSERT(sregs.crs[15] == 0, "cr15 == 0 (KVM_GET_SREGS)"); + + /* sync regs */ + TEST_ASSERT(sync_regs->crs[0] == 0xE0UL, "cr0 == 0xE0 (sync_regs)"); + TEST_ASSERT(sync_regs->crs[14] == 0xC2000000UL, + "cr14 == 0xC2000000 (sync_regs)"); + TEST_ASSERT(!memcmp(&sync_regs->crs[1], regs_null, 8 * 12), + "cr1-13 == 0 (sync_regs)"); + TEST_ASSERT(sync_regs->crs[15] == 0, "cr15 == 0 (sync_regs)"); + TEST_ASSERT(sync_regs->fpc == 0, "fpc == 0 (sync_regs)"); + TEST_ASSERT(sync_regs->todpr == 0, "todpr == 0 (sync_regs)"); + TEST_ASSERT(sync_regs->cputm == 0, "cputm == 0 (sync_regs)"); + TEST_ASSERT(sync_regs->ckc == 0, "ckc == 0 (sync_regs)"); + TEST_ASSERT(sync_regs->pp == 0, "pp == 0 (sync_regs)"); + TEST_ASSERT(sync_regs->gbea == 1, "gbea == 1 (sync_regs)"); + + /* kvm_run */ + TEST_ASSERT(run->psw_addr == 0, "psw_addr == 0 (kvm_run)"); + TEST_ASSERT(run->psw_mask == 0, "psw_mask == 0 (kvm_run)"); vcpu_fpu_get(vm, VCPU_ID, &fpu); TEST_ASSERT(!fpu.fpc, "fpc == 0"); @@ -111,9 +169,19 @@ static void assert_initial(void) test_one_reg(KVM_REG_S390_CLOCK_COMP, 0); } +static void assert_normal_noclear(void) +{ + TEST_ASSERT(sync_regs->crs[2] == 0x10, "cr2 == 10 (sync_regs)"); + TEST_ASSERT(sync_regs->crs[8] == 1, "cr10 == 1 (sync_regs)"); + TEST_ASSERT(sync_regs->crs[10] == 1, "cr10 == 1 (sync_regs)"); + TEST_ASSERT(sync_regs->crs[11] == -1, "cr11 == -1 (sync_regs)"); +} + static void assert_normal(void) { test_one_reg(KVM_REG_S390_PFTOKEN, KVM_S390_PFAULT_TOKEN_INVALID); + TEST_ASSERT(sync_regs->pft == KVM_S390_PFAULT_TOKEN_INVALID, + "pft == 0xff..... (sync_regs)"); assert_noirq(); } @@ -134,53 +202,67 @@ static void inject_irq(int cpu_id) static void test_normal(void) { - printf("Testing normal reset\n"); + pr_info("Testing normal reset\n"); /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code_initial); run = vcpu_state(vm, VCPU_ID); - regs = &run->s.regs; + sync_regs = &run->s.regs; vcpu_run(vm, VCPU_ID); inject_irq(VCPU_ID); vcpu_ioctl(vm, VCPU_ID, KVM_S390_NORMAL_RESET, 0); + + /* must clears */ assert_normal(); + /* must not clears */ + assert_normal_noclear(); + assert_initial_noclear(); + kvm_vm_free(vm); } static void test_initial(void) { - printf("Testing initial reset\n"); + pr_info("Testing initial reset\n"); vm = vm_create_default(VCPU_ID, 0, guest_code_initial); run = vcpu_state(vm, VCPU_ID); - regs = &run->s.regs; + sync_regs = &run->s.regs; vcpu_run(vm, VCPU_ID); inject_irq(VCPU_ID); vcpu_ioctl(vm, VCPU_ID, KVM_S390_INITIAL_RESET, 0); + + /* must clears */ assert_normal(); assert_initial(); + /* must not clears */ + assert_initial_noclear(); + kvm_vm_free(vm); } static void test_clear(void) { - printf("Testing clear reset\n"); + pr_info("Testing clear reset\n"); vm = vm_create_default(VCPU_ID, 0, guest_code_initial); run = vcpu_state(vm, VCPU_ID); - regs = &run->s.regs; + sync_regs = &run->s.regs; vcpu_run(vm, VCPU_ID); inject_irq(VCPU_ID); vcpu_ioctl(vm, VCPU_ID, KVM_S390_CLEAR_RESET, 0); + + /* must clears */ assert_normal(); assert_initial(); assert_clear(); + kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c index b705637ca14b..5731ccf34917 100644 --- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c +++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c @@ -42,6 +42,13 @@ static void guest_code(void) " values did not match: 0x%llx, 0x%llx\n", \ left->reg, right->reg) +#define REG_COMPARE32(reg) \ + TEST_ASSERT(left->reg == right->reg, \ + "Register " #reg \ + " values did not match: 0x%x, 0x%x\n", \ + left->reg, right->reg) + + static void compare_regs(struct kvm_regs *left, struct kvm_sync_regs *right) { int i; @@ -55,7 +62,7 @@ static void compare_sregs(struct kvm_sregs *left, struct kvm_sync_regs *right) int i; for (i = 0; i < 16; i++) - REG_COMPARE(acrs[i]); + REG_COMPARE32(acrs[i]); for (i = 0; i < 16; i++) REG_COMPARE(crs[i]); @@ -79,7 +86,7 @@ int main(int argc, char *argv[]) cap = kvm_check_cap(KVM_CAP_SYNC_REGS); if (!cap) { - fprintf(stderr, "CAP_SYNC_REGS not supported, skipping test\n"); + print_skip("CAP_SYNC_REGS not supported"); exit(KSFT_SKIP); } @@ -155,7 +162,7 @@ int main(int argc, char *argv[]) "r11 sync regs value incorrect 0x%llx.", run->s.regs.gprs[11]); TEST_ASSERT(run->s.regs.acrs[0] == 1 << 11, - "acr0 sync regs value incorrect 0x%llx.", + "acr0 sync regs value incorrect 0x%x.", run->s.regs.acrs[0]); vcpu_regs_get(vm, VCPU_ID, ®s); diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c new file mode 100644 index 000000000000..fcc840088c91 --- /dev/null +++ b/tools/testing/selftests/kvm/steal_time.c @@ -0,0 +1,352 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * steal/stolen time test + * + * Copyright (C) 2020, Red Hat, Inc. + */ +#define _GNU_SOURCE +#include <stdio.h> +#include <time.h> +#include <sched.h> +#include <pthread.h> +#include <linux/kernel.h> +#include <sys/syscall.h> +#include <asm/kvm.h> +#include <asm/kvm_para.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +#define NR_VCPUS 4 +#define ST_GPA_BASE (1 << 30) +#define MIN_RUN_DELAY_NS 200000UL + +static void *st_gva[NR_VCPUS]; +static uint64_t guest_stolen_time[NR_VCPUS]; + +#if defined(__x86_64__) + +/* steal_time must have 64-byte alignment */ +#define STEAL_TIME_SIZE ((sizeof(struct kvm_steal_time) + 63) & ~63) + +static void check_status(struct kvm_steal_time *st) +{ + GUEST_ASSERT(!(READ_ONCE(st->version) & 1)); + GUEST_ASSERT(READ_ONCE(st->flags) == 0); + GUEST_ASSERT(READ_ONCE(st->preempted) == 0); +} + +static void guest_code(int cpu) +{ + struct kvm_steal_time *st = st_gva[cpu]; + uint32_t version; + + GUEST_ASSERT(rdmsr(MSR_KVM_STEAL_TIME) == ((uint64_t)st_gva[cpu] | KVM_MSR_ENABLED)); + + memset(st, 0, sizeof(*st)); + GUEST_SYNC(0); + + check_status(st); + WRITE_ONCE(guest_stolen_time[cpu], st->steal); + version = READ_ONCE(st->version); + check_status(st); + GUEST_SYNC(1); + + check_status(st); + GUEST_ASSERT(version < READ_ONCE(st->version)); + WRITE_ONCE(guest_stolen_time[cpu], st->steal); + check_status(st); + GUEST_DONE(); +} + +static void steal_time_init(struct kvm_vm *vm) +{ + int i; + + if (!(kvm_get_supported_cpuid_entry(KVM_CPUID_FEATURES)->eax & + KVM_FEATURE_STEAL_TIME)) { + print_skip("steal-time not supported"); + exit(KSFT_SKIP); + } + + 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]); + + ret = _vcpu_set_msr(vm, i, MSR_KVM_STEAL_TIME, (ulong)st_gva[i] | KVM_STEAL_RESERVED_MASK); + TEST_ASSERT(ret == 0, "Bad GPA didn't fail"); + + vcpu_set_msr(vm, i, MSR_KVM_STEAL_TIME, (ulong)st_gva[i] | KVM_MSR_ENABLED); + } +} + +static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_steal_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpuid]); + int i; + + pr_info("VCPU%d:\n", vcpuid); + pr_info(" steal: %lld\n", st->steal); + pr_info(" version: %d\n", st->version); + pr_info(" flags: %d\n", st->flags); + pr_info(" preempted: %d\n", st->preempted); + pr_info(" u8_pad: "); + for (i = 0; i < 3; ++i) + pr_info("%d", st->u8_pad[i]); + pr_info("\n pad: "); + for (i = 0; i < 11; ++i) + pr_info("%d", st->pad[i]); + pr_info("\n"); +} + +#elif defined(__aarch64__) + +/* PV_TIME_ST must have 64-byte alignment */ +#define STEAL_TIME_SIZE ((sizeof(struct st_time) + 63) & ~63) + +#define SMCCC_ARCH_FEATURES 0x80000001 +#define PV_TIME_FEATURES 0xc5000020 +#define PV_TIME_ST 0xc5000021 + +struct st_time { + uint32_t rev; + uint32_t attr; + uint64_t st_time; +}; + +static int64_t smccc(uint32_t func, uint32_t arg) +{ + unsigned long ret; + + asm volatile( + "mov x0, %1\n" + "mov x1, %2\n" + "hvc #0\n" + "mov %0, x0\n" + : "=r" (ret) : "r" (func), "r" (arg) : + "x0", "x1", "x2", "x3"); + + return ret; +} + +static void check_status(struct st_time *st) +{ + GUEST_ASSERT(READ_ONCE(st->rev) == 0); + GUEST_ASSERT(READ_ONCE(st->attr) == 0); +} + +static void guest_code(int cpu) +{ + struct st_time *st; + int64_t status; + + status = smccc(SMCCC_ARCH_FEATURES, PV_TIME_FEATURES); + GUEST_ASSERT(status == 0); + status = smccc(PV_TIME_FEATURES, PV_TIME_FEATURES); + GUEST_ASSERT(status == 0); + status = smccc(PV_TIME_FEATURES, PV_TIME_ST); + GUEST_ASSERT(status == 0); + + status = smccc(PV_TIME_ST, 0); + GUEST_ASSERT(status != -1); + GUEST_ASSERT(status == (ulong)st_gva[cpu]); + + st = (struct st_time *)status; + GUEST_SYNC(0); + + check_status(st); + WRITE_ONCE(guest_stolen_time[cpu], st->st_time); + GUEST_SYNC(1); + + check_status(st); + WRITE_ONCE(guest_stolen_time[cpu], st->st_time); + GUEST_DONE(); +} + +static void steal_time_init(struct kvm_vm *vm) +{ + struct kvm_device_attr dev = { + .group = KVM_ARM_VCPU_PVTIME_CTRL, + .attr = KVM_ARM_VCPU_PVTIME_IPA, + }; + int i, ret; + + ret = _vcpu_ioctl(vm, 0, KVM_HAS_DEVICE_ATTR, &dev); + if (ret != 0 && errno == ENXIO) { + print_skip("steal-time not supported"); + exit(KSFT_SKIP); + } + + for (i = 0; i < NR_VCPUS; ++i) { + uint64_t st_ipa; + + vcpu_ioctl(vm, i, KVM_HAS_DEVICE_ATTR, &dev); + + dev.addr = (uint64_t)&st_ipa; + + /* 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]); + + st_ipa = (ulong)st_gva[i] | 1; + ret = _vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev); + TEST_ASSERT(ret == -1 && errno == EINVAL, "Bad IPA didn't report EINVAL"); + + st_ipa = (ulong)st_gva[i]; + vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev); + + ret = _vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev); + TEST_ASSERT(ret == -1 && errno == EEXIST, "Set IPA twice without EEXIST"); + + } +} + +static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct st_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpuid]); + + pr_info("VCPU%d:\n", vcpuid); + pr_info(" rev: %d\n", st->rev); + pr_info(" attr: %d\n", st->attr); + pr_info(" st_time: %ld\n", st->st_time); +} + +#endif + +static long get_run_delay(void) +{ + char path[64]; + long val[2]; + FILE *fp; + + sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); + fp = fopen(path, "r"); + fscanf(fp, "%ld %ld ", &val[0], &val[1]); + fclose(fp); + + return val[1]; +} + +static void *do_steal_time(void *arg) +{ + struct timespec ts, stop; + + clock_gettime(CLOCK_MONOTONIC, &ts); + stop = timespec_add_ns(ts, MIN_RUN_DELAY_NS); + + while (1) { + clock_gettime(CLOCK_MONOTONIC, &ts); + if (timespec_to_ns(timespec_sub(ts, stop)) >= 0) + break; + } + + return NULL; +} + +static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct ucall uc; + + vcpu_args_set(vm, vcpuid, 1, vcpuid); + + vcpu_ioctl(vm, vcpuid, KVM_RUN, NULL); + + switch (get_ucall(vm, vcpuid, &uc)) { + case UCALL_SYNC: + case UCALL_DONE: + break; + case UCALL_ABORT: + TEST_ASSERT(false, "%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); + default: + TEST_ASSERT(false, "Unexpected exit: %s", + exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason)); + } +} + +int main(int ac, char **av) +{ + struct kvm_vm *vm; + pthread_attr_t attr; + pthread_t thread; + cpu_set_t cpuset; + unsigned int gpages; + long stolen_time; + long run_delay; + bool verbose; + int i; + + verbose = ac > 1 && (!strncmp(av[1], "-v", 3) || !strncmp(av[1], "--verbose", 10)); + + /* Set CPU affinity so we can force preemption of the VCPU */ + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + pthread_attr_init(&attr); + pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset); + pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset); + + /* Create a one VCPU guest and an identity mapped memslot for the steal time structure */ + 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); + ucall_init(vm, NULL); + + /* Add the rest of the VCPUs */ + for (i = 1; i < NR_VCPUS; ++i) + vm_vcpu_add_default(vm, i, guest_code); + + steal_time_init(vm); + + /* Run test on each VCPU */ + for (i = 0; i < NR_VCPUS; ++i) { + /* First VCPU run initializes steal-time */ + run_vcpu(vm, i); + + /* Second VCPU run, expect guest stolen time to be <= run_delay */ + run_vcpu(vm, i); + sync_global_from_guest(vm, guest_stolen_time[i]); + stolen_time = guest_stolen_time[i]; + run_delay = get_run_delay(); + TEST_ASSERT(stolen_time <= run_delay, + "Expected stolen time <= %ld, got %ld", + run_delay, stolen_time); + + /* Steal time from the VCPU. The steal time thread has the same CPU affinity as the VCPUs. */ + run_delay = get_run_delay(); + pthread_create(&thread, &attr, do_steal_time, NULL); + do + pthread_yield(); + while (get_run_delay() - run_delay < MIN_RUN_DELAY_NS); + pthread_join(thread, NULL); + run_delay = get_run_delay() - run_delay; + TEST_ASSERT(run_delay >= MIN_RUN_DELAY_NS, + "Expected run_delay >= %ld, got %ld", + MIN_RUN_DELAY_NS, run_delay); + + /* Run VCPU again to confirm stolen time is consistent with run_delay */ + run_vcpu(vm, i); + sync_global_from_guest(vm, guest_stolen_time[i]); + stolen_time = guest_stolen_time[i] - stolen_time; + TEST_ASSERT(stolen_time >= run_delay, + "Expected stolen time >= %ld, got %ld", + run_delay, stolen_time); + + if (verbose) { + pr_info("VCPU%d: total-stolen-time=%ld test-stolen-time=%ld", i, + guest_stolen_time[i], stolen_time); + if (stolen_time == run_delay) + pr_info(" (BONUS: guest test-stolen-time even exactly matches test-run_delay)"); + pr_info("\n"); + steal_time_dump(vm, i); + } + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index 63cc9c3f5ab6..140e91901582 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -72,7 +72,7 @@ int main(int argc, char *argv[]) entry = kvm_get_supported_cpuid_entry(1); if (!(entry->ecx & X86_FEATURE_XSAVE)) { - printf("XSAVE feature not supported, skipping test\n"); + print_skip("XSAVE feature not supported"); return 0; } @@ -101,12 +101,12 @@ int main(int argc, char *argv[]) vcpu_sregs_set(vm, VCPU_ID, &sregs); break; case UCALL_ABORT: - TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); + TEST_FAIL("Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); break; case UCALL_DONE: goto done; default: - TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + TEST_FAIL("Unknown ucall %lu", uc.cmd); } } diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index 92915e6408e7..e6e62e5e75b2 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -21,10 +21,10 @@ void l2_guest_code(void) { - GUEST_SYNC(6); - GUEST_SYNC(7); + GUEST_SYNC(8); + /* Done, exit to L1 and never come back. */ vmcall(); } @@ -50,12 +50,17 @@ void l1_guest_code(struct vmx_pages *vmx_pages) GUEST_SYNC(5); GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); + current_evmcs->revision_id = -1u; + GUEST_ASSERT(vmlaunch()); + current_evmcs->revision_id = EVMCS_VERSION; + GUEST_SYNC(6); + GUEST_ASSERT(!vmlaunch()); GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); - GUEST_SYNC(8); + GUEST_SYNC(9); GUEST_ASSERT(!vmresume()); GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); - GUEST_SYNC(9); + GUEST_SYNC(10); } void guest_code(struct vmx_pages *vmx_pages) @@ -67,6 +72,10 @@ void guest_code(struct vmx_pages *vmx_pages) l1_guest_code(vmx_pages); GUEST_DONE(); + + /* Try enlightened vmptrld with an incorrect GPA */ + evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs); + GUEST_ASSERT(vmlaunch()); } int main(int argc, char *argv[]) @@ -87,7 +96,7 @@ int main(int argc, char *argv[]) if (!kvm_check_cap(KVM_CAP_NESTED_STATE) || !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { - printf("capabilities not available, skipping test\n"); + print_skip("capabilities not available"); exit(KSFT_SKIP); } @@ -109,20 +118,20 @@ int main(int argc, char *argv[]) switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: - TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], - __FILE__, uc.args[1]); + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); /* NOT REACHED */ case UCALL_SYNC: break; case UCALL_DONE: - goto done; + goto part1_done; default: - TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + TEST_FAIL("Unknown ucall %lu", uc.cmd); } /* UCALL_SYNC is handled here. */ TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && - uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx", + uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx", stage, (ulong)uc.args[1]); state = vcpu_save_state(vm, VCPU_ID); @@ -147,6 +156,10 @@ int main(int argc, char *argv[]) (ulong) regs2.rdi, (ulong) regs2.rsi); } -done: +part1_done: + _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, + "Unexpected successful VMEnter with invalid eVMCS pointer!"); + kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index 443a2b54645b..83323f3d7ca0 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -66,7 +66,7 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, TEST_ASSERT((entry->function >= 0x40000000) && (entry->function <= 0x4000000A), - "function %lx is our of supported range", + "function %x is our of supported range", entry->function); TEST_ASSERT(entry->index == 0, @@ -141,8 +141,7 @@ int main(int argc, char *argv[]) rv = kvm_check_cap(KVM_CAP_HYPERV_CPUID); if (!rv) { - fprintf(stderr, - "KVM_CAP_HYPERV_CPUID not supported, skip test\n"); + print_skip("KVM_CAP_HYPERV_CPUID not supported"); exit(KSFT_SKIP); } @@ -160,8 +159,7 @@ int main(int argc, char *argv[]) free(hv_cpuid_entries); if (!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { - fprintf(stderr, - "Enlightened VMCS is unsupported, skip related test\n"); + print_skip("Enlightened VMCS is unsupported"); goto vm_free; } diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c index 00bb97d76000..e6480fd5c4bd 100644 --- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c +++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c @@ -44,7 +44,7 @@ void *thr(void *arg) struct kvm_run *run = tc->run; res = ioctl(kvmcpu, KVM_RUN, 0); - printf("ret1=%d exit_reason=%d suberror=%d\n", + pr_info("ret1=%d exit_reason=%d suberror=%d\n", res, run->exit_reason, run->internal.suberror); return 0; @@ -93,12 +93,12 @@ int main(void) int warnings_before, warnings_after; if (!is_intel_cpu()) { - printf("Must be run on an Intel CPU, skipping test\n"); + print_skip("Must be run on an Intel CPU"); exit(KSFT_SKIP); } if (vm_is_unrestricted_guest(NULL)) { - printf("Unrestricted guest must be disabled, skipping test\n"); + print_skip("Unrestricted guest must be disabled"); exit(KSFT_SKIP); } diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c index f9334bd3cce9..1e89688cbbbf 100644 --- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c @@ -58,8 +58,7 @@ static void test_msr_platform_info_enabled(struct kvm_vm *vm) exit_reason_str(run->exit_reason)); get_ucall(vm, VCPU_ID, &uc); TEST_ASSERT(uc.cmd == UCALL_SYNC, - "Received ucall other than UCALL_SYNC: %u\n", - ucall); + "Received ucall other than UCALL_SYNC: %lu\n", uc.cmd); TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) == MSR_PLATFORM_INFO_MAX_TURBO_RATIO, "Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.", @@ -89,8 +88,7 @@ int main(int argc, char *argv[]) rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO); if (!rv) { - fprintf(stderr, - "KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n"); + print_skip("KVM_CAP_MSR_PLATFORM_INFO not supported"); exit(KSFT_SKIP); } diff --git a/tools/testing/selftests/kvm/x86_64/set_memory_region_test.c b/tools/testing/selftests/kvm/x86_64/set_memory_region_test.c new file mode 100644 index 000000000000..c6691cff4e19 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/set_memory_region_test.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <pthread.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include <linux/compiler.h> + +#include <test_util.h> +#include <kvm_util.h> +#include <processor.h> + +#define VCPU_ID 0 + +/* + * Somewhat arbitrary location and slot, intended to not overlap anything. The + * location and size are specifically 2mb sized/aligned so that the initial + * region corresponds to exactly one large page. + */ +#define MEM_REGION_GPA 0xc0000000 +#define MEM_REGION_SIZE 0x200000 +#define MEM_REGION_SLOT 10 + +static void guest_code(void) +{ + uint64_t val; + + do { + val = READ_ONCE(*((uint64_t *)MEM_REGION_GPA)); + } while (!val); + + if (val != 1) + ucall(UCALL_ABORT, 1, val); + + GUEST_DONE(); +} + +static void *vcpu_worker(void *data) +{ + struct kvm_vm *vm = data; + struct kvm_run *run; + struct ucall uc; + uint64_t cmd; + + /* + * Loop until the guest is done. Re-enter the guest on all MMIO exits, + * which will occur if the guest attempts to access a memslot while it + * is being moved. + */ + run = vcpu_state(vm, VCPU_ID); + do { + vcpu_run(vm, VCPU_ID); + } while (run->exit_reason == KVM_EXIT_MMIO); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason = %d", run->exit_reason); + + cmd = get_ucall(vm, VCPU_ID, &uc); + TEST_ASSERT(cmd == UCALL_DONE, "Unexpected val in guest = %lu", uc.args[0]); + return NULL; +} + +static void test_move_memory_region(void) +{ + pthread_t vcpu_thread; + struct kvm_vm *vm; + uint64_t *hva; + uint64_t gpa; + + vm = vm_create_default(VCPU_ID, 0, guest_code); + + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_THP, + MEM_REGION_GPA, MEM_REGION_SLOT, + MEM_REGION_SIZE / getpagesize(), 0); + + /* + * Allocate and map two pages so that the GPA accessed by guest_code() + * stays valid across the memslot move. + */ + 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); + + /* Ditto for the host mapping so that both pages can be zeroed. */ + hva = addr_gpa2hva(vm, MEM_REGION_GPA); + memset(hva, 0, 2 * 4096); + + pthread_create(&vcpu_thread, NULL, vcpu_worker, vm); + + /* Ensure the guest thread is spun up. */ + usleep(100000); + + /* + * Shift the region's base GPA. The guest should not see "2" as the + * hva->gpa translation is misaligned, i.e. the guest is accessing a + * different host pfn. + */ + vm_mem_region_move(vm, MEM_REGION_SLOT, MEM_REGION_GPA - 4096); + WRITE_ONCE(*hva, 2); + + usleep(100000); + + /* + * Note, value in memory needs to be changed *before* restoring the + * memslot, else the guest could race the update and see "2". + */ + WRITE_ONCE(*hva, 1); + + /* Restore the original base, the guest should see "1". */ + vm_mem_region_move(vm, MEM_REGION_SLOT, MEM_REGION_GPA); + + pthread_join(vcpu_thread, NULL); + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + int i, loops; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + if (argc > 1) + loops = atoi(argv[1]); + else + loops = 10; + + for (i = 0; i < loops; i++) + test_move_memory_region(); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index 8c063646f2a0..8230b6bc6b8f 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -117,7 +117,7 @@ int main(int argc, char *argv[]) vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); } else { - printf("will skip SMM test with VMX enabled\n"); + pr_info("will skip SMM test with VMX enabled\n"); vcpu_args_set(vm, VCPU_ID, 1, 0); } diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 3ab5ec3da9f4..5b1a016edf55 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -139,7 +139,7 @@ int main(int argc, char *argv[]) vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); } else { - printf("will skip nested state checks\n"); + pr_info("will skip nested state checks\n"); vcpu_args_set(vm, VCPU_ID, 1, 0); } @@ -152,20 +152,20 @@ int main(int argc, char *argv[]) switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: - TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], - __FILE__, uc.args[1]); + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); /* NOT REACHED */ case UCALL_SYNC: break; case UCALL_DONE: goto done; default: - TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + TEST_FAIL("Unknown ucall %lu", uc.cmd); } /* UCALL_SYNC is handled here. */ TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && - uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx", + uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx", stage, (ulong)uc.args[1]); state = vcpu_save_state(vm, VCPU_ID); diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c index e280f68f6365..0e1adb4e3199 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c @@ -61,16 +61,14 @@ int main(int argc, char *argv[]) switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: - TEST_ASSERT(false, "%s", - (const char *)uc.args[0]); + TEST_FAIL("%s", (const char *)uc.args[0]); /* NOT REACHED */ case UCALL_SYNC: break; case UCALL_DONE: goto done; default: - TEST_ASSERT(false, - "Unknown ucall 0x%x.", uc.cmd); + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); } } done: diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c index 5c8224256294..d672f0a473f8 100644 --- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c @@ -91,11 +91,11 @@ int main(int argc, char *argv[]) cap = kvm_check_cap(KVM_CAP_SYNC_REGS); if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) { - fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n"); + print_skip("KVM_CAP_SYNC_REGS not supported"); exit(KSFT_SKIP); } if ((cap & INVALID_SYNC_FIELD) != 0) { - fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n"); + print_skip("The \"invalid\" field is not invalid"); exit(KSFT_SKIP); } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c index 5dfb53546a26..fe40ade06a49 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c @@ -78,10 +78,10 @@ int main(int argc, char *argv[]) switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: - TEST_ASSERT(false, "%s", (const char *)uc.args[0]); + TEST_FAIL("%s", (const char *)uc.args[0]); /* NOT REACHED */ default: - TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + TEST_FAIL("Unknown ucall %lu", uc.cmd); } } } 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 a223a6401258..e894a638a155 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 @@ -21,7 +21,7 @@ /* The memory slot index to track dirty pages */ #define TEST_MEM_SLOT_INDEX 1 -#define TEST_MEM_SIZE 3 +#define TEST_MEM_PAGES 3 /* L1 guest test virtual memory offset */ #define GUEST_TEST_MEM 0xc0000000 @@ -91,15 +91,14 @@ int main(int argc, char *argv[]) vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, GUEST_TEST_MEM, TEST_MEM_SLOT_INDEX, - TEST_MEM_SIZE, + TEST_MEM_PAGES, KVM_MEM_LOG_DIRTY_PAGES); /* * 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_SIZE * 4096, 0); + virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM, TEST_MEM_PAGES, 0); /* * ... pages in the L2 GPA range [0xc0001000, 0xc0003000) will map to @@ -113,11 +112,11 @@ int main(int argc, char *argv[]) nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096, 0); nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096, 0); - bmap = bitmap_alloc(TEST_MEM_SIZE); + bmap = bitmap_alloc(TEST_MEM_PAGES); host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM); while (!done) { - memset(host_test_mem, 0xaa, TEST_MEM_SIZE * 4096); + memset(host_test_mem, 0xaa, TEST_MEM_PAGES * 4096); _vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", @@ -126,8 +125,8 @@ int main(int argc, char *argv[]) switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: - TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], - __FILE__, uc.args[1]); + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); /* NOT REACHED */ case UCALL_SYNC: /* @@ -152,7 +151,7 @@ int main(int argc, char *argv[]) done = true; break; default: - TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + TEST_FAIL("Unknown ucall %lu", uc.cmd); } } } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index 9ef7fab39d48..54cdefdfb49d 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -212,7 +212,7 @@ void test_vmx_nested_state(struct kvm_vm *vm) test_nested_state(vm, state); vcpu_nested_state_get(vm, VCPU_ID, state); TEST_ASSERT(state->size >= sizeof(*state) && state->size <= state_sz, - "Size must be between %d and %d. The size returned was %d.", + "Size must be between %ld and %d. The size returned was %d.", sizeof(*state), state_sz, state->size); TEST_ASSERT(state->hdr.vmx.vmxon_pa == -1ull, "vmxon_pa must be -1ull."); TEST_ASSERT(state->hdr.vmx.vmcs12_pa == -1ull, "vmcs_pa must be -1ull."); @@ -228,7 +228,7 @@ int main(int argc, char *argv[]) have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS); if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) { - printf("KVM_CAP_NESTED_STATE not available, skipping test\n"); + print_skip("KVM_CAP_NESTED_STATE not available"); exit(KSFT_SKIP); } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index 69e482a95c47..fbe8417cbc2c 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -121,8 +121,8 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) static void report(int64_t val) { - printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n", - val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE); + pr_info("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n", + val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE); } int main(int argc, char *argv[]) @@ -150,7 +150,7 @@ int main(int argc, char *argv[]) switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: - TEST_ASSERT(false, "%s", (const char *)uc.args[0]); + TEST_FAIL("%s", (const char *)uc.args[0]); /* NOT REACHED */ case UCALL_SYNC: report(uc.args[1]); @@ -158,7 +158,7 @@ int main(int argc, char *argv[]) case UCALL_DONE: goto done; default: - TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + TEST_FAIL("Unknown ucall %lu", uc.cmd); } } diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c index 851ea81b9d9f..3529376747c2 100644 --- a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c +++ b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c @@ -51,7 +51,7 @@ int main(int argc, char *argv[]) xss_supported = entry && !!(entry->eax & X86_FEATURE_XSAVES); } if (!xss_supported) { - printf("IA32_XSS is not supported by the vCPU.\n"); + print_skip("IA32_XSS is not supported by the vCPU"); exit(KSFT_SKIP); } diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 0d9438e9de2a..93bd59b46848 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -788,7 +788,7 @@ u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid) vcpu_ptimer(vcpu), TIMER_REG_CTL); case KVM_REG_ARM_PTIMER_CNT: return kvm_arm_timer_read(vcpu, - vcpu_vtimer(vcpu), TIMER_REG_CNT); + vcpu_ptimer(vcpu), TIMER_REG_CNT); case KVM_REG_ARM_PTIMER_CVAL: return kvm_arm_timer_read(vcpu, vcpu_ptimer(vcpu), TIMER_REG_CVAL); diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index eda7b624eab8..48d0ec44ad77 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -64,12 +64,12 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } -int kvm_arch_hardware_setup(void) +int kvm_arch_hardware_setup(void *opaque) { return 0; } -int kvm_arch_check_processor_compat(void) +int kvm_arch_check_processor_compat(void *opaque) { return 0; } @@ -625,6 +625,14 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu)) kvm_update_stolen_time(vcpu); + + if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) { + /* The distributor enable bits were changed */ + preempt_disable(); + vgic_v4_put(vcpu, false); + vgic_v4_load(vcpu); + preempt_enable(); + } } } @@ -1181,55 +1189,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, return r; } -/** - * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot - * @kvm: kvm instance - * @log: slot id and address to which we copy the log - * - * Steps 1-4 below provide general overview of dirty page logging. See - * kvm_get_dirty_log_protect() function description for additional details. - * - * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we - * always flush the TLB (step 4) even if previous step failed and the dirty - * bitmap may be corrupt. Regardless of previous outcome the KVM logging API - * does not preclude user space subsequent dirty log read. Flushing TLB ensures - * writes will be marked dirty for next log read. - * - * 1. Take a snapshot of the bit and clear it if needed. - * 2. Write protect the corresponding page. - * 3. Copy the snapshot to the userspace. - * 4. Flush TLB's if needed. - */ -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { - bool flush = false; - int r; - - mutex_lock(&kvm->slots_lock); - r = kvm_get_dirty_log_protect(kvm, log, &flush); - - if (flush) - kvm_flush_remote_tlbs(kvm); - - mutex_unlock(&kvm->slots_lock); - return r; } -int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) +void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) { - bool flush = false; - int r; - - mutex_lock(&kvm->slots_lock); - - r = kvm_clear_dirty_log_protect(kvm, log, &flush); - - if (flush) - kvm_flush_remote_tlbs(kvm); - - mutex_unlock(&kvm->slots_lock); - return r; + kvm_flush_remote_tlbs(kvm); } static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 19c961ac4e3c..e3b9ee268823 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1534,8 +1534,13 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot) { struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *memslot = id_to_memslot(slots, slot); - phys_addr_t start = memslot->base_gfn << PAGE_SHIFT; - phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; + phys_addr_t start, end; + + if (WARN_ON_ONCE(!memslot)) + return; + + start = memslot->base_gfn << PAGE_SHIFT; + end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; spin_lock(&kvm->mmu_lock); stage2_wp_range(kvm, start, end); @@ -2251,7 +2256,7 @@ out: void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { @@ -2349,17 +2354,10 @@ out: return ret; } -void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { } -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) -{ - return 0; -} - void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { } diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index 17e2bdd4b76f..14a162e295a9 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -12,7 +12,6 @@ #include <asm/cputype.h> #include <asm/kvm_emulate.h> -#include <asm/kvm_host.h> #include <kvm/arm_psci.h> #include <kvm/arm_hypercalls.h> diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c index cc12fe9b2df3..b13a9e3f99dd 100644 --- a/virt/kvm/arm/vgic/vgic-debug.c +++ b/virt/kvm/arm/vgic/vgic-debug.c @@ -178,6 +178,8 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, struct kvm_vcpu *vcpu) { char *type; + bool pending; + if (irq->intid < VGIC_NR_SGIS) type = "SGI"; else if (irq->intid < VGIC_NR_PRIVATE_IRQS) @@ -190,6 +192,16 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, if (irq->intid ==0 || irq->intid == VGIC_NR_PRIVATE_IRQS) print_header(s, irq, vcpu); + pending = irq->pending_latch; + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + int err; + + err = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &pending); + WARN_ON_ONCE(err); + } + seq_printf(s, " %s %4d " " %2d " "%d%d%d%d%d%d%d " @@ -201,7 +213,7 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, "\n", type, irq->intid, (irq->target_vcpu) ? irq->target_vcpu->vcpu_id : -1, - irq->pending_latch, + pending, irq->line_level, irq->active, irq->enabled, diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index ebc218840fc2..e72dcc454247 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -3,9 +3,11 @@ * VGICv3 MMIO handling functions */ +#include <linux/bitfield.h> #include <linux/irqchip/arm-gic-v3.h> #include <linux/kvm.h> #include <linux/kvm_host.h> +#include <linux/interrupt.h> #include <kvm/iodev.h> #include <kvm/arm_vgic.h> @@ -69,6 +71,8 @@ static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu, if (vgic->enabled) value |= GICD_CTLR_ENABLE_SS_G1; value |= GICD_CTLR_ARE_NS | GICD_CTLR_DS; + if (vgic->nassgireq) + value |= GICD_CTLR_nASSGIreq; break; case GICD_TYPER: value = vgic->nr_spis + VGIC_NR_PRIVATE_IRQS; @@ -80,6 +84,10 @@ static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu, value |= (INTERRUPT_ID_BITS_SPIS - 1) << 19; } break; + case GICD_TYPER2: + if (kvm_vgic_global_state.has_gicv4_1) + value = GICD_TYPER2_nASSGIcap; + break; case GICD_IIDR: value = (PRODUCT_ID_KVM << GICD_IIDR_PRODUCT_ID_SHIFT) | (vgic->implementation_rev << GICD_IIDR_REVISION_SHIFT) | @@ -97,17 +105,46 @@ static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu, unsigned long val) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - bool was_enabled = dist->enabled; switch (addr & 0x0c) { - case GICD_CTLR: + case GICD_CTLR: { + bool was_enabled, is_hwsgi; + + mutex_lock(&vcpu->kvm->lock); + + was_enabled = dist->enabled; + is_hwsgi = dist->nassgireq; + dist->enabled = val & GICD_CTLR_ENABLE_SS_G1; - if (!was_enabled && dist->enabled) + /* Not a GICv4.1? No HW SGIs */ + if (!kvm_vgic_global_state.has_gicv4_1) + val &= ~GICD_CTLR_nASSGIreq; + + /* Dist stays enabled? nASSGIreq is RO */ + if (was_enabled && dist->enabled) { + val &= ~GICD_CTLR_nASSGIreq; + val |= FIELD_PREP(GICD_CTLR_nASSGIreq, is_hwsgi); + } + + /* Switching HW SGIs? */ + dist->nassgireq = val & GICD_CTLR_nASSGIreq; + if (is_hwsgi != dist->nassgireq) + vgic_v4_configure_vsgis(vcpu->kvm); + + if (kvm_vgic_global_state.has_gicv4_1 && + was_enabled != dist->enabled) + kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_RELOAD_GICv4); + else if (!was_enabled && dist->enabled) vgic_kick_vcpus(vcpu->kvm); + + mutex_unlock(&vcpu->kvm->lock); break; + } case GICD_TYPER: + case GICD_TYPER2: case GICD_IIDR: + /* This is at best for documentation purposes... */ return; } } @@ -116,10 +153,22 @@ static int vgic_mmio_uaccess_write_v3_misc(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + switch (addr & 0x0c) { + case GICD_TYPER2: case GICD_IIDR: if (val != vgic_mmio_read_v3_misc(vcpu, addr, len)) return -EINVAL; + return 0; + case GICD_CTLR: + /* Not a GICv4.1? No HW SGIs */ + if (!kvm_vgic_global_state.has_gicv4_1) + val &= ~GICD_CTLR_nASSGIreq; + + dist->enabled = val & GICD_CTLR_ENABLE_SS_G1; + dist->nassgireq = val & GICD_CTLR_nASSGIreq; + return 0; } vgic_mmio_write_v3_misc(vcpu, addr, len, val); @@ -257,8 +306,18 @@ static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu, */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + bool state = irq->pending_latch; - if (irq->pending_latch) + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + int err; + + err = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &state); + WARN_ON(err); + } + + if (state) value |= (1U << i); vgic_put_irq(vcpu->kvm, irq); @@ -942,8 +1001,18 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) * generate interrupts of either group. */ if (!irq->group || allow_group1) { - irq->pending_latch = true; - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + if (!irq->hw) { + irq->pending_latch = true; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + } else { + /* HW SGI? Ask the GIC to inject it */ + int err; + err = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + true); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + } } else { raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 97fb2a40e6ba..2199302597fa 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -5,6 +5,8 @@ #include <linux/bitops.h> #include <linux/bsearch.h> +#include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/iodev.h> @@ -59,6 +61,11 @@ unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu, return value; } +static void vgic_update_vsgi(struct vgic_irq *irq) +{ + WARN_ON(its_prop_update_vsgi(irq->host_irq, irq->priority, irq->group)); +} + void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { @@ -71,7 +78,12 @@ void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->group = !!(val & BIT(i)); - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + vgic_update_vsgi(irq); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + } else { + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + } vgic_put_irq(vcpu->kvm, irq); } @@ -113,7 +125,21 @@ void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (vgic_irq_is_mapped_level(irq)) { + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + if (!irq->enabled) { + struct irq_data *data; + + irq->enabled = true; + data = &irq_to_desc(irq->host_irq)->irq_data; + while (irqd_irq_disabled(data)) + enable_irq(irq->host_irq); + } + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + continue; + } else if (vgic_irq_is_mapped_level(irq)) { bool was_high = irq->line_level; /* @@ -148,6 +174,8 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->hw && vgic_irq_is_sgi(irq->intid) && irq->enabled) + disable_irq_nosync(irq->host_irq); irq->enabled = false; @@ -167,10 +195,22 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); unsigned long flags; + bool val; raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (irq_is_pending(irq)) - value |= (1U << i); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + int err; + + val = false; + err = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &val); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + } else { + val = irq_is_pending(irq); + } + + value |= ((u32)val << i); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); @@ -215,6 +255,21 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, } raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + /* HW SGI? Ask the GIC to inject it */ + int err; + err = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + true); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + continue; + } + if (irq->hw) vgic_hw_irq_spending(vcpu, irq, is_uaccess); else @@ -269,6 +324,20 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + /* HW SGI? Ask the GIC to clear its pending bit */ + int err; + err = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + false); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + continue; + } + if (irq->hw) vgic_hw_irq_cpending(vcpu, irq, is_uaccess); else @@ -318,8 +387,15 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (irq->hw) { + if (irq->hw && !vgic_irq_is_sgi(irq->intid)) { vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); + } else if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + /* + * GICv4.1 VSGI feature doesn't track an active state, + * so let's not kid ourselves, there is nothing we can + * do here. + */ + irq->active = false; } else { u32 model = vcpu->kvm->arch.vgic.vgic_model; u8 active_source; @@ -493,6 +569,8 @@ void vgic_mmio_write_priority(struct kvm_vcpu *vcpu, raw_spin_lock_irqsave(&irq->irq_lock, flags); /* Narrow the priority range to what we actually support */ irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) + vgic_update_vsgi(irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 1bc09b523486..2c9fc13e2c59 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -540,6 +540,8 @@ int vgic_v3_map_resources(struct kvm *kvm) goto out; } + if (kvm_vgic_global_state.has_gicv4_1) + vgic_v4_configure_vsgis(kvm); dist->ready = true; out: diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c index 1eb0f8c76219..27ac833e5ec7 100644 --- a/virt/kvm/arm/vgic/vgic-v4.c +++ b/virt/kvm/arm/vgic/vgic-v4.c @@ -97,6 +97,104 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info) return IRQ_HANDLED; } +static void vgic_v4_sync_sgi_config(struct its_vpe *vpe, struct vgic_irq *irq) +{ + vpe->sgi_config[irq->intid].enabled = irq->enabled; + vpe->sgi_config[irq->intid].group = irq->group; + vpe->sgi_config[irq->intid].priority = irq->priority; +} + +static void vgic_v4_enable_vsgis(struct kvm_vcpu *vcpu) +{ + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + int i; + + /* + * With GICv4.1, every virtual SGI can be directly injected. So + * let's pretend that they are HW interrupts, tied to a host + * IRQ. The SGI code will do its magic. + */ + for (i = 0; i < VGIC_NR_SGIS; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, i); + struct irq_desc *desc; + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (irq->hw) + goto unlock; + + irq->hw = true; + irq->host_irq = irq_find_mapping(vpe->sgi_domain, i); + + /* Transfer the full irq state to the vPE */ + vgic_v4_sync_sgi_config(vpe, irq); + desc = irq_to_desc(irq->host_irq); + ret = irq_domain_activate_irq(irq_desc_get_irq_data(desc), + false); + if (!WARN_ON(ret)) { + /* Transfer pending state */ + ret = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + irq->pending_latch); + WARN_ON(ret); + irq->pending_latch = false; + } + unlock: + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +static void vgic_v4_disable_vsgis(struct kvm_vcpu *vcpu) +{ + int i; + + for (i = 0; i < VGIC_NR_SGIS; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, i); + struct irq_desc *desc; + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (!irq->hw) + goto unlock; + + irq->hw = false; + ret = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &irq->pending_latch); + WARN_ON(ret); + + desc = irq_to_desc(irq->host_irq); + irq_domain_deactivate_irq(irq_desc_get_irq_data(desc)); + unlock: + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +/* Must be called with the kvm lock held */ +void vgic_v4_configure_vsgis(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int i; + + kvm_arm_halt_guest(kvm); + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (dist->nassgireq) + vgic_v4_enable_vsgis(vcpu); + else + vgic_v4_disable_vsgis(vcpu); + } + + kvm_arm_resume_guest(kvm); +} + /** * vgic_v4_init - Initialize the GICv4 data structures * @kvm: Pointer to the VM being initialized @@ -141,6 +239,7 @@ int vgic_v4_init(struct kvm *kvm) kvm_for_each_vcpu(i, vcpu, kvm) { int irq = dist->its_vm.vpes[i]->irq; + unsigned long irq_flags = DB_IRQ_FLAGS; /* * Don't automatically enable the doorbell, as we're @@ -148,8 +247,14 @@ int vgic_v4_init(struct kvm *kvm) * blocked. Also disable the lazy disabling, as the * doorbell could kick us out of the guest too * early... + * + * On GICv4.1, the doorbell is managed in HW and must + * be left enabled. */ - irq_set_status_flags(irq, DB_IRQ_FLAGS); + if (kvm_vgic_global_state.has_gicv4_1) + irq_flags &= ~IRQ_NOAUTOEN; + irq_set_status_flags(irq, irq_flags); + ret = request_irq(irq, vgic_v4_doorbell_handler, 0, "vcpu", vcpu); if (ret) { diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index c7fefd6b1c80..769e4802645e 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -316,5 +316,6 @@ void vgic_its_invalidate_cache(struct kvm *kvm); bool vgic_supports_direct_msis(struct kvm *kvm); int vgic_v4_init(struct kvm *kvm); void vgic_v4_teardown(struct kvm *kvm); +void vgic_v4_configure_vsgis(struct kvm *kvm); #endif diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 70f03ce0e5c1..74bdb7bf3295 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -149,8 +149,6 @@ static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn); __visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); -static bool largepages_enabled = true; - #define KVM_EVENT_CREATE_VM 0 #define KVM_EVENT_DESTROY_VM 1 static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); @@ -566,7 +564,7 @@ static struct kvm_memslots *kvm_alloc_memslots(void) return NULL; for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) - slots->id_to_index[i] = slots->memslots[i].id = i; + slots->id_to_index[i] = -1; return slots; } @@ -580,18 +578,14 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) memslot->dirty_bitmap = NULL; } -/* - * Free any memory in @free but not in @dont. - */ -static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - if (!dont || free->dirty_bitmap != dont->dirty_bitmap) - kvm_destroy_dirty_bitmap(free); + kvm_destroy_dirty_bitmap(slot); - kvm_arch_free_memslot(kvm, free, dont); + kvm_arch_free_memslot(kvm, slot); - free->npages = 0; + slot->flags = 0; + slot->npages = 0; } static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) @@ -602,7 +596,7 @@ static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) return; kvm_for_each_memslot(memslot, slots) - kvm_free_memslot(kvm, memslot, NULL); + kvm_free_memslot(kvm, memslot); kvfree(slots); } @@ -860,9 +854,9 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) /* * Allocation size is twice as large as the actual dirty bitmap size. - * See x86's kvm_vm_ioctl_get_dirty_log() why this is needed. + * See kvm_vm_ioctl_get_dirty_log() why this is needed. */ -static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) +static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot) { unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot); @@ -874,63 +868,165 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) } /* - * Insert memslot and re-sort memslots based on their GFN, - * so binary search could be used to lookup GFN. - * Sorting algorithm takes advantage of having initially - * sorted array and known changed memslot position. + * Delete a memslot by decrementing the number of used slots and shifting all + * other entries in the array forward one spot. */ -static void update_memslots(struct kvm_memslots *slots, - struct kvm_memory_slot *new, - enum kvm_mr_change change) +static inline void kvm_memslot_delete(struct kvm_memslots *slots, + struct kvm_memory_slot *memslot) { - int id = new->id; - int i = slots->id_to_index[id]; struct kvm_memory_slot *mslots = slots->memslots; + int i; - WARN_ON(mslots[i].id != id); - switch (change) { - case KVM_MR_CREATE: - slots->used_slots++; - WARN_ON(mslots[i].npages || !new->npages); - break; - case KVM_MR_DELETE: - slots->used_slots--; - WARN_ON(new->npages || !mslots[i].npages); - break; - default: - break; - } + if (WARN_ON(slots->id_to_index[memslot->id] == -1)) + return; - while (i < KVM_MEM_SLOTS_NUM - 1 && - new->base_gfn <= mslots[i + 1].base_gfn) { - if (!mslots[i + 1].npages) - break; + slots->used_slots--; + + if (atomic_read(&slots->lru_slot) >= slots->used_slots) + atomic_set(&slots->lru_slot, 0); + + for (i = slots->id_to_index[memslot->id]; i < slots->used_slots; i++) { mslots[i] = mslots[i + 1]; slots->id_to_index[mslots[i].id] = i; - i++; } + mslots[i] = *memslot; + slots->id_to_index[memslot->id] = -1; +} + +/* + * "Insert" a new memslot by incrementing the number of used slots. Returns + * the new slot's initial index into the memslots array. + */ +static inline int kvm_memslot_insert_back(struct kvm_memslots *slots) +{ + return slots->used_slots++; +} + +/* + * Move a changed memslot backwards in the array by shifting existing slots + * with a higher GFN toward the front of the array. Note, the changed memslot + * itself is not preserved in the array, i.e. not swapped at this time, only + * its new index into the array is tracked. Returns the changed memslot's + * current index into the memslots array. + */ +static inline int kvm_memslot_move_backward(struct kvm_memslots *slots, + struct kvm_memory_slot *memslot) +{ + struct kvm_memory_slot *mslots = slots->memslots; + int i; + + if (WARN_ON_ONCE(slots->id_to_index[memslot->id] == -1) || + WARN_ON_ONCE(!slots->used_slots)) + return -1; /* - * The ">=" is needed when creating a slot with base_gfn == 0, - * so that it moves before all those with base_gfn == npages == 0. - * - * On the other hand, if new->npages is zero, the above loop has - * already left i pointing to the beginning of the empty part of - * mslots, and the ">=" would move the hole backwards in this - * case---which is wrong. So skip the loop when deleting a slot. + * Move the target memslot backward in the array by shifting existing + * memslots with a higher GFN (than the target memslot) towards the + * front of the array. */ - if (new->npages) { - while (i > 0 && - new->base_gfn >= mslots[i - 1].base_gfn) { - mslots[i] = mslots[i - 1]; - slots->id_to_index[mslots[i].id] = i; - i--; - } - } else - WARN_ON_ONCE(i != slots->used_slots); + for (i = slots->id_to_index[memslot->id]; i < slots->used_slots - 1; i++) { + if (memslot->base_gfn > mslots[i + 1].base_gfn) + break; + + WARN_ON_ONCE(memslot->base_gfn == mslots[i + 1].base_gfn); + + /* Shift the next memslot forward one and update its index. */ + mslots[i] = mslots[i + 1]; + slots->id_to_index[mslots[i].id] = i; + } + return i; +} + +/* + * Move a changed memslot forwards in the array by shifting existing slots with + * a lower GFN toward the back of the array. Note, the changed memslot itself + * is not preserved in the array, i.e. not swapped at this time, only its new + * index into the array is tracked. Returns the changed memslot's final index + * into the memslots array. + */ +static inline int kvm_memslot_move_forward(struct kvm_memslots *slots, + struct kvm_memory_slot *memslot, + int start) +{ + struct kvm_memory_slot *mslots = slots->memslots; + int i; + + for (i = start; i > 0; i--) { + if (memslot->base_gfn < mslots[i - 1].base_gfn) + break; + + WARN_ON_ONCE(memslot->base_gfn == mslots[i - 1].base_gfn); + + /* Shift the next memslot back one and update its index. */ + mslots[i] = mslots[i - 1]; + slots->id_to_index[mslots[i].id] = i; + } + return i; +} + +/* + * Re-sort memslots based on their GFN to account for an added, deleted, or + * moved memslot. Sorting memslots by GFN allows using a binary search during + * memslot lookup. + * + * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! I.e. the entry + * at memslots[0] has the highest GFN. + * + * The sorting algorithm takes advantage of having initially sorted memslots + * and knowing the position of the changed memslot. Sorting is also optimized + * by not swapping the updated memslot and instead only shifting other memslots + * and tracking the new index for the update memslot. Only once its final + * index is known is the updated memslot copied into its position in the array. + * + * - When deleting a memslot, the deleted memslot simply needs to be moved to + * the end of the array. + * + * - When creating a memslot, the algorithm "inserts" the new memslot at the + * end of the array and then it forward to its correct location. + * + * - When moving a memslot, the algorithm first moves the updated memslot + * backward to handle the scenario where the memslot's GFN was changed to a + * lower value. update_memslots() then falls through and runs the same flow + * as creating a memslot to move the memslot forward to handle the scenario + * where its GFN was changed to a higher value. + * + * Note, slots are sorted from highest->lowest instead of lowest->highest for + * historical reasons. Originally, invalid memslots where denoted by having + * GFN=0, thus sorting from highest->lowest naturally sorted invalid memslots + * to the end of the array. The current algorithm uses dedicated logic to + * delete a memslot and thus does not rely on invalid memslots having GFN=0. + * + * The other historical motiviation for highest->lowest was to improve the + * performance of memslot lookup. KVM originally used a linear search starting + * at memslots[0]. On x86, the largest memslot usually has one of the highest, + * if not *the* highest, GFN, as the bulk of the guest's RAM is located in a + * single memslot above the 4gb boundary. As the largest memslot is also the + * most likely to be referenced, sorting it to the front of the array was + * advantageous. The current binary search starts from the middle of the array + * and uses an LRU pointer to improve performance for all memslots and GFNs. + */ +static void update_memslots(struct kvm_memslots *slots, + struct kvm_memory_slot *memslot, + enum kvm_mr_change change) +{ + int i; + + if (change == KVM_MR_DELETE) { + kvm_memslot_delete(slots, memslot); + } else { + if (change == KVM_MR_CREATE) + i = kvm_memslot_insert_back(slots); + else + i = kvm_memslot_move_backward(slots, memslot); + i = kvm_memslot_move_forward(slots, memslot, i); - mslots[i] = *new; - slots->id_to_index[mslots[i].id] = i; + /* + * Copy the memslot to its new position in memslots and update + * its index accordingly. + */ + slots->memslots[i] = *memslot; + slots->id_to_index[memslot->id] = i; + } } static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem) @@ -984,6 +1080,112 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, } /* + * 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 + * use when invalidating a memslot prior to deleting/moving the memslot. + */ +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); + + if (change == KVM_MR_CREATE) + new_size = old_size + sizeof(struct kvm_memory_slot); + else + new_size = old_size; + + slots = kvzalloc(new_size, GFP_KERNEL_ACCOUNT); + if (likely(slots)) + memcpy(slots, old, old_size); + + return slots; +} + +static int kvm_set_memslot(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new, int as_id, + enum kvm_mr_change change) +{ + struct kvm_memory_slot *slot; + struct kvm_memslots *slots; + int r; + + slots = kvm_dup_memslots(__kvm_memslots(kvm, as_id), change); + if (!slots) + return -ENOMEM; + + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { + /* + * Note, the INVALID flag needs to be in the appropriate entry + * in the freshly allocated memslots, not in @old or @new. + */ + slot = id_to_memslot(slots, old->id); + 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. + */ + slots = install_new_memslots(kvm, as_id, slots); + + /* From this point no new shadow pages pointing to a deleted, + * or moved, memslot will be created. + * + * validation of sp->gfn happens in: + * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) + * - kvm_is_visible_gfn (mmu_check_root) + */ + kvm_arch_flush_shadow_memslot(kvm, slot); + } + + r = kvm_arch_prepare_memory_region(kvm, new, mem, change); + if (r) + goto out_slots; + + update_memslots(slots, new, change); + slots = install_new_memslots(kvm, as_id, slots); + + kvm_arch_commit_memory_region(kvm, mem, old, new, change); + + kvfree(slots); + return 0; + +out_slots: + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) + slots = install_new_memslots(kvm, as_id, slots); + kvfree(slots); + return r; +} + +static int kvm_delete_memslot(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot *old, int as_id) +{ + struct kvm_memory_slot new; + int r; + + if (!old->npages) + return -EINVAL; + + memset(&new, 0, sizeof(new)); + new.id = old->id; + + r = kvm_set_memslot(kvm, mem, old, &new, as_id, KVM_MR_DELETE); + if (r) + return r; + + kvm_free_memslot(kvm, old); + return 0; +} + +/* * Allocate some memory and give it an address in the guest physical address * space. * @@ -994,162 +1196,118 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, int __kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem) { - int r; - gfn_t base_gfn; - unsigned long npages; - struct kvm_memory_slot *slot; struct kvm_memory_slot old, new; - struct kvm_memslots *slots = NULL, *old_memslots; - int as_id, id; + struct kvm_memory_slot *tmp; enum kvm_mr_change change; + int as_id, id; + int r; r = check_memory_region_flags(mem); if (r) - goto out; + return r; - r = -EINVAL; as_id = mem->slot >> 16; id = (u16)mem->slot; /* General sanity checks */ if (mem->memory_size & (PAGE_SIZE - 1)) - goto out; + return -EINVAL; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) - goto out; + return -EINVAL; /* We can read the guest memory with __xxx_user() later on. */ if ((id < KVM_USER_MEM_SLOTS) && ((mem->userspace_addr & (PAGE_SIZE - 1)) || !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size))) - goto out; + return -EINVAL; if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM) - goto out; + return -EINVAL; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) - goto out; - - slot = id_to_memslot(__kvm_memslots(kvm, as_id), id); - base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; - npages = mem->memory_size >> PAGE_SHIFT; + return -EINVAL; - if (npages > KVM_MEM_MAX_NR_PAGES) - goto out; + /* + * Make a full copy of the old memslot, the pointer will become stale + * when the memslots are re-sorted by update_memslots(), and the old + * memslot needs to be referenced after calling update_memslots(), e.g. + * to free its resources and for arch specific behavior. + */ + tmp = id_to_memslot(__kvm_memslots(kvm, as_id), id); + if (tmp) { + old = *tmp; + tmp = NULL; + } else { + memset(&old, 0, sizeof(old)); + old.id = id; + } - new = old = *slot; + if (!mem->memory_size) + return kvm_delete_memslot(kvm, mem, &old, as_id); new.id = id; - new.base_gfn = base_gfn; - new.npages = npages; + new.base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; + new.npages = mem->memory_size >> PAGE_SHIFT; new.flags = mem->flags; + new.userspace_addr = mem->userspace_addr; - if (npages) { - if (!old.npages) - change = KVM_MR_CREATE; - else { /* Modify an existing slot. */ - if ((mem->userspace_addr != old.userspace_addr) || - (npages != old.npages) || - ((new.flags ^ old.flags) & KVM_MEM_READONLY)) - goto out; + if (new.npages > KVM_MEM_MAX_NR_PAGES) + return -EINVAL; - if (base_gfn != old.base_gfn) - change = KVM_MR_MOVE; - else if (new.flags != old.flags) - change = KVM_MR_FLAGS_ONLY; - else { /* Nothing to change. */ - r = 0; - goto out; - } - } - } else { - if (!old.npages) - goto out; + if (!old.npages) { + change = KVM_MR_CREATE; + new.dirty_bitmap = NULL; + memset(&new.arch, 0, sizeof(new.arch)); + } else { /* Modify an existing slot. */ + if ((new.userspace_addr != old.userspace_addr) || + (new.npages != old.npages) || + ((new.flags ^ old.flags) & KVM_MEM_READONLY)) + return -EINVAL; - change = KVM_MR_DELETE; - new.base_gfn = 0; - new.flags = 0; + if (new.base_gfn != old.base_gfn) + change = KVM_MR_MOVE; + else if (new.flags != old.flags) + change = KVM_MR_FLAGS_ONLY; + else /* Nothing to change. */ + return 0; + + /* Copy dirty_bitmap and arch from the current memslot. */ + new.dirty_bitmap = old.dirty_bitmap; + memcpy(&new.arch, &old.arch, sizeof(new.arch)); } if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { /* Check for overlaps */ - r = -EEXIST; - kvm_for_each_memslot(slot, __kvm_memslots(kvm, as_id)) { - if (slot->id == id) + kvm_for_each_memslot(tmp, __kvm_memslots(kvm, as_id)) { + if (tmp->id == id) continue; - if (!((base_gfn + npages <= slot->base_gfn) || - (base_gfn >= slot->base_gfn + slot->npages))) - goto out; + if (!((new.base_gfn + new.npages <= tmp->base_gfn) || + (new.base_gfn >= tmp->base_gfn + tmp->npages))) + return -EEXIST; } } - /* Free page dirty bitmap if unneeded */ + /* Allocate/free page dirty bitmap as needed */ if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES)) new.dirty_bitmap = NULL; + else if (!new.dirty_bitmap) { + r = kvm_alloc_dirty_bitmap(&new); + if (r) + return r; - r = -ENOMEM; - if (change == KVM_MR_CREATE) { - new.userspace_addr = mem->userspace_addr; - - if (kvm_arch_create_memslot(kvm, &new, npages)) - goto out_free; - } - - /* Allocate page dirty bitmap if needed */ - if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) { - if (kvm_create_dirty_bitmap(&new) < 0) - goto out_free; - } - - slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT); - if (!slots) - goto out_free; - memcpy(slots, __kvm_memslots(kvm, as_id), sizeof(struct kvm_memslots)); - - if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) { - slot = id_to_memslot(slots, id); - slot->flags |= KVM_MEMSLOT_INVALID; - - old_memslots = install_new_memslots(kvm, as_id, slots); - - /* From this point no new shadow pages pointing to a deleted, - * or moved, memslot will be created. - * - * validation of sp->gfn happens in: - * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) - * - kvm_is_visible_gfn (mmu_check_root) - */ - kvm_arch_flush_shadow_memslot(kvm, slot); - - /* - * We can re-use the old_memslots from above, the only difference - * from the currently installed memslots is the invalid flag. This - * will get overwritten by update_memslots anyway. - */ - slots = old_memslots; + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + bitmap_set(new.dirty_bitmap, 0, new.npages); } - r = kvm_arch_prepare_memory_region(kvm, &new, mem, change); + r = kvm_set_memslot(kvm, mem, &old, &new, as_id, change); if (r) - goto out_slots; - - /* actual memory is freed via old in kvm_free_memslot below */ - if (change == KVM_MR_DELETE) { - new.dirty_bitmap = NULL; - memset(&new.arch, 0, sizeof(new.arch)); - } - - update_memslots(slots, &new, change); - old_memslots = install_new_memslots(kvm, as_id, slots); - - kvm_arch_commit_memory_region(kvm, mem, &old, &new, change); + goto out_bitmap; - kvm_free_memslot(kvm, &old, &new); - kvfree(old_memslots); + if (old.dirty_bitmap && !new.dirty_bitmap) + kvm_destroy_dirty_bitmap(&old); return 0; -out_slots: - kvfree(slots); -out_free: - kvm_free_memslot(kvm, &new, &old); -out: +out_bitmap: + if (new.dirty_bitmap && !old.dirty_bitmap) + kvm_destroy_dirty_bitmap(&new); return r; } EXPORT_SYMBOL_GPL(__kvm_set_memory_region); @@ -1175,31 +1333,43 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, return kvm_set_memory_region(kvm, mem); } -int kvm_get_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log, int *is_dirty) +#ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT +/** + * kvm_get_dirty_log - get a snapshot of dirty pages + * @kvm: pointer to kvm instance + * @log: slot id and address to which we copy the log + * @is_dirty: set to '1' if any dirty pages were found + * @memslot: set to the associated memslot, always valid on success + */ +int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, + int *is_dirty, struct kvm_memory_slot **memslot) { struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; int i, as_id, id; unsigned long n; unsigned long any = 0; + *memslot = NULL; + *is_dirty = 0; + as_id = log->slot >> 16; id = (u16)log->slot; if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) return -EINVAL; slots = __kvm_memslots(kvm, as_id); - memslot = id_to_memslot(slots, id); - if (!memslot->dirty_bitmap) + *memslot = id_to_memslot(slots, id); + if (!(*memslot) || !(*memslot)->dirty_bitmap) return -ENOENT; - n = kvm_dirty_bitmap_bytes(memslot); + kvm_arch_sync_dirty_log(kvm, *memslot); + + n = kvm_dirty_bitmap_bytes(*memslot); for (i = 0; !any && i < n/sizeof(long); ++i) - any = memslot->dirty_bitmap[i]; + any = (*memslot)->dirty_bitmap[i]; - if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n)) + if (copy_to_user(log->dirty_bitmap, (*memslot)->dirty_bitmap, n)) return -EFAULT; if (any) @@ -1208,13 +1378,12 @@ int kvm_get_dirty_log(struct kvm *kvm, } EXPORT_SYMBOL_GPL(kvm_get_dirty_log); -#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT +#else /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ /** * kvm_get_dirty_log_protect - get a snapshot of dirty pages * and reenable dirty page tracking for the corresponding pages. * @kvm: pointer to kvm instance * @log: slot id and address to which we copy the log - * @flush: true if TLB flush is needed by caller * * We need to keep it in mind that VCPU threads can write to the bitmap * concurrently. So, to avoid losing track of dirty pages we keep the @@ -1231,8 +1400,7 @@ EXPORT_SYMBOL_GPL(kvm_get_dirty_log); * exiting to userspace will be logged for the next call. * */ -int kvm_get_dirty_log_protect(struct kvm *kvm, - struct kvm_dirty_log *log, bool *flush) +static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; @@ -1240,6 +1408,7 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, unsigned long n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; + bool flush; as_id = log->slot >> 16; id = (u16)log->slot; @@ -1248,13 +1417,15 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); + if (!memslot || !memslot->dirty_bitmap) + return -ENOENT; dirty_bitmap = memslot->dirty_bitmap; - if (!dirty_bitmap) - return -ENOENT; + + kvm_arch_sync_dirty_log(kvm, memslot); n = kvm_dirty_bitmap_bytes(memslot); - *flush = false; + flush = false; if (kvm->manual_dirty_log_protect) { /* * Unlike kvm_get_dirty_log, we always return false in *flush, @@ -1277,7 +1448,7 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, if (!dirty_bitmap[i]) continue; - *flush = true; + flush = true; mask = xchg(&dirty_bitmap[i], 0); dirty_bitmap_buffer[i] = mask; @@ -1288,21 +1459,55 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, spin_unlock(&kvm->mmu_lock); } + if (flush) + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); + if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(kvm_get_dirty_log_protect); + + +/** + * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot + * @kvm: kvm instance + * @log: slot id and address to which we copy the log + * + * Steps 1-4 below provide general overview of dirty page logging. See + * kvm_get_dirty_log_protect() function description for additional details. + * + * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we + * always flush the TLB (step 4) even if previous step failed and the dirty + * bitmap may be corrupt. Regardless of previous outcome the KVM logging API + * does not preclude user space subsequent dirty log read. Flushing TLB ensures + * writes will be marked dirty for next log read. + * + * 1. Take a snapshot of the bit and clear it if needed. + * 2. Write protect the corresponding page. + * 3. Copy the snapshot to the userspace. + * 4. Flush TLB's if needed. + */ +static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, + struct kvm_dirty_log *log) +{ + int r; + + mutex_lock(&kvm->slots_lock); + + r = kvm_get_dirty_log_protect(kvm, log); + + mutex_unlock(&kvm->slots_lock); + return r; +} /** * kvm_clear_dirty_log_protect - clear dirty bits in the bitmap * and reenable dirty page tracking for the corresponding pages. * @kvm: pointer to kvm instance * @log: slot id and address from which to fetch the bitmap of dirty pages - * @flush: true if TLB flush is needed by caller */ -int kvm_clear_dirty_log_protect(struct kvm *kvm, - struct kvm_clear_dirty_log *log, bool *flush) +static int kvm_clear_dirty_log_protect(struct kvm *kvm, + struct kvm_clear_dirty_log *log) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; @@ -1311,6 +1516,7 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm, unsigned long i, n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; + bool flush; as_id = log->slot >> 16; id = (u16)log->slot; @@ -1322,10 +1528,10 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm, slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); + if (!memslot || !memslot->dirty_bitmap) + return -ENOENT; dirty_bitmap = memslot->dirty_bitmap; - if (!dirty_bitmap) - return -ENOENT; n = ALIGN(log->num_pages, BITS_PER_LONG) / 8; @@ -1334,7 +1540,9 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm, (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63))) return -EINVAL; - *flush = false; + kvm_arch_sync_dirty_log(kvm, memslot); + + flush = false; dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n)) return -EFAULT; @@ -1357,28 +1565,32 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm, * a problem if userspace sets them in log->dirty_bitmap. */ if (mask) { - *flush = true; + flush = true; kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); } } spin_unlock(&kvm->mmu_lock); + if (flush) + kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); + return 0; } -EXPORT_SYMBOL_GPL(kvm_clear_dirty_log_protect); -#endif -bool kvm_largepages_enabled(void) +static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, + struct kvm_clear_dirty_log *log) { - return largepages_enabled; -} + int r; -void kvm_disable_largepages(void) -{ - largepages_enabled = false; + mutex_lock(&kvm->slots_lock); + + r = kvm_clear_dirty_log_protect(kvm, log); + + mutex_unlock(&kvm->slots_lock); + return r; } -EXPORT_SYMBOL_GPL(kvm_disable_largepages); +#endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { @@ -1754,12 +1966,6 @@ kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); -kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) -{ - return gfn_to_pfn_memslot_atomic(gfn_to_memslot(kvm, gfn), gfn); -} -EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); - kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); @@ -3310,9 +3516,6 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_IOEVENTFD_ANY_LENGTH: case KVM_CAP_CHECK_EXTENSION_VM: case KVM_CAP_ENABLE_CAP_VM: -#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT - case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: -#endif return 1; #ifdef CONFIG_KVM_MMIO case KVM_CAP_COALESCED_MMIO: @@ -3320,6 +3523,10 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_COALESCED_PIO: return 1; #endif +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: + return KVM_DIRTY_LOG_MANUAL_CAPS; +#endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; @@ -3347,11 +3554,17 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, { switch (cap->cap) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT - case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: - if (cap->flags || (cap->args[0] & ~1)) + case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: { + u64 allowed_options = KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE; + + if (cap->args[0] & KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE) + allowed_options = KVM_DIRTY_LOG_MANUAL_CAPS; + + if (cap->flags || (cap->args[0] & ~allowed_options)) return -EINVAL; kvm->manual_dirty_log_protect = cap->args[0]; return 0; + } #endif default: return kvm_vm_ioctl_enable_cap(kvm, cap); @@ -4435,14 +4648,22 @@ struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void) return &kvm_running_vcpu; } -static void check_processor_compat(void *rtn) +struct kvm_cpu_compat_check { + void *opaque; + int *ret; +}; + +static void check_processor_compat(void *data) { - *(int *)rtn = kvm_arch_check_processor_compat(); + struct kvm_cpu_compat_check *c = data; + + *c->ret = kvm_arch_check_processor_compat(c->opaque); } int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, struct module *module) { + struct kvm_cpu_compat_check c; int r; int cpu; @@ -4466,12 +4687,14 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, goto out_free_0; } - r = kvm_arch_hardware_setup(); + r = kvm_arch_hardware_setup(opaque); if (r < 0) goto out_free_1; + c.ret = &r; + c.opaque = opaque; for_each_online_cpu(cpu) { - smp_call_function_single(cpu, check_processor_compat, &r, 1); + smp_call_function_single(cpu, check_processor_compat, &c, 1); if (r < 0) goto out_free_2; } |