- 05 Oct, 2021 1 commit
-
-
git://github.com/kvm-riscv/linuxPaolo Bonzini authored
Initial KVM RISC-V support Following features are supported by the initial KVM RISC-V support: 1. No RISC-V specific KVM IOCTL 2. Loadable KVM RISC-V module 3. Minimal possible KVM world-switch which touches only GPRs and few CSRs 4. Works on both RV64 and RV32 host 5. Full Guest/VM switch via vcpu_get/vcpu_put infrastructure 6. KVM ONE_REG interface for VCPU register access from KVM user-space 7. Interrupt controller emulation in KVM user-space 8. Timer and IPI emuation in kernel 9. Both Sv39x4 and Sv48x4 supported for RV64 host 10. MMU notifiers supported 11. Generic dirty log supported 12. FP lazy save/restore supported 13. SBI v0.1 emulation for Guest/VM 14. Forward unhandled SBI calls to KVM user-space 15. Hugepage support for Guest/VM 16. IOEVENTFD support for Vhost
-
- 04 Oct, 2021 18 commits
-
-
Anup Patel authored
Add myself as maintainer for KVM RISC-V and Atish as designated reviewer. Signed-off-by:
Atish Patra <atish.patra@wdc.com> Signed-off-by:
Anup Patel <anup.patel@wdc.com> Acked-by:
Paolo Bonzini <pbonzini@redhat.com> Reviewed-by:
Alexander Graf <graf@amazon.com> Acked-by:
Palmer Dabbelt <palmerdabbelt@google.com>
-
Anup Patel authored
Document RISC-V specific parts of the KVM API, such as: - The interrupt numbers passed to the KVM_INTERRUPT ioctl. - The states supported by the KVM_{GET,SET}_MP_STATE ioctls. - The registers supported by the KVM_{GET,SET}_ONE_REG interface and the encoding of those register ids. - The exit reason KVM_EXIT_RISCV_SBI for SBI calls forwarded to userspace tool. CC: Jonathan Corbet <corbet@lwn.net> CC: linux-doc@vger.kernel.org Signed-off-by: -
Atish Patra authored
The KVM host kernel is running in HS-mode needs so we need to handle the SBI calls coming from guest kernel running in VS-mode. This patch adds SBI v0.1 support in KVM RISC-V. Almost all SBI v0.1 calls are implemented in KVM kernel module except GETCHAR and PUTCHART calls which are forwarded to user space because these calls cannot be implemented in kernel space. In future, when we implement SBI v0.2 for Guest, we will forward SBI v0.2 experimental and vendor extension calls to user space. Signed-off-by:
-
Atish Patra authored
Add a KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctl interface for floating point registers such as F0-F31 and FCSR. This support is added for both 'F' and 'D' extensions. Signed-off-by:
-
Atish Patra authored
This patch adds floating point (F and D extension) context save/restore for guest VCPUs. The FP context is saved and restored lazily only when kernel enter/exits the in-kernel run loop and not during the KVM world switch. This way FP save/restore has minimal impact on KVM performance. Signed-off-by:
-
Atish Patra authored
The RISC-V hypervisor specification doesn't have any virtual timer feature. Due to this, the guest VCPU timer will be programmed via SBI calls. The host will use a separate hrtimer event for each guest VCPU to provide timer functionality. We inject a virtual timer interrupt to the guest VCPU whenever the guest VCPU hrtimer event expires. This patch adds guest VCPU timer implementation along with ONE_REG interface to access VCPU timer state from user space. Signed-off-by:
Daniel Lezcano <daniel.lezcano@linaro.org> Acked-by:
-
Anup Patel authored
This patch implements MMU notifiers for KVM RISC-V so that Guest physical address space is in-sync with Host physical address space. This will allow swapping, page migration, etc to work transparently with KVM RISC-V. Signed-off-by:
-
Anup Patel authored
This patch implements all required functions for programming the stage2 page table for each Guest/VM. At high-level, the flow of stage2 related functions is similar from KVM ARM/ARM64 implementation but the stage2 page table format is quite different for KVM RISC-V. [jiangyifei: stage2 dirty log support] Signed-off-by:
Yifei Jiang <jiangyifei@huawei.com> Signed-off-by:
-
Anup Patel authored
We implement a simple VMID allocator for Guests/VMs which: 1. Detects number of VMID bits at boot-time 2. Uses atomic number to track VMID version and increments VMID version whenever we run-out of VMIDs 3. Flushes Guest TLBs on all host CPUs whenever we run-out of VMIDs 4. Force updates HW Stage2 VMID for each Guest VCPU whenever VMID changes using VCPU request KVM_REQ_UPDATE_HGATP Signed-off-by:
-
Anup Patel authored
We get illegal instruction trap whenever Guest/VM executes WFI instruction. This patch handles WFI trap by blocking the trapped VCPU using kvm_vcpu_block() API. The blocked VCPU will be automatically resumed whenever a VCPU interrupt is injected from user-space or from in-kernel IRQCHIP emulation. Signed-off-by:
-
Anup Patel authored
We will get stage2 page faults whenever Guest/VM access SW emulated MMIO device or unmapped Guest RAM. This patch implements MMIO read/write emulation by extracting MMIO details from the trapped load/store instruction and forwarding the MMIO read/write to user-space. The actual MMIO emulation will happen in user-space and KVM kernel module will only take care of register updates before resuming the trapped VCPU. The handling for stage2 page faults for unmapped Guest RAM will be implemeted by a separate patch later. [jiangyifei: ioeventfd and in-kernel mmio device support] Signed-off-by:
-
Anup Patel authored
This patch implements the VCPU world-switch for KVM RISC-V. The KVM RISC-V world-switch (i.e. __kvm_riscv_switch_to()) mostly switches general purpose registers, SSTATUS, STVEC, SSCRATCH and HSTATUS CSRs. Other CSRs are switched via vcpu_load() and vcpu_put() interface in kvm_arch_vcpu_load() and kvm_arch_vcpu_put() functions respectively. Signed-off-by:
-
Anup Patel authored
For KVM RISC-V, we use KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls to access VCPU config and registers from user-space. We have three types of VCPU registers: 1. CONFIG - these are VCPU config and capabilities 2. CORE - these are VCPU general purpose registers 3. CSR - these are VCPU control and status registers The CONFIG register available to user-space is ISA. The ISA register is a read and write register where user-space can only write the desired VCPU ISA capabilities before running the VCPU. The CORE registers available to user-space are PC, RA, SP, GP, TP, A0-A7, T0-T6, S0-S11 and MODE. Most of these are RISC-V general registers except PC and MODE. The PC register represents program counter whereas the MODE register represent VCPU privilege mode (i.e. S/U-mode). The CSRs available to user-space are SSTATUS, SIE, STVEC, SSCRATCH, SEPC, SCAUSE, STVAL, SIP, and SATP. All of these are read/write registers. In future, more VCPU register types will be added (such as FP) for the KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls. Signed-off-by:
-
Anup Patel authored
This patch implements VCPU interrupts and requests which are both asynchronous events. The VCPU interrupts can be set/unset using KVM_INTERRUPT ioctl from user-space. In future, the in-kernel IRQCHIP emulation will use kvm_riscv_vcpu_set_interrupt() and kvm_riscv_vcpu_unset_interrupt() functions to set/unset VCPU interrupts. Important VCPU requests implemented by this patch are: KVM_REQ_SLEEP - set whenever VCPU itself goes to sleep state KVM_REQ_VCPU_RESET - set whenever VCPU reset is requested The WFI trap-n-emulate (added later) will use KVM_REQ_SLEEP request and kvm_riscv_vcpu_has_interrupt() function. The KVM_REQ_VCPU_RESET request will be used by SBI emulation (added later) to power-up a VCPU in power-off state. The user-space can use the GET_MPSTATE/SET_MPSTATE ioctls to get/set power state of a VCPU. Signed-off-by:
-
Anup Patel authored
This patch implements VCPU create, init and destroy functions required by generic KVM module. We don't have much dynamic resources in struct kvm_vcpu_arch so these functions are quite simple for KVM RISC-V. Signed-off-by:
-
Anup Patel authored
This patch adds initial skeletal KVM RISC-V support which has: 1. A simple implementation of arch specific VM functions except kvm_vm_ioctl_get_dirty_log() which will implemeted in-future as part of stage2 page loging. 2. Stubs of required arch specific VCPU functions except kvm_arch_vcpu_ioctl_run() which is semi-complete and extended by subsequent patches. 3. Stubs for required arch specific stage2 MMU functions. Signed-off-by:
-
Anup Patel authored
This patch adds asm/kvm_csr.h for RISC-V hypervisor extension related defines. Signed-off-by:
-
Paolo Bonzini authored
Merge tag 'kvm-s390-master-5.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into kvm-master KVM: s390: allow to compile without warning with W=1
-
- 01 Oct, 2021 21 commits
-
-
David Stevens authored
Avoid allocating the gfn_track arrays if nothing needs them. If there are no external to KVM users of the API (i.e. no GVT-g), then page tracking is only needed for shadow page tables. This means that when tdp is enabled and there are no external users, then the gfn_track arrays can be lazily allocated when the shadow MMU is actually used. This avoid allocations equal to .05% of guest memory when nested virtualization is not used, if the kernel is compiled without GVT-g. Signed-off-by:
David Stevens <stevensd@chromium.org> Message-Id: <20210922045859.2011227-3-stevensd@google.com> Signed-off-by:
-
David Stevens authored
Add a config option that allows kvm to determine whether or not there are any external users of page tracking. Signed-off-by:
-
Krish Sadhukhan authored
According to section "TLB Flush" in APM vol 2, "Support for TLB_CONTROL commands other than the first two, is optional and is indicated by CPUID Fn8000_000A_EDX[FlushByAsid]. All encodings of TLB_CONTROL not defined in the APM are reserved." Signed-off-by:Krish Sadhukhan <krish.sadhukhan@oracle.com> Message-Id: <20210920235134.101970-3-krish.sadhukhan@oracle.com> Signed-off-by:
-
Juergen Gross authored
By switching from kfree() to kvfree() in kvm_arch_free_vm() Arm64 can use the common variant. This can be accomplished by adding another macro __KVM_HAVE_ARCH_VM_FREE, which will be used only by x86 for now. Further simplification can be achieved by adding __kvm_arch_free_vm() doing the common part. Suggested-by:
Juergen Gross <jgross@suse.com> Message-Id: <20210903130808.30142-5-jgross@suse.com> Signed-off-by:
-
Babu Moger authored
Predictive Store Forwarding: AMD Zen3 processors feature a new technology called Predictive Store Forwarding (PSF). PSF is a hardware-based micro-architectural optimization designed to improve the performance of code execution by predicting address dependencies between loads and stores. How PSF works: It is very common for a CPU to execute a load instruction to an address that was recently written by a store. Modern CPUs implement a technique known as Store-To-Load-Forwarding (STLF) to improve performance in such cases. With STLF, data from the store is forwarded directly to the load without having to wait for it to be written to memory. In a typical CPU, STLF occurs after the address of both the load and store are calculated and determined to match. PSF expands on this by speculating on the relationship between loads and stores without waiting for the address calculation to complete. With PSF, the CPU learns over time the relationship between loads and stores. If STLF typically occurs between a particular store and load, the CPU will remember this. In typical code, PSF provides a performance benefit by speculating on the load result and allowing later instructions to begin execution sooner than they otherwise would be able to. The details of security analysis of AMD predictive store forwarding is documented here. https://www.amd.com/system/files/documents/security-analysis-predictive-store-forwarding.pdf Predictive Store Forwarding controls: There are two hardware control bits which influence the PSF feature: - MSR 48h bit 2 – Speculative Store Bypass (SSBD) - MSR 48h bit 7 – Predictive Store Forwarding Disable (PSFD) The PSF feature is disabled if either of these bits are set. These bits are controllable on a per-thread basis in an SMT system. By default, both SSBD and PSFD are 0 meaning that the speculation features are enabled. While the SSBD bit disables PSF and speculative store bypass, PSFD only disables PSF. PSFD may be desirable for software which is concerned with the speculative behavior of PSF but desires a smaller performance impact than setting SSBD. Support for PSFD is indicated in CPUID Fn8000_0008 EBX[28]. All processors that support PSF will also support PSFD. Linux kernel does not have the interface to enable/disable PSFD yet. Plan here is to expose the PSFD technology to KVM so that the guest kernel can make use of it if they wish to. Signed-off-by:
Babu Moger <Babu.Moger@amd.com> Message-Id: <163244601049.30292.5855870305350227855.stgit@bmoger-ubuntu> [Keep feature private to KVM, as requested by Borislav Petkov. - Paolo] Signed-off-by:
-
David Matlack authored
mmu_try_to_unsync_pages checks if page tracking is active for the given gfn, which requires knowing the memslot. We can pass down the memslot via make_spte to avoid this lookup. The memslot is also handy for make_spte's marking of the gfn as dirty: we can test whether dirty page tracking is enabled, and if so ensure that pages are mapped as writable with 4K granularity. Apart from the warning, no functional change is intended. Signed-off-by:
David Matlack <dmatlack@google.com> Message-Id: <20210813203504.2742757-7-dmatlack@google.com> Signed-off-by:
-
David Matlack authored
Avoid the memslot lookup in rmap_add, by passing it down from the fault handling code to mmu_set_spte and then to rmap_add. No functional change intended. Signed-off-by:
-
Paolo Bonzini authored
mmu_set_spte is called for either PTE prefetching or page faults. The three boolean arguments write_fault, speculative and host_writable are always respectively false/true/true for prefetching and coming from a struct kvm_page_fault for page faults. Let mmu_set_spte distinguish these two situation by accepting a possibly NULL struct kvm_page_fault argument. Signed-off-by: -
Paolo Bonzini authored
The level and A/D bit support of the new SPTE can be found in the role, which is stored in the kvm_mmu_page struct. This merges two arguments into one. For the TDP MMU, the kvm_mmu_page was not used (kvm_tdp_mmu_map does not use it if the SPTE is already present) so we fetch it just before calling make_spte. Signed-off-by: -
Paolo Bonzini authored
Prepare for removing the ad_disabled argument of make_spte; instead it can be found in the role of a struct kvm_mmu_page. First of all, the TDP MMU must set the role accurately. Signed-off-by: -
Paolo Bonzini authored
The level of the new SPTE can be found in the kvm_mmu_page struct; there is no need to pass it down. Signed-off-by: -
Paolo Bonzini authored
Now that make_spte is called directly by the shadow MMU (rather than wrapped by set_spte), it only has to return one boolean value. Signed-off-by: -
Paolo Bonzini authored
Since the two callers of set_spte do different things with the results, inlining it actually makes the code simpler to reason about. For example, FNAME(sync_page) already has a struct kvm_mmu_page *, but set_spte had to fish it back out of sptep's private page data. Signed-off-by: -
Paolo Bonzini authored
Since the two callers of set_spte do different things with the results, inlining it actually makes the code simpler to reason about. For example, mmu_set_spte looks quite like tdp_mmu_map_handle_target_level, but the similarity is hidden by set_spte. Signed-off-by: -
David Matlack authored
Now that kvm_page_fault has a pointer to the memslot it can be passed down to the page tracking code to avoid a redundant slot lookup. No functional change intended. Signed-off-by:
-
David Matlack authored
The memslot for the faulting gfn is used throughout the page fault handling code, so capture it in kvm_page_fault as soon as we know the gfn and use it in the page fault handling code that has direct access to the kvm_page_fault struct. Replace various tests using is_noslot_pfn with more direct tests on fault->slot being NULL. This, in combination with the subsequent patch, improves "Populate memory time" in dirty_log_perf_test by 5% when using the legacy MMU. There is no discerable improvement to the performance of the TDP MMU. No functional change intended. Suggested-by:
Ben Gardon <bgardon@google.com> Signed-off-by:
-
Paolo Bonzini authored
tdp_mmu_map_set_spte_atomic is not taking care of dirty logging anymore, the only difference that remains is that it takes a vCPU instead of the struct kvm. Merge the two functions. Signed-off-by: -
Paolo Bonzini authored
This simplifies set_spte, which we want to remove, and unifies code between the shadow MMU and the TDP MMU. The warning will be added back later to make_spte as well. There is a small disadvantage in the TDP MMU; it may unnecessarily mark a page as dirty twice if two vCPUs end up mapping the same page twice. However, this is a very small cost for a case that is already rare. Signed-off-by: -
David Matlack authored
Consolidate rmap_recycle and rmap_add into a single function since they are only ever called together (and only from one place). This has a nice side effect of eliminating an extra kvm_vcpu_gfn_to_memslot(). In addition it makes mmu_set_spte(), which is a very long function, a little shorter. No functional change intended. Signed-off-by:
-
Sean Christopherson authored
WARN and bail if the shadow walk for faulting in a SPTE terminates early, i.e. doesn't reach the expected level because the walk encountered a terminal SPTE. The shadow walks for page faults are subtle in that they install non-leaf SPTEs (zapping leaf SPTEs if necessary!) in the loop body, and consume the newly created non-leaf SPTE in the loop control, e.g. __shadow_walk_next(). In other words, the walks guarantee that the walk will stop if and only if the target level is reached by installing non-leaf SPTEs to guarantee the walk remains valid. Opportunistically use fault->goal-level instead of it.level in FNAME(fetch) to further clarify that KVM always installs the leaf SPTE at the target level. Reviewed-by:
Lai Jiangshan <jiangshanlai@gmail.com> Signed-off-by:
Sean Christopherson <seanjc@google.com> Signed-off-by:
Lai Jiangshan <laijs@linux.alibaba.com> Message-Id: <20210906122547.263316-1-jiangshanlai@gmail.com> Signed-off-by:
-
Paolo Bonzini authored
Pass struct kvm_page_fault to tracepoints instead of extracting the arguments from the struct. This also lets the kvm_mmu_spte_requested tracepoint pick the gfn directly from fault->gfn, instead of using the address. Signed-off-by:
-
