- 11 Jun, 2022 25 commits
-
-
Sean Christopherson authored
Multiplex the return value and fd (on success) in __kvm_create_device() to mimic common library helpers that return file descriptors, e.g. open(). Signed-off-by:
Sean Christopherson <seanjc@google.com> Signed-off-by:
Paolo Bonzini <pbonzini@redhat.com>
-
Sean Christopherson authored
Move KVM_CREATE_DEVICE_TEST to its own helper, identifying "real" versus "test" device creation based on a hardcoded boolean buried in the middle of a param list is painful for readers. Signed-off-by:
-
Sean Christopherson authored
Remove the two calls that pass @test=true to kvm_create_device() and drop the @test param entirely. The two removed calls don't check the return value of kvm_create_device(), so other than verifying KVM doesn't explode, which is extremely unlikely given that the non-test variant was _just_ called, they are pointless and provide no validation coverage. Signed-off-by:
-
Sean Christopherson authored
Use the KVM_IOCTL_ERROR() macro to generate error messages for a handful of one-off arm64 ioctls. The calls in question are made without an associated struct kvm_vm/kvm_vcpu as they are used to configure those structs, i.e. can't be easily converted to e.g. vcpu_ioctl(). Signed-off-by:
-
Sean Christopherson authored
Fold kvm_util_internal.h into kvm_util_base.h, i.e. make all KVM utility stuff "public". Hiding struct implementations from tests has been a massive failure, as it has led to pointless and poorly named wrappers, unnecessarily opaque code, etc... Not to mention that the approach was a complete failure as evidenced by the non-zero number of tests that were including kvm_util_internal.h. Signed-off-by:
-
Sean Christopherson authored
Make regs_dump() and sregs_dump() static, they're only implemented by x86 and only used internally. Signed-off-by:
-
Sean Christopherson authored
Use __KVM_SYSCALL_ERROR() to report and pretty print non-KVM syscall and ioctl errors, e.g. for mmap(), munmap(), uffd ioctls, etc... Signed-off-by:
-
Sean Christopherson authored
Use the recently introduced KVM-specific ioctl() helpers instead of open coding calls to ioctl() just to pretty print the ioctl name. Signed-off-by:
-
Sean Christopherson authored
Make kvm_ioctl() a macro wrapper and print the _name_ of the ioctl on failure instead of the number. Deliberately do not use __stringify(), as that will expand the ioctl all the way down to its numerical sequence, again the intent is to print the name of the macro. Signed-off-by:
-
Sean Christopherson authored
Use the recently introduced VM-specific ioctl() helpers instead of open coding calls to ioctl() just to pretty print the ioctl name. Keep a few open coded assertions that provide additional info. Signed-off-by:
-
Sean Christopherson authored
Make vm_ioctl() a macro wrapper and print the _name_ of the ioctl on failure instead of the number. Deliberately do not use __stringify(), as that will expand the ioctl all the way down to its numerical sequence. Again the intent is to print the name of the macro. Signed-off-by:
-
Sean Christopherson authored
Add vcpu_get() to wrap vcpu_find() and deduplicate a pile of code that asserts the requested vCPU exists. Signed-off-by:
-
Sean Christopherson authored
Drop vcpu_get_fd(), it no longer has any users, and really should not exist as the framework has failed if tests need to manually operate on a vCPU fd. Signed-off-by:
-
Sean Christopherson authored
Use vcpu_access_device_attr() in arm's arch_timer test instead of manually retrieving the vCPU's fd. This will allow dropping vcpu_get_fd() in a future patch. Signed-off-by:
-
Sean Christopherson authored
Add __vcpu_run() so that tests that want to avoid asserts on KVM_RUN failures don't need to open code the ioctl() call. Signed-off-by:
-
Sean Christopherson authored
Use the recently introduced vCPU-specific ioctl() helpers instead of open coding calls to ioctl() just to pretty print the ioctl name. Signed-off-by:
-
Sean Christopherson authored
Split vcpu_nested_state_set() into a wrapper that asserts, and an inner helper that does not. Passing a bool is all kinds of awful as it's unintuitive for readers and requires returning an 'int' from a function that for most users can never return anything other than "success". Signed-off-by:
-
Sean Christopherson authored
Drop @mode from vm_create() and have it use VM_MODE_DEFAULT. Add and use an inner helper, __vm_create(), to service the handful of tests that want something other than VM_MODE_DEFAULT. Signed-off-by:
-
Sean Christopherson authored
Make vcpu_ioctl() a macro wrapper and pretty the _name_ of the ioctl on failure instead of the number. Add inner macros to allow handling cases where the name of the ioctl needs to be resolved higher up the stack, and to allow using the formatting for non-ioctl syscalls without being technically wrong. Deliberately do not use __stringify(), as that will expand the ioctl all the way down to its numerical sequence, again the intent is to print the name of the macro. Signed-off-by:
-
Sean Christopherson authored
Add a second underscore to inner ioctl() helpers to better align with commonly accepted kernel coding style, and to allow using a single underscore variant in the future for macro shenanigans. Signed-off-by:
-
Sean Christopherson authored
Drop the @perm param from vm_create() and always open VM file descriptors with O_RDWR. There's no legitimate use case for other permissions, and if a selftest wants to do oddball negative testing it can open code the necessary bits instead of forcing a bunch of tests to provide useless information. Signed-off-by:
-
Sean Christopherson authored
Drop declarations for allocate_kvm_dirty_log() and vm_create_device(), which no longer have implementations. Signed-off-by:
-
Sean Christopherson authored
When iterating over vCPUs, invoke access_v3_redist_reg() on the "current" vCPU instead of vCPU0, which is presumably what was intended by iterating over all vCPUs. Signed-off-by:
-
Sean Christopherson authored
Update 'ret' with the return value of _kvm_device_access() prior to asserting that ret is non-zero. In the current code base, the flaw is benign as 'ret' is guaranteed to be -EBUSY from the previous run_vcpu(), which also means that errno==EBUSY prior to _kvm_device_access(), thus the "errno == EFAULT" part of the assert means that a false negative is impossible (unless the kernel is being truly mean and spuriously setting errno=EFAULT while returning success). Signed-off-by:
-
Sean Christopherson authored
The x86-only KVM_CAP_TRIPLE_FAULT_EVENT was (appropriately) renamed to KVM_CAP_X86_TRIPLE_FAULT_EVENT when the patches were applied, but the docs and selftests got left behind. Fix them. Signed-off-by:
-
- 10 Jun, 2022 8 commits
-
-
Sean Christopherson authored
Bug the VM and terminate emulation if an out-of-bounds read into the emulator's data cache occurs. Knowingly contuining on all but guarantees that KVM will overwrite random kernel data, which is far, far worse than killing the VM. Signed-off-by:
Kees Cook <keescook@chromium.org> Reviewed-by:
Vitaly Kuznetsov <vkuznets@redhat.com> Message-Id: <20220526210817.3428868-9-seanjc@google.com> Signed-off-by:
-
Sean Christopherson authored
Bug the VM if KVM's emulator attempts to inject a bogus exception vector. The guest is likely doomed even if KVM continues on, and propagating a bad vector to the rest of KVM runs the risk of breaking other assumptions in KVM and thus triggering a more egregious bug. All existing users of emulate_exception() have hardcoded vector numbers (__load_segment_descriptor() uses a few different vectors, but they're all hardcoded), and future users are likely to follow suit, i.e. the change to emulate_exception() is a glorified nop. As for the ctxt->exception.vector check in x86_emulate_insn(), the few known times the WARN has been triggered in the past is when the field was not set when synthesizing a fault, i.e. for all intents and purposes the check protects against consumption of uninitialized data. Signed-off-by:
-
Sean Christopherson authored
Bug the VM, i.e. kill it, if the emulator accesses a non-existent GPR, i.e. generates an out-of-bounds GPR index. Continuing on all but gaurantees some form of data corruption in the guest, e.g. even if KVM were to redirect to a dummy register, KVM would be incorrectly read zeros and drop writes. Note, bugging the VM doesn't completely prevent data corruption, e.g. the current round of emulation will complete before the vCPU bails out to userspace. But, the very act of killing the guest can also cause data corruption, e.g. due to lack of file writeback before termination, so taking on additional complexity to cleanly bail out of the emulator isn't justified, the goal is purely to stem the bleeding and alert userspace that something has gone horribly wrong, i.e. to avoid _silent_ data corruption. Signed-off-by:
-
Sean Christopherson authored
Reduce the number of GPRs emulated by 32-bit KVM from 16 to 8. KVM does not support emulating 64-bit mode on 32-bit host kernels, and so should never generate accesses to R8-15. Opportunistically use NR_EMULATOR_GPRS in rsm_load_state_{32,64}() now that it is precise and accurate for both flavors. Wrap the definition with full #ifdef ugliness; sadly, IS_ENABLED() doesn't guarantee a compile-time constant as far as BUILD_BUG_ON() is concerned. Signed-off-by: -
Sean Christopherson authored
Use a u16 instead of a u32 to track the dirty/valid status of GPRs in the emulator. Unlike struct kvm_vcpu_arch, x86_emulate_ctxt tracks only the "true" GPRs, i.e. doesn't include RIP in its array, and so only needs to track 16 registers. Note, maxing out at 16 GPRs is a fundamental property of x86-64 and will not change barring a massive architecture update. Legacy x86 ModRM and SIB encodings use 3 bits for GPRs, i.e. support 8 registers. x86-64 uses a single bit in the REX prefix for each possible reference type to double the number of supported GPRs to 16 registers (4 bits). Reviewed-by:
-
Sean Christopherson authored
Omit RIP from the emulator's _regs array, which is used only for GPRs, i.e. registers that can be referenced via ModRM and/or SIB bytes. The emulator uses the dedicated _eip field for RIP, and manually reads from _eip to handle RIP-relative addressing. To avoid an even bigger, slightly more dangerous change, hardcode the number of GPRs to 16 for the time being even though 32-bit KVM's emulator technically should only have 8 GPRs. Add a TODO to address that in a future commit. See also the comments above the read_gpr() and write_gpr() declarations, and obviously the handling in writeback_registers(). No functional change intended. Signed-off-by:
-
Sean Christopherson authored
WARN and truncate the incoming GPR number/index when reading/writing GPRs in the emulator to guard against KVM bugs, e.g. to avoid out-of-bounds accesses to ctxt->_regs[] if KVM generates a bogus index. Truncate the index instead of returning e.g. zero, as reg_write() returns a pointer to the register, i.e. returning zero would result in a NULL pointer dereference. KVM could also force the index to any arbitrary GPR, but that's no better or worse, just different. Open code the restriction to 16 registers; RIP is handled via _eip and should never be accessed through reg_read() or reg_write(). See the comments above the declarations of reg_read() and reg_write(), and the behavior of writeback_registers(). The horrific open coded mess will be cleaned up in a future commit. There are no such bugs known to exist in the emulator, but determining that KVM is bug-free is not at all simple and requires a deep dive into the emulator. The code is so convoluted that GCC-12 with the recently enable -Warray-bounds spits out a false-positive due to a GCC bug: arch/x86/kvm/emulate.c:254:27: warning: array subscript 32 is above array bounds of 'long unsigned int[17]' [-Warray-bounds] 254 | return ctxt->_regs[nr]; | ~~~~~~~~~~~^~~~ In file included from arch/x86/kvm/emulate.c:23: arch/x86/kvm/kvm_emulate.h: In function 'reg_rmw': arch/x86/kvm/kvm_emulate.h:366:23: note: while referencing '_regs' 366 | unsigned long _regs[NR_VCPU_REGS]; | ^~~~~ Link: https://lore.kernel.org/all/YofQlBrlx18J7h9Y@google.com Link: https://bugzilla.kernel.org/show_bug.cgi?id=216026 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105679Reported-and-tested-by:Robert Dinse <nanook@eskimo.com> Reported-by:
-
Sean Christopherson authored
Capture ctxt->regs_dirty in a local 'unsigned long' instead of casting it to an 'unsigned long *' for use in for_each_set_bit(). The bitops helpers really do read the entire 'unsigned long', even though the walking of the read value is capped at the specified size. I.e. 64-bit KVM is reading memory beyond ctxt->regs_dirty, which is a u32 and thus 4 bytes, whereas an unsigned long is 8 bytes. Functionally it's not an issue because regs_dirty is in the middle of x86_emulate_ctxt, i.e. KVM is just reading its own memory, but relying on that coincidence is gross and unsafe. Reviewed-by:
-
- 09 Jun, 2022 7 commits
-
-
Paolo Bonzini authored
s390: * add an interface to provide a hypervisor dump for secure guests * improve selftests to show tests x86: * Intel IPI virtualization * Allow getting/setting pending triple fault with KVM_GET/SET_VCPU_EVENTS * PEBS virtualization * Simplify PMU emulation by just using PERF_TYPE_RAW events * More accurate event reinjection on SVM (avoid retrying instructions) * Allow getting/setting the state of the speaker port data bit * Rewrite gfn-pfn cache refresh * Refuse starting the module if VM-Entry/VM-Exit controls are inconsistent * "Notify" VM exit
-
David Matlack authored
The selftests nested code only supports 4-level paging at the moment. This means it cannot map nested guest physical addresses with more than 48 bits. Allow perf_test_util nested mode to work on hosts with more than 48 physical addresses by restricting the guest test region to 48-bits. While here, opportunistically fix an off-by-one error when dealing with vm_get_max_gfn(). perf_test_util.c was treating this as the maximum number of GFNs, rather than the maximum allowed GFN. This didn't result in any correctness issues, but it did end up shifting the test region down slightly when using huge pages. Suggested-by:
David Matlack <dmatlack@google.com> Message-Id: <20220520233249.3776001-12-dmatlack@google.com> Signed-off-by:
-
David Matlack authored
Add an option to dirty_log_perf_test that configures the vCPUs to run in L2 instead of L1. This makes it possible to benchmark the dirty logging performance of nested virtualization, which is particularly interesting because KVM must shadow L1's EPT/NPT tables. For now this support only works on x86_64 CPUs with VMX. Otherwise passing -n results in the test being skipped. Signed-off-by:
-
David Matlack authored
Break up the long lines for LIBKVM and alphabetize each architecture. This makes reading the Makefile easier, and will make reading diffs to LIBKVM easier. No functional change intended. Reviewed-by:
Peter Xu <peterx@redhat.com> Signed-off-by:
-
David Matlack authored
The linker does obey strong/weak symbols when linking static libraries, it simply resolves an undefined symbol to the first-encountered symbol. This means that defining __weak arch-generic functions and then defining arch-specific strong functions to override them in libkvm will not always work. More specifically, if we have: lib/generic.c: void __weak foo(void) { pr_info("weak\n"); } void bar(void) { foo(); } lib/x86_64/arch.c: void foo(void) { pr_info("strong\n"); } And a selftest that calls bar(), it will print "weak". Now if you make generic.o explicitly depend on arch.o (e.g. add function to arch.c that is called directly from generic.c) it will print "strong". In other words, it seems that the linker is free to throw out arch.o when linking because generic.o does not explicitly depend on it, which causes the linker to lose the strong symbol. One solution is to link libkvm.a with --whole-archive so that the linker doesn't throw away object files it thinks are unnecessary. However that is a bit difficult to plumb since we are using the common selftests makefile rules. An easier solution is to drop libkvm.a just link selftests with all the .o files that were originally in libkvm.a. Reviewed-by: -
David Matlack authored
Drop the "all: $(STATIC_LIBS)" rule. The KVM selftests already depend on $(STATIC_LIBS), so there is no reason to have an extra "all" rule. Suggested-by:
-
David Matlack authored
Create a small helper function to check if a given EPT/VPID capability is supported. This will be re-used in a follow-up commit to check for 1G page support. No functional change intended. Reviewed-by:
-
