summaryrefslogtreecommitdiff
path: root/sys/dev/nvmm
AgeCommit message (Expand)Author
2020-08-05Simplify, remove unnecessary #ifdef DIAGNOSTIC around KASSERTs.maxv
2020-08-01Put the few x86-specific structures under #ifdef __x86_64__, for clarity.maxv
2020-07-19Switch to fpu_kern_enter/leave, to prevent clobbering, now that the kernelmaxv
2020-07-19The TLB flush IPIs do not respect the IPL, so enforcing IPL_HIGH has nomaxv
2020-07-18Now that the IDT is per-CPU, it must be saved/restored on each CPUmaxv
2020-07-14Introduce per-cpu IDTsyamaguchi
2020-07-03Print the backend name when attaching.maxv
2020-06-25Register NVMM as an actual pseudo-device. Without PMF handler, tomaxv
2020-06-18stylemaxv
2020-05-24Gather the conditions to return from the VCPU loops in nvmm_return_needed(),maxv
2020-05-21Complete rev1.26: reset nvmm_impl to NULL in nvmm_fini().maxv
2020-05-21Improve the CPUID emulation on nvmm-intel: limit the highest basic andmaxv
2020-05-10Respect the convention for the hypervisor information: return the highestmaxv
2020-05-09Improve the CPUID emulation of basic leaves:maxv
2020-05-09On Intel CPUs, CPUID leaf 0xB, too, provides topology information, somaxv
2020-04-30If we were processing a software int/excp, and got a VMEXIT in the middle,maxv
2020-04-30When the identification fails, print the reason.maxv
2020-04-26In nvmm_open(), make sure an implementation was found. This fixes anmaxv
2020-03-22x86 pmap:ad
2020-03-14- Hide the details of SPCF_SHOULDYIELD and related behind a couple of smallad
2020-03-12vmx_vmptrst(): only used when DIAGNOSTICtnn
2020-02-21Explicitly cast pointers to uintptr_t before casting to enums. They arejoerg
2020-01-09Registering the host's CR0 is done outside of the VCPU loop, so it must bemaxv
2020-01-09Mmh, as noted in PR/54847, this should be uint64_t, not uint16_t. Harmlessmaxv
2019-12-10pg->phys_addr > VM_PAGE_TO_PHYS(pg)ad
2019-11-20Hide XSAVES-specific stuff and the masked extended states.maxv
2019-11-16Don't report MWAITX by default.maxv
2019-10-28Add nram in struct nvmm_ctl_mach_info.maxv
2019-10-28A few changes:maxv
2019-10-27Change the way root_owner works: consider the calling process as root_ownermaxv
2019-10-27Add PCID support in the guests. This speeds up most 64bit guests, becausemaxv
2019-10-27Mask CPUID leaf 0x0A on Intel, because we don't want the guest to try (andmaxv
2019-10-27Add a new VCPU conf option, that allows userland to request VMEXITs after amaxv
2019-10-23Miscellaneous changes in NVMM, to address several inconsistencies andmaxv
2019-10-12Rewrite the FPU code on x86. This greatly simplifies the logic and removesmaxv
2019-10-04Switch to the new PTE naming.maxv
2019-10-04Fix definition for MWAIT. It should be bit 11, not 12; 12 is the armedmaxv
2019-10-04Add definitions for RDPRU, MCOMMIT, GMET and VTE.maxv
2019-09-13Always set hwcode on error. Useful for debugging.maxv
2019-07-06Localify two functions that are no longer used outside. Also return themaxv
2019-06-16Make sure VMX-outside-SMX is allowed. It may not be if the BIOS decided tomaxv
2019-05-18Now that SVS cannot be disabled at run time, MSR_LSTAR is static, so nomaxv
2019-05-15NVMM: Expose MD_CLEAR to the guests.maxv
2019-05-11Rework the machine configuration interface.maxv
2019-05-01Use the comm page to inject events, rather than ioctls, and commit them inmaxv
2019-04-29Stop taking care of the INT/NMI windows in the kernel, the emulator ismaxv
2019-04-28Modify the communication layer between the kernel NVMM driver and libnvmm:maxv
2019-04-27Mmh, fix nvmm_vcpu_create(), the cpuid is given, and must not be chosenmaxv
2019-04-27Reorder the NVMM headers, to make a clear(er) distinction between MI andmaxv
2019-04-27If guest events were being processed when a #VMEXIT occurred, reschedulemaxv