Skip to content

changed 0xD for 0x0 leaf in timer #663

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
NotRequiem merged 1 commit into from
Mar 31, 2026
+3 −3
Merged

changed 0xD for 0x0 leaf in timer #663

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions src/vmaware.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5132,7 +5132,7 @@

std::string line;
int processors = 0;
bool in_section = false;

Check warning on line 5135 in src/vmaware.hpp

View workflow job for this annotation

GitHub Actions / Analyze (cpp, gcc-14, Ninja Multi-Config, Debug, ON) 

variable 'in_section' set but not used [-Wunused-but-set-variable]
int cur_phys = -1, cur_core = -1;
std::vector<std::pair<int, int>> cores;

Expand Down Expand Up @@ -5377,7 +5377,7 @@
debug("TIMER: Running inside a binary translation layer");
return false;
}
if (util::hyper_x() != HYPERV_UNKNOWN) threshold = 20.0;
if (util::hyper_x() != HYPERV_UNKNOWN) threshold = 25.0;

// prevent false sharing when triggering hypervisor exits with the intentional data race condition
struct alignas(64) cache_state {
Expand Down Expand Up @@ -5647,7 +5647,7 @@
v_pre = state.counter;
std::atomic_signal_fence(std::memory_order_seq_cst); // _ReadWriteBarrier() aka dont emit runtime fences
// force cpuid collection here so that the hypervisor is either forced to disable interception and try to bypass latency, or intercept cpuid and try to bypass XSAVE states
trigger_vmexit(dummy_res, 0xD, 0);
trigger_vmexit(dummy_res, 0x0, 0); // fastest cpuid path, on purpose for stability in the measurement
std::atomic_signal_fence(std::memory_order_seq_cst);
v_post = state.counter;

Expand Down Expand Up @@ -12010,7 +12010,7 @@
// veh will already detect if Dr0 fired successfully
}

// Cleanup
// cleanup
rtl_remove_vectored_exception_handler(veh_handle);

ctx.Dr0 = 0;
Expand Down
Loading