summaryrefslogtreecommitdiff
path: root/targets
Commit message (Collapse)AuthorAge
* trace: what push, call and ret touch; names for data; the stack's roles, sharperGabriel Schneider5 days
| | | | | | | | | | | | | | For a disassembly that points at the stack word it touched. The stack's own instructions have touches (push, call and enter write at rsp-8; pop and ret read at rsp; leave at rbp), and a rep string instruction its whole range. An address a global or static object holds is named (head+0, libc.so.6!main_arena+96). The saved rbp has its role at the push that makes it; every local in a shared word is given; the stack protector's copy is found by seeing its store; ztrace show labels each stack word. Six bytes a moment and 3% slower on the list by instruction. Co-Authored-By: Claude Fable 5.2 <[email protected]> Claude-Session: https://claude.ai/code/session_016Y9MNCKgYCGiANnEwcEQxa
* trace: a function's basic blocks; ASan's shadow memoryGabriel Schneider5 days
| | | | | | | | | | | | | | | | | For a graph of a function's blocks: at the first stop inside it a function's blocks are recorded once (bounds, how each ends, where its edges go), with every instruction's text up to 2048 of them; telescope.blocks reads them, and a branch event ties a run to the edge it took. Stripped libraries get blocks from their unwind bounds. For a plain build seen against an ASan one: record --asan keeps the shadow of every region it records, the offset found from the process; telescope.shadow gives an address's shadow byte. The report functions are named and the chain holds from inside the report to main. Tested on an overflowing target built plain, with gcc's ASan and with clang's. Co-Authored-By: Claude Fable 5.2 <[email protected]> Claude-Session: https://claude.ai/code/session_016Y9MNCKgYCGiANnEwcEQxa
* trace: names for PLT stubs and GOT slots; a call followed down; the vDSO is ↵Gabriel Schneider6 days
| | | | | | | | | | | | | | | | | | | | run through For a disassembly that follows a call into libc. A stub is open@plt and a slot open@got, from the relocations (libc's own, IFUNC and nameless, by the function they resolve to); telescope.got says what a slot holds and whether it is still lazy. A library function's entry is named even when its mapping was not known yet, by the alias the program imports. The chain holds through the stub's jump, the callee's first instruction, the syscall and the loader's resolver: ld.so's unwind section lacks the entry that ends it, which lost every frame there. A syscall is tied to its instruction's moment, and each frame's call is recorded with the row before it. Stepped by instruction, a call into the vDSO is one moment and its return the next: its clock loop, single-stepped, made three million moments of three reads. Co-Authored-By: Claude Fable 5.2 <[email protected]> Claude-Session: https://claude.ai/code/session_016Y9MNCKgYCGiANnEwcEQxa
* trace: glibc's heap, read from a recording at any momentGabriel Schneider6 days
| | | | | | | | | | | | | | | | | record --heap keeps the arena, the tcache and, of every chunk, its size word and the links of those on a list: free chunks stay readable, which --alloc dropped at the free. zt.heap.glibc gives the chunks in address order, the tcache's and the bins' chains (safe-linking as the stored value and the pointer it protects), the top; each with the address of the word it was read from, each chain saying how it ended. ztrace show prints it. Layouts for glibc 2.44 (no fastbins; a tcache made at the first free, counting the slots left) and 2.40; the arena found by symbol or by the struct whose next points at itself. Against pwndbg on 2.40: the same at every stop. Three bytes a moment and a sixth slower on the list by instruction. Co-Authored-By: Claude Fable 5.2 <[email protected]> Claude-Session: https://claude.ai/code/session_016Y9MNCKgYCGiANnEwcEQxa
* agent: its handlers act with the thread's protection keys and float modes, ↵Gabriel Schneider6 days
| | | | | | | | | | | | | | | | | | | | | | | | | | | not a handler's The kernel starts a signal handler with default PKRU (key 0 only) and default MXCSR and x87 control word, the thread's own saved in the frame. The SIGSYS handler makes the thread's syscalls and clones its threads from there, so under --syscalls: - a pkey_alloc's new rights were undone when the handler returned; - a thread was born with no right to keyed memory (V8's compiler threads fault reading the code space: d8 died of SEGV_PKUERR, and the 35 seconds were its core dump, not a spin); - a buffer in keyed memory was EFAULT to the kernel, and a fault to the agent reading it for the event; - a thread started without its maker's float modes (flush-to-zero). Both handlers now take the thread's PKRU and control words from the frame first (signal.adopt), and the SIGSYS one writes PKRU back to the frame after the syscall. Watched memory is read, and hooked code patched, with every key open, so a key the thread itself cannot use hides nothing. test-agent: agent_pkey (a keyed page read, given to syscalls, watched, read by a later thread; skips itself without keys), and agent_sys's thread checks its MXCSR. README: --alloc and programs with their own malloc; the core dump. Co-Authored-By: Claude Fable 5.2 <[email protected]>
* ztrace probe: BPF on syscalls, scheduling, kprobes, uprobes and USDTGabriel Schneider6 days
| | | | | | | | | | | | | | | | Programs built as instruction arrays for one process (no compiler, no libbpf), writing Events into a BPF ring buffer; a drop counter in a map; task_struct offsets from the kernel's BTF; a USDT probe's arguments read in the kernel at the probe. Without CAP_BPF and CAP_PERFMON it says so; --dry-run builds and lists everything. Tested offline by running the programs in a small BPF machine, and for real by test-kernel-vm, which boots this kernel in QEMU where we are root. ztrace perf: moments are no longer cut per event unless --cut; --max-size, and a full recording stops the target and says so. perf.Sorted merges two backends' events by time. Co-Authored-By: Claude Fable 5.2 <[email protected]>
* ztrace perf: the kernel's view of a program, unprivilegedGabriel Schneider6 days
| | | | | | | | | | | | | perf_event_open on a held child: counters, a sampling profile, every page fault with its registers, maps, threads, context switches, every syscall (the per-syscall tracepoints, the only ones open to a user), and the debug registers as watchpoints and breakpoints that do not stop the target. One time-ordered stream of Events into a Sink; --threads follows with a ring per CPU. usdt.zig: the notes of <sys/sdt.h> and their arguments from a Regs and a memory reader, independent of BPF. test-kernel runs all of it on targets/kernel_*. Co-Authored-By: Claude Fable 5.2 <[email protected]>
* agent_list: the page is read through a volatile pointerGabriel Schneider6 days
| | | | | Without UBSan the compiler at -O1 folds the read and deletes aligned_alloc with it, and the list check counts one allocation short.
* agent: bench-agent and its numbers, hooks with names, an archive cc can linkGabriel Schneider6 days
| | | | | | | | | | | | | zig build bench-agent runs each capability against its native loop and prints what it costs and writes; README has the table. ztrace run looks at the ring a little longer before sleeping (a target that finds the tracer asleep pays a futex wake an event). A hooked function's name is defined as the string of its address, so the recorder's call stack reads fib. A static link without libc's malloc says which -u to add. The archive carries no stack probes, so cc links it in debug builds too. Tests for --wrap (musl, zig cc) and for a recording that fills. Co-Authored-By: Claude Fable 5.2 <[email protected]>
* agent: the in-process backend, and ztrace run's options for itGabriel Schneider6 days
| | | | | | | | | | | | | | libztrace-agent.so (preloaded) and libztrace-agent.a (linked in), one source: map and thread_start at startup; alloc/free from the interposed allocator; syscall_enter/exit through Syscall User Dispatch; call/ret from int3 hooks; mem_write from watched regions diffed in-process; the target-side API (include/ztrace.h, and the ztrace-agent module for Zig). ztrace run turns each on (--alloc --syscalls --hook --watch), chooses the moments (--cut), and stops the target at event kinds without ptrace (--stop-at, --read, -i). test-agent records real targets and checks the recordings. Co-Authored-By: Claude Fable 5.2 <[email protected]>
* llvm: a pass that instruments for animation, its runtime, ztrace ccGabriel Schneider6 days
| | | | | | | | | | | | | | | | llvm/pass.cpp is an LLVM pass plugin: lines, stores, loads, calls and variables, each call into the runtime carrying names and type descriptions, selected by globs (-ztrace-only, -ztrace-mem), before the optimizer by default. src/instr/rt.zig is the runtime (libztrace-rt.a), which also answers clang's own coverage and -finstrument-functions hooks; src/instr/types.zig the grammar of the type descriptions and its parser. ztrace cc adds all of it to a compiler command. test-llvm compiles fib, two sorts, a linked list and a BFS through ztrace cc and asserts on their recordings; bench-llvm measures what each selection costs. Co-Authored-By: Claude Fable 5.2 <[email protected]>
* targets, test-debugger, bench-debuggerGabriel Schneider6 days
| | | | | | | | | | | A linked list, a graph search in Zig, the same C under glibc and musl, two threads. The tests drive the debugger over them: breakpoint counts, the lines a step walks (as gdb), a list snapshotted by a hook, a watch's words, the syscalls that tell glibc from musl, threads, attach, and scripted dbg and record sessions. The bench measures steps, stops and memory access from bare ptrace up to a recording. Co-Authored-By: Claude Fable 5.2 <[email protected]>
* ztrace: the event, the ring, the recording, a ptrace loopGabriel Schneider6 days
One 64-byte Event for every backend; a shared-memory ring from target to tracer with stop/resume; a Recorder that folds events into xitdb moments (registers, memory in 64-byte chunks with known-byte masks, strings) and a Trace that reads any moment back; a minimal ptrace Process; ztrace record, run and dump. Per-area build files so the areas grow apart.