- Detail the multi-stage infection process using ptrace
- Explain memory exchange optimization via memfd
- Describe the PIE relocation and GOT patching
- Explain the daemon mode and request-response control loop
- Document the 'cure' operation for returning tasks to their original state
Signed-off-by: Andrei Vagin <avagin@google.com>
- Explain the 2MB sliding window (PMC_SIZE) mechanism
- Describe greedy prefetching for adjacent small VMAs
- Document the usage of ioctl(PAGEMAP_SCAN) on modern kernels
- Clarify cache invalidation strategies during dump phases
- Mention the CRIU_PMC_OFF environment variable for debugging
Signed-off-by: Andrei Vagin <avagin@google.com>
- Explain 'splice' (default) vs 'read' (traditional) pre-dump modes
- Detail the zero-copy gifting mechanism using vmsplice() and SPLICE_F_GIFT
- Explain how COW ensures consistency while capturing memory from running tasks
- Describe parallel draining of pages to minimize freeze time
Signed-off-by: Andrei Vagin <avagin@google.com>
- Formalize the stages of the Mount V2 engine
- Explain the role of the Root Yard (root_yard_mp)
- Describe pre-fork plain mounting and source resolution
- Detail propagation restoration via MOVE_MOUNT_SET_GROUP
- Explain the final pivot_root and post-fork fixup stages
Signed-off-by: Andrei Vagin <avagin@google.com>
- Explain the shift from path-based to FD-based mounting
- Detail the use of detached mounts via open_tree() and fsopen()
- Describe propagation grouping via MOVE_MOUNT_SET_GROUP (v5.15+)
- Explain the tree construction and atomic final attachment process
- Update kernel requirements and fallback behavior
Signed-off-by: Andrei Vagin <avagin@google.com>
- Detail key information captured from /proc/pid/mountinfo
- Explain the restoration challenges (dependencies, propagation)
- Document the Mount V2 engine and its benefits
- Explain external mount mapping and auto-detection
- List common issues like overmounts and unsupported filesystems
Signed-off-by: Andrei Vagin <avagin@google.com>
- Explain the in_parent flag in pagemap entries
- Detail detection of unchanged pages via soft-dirty bit
- Document the --auto-dedup mode for dump and restore
- Describe online disk space reclamation using FALLOC_FL_PUNCH_HOLE
- Clarify image chaining and sparse file support
Signed-off-by: Andrei Vagin <avagin@google.com>
- Detail the multi-stage dumping approach involving parasite injection
- Explain zero-copy dumping using vmsplice() and SPLICE_F_GIFT
- Describe the use of splice() for efficient image writing and page server transport
- Document VMA re-mapping and content filling during restoration
- Add references to COW preservation and lazy migration (userfaultfd)
Signed-off-by: Andrei Vagin <avagin@google.com>
- Explain the soft-dirty bit mechanism for tracking modified pages
- Document the usage of ioctl(PAGEMAP_SCAN) for efficient scanning (kernel v6.7+)
- Describe the iterative pre-dump workflow and image chaining
- Detail the consolidation of pages during restoration
- Mention the role of the page server in minimizing disk I/O
Signed-off-by: Andrei Vagin <avagin@google.com>
- Clarify feature detection for system calls, filesystems, and namespaces
- Update persistent caching locations (/run/criu.kdat vs XDG_RUNTIME_DIR)
- Distinguish between kerndat (host capabilities) and inventory (checkpoint metadata)
- Mention 'criu check --extra' for runtime inspection
Signed-off-by: Andrei Vagin <avagin@google.com>
- Explain the kernel pointer comparison mechanism of kcmp()
- Describe the two-level red-black tree optimization (genid + kcmp sub-tree)
- List all supported KCMP_* types (FILE, VM, FILES, FS, EPOLL_TFD, etc.)
- Clarify how genid minimizes expensive system calls
Signed-off-by: Andrei Vagin <avagin@google.com>
- Describe the (inode, device) to path resolution problem
- List default heuristic scan hints (/etc, /var/log, etc.)
- Explain user-defined scan paths via --irmap-scan-path
- Detail the pre-dump optimization and irmap-cache.img
- Clarify the status of Irmap vs open_by_handle_at on modern kernels
Signed-off-by: Andrei Vagin <avagin@google.com>
- Formalize Master and Slave descriptor roles
- Explain the SCM_RIGHTS distribution mechanism
- Document transport socket naming and 'criu_run_id' usage
- Detail deterministic master selection to avoid deadlocks
- Explain dynamic service FD relocation during collisions
Signed-off-by: Andrei Vagin <avagin@google.com>
- Detail the challenges of finding the 'watchee' path
- Explain the use of open_by_handle_at() and Irmap
- Explicitly document that pending events are dropped with a warning
- Explain how spurious events are generated during restore (ghost files)
- Add details for Fanotify inode and mount marks
Signed-off-by: Andrei Vagin <avagin@google.com>
- Explain the PTRACE_SEIZE and PTRACE_INTERRUPT sequence
- Detail the transparency of ptrace-stop (TRAP_STOP)
- Document cgroup v1 and v2 freezer mechanisms
- Mention kernel kludges for v1 freezer unreliability
- Clarify the relationship between freezer and ptrace
Signed-off-by: Andrei Vagin <avagin@google.com>
- Formalize TASK_ALIVE, TASK_STOPPED, and TASK_DEAD states
- Explain the rationale for default behaviors in dump/restore
- Mention pre-dump enforcement of the Running state
- Document the use of --leave-stopped for debugging
- Add instructions for resuming trees via SIGCONT and pstree_cont.py
Signed-off-by: Andrei Vagin <avagin@google.com>
- Formalize the Master and Slave descriptor concepts
- Describe the 'open()' state machine and early FD distribution via SCM_RIGHTS
- Document the inter-process synchronization (set_fds_event, futexes)
- List key dependencies (TTYs, Unix Sockets, Epoll)
- Add notes on Service FDs and restoration ordering
Signed-off-by: Andrei Vagin <avagin@google.com>
- Detail the Linux file object hierarchy (Inode, Dentry, File)
- Explain the SCM_RIGHTS mechanism for retrieving local FD copies
- Describe the gen_id and kcmp optimization for shared file detection
- Clarify the two-tier image storage structure (fdinfo vs specialized images)
Signed-off-by: Andrei Vagin <avagin@google.com>
- Formalize the architectural comparison (userspace vs. kernel integration)
- Highlight the dangers of DMTCP's fake PID virtualization
- Explain CRIU's usage of ns_last_pid and clone3 for real PID restoration
- Improve overall technical clarity and structure
Signed-off-by: Andrei Vagin <avagin@google.com>
- Explain the identification of COW candidates by comparing parent/child VMAs
- Describe the pre-mapping strategy before fork to leverage kernel sharing
- Detail the content verification and manual COW triggering
- Document the use of madvise(MADV_DONTNEED) for final memory layout accuracy
- Clarify current limitations regarding reparenting and VMA movement
Signed-off-by: Andrei Vagin <avagin@google.com>
- Embed DMTCP description and characteristics
- Update CRIU supported architectures (s390, MIPS, RISC-V, etc.)
- Refine the comparison table for accuracy and modern features
- Add more context for BLCR, PinPlay, and Legacy OpenVZ
Signed-off-by: Andrei Vagin <avagin@google.com>
- Document the use of 'compel hgen' for header generation
- Update the example header format to include structured relocations
- Describe the 'parasite_blob_desc' setup functions
- Refine the build procedure steps
Signed-off-by: Andrei Vagin <avagin@google.com>
- Clarify freezing mechanisms (PTRACE_INTERRUPT, Freezer CGroup)
- Detail the parasite injection and bootstrap process
- Explain the role of the restorer blob as a PIE and its conflict avoidance
- Document the final transition via sigreturn
Signed-off-by: Andrei Vagin <avagin@google.com>
- Explain the core problem of TCP 4-tuple mismatch
- Describe solutions for listening, in-flight, and established sockets
- Document the UPDATE_INETSK plugin hook for programmatic IP remapping
- Add a summary table of options and flags
Signed-off-by: Andrei Vagin <avagin@google.com>
- Document full CGroup v2 support and properties
- Explain CGroup namespace (CLONE_NEWCGROUP) handling
- Clarify the 'soft mode' default and other restoration strategies
- Detail the root mount requirement for bind-mounted subgroups
Signed-off-by: Andrei Vagin <avagin@google.com>
- Explain metadata collection from /proc and BPF syscall
- Describe data serialization using batch operations
- Add details about frozen maps handling
- Clarify current limitations regarding map_extra and BTF
Signed-off-by: Andrei Vagin <avagin@google.com>
- Explain how CRIU restores AIO context IDs and ring buffers
- Describe the tail synchronization technique using dummy /dev/null requests
- Clarify the lack of support for in-flight events and its implications
Signed-off-by: Andrei Vagin <avagin@google.com>
- Replace FIXME with a detailed description of the current approach
- Explain architecture detection using PTRACE_GETREGSET
- Describe the restoration process via sigreturn and mode switching
- Update vsyscall handling details
- Clarify the status of x32 support and TIF_IA32 removal
Signed-off-by: Andrei Vagin <avagin@google.com>
Private anonymous VMA contents have to be copied inside the PIE
restorer after mappings are placed at their final addresses.
Replace the synchronous preadv loop with a bounded Linux native AIO
window that submits page-read iovecs, reaps completions, and
resubmits short reads.
Keep auto-dedup punching on completed byte ranges and tear down the
AIO context on both success and error paths. The pages fd is
prepared for O_DIRECT before entering the restorer.
VMA page reads are page-aligned by construction: the destination
buffers are page-aligned, the iovec lengths are page multiples, and
the file offsets are page-aligned. O_DIRECT completions are
therefore always a whole number of pages (short reads only occur at
MAX_RW_COUNT or at EOF on page-multiple files), so resubmitting a
short read keeps its offset and buffers aligned without masking the
completion length.
Assisted-by: Claude:claude-sonnet-4-6
Assisted-by: Claude:claude-opus-4-7
Assisted-by: Codex:gpt-5
Signed-off-by: Dan Feigin <dfeigin@nvidia.com>
Shared-memory restore currently issues page reads one pagemap entry
at a time. Use the existing PR_ASYNC path to enqueue shmem and
memfd-shmem reads, then flush each batch with one async-queue sync
pass.
Restore shmem, sysv-shmem and memfd-shmem content through a single
flat do_restore_shmem_content() loop that owns its page_read, and
map the memfd the same way as anonymous shmem so both share one
restore path instead of an extra temporary mapping.
Shmem segments are mapped via mmap() (page-aligned addresses) and
the pagemap offsets are PAGE_SIZE multiples, so the batched reads
are page-aligned and need no special O_DIRECT alignment handling.
Assisted-by: Claude:claude-sonnet-4-6
Assisted-by: Claude:claude-opus-4-7
Assisted-by: Codex:gpt-5
Signed-off-by: Dan Feigin <dfeigin@nvidia.com>
Native AIO page restore needs the pages image fd to support direct
I/O, but some filesystems accept O_DIRECT with fcntl() and reject
the first read with EINVAL.
Enable O_DIRECT after the image headers are read, probe with an
aligned read, and fall back to buffered sequential I/O when the
probe reports EINVAL. Cache the result in page_read so normal page
reads do not need a flag lookup per request.
The streamer fd (opts.stream) is excluded from the probe because
its read loop uses arbitrary user buffers that are not aligned for
O_DIRECT.
PAGE_SIZE is not a compile-time constant on aarch64 (sysconf-backed
runtime value to support 4K/16K/64K kernels), so the probe buffer
is allocated with posix_memalign() instead of a stack array with
__attribute__((aligned(PAGE_SIZE))).
The single-page COW comparison buffer in restore_priv_vma_content()
is likewise allocated with posix_memalign() so direct reads into it
are page-aligned; this lets the local read path drop its per-read
bounce buffer.
Assisted-by: Claude:claude-sonnet-4-6
Assisted-by: Claude:claude-opus-4-7
Assisted-by: Codex:gpt-5
Signed-off-by: Dan Feigin <dfeigin@nvidia.com>
The restorer already has io_setup, io_submit, and io_getevents
syscall wrappers for all supported architectures. Native AIO restore
also needs io_destroy to release the AIO context before leaving the
restorer path.
Add the missing io_destroy syscall entries next to the existing
native AIO syscalls.
Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Dan Feigin <dfeigin@nvidia.com>
The alpine-test CI job runs all ~483 zdtm tests sequentially three
times (normal, mntns-compat-mode, criu-config), followed by many
non-shardable tests. This dominates overall CI wait time. With only
2 jobs running in parallel (GCC and CLANG) the alpine tests take
around 30 minutes.
Use the existing --test-shard-index and --test-shard-count flags
already built into test/zdtm.py to split the zdtm test suite across
four parallel runners (shards 0-3). A fifth shard runs all
non-shardable tests (lazy pages, fault injection, test/others/*,
rootless, compel, plugins, etc.) independently and in parallel with
the zdtm shards. This increases parallelism from 2 to 10 jobs and
reduces the alpine test wall-clock time from ~30 to ~10 minutes.
Changes:
- run-ci-tests.sh: Build SHARD_OPTS from ZDTM_SHARD_INDEX/COUNT
env vars and pass them to zdtm.py. Extract all non-shardable
tests into a run_non_shardable_tests() function. Dispatch based
on shard index: 0-3 run zdtm slices, 4 runs non-shardable
tests, unset runs everything sequentially (preserving existing
behavior). Validate that ZDTM_SHARD_INDEX is set when
ZDTM_SHARD_COUNT is set.
- Makefile: Pass ZDTM_SHARD_INDEX and ZDTM_SHARD_COUNT into the
container when set. Split long container run command across
multiple lines for readability.
- ci.yml: Add shard: [0, 1, 2, 3, 4] to the alpine-test matrix,
producing 10 jobs (2 compilers x 5 shards). Job labels now show
descriptive shard names (e.g. "zdtm 1/4", "non-zdtm") instead
of raw indices.
When sharding is not configured the script behaves identically to
before, so other CI jobs (aarch64, compat, gcov, etc.) are
unaffected.
Assisted-by: Claude:claude-opus-4-6
Signed-off-by: Adrian Reber <areber@redhat.com>
Starting with Linux 7.1, the kernel enforces strict read-only field
protection for the rseq V2 ABI. Userspace is no longer allowed to
modify kernel-managed fields (cpu_id_start, cpu_id, node_id, mm_cid)
while rseq is registered. Violations are detected on the next context
switch and the offending process is killed with SIGSEGV.
The rseq01 test was zeroing the entire glibc-registered rseq area
with memset() before calling test_init(), which internally calls
fork(). This corrupted the read-only fields while the glibc rseq
registration was still active, causing the kernel to send SIGSEGV
during the fork.
Fix this by calling unregister_old_rseq() before the memset in both
main() and thread_routine(), so the kernel is no longer monitoring
those fields when they are zeroed. The subsequent register_thread()
call re-registers rseq with the clean area.
Link: 7f00232152
Assisted-by: Claude Code (https://claude.ai/code):claude-opus-4-6
Signed-off-by: Adrian Reber <areber@redhat.com>
Commit
1961c5e0de ("plugins/amdgpu: Cleanup env variable handling")
converted some error logs into warnings under the rationale of failures
not being fatal, but the execution continues with the default values.
Convert one more such error to a warning, as pointed out by Copilot that
makes things more consistent.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Copilot reports a possible false positive error on strtoul conversion due
errno not being reset on success. Fix it by clearing errnor prior to the
call.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Copilot reports %d is correct for boolean and %zx for size_t, fix it.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Fixes: 1961c5e0de ("plugins/amdgpu: Cleanup env variable handling")
A bunch of globals defined at the top of amdgpu_plugin.c only needs local
scope so make it so.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
It is a bit tidier to make the helpers return the value instead of passing
in the pointer, so lets make them take the default and return the overall
result, allowing the call sites to consolidate into a single line.
While at it we make the helpers static since they are not used outside the
file and demote the parsing errors to warning log messages since the
plugin does continue operating.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
In restorer_get_vma_hint, if a VMA from self_vma_list or tgt_vma_list
overlaps with the current candidate region (prev_vma_end + vma_len), we
advance prev_vma_end and move to the next VMA in the list. However, we
must then restart the check from the beginning of the while loop to
ensure that the updated candidate region doesn't overlap with any other
VMAs.
Fixes#3018
Fixes: 2c9ee0abd2 ("restore: update prev_vma_end after processing the last vma in a list")
Signed-off-by: Andrei Vagin <avagin@google.com>
mmaps done just for reserving address space something like
void *addr = mmap(NULL, SIZE, PROT_NONE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
Ensure that these do not have ac flag set in /proc/pid/smaps.
Signed-off-by: Bhavik Sachdev <b.sachdev1904@gmail.com>
