criu: Version 4.2 (CRIUTIBILITY)

Documentation/criu-amdgpu-plugin.txt

@@ -15,7 +15,6 @@ Checkpoint / Restore inside a docker container
 Pytorch
 Tensorflow
 Using CRIU Image Streamer
-Parallel Restore
 
 DESCRIPTION
 -----------

Makefile.versions

@@ -1,10 +1,10 @@
 #
 # CRIU version.
 CRIU_VERSION_MAJOR	:= 4
-CRIU_VERSION_MINOR	:= 1
-CRIU_VERSION_SUBLEVEL	:= 1
+CRIU_VERSION_MINOR	:= 2
+CRIU_VERSION_SUBLEVEL	:=
 CRIU_VERSION_EXTRA	:=
-CRIU_VERSION_NAME	:= CRISCV
+CRIU_VERSION_NAME	:= CRIUTIBILITY
 CRIU_VERSION		:= $(CRIU_VERSION_MAJOR)$(if $(CRIU_VERSION_MINOR),.$(CRIU_VERSION_MINOR))$(if $(CRIU_VERSION_SUBLEVEL),.$(CRIU_VERSION_SUBLEVEL))$(if $(CRIU_VERSION_EXTRA),.$(CRIU_VERSION_EXTRA))
 
 export CRIU_VERSION_MAJOR CRIU_VERSION_MINOR CRIU_VERSION_SUBLEVEL

coredump/criu_coredump/coredump.py

@@ -794,7 +794,8 @@ def _get_page(self, pid, page_no):
         off = 0  # in pages
         for m in pagemap[1:]:
             found = False
-            num_pages = m.get("nr_pages", m.compat_nr_pages)
+            num_pages = m.get("nr_pages", m["compat_nr_pages"])
+
             for i in range(num_pages):
                 if m["vaddr"] + i * PAGESIZE == page_no * PAGESIZE:
                     found = True

plugins/amdgpu/Makefile

@@ -27,7 +27,7 @@ endif
 criu-amdgpu.pb-c.c: criu-amdgpu.proto
 		protoc --proto_path=. --c_out=. criu-amdgpu.proto
 
-amdgpu_plugin.so: amdgpu_plugin.c amdgpu_plugin_drm.c amdgpu_plugin_topology.c amdgpu_plugin_util.c criu-amdgpu.pb-c.c amdgpu_socket_utils.c
+amdgpu_plugin.so: amdgpu_plugin.c amdgpu_plugin_drm.c amdgpu_plugin_topology.c amdgpu_plugin_util.c criu-amdgpu.pb-c.c
 	$(CC) $(PLUGIN_CFLAGS) $(shell $(COMPEL) includes) $^ -o $@ $(PLUGIN_INCLUDE) $(PLUGIN_LDFLAGS) $(LIBDRM_INC)
 
 amdgpu_plugin_clean:

plugins/amdgpu/README.md

@@ -3,8 +3,7 @@ Supporting ROCm with CRIU
 
 _Felix Kuehling <Felix.Kuehling@amd.com>_<br>
 _Rajneesh Bardwaj <Rajneesh.Bhardwaj@amd.com>_<br>
-_David Yat Sin <David.YatSin@amd.com>_<br>
-_Yanning Yang <yangyanning@sjtu.edu.cn>_
+_David Yat Sin <David.YatSin@amd.com>_
 
 # Introduction
 
@@ -225,26 +224,6 @@ to resume execution on the GPUs.
 *This new plugin is enabled by the new hook `__RESUME_DEVICES_LATE` in our RFC
 patch series.*
 
-## Restoring BO content in parallel
-
-Restoring the BO content is an important part in the restore of GPU state and
-usually takes a significant amount of time. A possible location for this
-procedure is the `cr_plugin_restore_file` hook. However, restoring in this hook
-blocks the target process from performing other restore operations, which
-hinders further optimization of the restore process.
-
-Therefore, a new plugin hook that runs in the master restore process is
-introduced, and it interacts with the `cr_plugin_restore_file` hook to complete
-the restore of BO content. Specifically, the target process only needs to send
-the relevant BOs to the master restore process, while this new hook handles all
-the restore of buffer objects. Through this method, during the restore of the BO
-content, the target process can perform other restore operations, thus
-accelerating the restore procedure. This is an implementation of the gCROP
-method proposed in the ACM SoCC'24 paper: [On-demand and Parallel
-Checkpoint/Restore for GPU Applications](https://dl.acm.org/doi/10.1145/3698038.3698510).
-
-*This optimization technique is enabled by the `__POST_FORKING` hook.*
-
 ## Other CRIU changes
 
 In addition to the new plugins, we need to make some changes to CRIU itself to