Skip to content

fix SIGSEGV when release resources #52

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

Open
alpha-baby wants to merge 1 commit into
base: devel
Choose a base branch
from
+8 −0
Open

fix SIGSEGV when release resources #52

Show file tree
Hide file tree
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
2 changes: 2 additions & 0 deletions src/modules/transport/ibgda/ibgda.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4105,6 +4105,7 @@ int nvshmemt_ibgda_finalize(nvshmem_transport_t transport) {
INFO(ibgda_state->log_level, "ibv_dealloc_pd failed for device %d Err: %d:%s.\n", i,
errno, strerror(errno));
}
device->common_device.pd = NULL;
}

if (device->common_device.context) {
Expand All @@ -4117,6 +4118,7 @@ int nvshmemt_ibgda_finalize(nvshmem_transport_t transport) {
NVSHMEMI_WARN_PRINT("ibv_close_device failed for device %d Err: %d:%s.\n", i, errno,
strerror(errno));
}
device->common_device.context = NULL;
}
status = 0;
// NVSHMEMI_NZ_ERROR_JMP(status, NVSHMEMX_ERROR_INTERNAL, out,
Expand Down
6 changes: 6 additions & 0 deletions src/modules/transport/ibrc/ibrc.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -732,33 +732,39 @@ int nvshmemt_ibrc_finalize(nvshmem_transport_t transport) {
status = ftable.dereg_mr(((struct ibrc_device *)state->devices)[dev_id].bpool_mr);
NVSHMEMI_NZ_ERROR_JMP(status, NVSHMEMX_ERROR_INTERNAL, out,
"ibv_dereg_mr failed \n");
((struct ibrc_device *)state->devices)[dev_id].bpool_mr = NULL;
}
if (((struct ibrc_device *)state->devices)[dev_id].send_cq) {
status = ftable.destroy_cq(((struct ibrc_device *)state->devices)[dev_id].send_cq);
NVSHMEMI_NZ_ERROR_JMP(status, NVSHMEMX_ERROR_INTERNAL, out,
"ibv_destroy_cq failed \n");
((struct ibrc_device *)state->devices)[dev_id].send_cq = NULL;
}
if (((struct ibrc_device *)state->devices)[dev_id].recv_cq) {
status = ftable.destroy_cq(((struct ibrc_device *)state->devices)[dev_id].recv_cq);
NVSHMEMI_NZ_ERROR_JMP(status, NVSHMEMX_ERROR_INTERNAL, out,
"ibv_destroy_cq failed \n");
((struct ibrc_device *)state->devices)[dev_id].recv_cq = NULL;
}
if (((struct ibrc_device *)state->devices)[dev_id].srq) {
status = ftable.destroy_srq(((struct ibrc_device *)state->devices)[dev_id].srq);
NVSHMEMI_NZ_ERROR_JMP(status, NVSHMEMX_ERROR_INTERNAL, out,
"ibv_destroy_srq failed \n");
((struct ibrc_device *)state->devices)[dev_id].srq = NULL;
}
if (((struct ibrc_device *)state->devices)[dev_id].common_device.pd) {
status = ftable.dealloc_pd(
((struct ibrc_device *)state->devices)[dev_id].common_device.pd);
NVSHMEMI_NZ_ERROR_JMP(status, NVSHMEMX_ERROR_INTERNAL, out,
"ibv_dealloc_pd failed \n");
((struct ibrc_device *)state->devices)[dev_id].pd = NULL;
}
if (((struct ibrc_device *)state->devices)[dev_id].common_device.context) {
status = ftable.close_device(
((struct ibrc_device *)state->devices)[dev_id].common_device.context);
NVSHMEMI_NZ_ERROR_JMP(status, NVSHMEMX_ERROR_INTERNAL, out,
"ibv_close_device failed \n");
((struct ibrc_device *)state->devices)[dev_id].context = NULL;
}
}
free(state->devices);
Expand Down