This is a note to let you know that I've just added the patch titled
RDMA/irdma: Fix data race on CQP request done
to the 6.1-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
rdma-irdma-fix-data-race-on-cqp-request-done.patch
and it can be found in the queue-6.1 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit e9397bf7e8eb75047f210179194e55687b75c511
Author: Shiraz Saleem <shiraz.saleem@xxxxxxxxx>
Date: Tue Jul 11 12:52:53 2023 -0500
RDMA/irdma: Fix data race on CQP request done
[ Upstream commit f0842bb3d38863777e3454da5653d80b5fde6321 ]
KCSAN detects a data race on cqp_request->request_done memory location
which is accessed locklessly in irdma_handle_cqp_op while being
updated in irdma_cqp_ce_handler.
Annotate lockless intent with READ_ONCE/WRITE_ONCE to avoid any
compiler optimizations like load fusing and/or KCSAN warning.
[222808.417128] BUG: KCSAN: data-race in irdma_cqp_ce_handler [irdma] / irdma_wait_event [irdma]
[222808.417532] write to 0xffff8e44107019dc of 1 bytes by task 29658 on cpu 5:
[222808.417610] irdma_cqp_ce_handler+0x21e/0x270 [irdma]
[222808.417725] cqp_compl_worker+0x1b/0x20 [irdma]
[222808.417827] process_one_work+0x4d1/0xa40
[222808.417835] worker_thread+0x319/0x700
[222808.417842] kthread+0x180/0x1b0
[222808.417852] ret_from_fork+0x22/0x30
[222808.417918] read to 0xffff8e44107019dc of 1 bytes by task 29688 on cpu 1:
[222808.417995] irdma_wait_event+0x1e2/0x2c0 [irdma]
[222808.418099] irdma_handle_cqp_op+0xae/0x170 [irdma]
[222808.418202] irdma_cqp_cq_destroy_cmd+0x70/0x90 [irdma]
[222808.418308] irdma_puda_dele_rsrc+0x46d/0x4d0 [irdma]
[222808.418411] irdma_rt_deinit_hw+0x179/0x1d0 [irdma]
[222808.418514] irdma_ib_dealloc_device+0x11/0x40 [irdma]
[222808.418618] ib_dealloc_device+0x2a/0x120 [ib_core]
[222808.418823] __ib_unregister_device+0xde/0x100 [ib_core]
[222808.418981] ib_unregister_device+0x22/0x40 [ib_core]
[222808.419142] irdma_ib_unregister_device+0x70/0x90 [irdma]
[222808.419248] i40iw_close+0x6f/0xc0 [irdma]
[222808.419352] i40e_client_device_unregister+0x14a/0x180 [i40e]
[222808.419450] i40iw_remove+0x21/0x30 [irdma]
[222808.419554] auxiliary_bus_remove+0x31/0x50
[222808.419563] device_remove+0x69/0xb0
[222808.419572] device_release_driver_internal+0x293/0x360
[222808.419582] driver_detach+0x7c/0xf0
[222808.419592] bus_remove_driver+0x8c/0x150
[222808.419600] driver_unregister+0x45/0x70
[222808.419610] auxiliary_driver_unregister+0x16/0x30
[222808.419618] irdma_exit_module+0x18/0x1e [irdma]
[222808.419733] __do_sys_delete_module.constprop.0+0x1e2/0x310
[222808.419745] __x64_sys_delete_module+0x1b/0x30
[222808.419755] do_syscall_64+0x39/0x90
[222808.419763] entry_SYSCALL_64_after_hwframe+0x63/0xcd
[222808.419829] value changed: 0x01 -> 0x03
Fixes: 915cc7ac0f8e ("RDMA/irdma: Add miscellaneous utility definitions")
Signed-off-by: Shiraz Saleem <shiraz.saleem@xxxxxxxxx>
Link: https://lore.kernel.org/r/20230711175253.1289-4-shiraz.saleem@xxxxxxxxx
Signed-off-by: Leon Romanovsky <leon@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c
index 43dfa4761f069..05a403f3ffd40 100644
--- a/drivers/infiniband/hw/irdma/hw.c
+++ b/drivers/infiniband/hw/irdma/hw.c
@@ -2068,7 +2068,7 @@ void irdma_cqp_ce_handler(struct irdma_pci_f *rf, struct irdma_sc_cq *cq)
cqp_request->compl_info.error = info.error;
if (cqp_request->waiting) {
- cqp_request->request_done = true;
+ WRITE_ONCE(cqp_request->request_done, true);
wake_up(&cqp_request->waitq);
irdma_put_cqp_request(&rf->cqp, cqp_request);
} else {
diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h
index 65e966ad34530..e64205839d039 100644
--- a/drivers/infiniband/hw/irdma/main.h
+++ b/drivers/infiniband/hw/irdma/main.h
@@ -159,8 +159,8 @@ struct irdma_cqp_request {
void (*callback_fcn)(struct irdma_cqp_request *cqp_request);
void *param;
struct irdma_cqp_compl_info compl_info;
+ bool request_done; /* READ/WRITE_ONCE macros operate on it */
bool waiting:1;
- bool request_done:1;
bool dynamic:1;
};
diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c
index 90ca4a1b60c21..8c7617776e58b 100644
--- a/drivers/infiniband/hw/irdma/utils.c
+++ b/drivers/infiniband/hw/irdma/utils.c
@@ -481,7 +481,7 @@ void irdma_free_cqp_request(struct irdma_cqp *cqp,
if (cqp_request->dynamic) {
kfree(cqp_request);
} else {
- cqp_request->request_done = false;
+ WRITE_ONCE(cqp_request->request_done, false);
cqp_request->callback_fcn = NULL;
cqp_request->waiting = false;
@@ -515,7 +515,7 @@ irdma_free_pending_cqp_request(struct irdma_cqp *cqp,
{
if (cqp_request->waiting) {
cqp_request->compl_info.error = true;
- cqp_request->request_done = true;
+ WRITE_ONCE(cqp_request->request_done, true);
wake_up(&cqp_request->waitq);
}
wait_event_timeout(cqp->remove_wq,
@@ -571,7 +571,7 @@ static int irdma_wait_event(struct irdma_pci_f *rf,
do {
irdma_cqp_ce_handler(rf, &rf->ccq.sc_cq);
if (wait_event_timeout(cqp_request->waitq,
- cqp_request->request_done,
+ READ_ONCE(cqp_request->request_done),
msecs_to_jiffies(CQP_COMPL_WAIT_TIME_MS)))
break;
