mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-29 13:53:33 +00:00
qed: fix possible unpaired spin_{un}lock_bh in _qed_mcp_cmd_and_union()
[ Upstream commit 6206b7981a
]
Liajian reported a bug_on hit on a ThunderX2 arm64 server with FastLinQ
QL41000 ethernet controller:
BUG: scheduling while atomic: kworker/0:4/531/0x00000200
[qed_probe:488()]hw prepare failed
kernel BUG at mm/vmalloc.c:2355!
Internal error: Oops - BUG: 0 [#1] SMP
CPU: 0 PID: 531 Comm: kworker/0:4 Tainted: G W 5.4.0-77-generic #86-Ubuntu
pstate: 00400009 (nzcv daif +PAN -UAO)
Call trace:
vunmap+0x4c/0x50
iounmap+0x48/0x58
qed_free_pci+0x60/0x80 [qed]
qed_probe+0x35c/0x688 [qed]
__qede_probe+0x88/0x5c8 [qede]
qede_probe+0x60/0xe0 [qede]
local_pci_probe+0x48/0xa0
work_for_cpu_fn+0x24/0x38
process_one_work+0x1d0/0x468
worker_thread+0x238/0x4e0
kthread+0xf0/0x118
ret_from_fork+0x10/0x18
In this case, qed_hw_prepare() returns error due to hw/fw error, but in
theory work queue should be in process context instead of interrupt.
The root cause might be the unpaired spin_{un}lock_bh() in
_qed_mcp_cmd_and_union(), which causes botton half is disabled incorrectly.
Reported-by: Lijian Zhang <Lijian.Zhang@arm.com>
Signed-off-by: Jia He <justin.he@arm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
parent
ac1f88dcf4
commit
5bfc9b4c6e
1 changed files with 17 additions and 6 deletions
|
@ -497,14 +497,18 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
|
|||
|
||||
spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
|
||||
|
||||
if (!qed_mcp_has_pending_cmd(p_hwfn))
|
||||
if (!qed_mcp_has_pending_cmd(p_hwfn)) {
|
||||
spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
|
||||
break;
|
||||
}
|
||||
|
||||
rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt);
|
||||
if (!rc)
|
||||
if (!rc) {
|
||||
spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
|
||||
break;
|
||||
else if (rc != -EAGAIN)
|
||||
} else if (rc != -EAGAIN) {
|
||||
goto err;
|
||||
}
|
||||
|
||||
spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
|
||||
|
||||
|
@ -521,6 +525,8 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
|
|||
return -EAGAIN;
|
||||
}
|
||||
|
||||
spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
|
||||
|
||||
/* Send the mailbox command */
|
||||
qed_mcp_reread_offsets(p_hwfn, p_ptt);
|
||||
seq_num = ++p_hwfn->mcp_info->drv_mb_seq;
|
||||
|
@ -547,14 +553,18 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
|
|||
|
||||
spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
|
||||
|
||||
if (p_cmd_elem->b_is_completed)
|
||||
if (p_cmd_elem->b_is_completed) {
|
||||
spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
|
||||
break;
|
||||
}
|
||||
|
||||
rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt);
|
||||
if (!rc)
|
||||
if (!rc) {
|
||||
spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
|
||||
break;
|
||||
else if (rc != -EAGAIN)
|
||||
} else if (rc != -EAGAIN) {
|
||||
goto err;
|
||||
}
|
||||
|
||||
spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
|
||||
} while (++cnt < max_retries);
|
||||
|
@ -575,6 +585,7 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
|
|||
return -EAGAIN;
|
||||
}
|
||||
|
||||
spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
|
||||
qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem);
|
||||
spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
|
||||
|
||||
|
|
Loading…
Reference in a new issue