On 2024/11/2 0:27, Chuck Lever wrote:
On Fri, Nov 01, 2024 at 11:55:11AM +0000, Simon Horman wrote:
On Thu, Oct 24, 2024 at 09:55:20AM +0800, Ye Bin wrote:
From: Ye Bin <yebin10@xxxxxxxxxx>
There's issue as follows:
RPC: Registered rdma transport module.
RPC: Registered rdma backchannel transport module.
RPC: Unregistered rdma transport module.
RPC: Unregistered rdma backchannel transport module.
BUG: unable to handle page fault for address: fffffbfff80c609a
PGD 123fee067 P4D 123fee067 PUD 123fea067 PMD 10c624067 PTE 0
Oops: Oops: 0000 [#1] PREEMPT SMP KASAN NOPTI
RIP: 0010:percpu_counter_destroy_many+0xf7/0x2a0
Call Trace:
<TASK>
__die+0x1f/0x70
page_fault_oops+0x2cd/0x860
spurious_kernel_fault+0x36/0x450
do_kern_addr_fault+0xca/0x100
exc_page_fault+0x128/0x150
asm_exc_page_fault+0x26/0x30
percpu_counter_destroy_many+0xf7/0x2a0
mmdrop+0x209/0x350
finish_task_switch.isra.0+0x481/0x840
schedule_tail+0xe/0xd0
ret_from_fork+0x23/0x80
ret_from_fork_asm+0x1a/0x30
</TASK>
If register_sysctl() return NULL, then svc_rdma_proc_cleanup() will not
destroy the percpu counters which init in svc_rdma_proc_init().
If CONFIG_HOTPLUG_CPU is enabled, residual nodes may be in the
'percpu_counters' list. The above issue may occur once the module is
removed. If the CONFIG_HOTPLUG_CPU configuration is not enabled, memory
leakage occurs.
To solve above issue just destroy all percpu counters when
register_sysctl() return NULL.
Fixes: 1e7e55731628 ("svcrdma: Restore read and write stats")
Fixes: 22df5a22462e ("svcrdma: Convert rdma_stat_sq_starve to a per-CPU counter")
Fixes: df971cd853c0 ("svcrdma: Convert rdma_stat_recv to a per-CPU counter")
Signed-off-by: Ye Bin <yebin10@xxxxxxxxxx>
---
net/sunrpc/xprtrdma/svc_rdma.c | 18 +++++++++++++-----
1 file changed, 13 insertions(+), 5 deletions(-)
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index 58ae6ec4f25b..11dff4d58195 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -233,25 +233,33 @@ static int svc_rdma_proc_init(void)
rc = percpu_counter_init(&svcrdma_stat_read, 0, GFP_KERNEL);
if (rc)
- goto out_err;
+ goto err;
rc = percpu_counter_init(&svcrdma_stat_recv, 0, GFP_KERNEL);
if (rc)
- goto out_err;
+ goto err_read;
rc = percpu_counter_init(&svcrdma_stat_sq_starve, 0, GFP_KERNEL);
if (rc)
- goto out_err;
+ goto err_recv;
rc = percpu_counter_init(&svcrdma_stat_write, 0, GFP_KERNEL);
if (rc)
- goto out_err;
+ goto err_sq;
svcrdma_table_header = register_sysctl("sunrpc/svc_rdma",
svcrdma_parm_table);
+ if (!svcrdma_table_header)
Hi Ye Bin,
Should rc be set to a negative error value here,
as is the case for other error cases above?
Flagged by Smatch.
I can add "rc = -ENOMEM;" to the applied patch.
I'm sorry for the late reply. Thank you very much for your revision.
+ goto err_write;
+
return 0;
-out_err:
+err_write:
+ percpu_counter_destroy(&svcrdma_stat_write);
+err_sq:
percpu_counter_destroy(&svcrdma_stat_sq_starve);
+err_recv:
percpu_counter_destroy(&svcrdma_stat_recv);
+err_read:
percpu_counter_destroy(&svcrdma_stat_read);
+err:
return rc;
}
--
2.34.1
