The in_softirq() in netfs_rreq_terminated() works fine for the cache being
on a normal disk, as the completion handlers may get called in softirq
context, but for an NVMe drive, the completion handler may get called in
IRQ context.
Fix to use in_interrupt() instead of in_softirq() throughout the read
helpers, particularly when deciding whether to punt code that might sleep
off to a worker thread.
The symptom involves warnings like the following appearing and the kernel
hanging:
WARNING: CPU: 0 PID: 0 at kernel/softirq.c:175 __local_bh_enable_ip+0x35/0x50
...
RIP: 0010:__local_bh_enable_ip+0x35/0x50
...
Call Trace:
<IRQ>
rxrpc_kernel_begin_call+0x7d/0x1b0 [rxrpc]
? afs_rx_new_call+0x40/0x40 [kafs]
? afs_alloc_call+0x28/0x120 [kafs]
afs_make_call+0x120/0x510 [kafs]
? afs_rx_new_call+0x40/0x40 [kafs]
? afs_alloc_flat_call+0xba/0x100 [kafs]
? __kmalloc+0x167/0x2f0
? afs_alloc_flat_call+0x9b/0x100 [kafs]
afs_wait_for_operation+0x2d/0x200 [kafs]
afs_do_sync_operation+0x16/0x20 [kafs]
afs_req_issue_op+0x8c/0xb0 [kafs]
netfs_rreq_assess+0x125/0x7d0 [netfs]
? cachefiles_end_operation+0x40/0x40 [cachefiles]
netfs_subreq_terminated+0x117/0x220 [netfs]
cachefiles_read_complete+0x21/0x60 [cachefiles]
iomap_dio_bio_end_io+0xdd/0x110
blk_update_request+0x20a/0x380
blk_mq_end_request+0x1c/0x120
nvme_process_cq+0x159/0x1f0 [nvme]
nvme_irq+0x10/0x20 [nvme]
__handle_irq_event_percpu+0x37/0x150
handle_irq_event+0x49/0xb0
handle_edge_irq+0x7c/0x200
asm_call_irq_on_stack+0xf/0x20
</IRQ>
common_interrupt+0xad/0x120
asm_common_interrupt+0x1e/0x40
...
Reported-by: Marc Dionne <marc.dionne@xxxxxxxxxxxx>
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
cc: linux-mm@xxxxxxxxx
cc: linux-cachefs@xxxxxxxxxx
cc: linux-afs@xxxxxxxxxxxxxxxxxxx
cc: linux-nfs@xxxxxxxxxxxxxxx
cc: linux-cifs@xxxxxxxxxxxxxxx
cc: ceph-devel@xxxxxxxxxxxxxxx
cc: v9fs-developer@xxxxxxxxxxxxxxxxxxxxx
cc: linux-fsdevel@xxxxxxxxxxxxxxx
---
read_helper.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c
index 9191a3617d91..db582008b4bd 100644
--- a/fs/netfs/read_helper.c
+++ b/fs/netfs/read_helper.c
@@ -96,7 +96,7 @@ static void netfs_free_read_request(struct work_struct *work)
static void netfs_put_read_request(struct netfs_read_request *rreq)
{
if (refcount_dec_and_test(&rreq->usage)) {
- if (in_softirq()) {
+ if (in_interrupt()) {
rreq->work.func = netfs_free_read_request;
if (!queue_work(system_unbound_wq, &rreq->work))
BUG();
@@ -353,7 +353,7 @@ static void netfs_rreq_write_to_cache_work(struct work_struct *work)
static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq)
{
- if (in_softirq()) {
+ if (in_interrupt()) {
rreq->work.func = netfs_rreq_write_to_cache_work;
if (!queue_work(system_unbound_wq, &rreq->work))
BUG();
@@ -479,7 +479,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_read_request *rreq)
{
struct netfs_read_subrequest *subreq;
- WARN_ON(in_softirq());
+ WARN_ON(in_interrupt());
trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit);
@@ -577,7 +577,7 @@ static void netfs_rreq_work(struct work_struct *work)
static void netfs_rreq_terminated(struct netfs_read_request *rreq)
{
if (test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags) &&
- in_softirq()) {
+ in_interrupt()) {
if (!queue_work(system_unbound_wq, &rreq->work))
BUG();
} else {
