Re: [RESEND PATCH] nvme: Use spin_lock_irqsave() when taking the ctrl->lock
On 2020-08-12 3:19 p.m., Keith Busch wrote:
> On Wed, Aug 12, 2020 at 03:01:19PM -0600, Logan Gunthorpe wrote:
>> @@ -2971,15 +2971,16 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid,
>> u8 log_page, u8 lsp, u8 csi,
>> static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
>> {
>> struct nvme_cel *cel, *ret = NULL;
>> +unsigned long flags;
>>
>> -spin_lock(>lock);
>> +spin_lock_irqsave(>lock, flags);
>> list_for_each_entry(cel, >cels, entry) {
>> if (cel->csi == csi) {
>> ret = cel;
>> break;
>> }
>> }
>> -spin_unlock(>lock);
>> +spin_unlock_irqrestore(>lock, flags);
>>
>> return ret;
>> }
>> @@ -2988,6 +2989,7 @@ static int nvme_get_effects_log(struct nvme_ctrl
>> *ctrl, u8 csi,
>> struct nvme_effects_log **log)
>> {
>> struct nvme_cel *cel = nvme_find_cel(ctrl, csi);
>> +unsigned long flags;
>> int ret;
>>
>> if (cel)
>> @@ -3006,9 +3008,9 @@ static int nvme_get_effects_log(struct nvme_ctrl
>> *ctrl, u8 csi,
>>
>> cel->csi = csi;
>>
>> -spin_lock(>lock);
>> +spin_lock_irqsave(>lock, flags);
>> list_add_tail(>entry, >cels);
>> -spin_unlock(>lock);
>> +spin_unlock_irqrestore(>lock, flags);
>> out:
>> *log = >log;
>> return 0;
>>
>
> Neither of these are ever called from an interrupt disabled context,
> correct? If so, you can just use spin_lock_irq() without saving the
> current irq state.
Yes, I believe that is correct. I'll send a v2 shortly.
Thanks,
Logan
Re: [RESEND PATCH] nvme: Use spin_lock_irqsave() when taking the ctrl->lock
On Wed, Aug 12, 2020 at 03:01:19PM -0600, Logan Gunthorpe wrote:
> @@ -2971,15 +2971,16 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8
> log_page, u8 lsp, u8 csi,
> static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
> {
> struct nvme_cel *cel, *ret = NULL;
> + unsigned long flags;
>
> - spin_lock(>lock);
> + spin_lock_irqsave(>lock, flags);
> list_for_each_entry(cel, >cels, entry) {
> if (cel->csi == csi) {
> ret = cel;
> break;
> }
> }
> - spin_unlock(>lock);
> + spin_unlock_irqrestore(>lock, flags);
>
> return ret;
> }
> @@ -2988,6 +2989,7 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl,
> u8 csi,
> struct nvme_effects_log **log)
> {
> struct nvme_cel *cel = nvme_find_cel(ctrl, csi);
> + unsigned long flags;
> int ret;
>
> if (cel)
> @@ -3006,9 +3008,9 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl,
> u8 csi,
>
> cel->csi = csi;
>
> - spin_lock(>lock);
> + spin_lock_irqsave(>lock, flags);
> list_add_tail(>entry, >cels);
> - spin_unlock(>lock);
> + spin_unlock_irqrestore(>lock, flags);
> out:
> *log = >log;
> return 0;
>
Neither of these are ever called from an interrupt disabled context,
correct? If so, you can just use spin_lock_irq() without saving the
current irq state.
[RESEND PATCH] nvme: Use spin_lock_irqsave() when taking the ctrl->lock
When locking the ctrl->lock spinlock IRQs need to be disabled to avoid a
dead lock. The new spin_lock() calls recently added produce the
following lockdep warning when running the blktest nvme/003:
WARNING: inconsistent lock state
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
ksoftirqd/2/22 [HC0[0]:SC1[1]:HE0:SE0] takes:
888276a8c4c0 (>lock){+.?.}-{2:2}, at:
nvme_keep_alive_end_io+0x50/0xc0
{SOFTIRQ-ON-W} state was registered at:
lock_acquire+0x164/0x500
_raw_spin_lock+0x28/0x40
nvme_get_effects_log+0x37/0x1c0
nvme_init_identify+0x9e4/0x14f0
nvme_reset_work+0xadd/0x2360
process_one_work+0x66b/0xb70
worker_thread+0x6e/0x6c0
kthread+0x1e7/0x210
ret_from_fork+0x22/0x30
irq event stamp: 1449221
hardirqs last enabled at (1449220): []
ktime_get+0xf9/0x140
hardirqs last disabled at (1449221): []
_raw_spin_lock_irqsave+0x25/0x60
softirqs last enabled at (1449210): []
__do_softirq+0x447/0x595
softirqs last disabled at (1449215): []
run_ksoftirqd+0x35/0x50
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
lock(>lock);
lock(>lock);
*** DEADLOCK ***
no locks held by ksoftirqd/2/22.
stack backtrace:
CPU: 2 PID: 22 Comm: ksoftirqd/2 Not tainted
5.8.0-rc4-eid-vmlocalyes-dbg-00157-g7236657c6b3a #1450
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-1 04/01/2014
Call Trace:
dump_stack+0xc8/0x11a
print_usage_bug.cold.63+0x235/0x23e
mark_lock+0xa9c/0xcf0
__lock_acquire+0xd9a/0x2b50
lock_acquire+0x164/0x500
_raw_spin_lock_irqsave+0x40/0x60
nvme_keep_alive_end_io+0x50/0xc0
blk_mq_end_request+0x158/0x210
nvme_complete_rq+0x146/0x500
nvme_loop_complete_rq+0x26/0x30 [nvme_loop]
blk_done_softirq+0x187/0x1e0
__do_softirq+0x118/0x595
run_ksoftirqd+0x35/0x50
smpboot_thread_fn+0x1d3/0x310
kthread+0x1e7/0x210
ret_from_fork+0x22/0x30
Fixes: be93e87e7802 ("nvme: support for multiple Command Sets Supported and
Effects log pages")
Signed-off-by: Logan Gunthorpe
---
drivers/nvme/host/core.c | 10 ++
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 15abc00db3d3..312614467adb 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2971,15 +2971,16 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8
log_page, u8 lsp, u8 csi,
static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
{
struct nvme_cel *cel, *ret = NULL;
+ unsigned long flags;
- spin_lock(>lock);
+ spin_lock_irqsave(>lock, flags);
list_for_each_entry(cel, >cels, entry) {
if (cel->csi == csi) {
ret = cel;
break;
}
}
- spin_unlock(>lock);
+ spin_unlock_irqrestore(>lock, flags);
return ret;
}
@@ -2988,6 +2989,7 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl,
u8 csi,
struct nvme_effects_log **log)
{
struct nvme_cel *cel = nvme_find_cel(ctrl, csi);
+ unsigned long flags;
int ret;
if (cel)
@@ -3006,9 +3008,9 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl,
u8 csi,
cel->csi = csi;
- spin_lock(>lock);
+ spin_lock_irqsave(>lock, flags);
list_add_tail(>entry, >cels);
- spin_unlock(>lock);
+ spin_unlock_irqrestore(>lock, flags);
out:
*log = >log;
return 0;
base-commit: 4d3c0eaf0d44a4f8f7d53b7835e670eafc96c450
--
2.20.1
