On Sun, May 22, 2022 at 12:32 AM Donald Buczek <buczek@xxxxxxxxxxxxx> wrote:
>
> On 19.05.22 21:13, Logan Gunthorpe wrote:
> > The mdadm test 21raid5cache randomly fails with NULL pointer accesses
> > conf->log when run repeatedly. conf->log was sort of protected with
> > a RCU, but most dereferences were not done with the correct functions.
> >
> > Add rcu_read_locks() and rcu_access_pointers() to the appropriate
> > places.
> >
> > Signed-off-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
[...]
> > diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h
> > index f26e6f4c7f9a..24b4dbd5b25c 100644
> > --- a/drivers/md/raid5-log.h
> > +++ b/drivers/md/raid5-log.h
> > @@ -58,7 +58,7 @@ static inline int log_stripe(struct stripe_head *sh, struct stripe_head_state *s
> > {
> > struct r5conf *conf = sh->raid_conf;
> >
> > - if (conf->log) {
> > + if (rcu_access_pointer(conf->log)) {
>
>
> A problem here is that `struct r5l_log` of `conf->log` is private to raid5-cache.c and gcc below version 10 (wrongly) regards the `typeof(*p) *local` declaration of __rcu_access_pointer as a dereference:
>
> CC drivers/md/raid5.o
>
> In file included from ./include/linux/rculist.h:11:0,
>
> from ./include/linux/dcache.h:8,
>
> from ./include/linux/fs.h:8,
>
> from ./include/linux/highmem.h:5,
>
> from ./include/linux/bvec.h:10,
>
> from ./include/linux/blk_types.h:10,
>
> from ./include/linux/blkdev.h:9,
>
> from drivers/md/raid5.c:38:
>
> drivers/md/raid5-log.h: In function ‘log_stripe’:
>
> ./include/linux/rcupdate.h:384:9: error: dereferencing pointer to incomplete type ‘struct r5l_log’
>
> typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \
>
> ^
>
> ./include/linux/rcupdate.h:495:31: note: in expansion of macro ‘__rcu_access_pointer’
>
> #define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu)
>
> ^~~~~~~~~~~~~~~~~~~~
>
> drivers/md/raid5-log.h:61:6: note: in expansion of macro ‘rcu_access_pointer’
>
> if (rcu_access_pointer(conf->log)) {
>
> ^~~~~~~~~~~~~~~~~~
>
> make[2]: *** [scripts/Makefile.build:288: drivers/md/raid5.o] Error 1
>
> make[1]: *** [scripts/Makefile.build:550: drivers/md] Error 2
>
> make: *** [Makefile:1834: drivers] Error 2
This is annoying.. And there are a few other cases in raid5-log.h and
raid5.c.
Maybe we should move the definition of r5l_log to raid5-log.h?
Thanks,
Song
>
>
> See https://godbolt.org/z/TPP8MdKbc to test compiler versions with this construct.
>
> Best
>
> Donald
>
>
> > if (!test_bit(STRIPE_R5C_CACHING, &sh->state)) {
> > /* writing out phase */
> > if (s->waiting_extra_page)
> > @@ -79,7 +79,7 @@ static inline void log_stripe_write_finished(struct stripe_head *sh)
> > {
> > struct r5conf *conf = sh->raid_conf;
> >
> > - if (conf->log)
> > + if (rcu_access_pointer(conf->log))
> > r5l_stripe_write_finished(sh);
> > else if (raid5_has_ppl(conf))
> > ppl_stripe_write_finished(sh);
> > @@ -87,7 +87,7 @@ static inline void log_stripe_write_finished(struct stripe_head *sh)
> >
> > static inline void log_write_stripe_run(struct r5conf *conf)
> > {
> > - if (conf->log)
> > + if (rcu_access_pointer(conf->log))
> > r5l_write_stripe_run(conf);
> > else if (raid5_has_ppl(conf))
> > ppl_write_stripe_run(conf);
> > @@ -95,7 +95,7 @@ static inline void log_write_stripe_run(struct r5conf *conf)
> >
> > static inline void log_flush_stripe_to_raid(struct r5conf *conf)
> > {
> > - if (conf->log)
> > + if (rcu_access_pointer(conf->log))
> > r5l_flush_stripe_to_raid(conf);
> > else if (raid5_has_ppl(conf))
> > ppl_write_stripe_run(conf);
> > @@ -105,7 +105,7 @@ static inline int log_handle_flush_request(struct r5conf *conf, struct bio *bio)
> > {
> > int ret = -ENODEV;
> >
> > - if (conf->log)
> > + if (rcu_access_pointer(conf->log))
> > ret = r5l_handle_flush_request(conf, bio);
> > else if (raid5_has_ppl(conf))
> > ret = ppl_handle_flush_request(bio);
> > @@ -115,7 +115,7 @@ static inline int log_handle_flush_request(struct r5conf *conf, struct bio *bio)
> >
> > static inline void log_quiesce(struct r5conf *conf, int quiesce)
> > {
> > - if (conf->log)
> > + if (rcu_access_pointer(conf->log))
> > r5l_quiesce(conf, quiesce);
> > else if (raid5_has_ppl(conf))
> > ppl_quiesce(conf, quiesce);
> > @@ -123,7 +123,7 @@ static inline void log_quiesce(struct r5conf *conf, int quiesce)
> >
> > static inline void log_exit(struct r5conf *conf)
> > {
> > - if (conf->log)
> > + if (rcu_access_pointer(conf->log))
> > r5l_exit_log(conf);
> > else if (raid5_has_ppl(conf))
> > ppl_exit_log(conf);
> > diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
[...]
