On Sun, May 22, 2022 at 06:36:56PM +0800, Muchun Song wrote:
> On Mon, May 09, 2022 at 11:38:16AM -0700, Roman Gushchin wrote:
> > This commit introduces the /sys/kernel/debug/shrinker debugfs
> > interface which provides an ability to observe the state of
> > individual kernel memory shrinkers.
> >
> > Because the feature adds some memory overhead (which shouldn't be
> > large unless there is a huge amount of registered shrinkers), it's
> > guarded by a config option (enabled by default).
> >
> > This commit introduces the "count" interface for each shrinker
> > registered in the system.
> >
> > The output is in the following format:
>
> Hi Roman,
Hi Muchun!
Thank you for taking a look!
>
> Shoud we print a title to show what those numbers mean? In this case,
> it is more understandable.
No, I don't think so: this interface is not supposed to be used by
an average user and those who will be using it can refer to the provided
documentation. Printing the header each time will add some overhead for
no good reason.
> > <cgroup inode id> <nr of objects on node 0> <nr of objects on node 1>...
> > <cgroup inode id> <nr of objects on node 0> <nr of objects on node 1>...
> > ...
> >
> > To reduce the size of output on machines with many thousands cgroups,
> > if the total number of objects on all nodes is 0, the line is omitted.
> >
> > If the shrinker is not memcg-aware or CONFIG_MEMCG is off, 0 is
> > printed as cgroup inode id. If the shrinker is not numa-aware, 0's are
> > printed for all nodes except the first one.
> >
> > This commit gives debugfs entries simple numeric names, which are not
> > very convenient. The following commit in the series will provide
> > shrinkers with more meaningful names.
> >
> > Signed-off-by: Roman Gushchin <roman.gushchin@xxxxxxxxx>
> > ---
> > include/linux/shrinker.h | 19 ++++-
> > lib/Kconfig.debug | 9 +++
> > mm/Makefile | 1 +
> > mm/shrinker_debug.c | 171 +++++++++++++++++++++++++++++++++++++++
> > mm/vmscan.c | 6 +-
> > 5 files changed, 203 insertions(+), 3 deletions(-)
> > create mode 100644 mm/shrinker_debug.c
> >
> > diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
> > index 76fbf92b04d9..2ced8149c513 100644
> > --- a/include/linux/shrinker.h
> > +++ b/include/linux/shrinker.h
> > @@ -72,6 +72,10 @@ struct shrinker {
> > #ifdef CONFIG_MEMCG
> > /* ID in shrinker_idr */
> > int id;
> > +#endif
> > +#ifdef CONFIG_SHRINKER_DEBUG
> > + int debugfs_id;
> > + struct dentry *debugfs_entry;
> > #endif
> > /* objs pending delete, per node */
> > atomic_long_t *nr_deferred;
> > @@ -94,4 +98,17 @@ extern int register_shrinker(struct shrinker *shrinker);
> > extern void unregister_shrinker(struct shrinker *shrinker);
> > extern void free_prealloced_shrinker(struct shrinker *shrinker);
> > extern void synchronize_shrinkers(void);
> > -#endif
> > +
> > +#ifdef CONFIG_SHRINKER_DEBUG
> > +extern int shrinker_debugfs_add(struct shrinker *shrinker);
> > +extern void shrinker_debugfs_remove(struct shrinker *shrinker);
> > +#else /* CONFIG_SHRINKER_DEBUG */
> > +static inline int shrinker_debugfs_add(struct shrinker *shrinker)
> > +{
> > + return 0;
> > +}
> > +static inline void shrinker_debugfs_remove(struct shrinker *shrinker)
> > +{
> > +}
> > +#endif /* CONFIG_SHRINKER_DEBUG */
> > +#endif /* _LINUX_SHRINKER_H */
> > diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
> > index 3fd7a2e9eaf1..5fa65a649798 100644
> > --- a/lib/Kconfig.debug
> > +++ b/lib/Kconfig.debug
> > @@ -733,6 +733,15 @@ config SLUB_STATS
> > out which slabs are relevant to a particular load.
> > Try running: slabinfo -DA
> >
> > +config SHRINKER_DEBUG
> > + default y
> > + bool "Enable shrinker debugging support"
> > + depends on DEBUG_FS
> > + help
> > + Say Y to enable the shrinker debugfs interface which provides
> > + visibility into the kernel memory shrinkers subsystem.
> > + Disable it to avoid an extra memory footprint.
> > +
> > config HAVE_DEBUG_KMEMLEAK
> > bool
> >
> > diff --git a/mm/Makefile b/mm/Makefile
> > index 298c9991ab75..8083fa85a348 100644
> > --- a/mm/Makefile
> > +++ b/mm/Makefile
> > @@ -133,3 +133,4 @@ obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o
> > obj-$(CONFIG_IO_MAPPING) += io-mapping.o
> > obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
> > obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
> > +obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
> > diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c
> > new file mode 100644
> > index 000000000000..fd1f805a581a
> > --- /dev/null
> > +++ b/mm/shrinker_debug.c
> > @@ -0,0 +1,171 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +#include <linux/idr.h>
> > +#include <linux/slab.h>
> > +#include <linux/debugfs.h>
> > +#include <linux/seq_file.h>
> > +#include <linux/shrinker.h>
> > +#include <linux/memcontrol.h>
> > +
> > +/* defined in vmscan.c */
> > +extern struct rw_semaphore shrinker_rwsem;
> > +extern struct list_head shrinker_list;
> > +
> > +static DEFINE_IDA(shrinker_debugfs_ida);
> > +static struct dentry *shrinker_debugfs_root;
> > +
> > +static unsigned long shrinker_count_objects(struct shrinker *shrinker,
> > + struct mem_cgroup *memcg,
> > + unsigned long *count_per_node)
> > +{
> > + unsigned long nr, total = 0;
> > + int nid;
> > +
> > + for_each_node(nid) {
> > + if (nid == 0 || (shrinker->flags & SHRINKER_NUMA_AWARE)) {
> > + struct shrink_control sc = {
> > + .gfp_mask = GFP_KERNEL,
> > + .nid = nid,
> > + .memcg = memcg,
> > + };
> > +
> > + nr = shrinker->count_objects(shrinker, &sc);
> > + if (nr == SHRINK_EMPTY)
> > + nr = 0;
> > + } else {
> > + nr = 0;
>
> For efficiency, we could break here, right?
Not really, we need to fill count_per_node[] with zeros.
>
> > + }
> > +
> > + count_per_node[nid] = nr;
> > + total += nr;
> > + }
> > +
> > + return total;
> > +}
> > +
> > +static int shrinker_debugfs_count_show(struct seq_file *m, void *v)
> > +{
> > + struct shrinker *shrinker = (struct shrinker *)m->private;
>
> Maybe we cound drop the cast since m->private is a void * type.
Ok.
>
> > + unsigned long *count_per_node = NULL;
>
> Do not need to be initialized, right?
Right, will fix in v4.
>
> > + struct mem_cgroup *memcg;
> > + unsigned long total;
> > + bool memcg_aware;
> > + int ret, nid;
> > +
> > + count_per_node = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL);
> > + if (!count_per_node)
> > + return -ENOMEM;
> > +
> > + ret = down_read_killable(&shrinker_rwsem);
> > + if (ret) {
> > + kfree(count_per_node);
> > + return ret;
> > + }
> > + rcu_read_lock();
> > +
> > + memcg_aware = shrinker->flags & SHRINKER_MEMCG_AWARE;
> > +
> > + memcg = mem_cgroup_iter(NULL, NULL, NULL);
> > + do {
> > + if (memcg && !mem_cgroup_online(memcg))
> > + continue;
> > +
> > + total = shrinker_count_objects(shrinker,
> > + memcg_aware ? memcg : NULL,
> > + count_per_node);
> > + if (total) {
> > + seq_printf(m, "%lu", mem_cgroup_ino(memcg));
> > + for_each_node(nid)
> > + seq_printf(m, " %lu", count_per_node[nid]);
> > + seq_puts(m, "\n");
>
> seq_putc(m, '\n') is more efficient.
Ok.
>
> > + }
> > +
> > + if (!memcg_aware) {
> > + mem_cgroup_iter_break(NULL, memcg);
> > + break;
> > + }
> > +
> > + if (signal_pending(current)) {
> > + mem_cgroup_iter_break(NULL, memcg);
> > + ret = -EINTR;
> > + break;
> > + }
> > +
> > + cond_resched();
>
> We are in rcu read lock, cannot be scheduled, right?
This is a good one, thanks. Fixed.
>
> > + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
> > +
> > + rcu_read_unlock();
> > + up_read(&shrinker_rwsem);
> > +
> > + kfree(count_per_node);
> > + return ret;
> > +}
> > +DEFINE_SHOW_ATTRIBUTE(shrinker_debugfs_count);
> > +
> > +int shrinker_debugfs_add(struct shrinker *shrinker)
> > +{
> > + struct dentry *entry;
> > + char buf[16];
> > + int id;
> > +
> > + lockdep_assert_held(&shrinker_rwsem);
> > +
> > + /* debugfs isn't initialized yet, add debugfs entries later. */
> > + if (!shrinker_debugfs_root)
> > + return 0;
> > +
> > + id = ida_alloc(&shrinker_debugfs_ida, GFP_KERNEL);
> > + if (id < 0)
> > + return id;
> > + shrinker->debugfs_id = id;
> > +
> > + snprintf(buf, sizeof(buf), "%d", id);
> > +
> > + /* create debugfs entry */
> > + entry = debugfs_create_dir(buf, shrinker_debugfs_root);
> > + if (IS_ERR(entry)) {
> > + ida_free(&shrinker_debugfs_ida, id);
> > + return PTR_ERR(entry);
> > + }
> > + shrinker->debugfs_entry = entry;
> > +
> > + debugfs_create_file("count", 0220, entry, shrinker,
> > + &shrinker_debugfs_count_fops);
> > + return 0;
> > +}
> > +
> > +void shrinker_debugfs_remove(struct shrinker *shrinker)
> > +{
> > + lockdep_assert_held(&shrinker_rwsem);
> > +
> > + if (!shrinker->debugfs_entry)
> > + return;
> > +
> > + debugfs_remove_recursive(shrinker->debugfs_entry);
> > + ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id);
> > +}
> > +
> > +static int __init shrinker_debugfs_init(void)
> > +{
> > + struct shrinker *shrinker;
> > + int ret;
> > +
> > + if (!debugfs_initialized())
> > + return -ENODEV;
> > +
>
> Redundant check since it is checked in debugfs_create_dir().
> So I think we could remove this.
>
> > + shrinker_debugfs_root = debugfs_create_dir("shrinker", NULL);
>
> We should use IS_ERR() to detect the error code. So the following
> check is wrong.
Right, will fix in the next version.
>
> > + if (!shrinker_debugfs_root)
> > + return -ENOMEM;
> > +
> > + /* Create debugfs entries for shrinkers registered at boot */
> > + ret = down_write_killable(&shrinker_rwsem);
>
> How could we kill this process? IIUC, late_initcall() is called
> from early init process, there is no way to kill this. Right?
> If yes, I think we could just use down_write().
Ok, agree.
Thanks!
