--- /dev/null
+From 20cb1c2fb7568a6054c55defe044311397e01ddb Mon Sep 17 00:00:00 2001
+From: Ming Lei <ming.lei@redhat.com>
+Date: Sat, 10 Jun 2023 07:42:49 +0800
+Subject: blk-cgroup: Flush stats before releasing blkcg_gq
+
+From: Ming Lei <ming.lei@redhat.com>
+
+commit 20cb1c2fb7568a6054c55defe044311397e01ddb upstream.
+
+As noted by Michal, the blkg_iostat_set's in the lockless list hold
+reference to blkg's to protect against their removal. Those blkg's
+hold reference to blkcg. When a cgroup is being destroyed,
+cgroup_rstat_flush() is only called at css_release_work_fn() which
+is called when the blkcg reference count reaches 0. This circular
+dependency will prevent blkcg and some blkgs from being freed after
+they are made offline.
+
+It is less a problem if the cgroup to be destroyed also has other
+controllers like memory that will call cgroup_rstat_flush() which will
+clean up the reference count. If block is the only controller that uses
+rstat, these offline blkcg and blkgs may never be freed leaking more
+and more memory over time.
+
+To prevent this potential memory leak:
+
+- flush blkcg per-cpu stats list in __blkg_release(), when no new stat
+can be added
+
+- add global blkg_stat_lock for covering concurrent parent blkg stat
+update
+
+- don't grab bio->bi_blkg reference when adding the stats into blkcg's
+per-cpu stat list since all stats are guaranteed to be consumed before
+releasing blkg instance, and grabbing blkg reference for stats was the
+most fragile part of original patch
+
+Based on Waiman's patch:
+
+https://lore.kernel.org/linux-block/20221215033132.230023-3-longman@redhat.com/
+
+Fixes: 3b8cc6298724 ("blk-cgroup: Optimize blkcg_rstat_flush()")
+Cc: stable@vger.kernel.org
+Reported-by: Jay Shin <jaeshin@redhat.com>
+Acked-by: Tejun Heo <tj@kernel.org>
+Cc: Waiman Long <longman@redhat.com>
+Cc: mkoutny@suse.com
+Cc: Yosry Ahmed <yosryahmed@google.com>
+Signed-off-by: Ming Lei <ming.lei@redhat.com>
+Link: https://lore.kernel.org/r/20230609234249.1412858-1-ming.lei@redhat.com
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ block/blk-cgroup.c | 41 ++++++++++++++++++++++++++++++++---------
+ 1 file changed, 32 insertions(+), 9 deletions(-)
+
+--- a/block/blk-cgroup.c
++++ b/block/blk-cgroup.c
+@@ -35,6 +35,8 @@
+ #include "blk-throttle.h"
+ #include "blk-rq-qos.h"
+
++static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu);
++
+ /*
+ * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
+ * blkcg_pol_register_mutex nests outside of it and synchronizes entire
+@@ -58,6 +60,8 @@ static LIST_HEAD(all_blkcgs); /* protec
+ bool blkcg_debug_stats = false;
+ static struct workqueue_struct *blkcg_punt_bio_wq;
+
++static DEFINE_RAW_SPINLOCK(blkg_stat_lock);
++
+ #define BLKG_DESTROY_BATCH_SIZE 64
+
+ /*
+@@ -153,9 +157,20 @@ static void blkg_free(struct blkcg_gq *b
+ static void __blkg_release(struct rcu_head *rcu)
+ {
+ struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head);
++ struct blkcg *blkcg = blkg->blkcg;
++ int cpu;
+
+ WARN_ON(!bio_list_empty(&blkg->async_bios));
+
++ /*
++ * Flush all the non-empty percpu lockless lists before releasing
++ * us, given these stat belongs to us.
++ *
++ * blkg_stat_lock is for serializing blkg stat update
++ */
++ for_each_possible_cpu(cpu)
++ __blkcg_rstat_flush(blkcg, cpu);
++
+ /* release the blkcg and parent blkg refs this blkg has been holding */
+ css_put(&blkg->blkcg->css);
+ if (blkg->parent)
+@@ -866,17 +881,12 @@ static void blkcg_iostat_update(struct b
+ u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
+ }
+
+-static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
++static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu)
+ {
+- struct blkcg *blkcg = css_to_blkcg(css);
+ struct llist_head *lhead = per_cpu_ptr(blkcg->lhead, cpu);
+ struct llist_node *lnode;
+ struct blkg_iostat_set *bisc, *next_bisc;
+
+- /* Root-level stats are sourced from system-wide IO stats */
+- if (!cgroup_parent(css->cgroup))
+- return;
+-
+ rcu_read_lock();
+
+ lnode = llist_del_all(lhead);
+@@ -884,6 +894,14 @@ static void blkcg_rstat_flush(struct cgr
+ goto out;
+
+ /*
++ * For covering concurrent parent blkg update from blkg_release().
++ *
++ * When flushing from cgroup, cgroup_rstat_lock is always held, so
++ * this lock won't cause contention most of time.
++ */
++ raw_spin_lock(&blkg_stat_lock);
++
++ /*
+ * Iterate only the iostat_cpu's queued in the lockless list.
+ */
+ llist_for_each_entry_safe(bisc, next_bisc, lnode, lnode) {
+@@ -906,13 +924,19 @@ static void blkcg_rstat_flush(struct cgr
+ if (parent && parent->parent)
+ blkcg_iostat_update(parent, &blkg->iostat.cur,
+ &blkg->iostat.last);
+- percpu_ref_put(&blkg->refcnt);
+ }
+-
++ raw_spin_unlock(&blkg_stat_lock);
+ out:
+ rcu_read_unlock();
+ }
+
++static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
++{
++ /* Root-level stats are sourced from system-wide IO stats */
++ if (cgroup_parent(css->cgroup))
++ __blkcg_rstat_flush(css_to_blkcg(css), cpu);
++}
++
+ /*
+ * We source root cgroup stats from the system-wide stats to avoid
+ * tracking the same information twice and incurring overhead when no
+@@ -2043,7 +2067,6 @@ void blk_cgroup_bio_start(struct bio *bi
+
+ llist_add(&bis->lnode, lhead);
+ WRITE_ONCE(bis->lqueued, true);
+- percpu_ref_get(&bis->blkg->refcnt);
+ }
+
+ u64_stats_update_end_irqrestore(&bis->sync, flags);
--- /dev/null
+From 3d2af77e31ade05ff7ccc3658c3635ec1bea0979 Mon Sep 17 00:00:00 2001
+From: Waiman Long <longman@redhat.com>
+Date: Tue, 6 Jun 2023 14:07:24 -0400
+Subject: blk-cgroup: Reinit blkg_iostat_set after clearing in blkcg_reset_stats()
+
+From: Waiman Long <longman@redhat.com>
+
+commit 3d2af77e31ade05ff7ccc3658c3635ec1bea0979 upstream.
+
+When blkg_alloc() is called to allocate a blkcg_gq structure
+with the associated blkg_iostat_set's, there are 2 fields within
+blkg_iostat_set that requires proper initialization - blkg & sync.
+The former field was introduced by commit 3b8cc6298724 ("blk-cgroup:
+Optimize blkcg_rstat_flush()") while the later one was introduced by
+commit f73316482977 ("blk-cgroup: reimplement basic IO stats using
+cgroup rstat").
+
+Unfortunately those fields in the blkg_iostat_set's are not properly
+re-initialized when they are cleared in v1's blkcg_reset_stats(). This
+can lead to a kernel panic due to NULL pointer access of the blkg
+pointer. The missing initialization of sync is less problematic and
+can be a problem in a debug kernel due to missing lockdep initialization.
+
+Fix these problems by re-initializing them after memory clearing.
+
+Fixes: 3b8cc6298724 ("blk-cgroup: Optimize blkcg_rstat_flush()")
+Fixes: f73316482977 ("blk-cgroup: reimplement basic IO stats using cgroup rstat")
+Signed-off-by: Waiman Long <longman@redhat.com>
+Reviewed-by: Ming Lei <ming.lei@redhat.com>
+Acked-by: Tejun Heo <tj@kernel.org>
+Link: https://lore.kernel.org/r/20230606180724.2455066-1-longman@redhat.com
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ block/blk-cgroup.c | 5 +++++
+ 1 file changed, 5 insertions(+)
+
+--- a/block/blk-cgroup.c
++++ b/block/blk-cgroup.c
+@@ -544,8 +544,13 @@ static int blkcg_reset_stats(struct cgro
+ struct blkg_iostat_set *bis =
+ per_cpu_ptr(blkg->iostat_cpu, cpu);
+ memset(bis, 0, sizeof(*bis));
++
++ /* Re-initialize the cleared blkg_iostat_set */
++ u64_stats_init(&bis->sync);
++ bis->blkg = blkg;
+ }
+ memset(&blkg->iostat, 0, sizeof(blkg->iostat));
++ u64_stats_init(&blkg->iostat.sync);
+
+ for (i = 0; i < BLKCG_MAX_POLS; i++) {
+ struct blkcg_policy *pol = blkcg_policy[i];
--- /dev/null
+From 944520f85d5b1fb2f9ea243be41f9c9af3d4cef3 Mon Sep 17 00:00:00 2001
+From: Paul Cercueil <paul@crapouillou.net>
+Date: Thu, 22 Jun 2023 19:59:34 +0200
+Subject: MIPS: DTS: CI20: Raise VDDCORE voltage to 1.125 volts
+
+From: Paul Cercueil <paul@crapouillou.net>
+
+commit 944520f85d5b1fb2f9ea243be41f9c9af3d4cef3 upstream.
+
+Commit 08384e80a70f ("MIPS: DTS: CI20: Fix ACT8600 regulator node
+names") caused the VDDCORE power supply (regulated by the ACT8600's
+DCDC1 output) to drop from a voltage of 1.2V configured by the
+bootloader, to the 1.1V set in the Device Tree.
+
+According to the documentation, the VDDCORE supply should be between
+0.99V and 1.21V; both values are therefore within the supported range.
+
+However, VDDCORE being 1.1V results in the CI20 being very unstable,
+with corrupted memory, failures to boot, or reboots at random. The
+reason might be succint drops of the voltage below the minimum required.
+
+Raising the minimum voltage to 1.125 volts seems to be enough to address
+this issue, while still keeping a relatively low core voltage which
+helps for power consumption and thermals.
+
+Fixes: 08384e80a70f ("MIPS: DTS: CI20: Fix ACT8600 regulator node names")
+Signed-off-by: Paul Cercueil <paul@crapouillou.net>
+Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/mips/boot/dts/ingenic/ci20.dts | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/arch/mips/boot/dts/ingenic/ci20.dts
++++ b/arch/mips/boot/dts/ingenic/ci20.dts
+@@ -240,8 +240,8 @@
+
+ regulators {
+ vddcore: DCDC1 {
+- regulator-min-microvolt = <1100000>;
+- regulator-max-microvolt = <1100000>;
++ regulator-min-microvolt = <1125000>;
++ regulator-max-microvolt = <1125000>;
+ regulator-always-on;
+ };
+ vddmem: DCDC2 {
projects / thirdparty / kernel / stable-queue.git / commitdiff
