x86/amd_node: Fix PCI device reference counting in amd_smn_init()grafted

The local "root" pointer is a temporary variable used during the device
search. Therefore, refcount related to the search iterators should be cleaned
up after the search is complete.

Use the __free() cleanup macro to ensure the refcount is decremented when the
temporary pointer goes out of scope.

Additionally, increment the refcount when caching a root pointer. This ensures
the in-use refcount is separate from the temporary search refcounting.

Finally, drop the redundant "root = NULL" before the second search loop. The
pci_get_class() iterator always decrements the refcount of its "from"
argument, so the first loop can only fall through with "root" already NULL.

Fixes: 0a4b61d9c2e4 ("x86/amd_node: Fix AMD root device caching")
Closes: https://sashiko.dev/#/patchset/20260806160159.230453-1-jason.andryuk%40amd.com
Reported-by: Sashiko <sashiko-bot@kernel.org>
Assisted-by: LLM
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Cc: <stable@kernel.org>
Link: https://patch.msgid.link/20260903154325.74343-1-yazen.ghannam@amd.com

1 files changed, 150 insertions, 0 deletions

diff --git a/block/blk-cgroup-rwstat.h b/block/blk-cgroup-rwstat.h
new file mode 100644
index 000000000..703a16fe1
--- /dev/null
+++ b/block/blk-cgroup-rwstat.h
@@ -0,0 +1,150 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT.
+ * Do not use in new code.
+ */
+#ifndef _BLK_CGROUP_RWSTAT_H
+#define _BLK_CGROUP_RWSTAT_H
+
+#include "blk-cgroup.h"
+
+enum blkg_rwstat_type {
+	BLKG_RWSTAT_READ,
+	BLKG_RWSTAT_WRITE,
+	BLKG_RWSTAT_SYNC,
+	BLKG_RWSTAT_ASYNC,
+	BLKG_RWSTAT_DISCARD,
+
+	BLKG_RWSTAT_NR,
+	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
+};
+
+/*
+ * blkg_[rw]stat->aux_cnt is excluded for local stats but included for
+ * recursive.  Used to carry stats of dead children.
+ */
+struct blkg_rwstat {
+	struct percpu_counter		cpu_cnt[BLKG_RWSTAT_NR];
+	atomic64_t			aux_cnt[BLKG_RWSTAT_NR];
+};
+
+struct blkg_rwstat_sample {
+	u64				cnt[BLKG_RWSTAT_NR];
+};
+
+static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat,
+		unsigned int idx)
+{
+	return atomic64_read(&rwstat->aux_cnt[idx]) +
+		percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]);
+}
+
+int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp);
+void blkg_rwstat_exit(struct blkg_rwstat *rwstat);
+u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+			 const struct blkg_rwstat_sample *rwstat);
+u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+		       int off);
+void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
+		int off, struct blkg_rwstat_sample *sum);
+
+
+/**
+ * blkg_rwstat_add - add a value to a blkg_rwstat
+ * @rwstat: target blkg_rwstat
+ * @opf: REQ_OP and flags
+ * @val: value to add
+ *
+ * Add @val to @rwstat.  The counters are chosen according to @rw.  The
+ * caller is responsible for synchronizing calls to this function.
+ */
+static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
+				   blk_opf_t opf, uint64_t val)
+{
+	struct percpu_counter *cnt;
+
+	if (op_is_discard(opf))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
+	else if (op_is_write(opf))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
+	else
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
+
+	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
+
+	if (op_is_sync(opf))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC];
+	else
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC];
+
+	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
+}
+
+/**
+ * blkg_rwstat_read - read the current values of a blkg_rwstat
+ * @rwstat: blkg_rwstat to read
+ * @result: where to put the current values
+ *
+ * Read the current snapshot of @rwstat and return it in the @result counts.
+ */
+static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat,
+		struct blkg_rwstat_sample *result)
+{
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		result->cnt[i] =
+			percpu_counter_sum_positive(&rwstat->cpu_cnt[i]);
+}
+
+/**
+ * blkg_rwstat_total - read the total count of a blkg_rwstat
+ * @rwstat: blkg_rwstat to read
+ *
+ * Return the total count of @rwstat regardless of the IO direction.  This
+ * function can be called without synchronization and takes care of u64
+ * atomicity.
+ */
+static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat)
+{
+	struct blkg_rwstat_sample tmp = { };
+
+	blkg_rwstat_read(rwstat, &tmp);
+	return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE];
+}
+
+/**
+ * blkg_rwstat_reset - reset a blkg_rwstat
+ * @rwstat: blkg_rwstat to reset
+ */
+static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat)
+{
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
+		percpu_counter_set(&rwstat->cpu_cnt[i], 0);
+		atomic64_set(&rwstat->aux_cnt[i], 0);
+	}
+}
+
+/**
+ * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count
+ * @to: the destination blkg_rwstat
+ * @from: the source
+ *
+ * Add @from's count including the aux one to @to's aux count.
+ */
+static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to,
+				       struct blkg_rwstat *from)
+{
+	u64 sum[BLKG_RWSTAT_NR];
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]);
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]),
+			     &to->aux_cnt[i]);
+}
+#endif	/* _BLK_CGROUP_RWSTAT_H */