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, 140 insertions, 0 deletions

diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
new file mode 100644
index 000000000..d4a54b4e1
--- /dev/null
+++ b/io_uring/zcrx.h
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_ZC_RX_H
+#define IOU_ZC_RX_H
+
+#include <linux/io_uring_types.h>
+#include <linux/dma-buf.h>
+#include <linux/socket.h>
+#include <net/page_pool/types.h>
+#include <net/net_trackers.h>
+
+#define ZCRX_SUPPORTED_REG_FLAGS	(ZCRX_REG_IMPORT | ZCRX_REG_NODEV)
+#define ZCRX_FEATURES			(ZCRX_FEATURE_RX_PAGE_SIZE |\
+					 ZCRX_FEATURE_EVENT)
+#define ZCRX_EVENT_TYPE_MASK		((1U << ZCRX_EVENT_ALLOC_FAIL) |\
+					 (1U << ZCRX_EVENT_COPY))
+
+struct io_zcrx_mem {
+	unsigned long			size;
+	bool				is_dmabuf;
+
+	struct page			**pages;
+	unsigned long			nr_folios;
+	struct sg_table			page_sg_table;
+	unsigned long			account_pages;
+	struct sg_table			*sgt;
+
+	struct dma_buf_attachment	*attach;
+	struct dma_buf			*dmabuf;
+};
+
+struct io_zcrx_area {
+	struct net_iov_area	nia;
+	struct io_zcrx_ifq	*ifq;
+	atomic_t		*user_refs;
+
+	bool			is_mapped;
+	u16			area_id;
+
+	/* freelist */
+	u32			free_count;
+	u32			*freelist;
+
+	struct io_zcrx_mem	mem;
+};
+
+struct zcrx_rq_hdr {
+	u32		head ____cacheline_aligned_in_smp;
+	u32		tail ____cacheline_aligned_in_smp;
+};
+
+struct zcrx_rq {
+	spinlock_t			lock;
+	struct zcrx_rq_hdr		*ring;
+	struct io_uring_zcrx_rqe	*rqes;
+	u32				cached_head;
+	u32				cached_tail;
+	u32				nr_entries;
+};
+
+struct io_zcrx_ifq {
+	/* read-protected by any of: ->pp_lock, ->alloc_lock, ->rq.lock */
+	struct io_zcrx_area		**areas;
+	unsigned			nr_areas;
+
+	unsigned			niov_shift;
+	struct user_struct		*user;
+	struct mm_struct		*mm_account;
+	bool				kern_readable;
+
+	struct zcrx_rq			rq ____cacheline_aligned_in_smp;
+	spinlock_t			alloc_lock ____cacheline_aligned_in_smp;
+
+	u32				if_rxq;
+	struct device			*dev;
+	struct net_device		*netdev;
+	netdevice_tracker		netdev_tracker;
+	refcount_t			refs;
+	/* counts userspace facing users like io_uring */
+	refcount_t			user_refs;
+
+	/*
+	 * Page pool and net configuration lock, can be taken deeper in the
+	 * net stack.
+	 */
+	struct mutex			pp_lock;
+	struct io_mapped_region		rq_region;
+
+	spinlock_t			ctx_lock;
+	struct io_ring_ctx		*master_ctx;
+	u32				allowed_notif_mask;
+	u32				fired_notifs;
+	u64				notif_data;
+	struct zcrx_stats		*notif_stats;
+};
+
+#if defined(CONFIG_IO_URING_ZCRX)
+int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_arg);
+int io_register_zcrx(struct io_ring_ctx *ctx,
+			 struct io_uring_zcrx_ifq_reg __user *arg);
+void io_unregister_zcrx(struct io_ring_ctx *ctx);
+void io_terminate_zcrx(struct io_ring_ctx *ctx);
+int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+		 struct socket *sock, unsigned int flags,
+		 unsigned issue_flags, unsigned int *len);
+struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ctx,
+					    unsigned int id);
+#else
+static inline int io_register_zcrx(struct io_ring_ctx *ctx,
+				   struct io_uring_zcrx_ifq_reg __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+static inline void io_unregister_zcrx(struct io_ring_ctx *ctx)
+{
+}
+static inline void io_terminate_zcrx(struct io_ring_ctx *ctx)
+{
+}
+static inline int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+			       struct socket *sock, unsigned int flags,
+			       unsigned issue_flags, unsigned int *len)
+{
+	return -EOPNOTSUPP;
+}
+static inline struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ctx,
+							  unsigned int id)
+{
+	return NULL;
+}
+static inline int io_zcrx_ctrl(struct io_ring_ctx *ctx,
+				void __user *arg, unsigned nr_arg)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+int io_recvzc(struct io_kiocb *req, unsigned int issue_flags);
+int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+
+#endif