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, 95 insertions, 0 deletions

diff --git a/include/rdma/rw.h b/include/rdma/rw.h
new file mode 100644
index 000000000..6a1d08614
--- /dev/null
+++ b/include/rdma/rw.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2016 HGST, a Western Digital Company.
+ */
+#ifndef _RDMA_RW_H
+#define _RDMA_RW_H
+
+#include <linux/bvec.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_cm.h>
+#include <rdma/mr_pool.h>
+
+struct rdma_rw_ctx {
+	/* number of RDMA READ/WRITE WRs (not counting MR WRs) */
+	u32			nr_ops;
+
+	/* tag for the union below: */
+	u8			type;
+
+	union {
+		/* for mapping a single SGE: */
+		struct {
+			struct ib_sge		sge;
+			struct ib_rdma_wr	wr;
+		} single;
+
+		/* for mapping of multiple SGEs: */
+		struct {
+			struct ib_sge		*sges;
+			struct ib_rdma_wr	*wrs;
+		} map;
+
+		/* for IOVA-based mapping of bvecs into contiguous DMA range: */
+		struct {
+			struct dma_iova_state	state;
+			struct ib_sge		sge;
+			struct ib_rdma_wr	wr;
+			size_t			mapped_len;
+		} iova;
+
+		/* for registering multiple WRs: */
+		struct rdma_rw_reg_ctx {
+			struct ib_sge		sge;
+			struct ib_rdma_wr	wr;
+			struct ib_reg_wr	reg_wr;
+			struct ib_send_wr	inv_wr;
+			struct ib_mr		*mr;
+			struct sg_table		sgt;
+		} *reg;
+	};
+};
+
+int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u32 port_num,
+		struct scatterlist *sg, u32 sg_cnt, u32 sg_offset,
+		u64 remote_addr, u32 rkey, enum dma_data_direction dir);
+void rdma_rw_ctx_destroy(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+			 u32 port_num, struct scatterlist *sg, u32 sg_cnt,
+			 enum dma_data_direction dir);
+
+struct bio_vec;
+
+int rdma_rw_ctx_init_bvec(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+		u32 port_num, const struct bio_vec *bvecs, u32 nr_bvec,
+		struct bvec_iter iter, u64 remote_addr, u32 rkey,
+		enum dma_data_direction dir);
+void rdma_rw_ctx_destroy_bvec(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+		u32 port_num, const struct bio_vec *bvecs, u32 nr_bvec,
+		enum dma_data_direction dir);
+
+int rdma_rw_ctx_signature_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+		u32 port_num, struct scatterlist *sg, u32 sg_cnt,
+		struct scatterlist *prot_sg, u32 prot_sg_cnt,
+		struct ib_sig_attrs *sig_attrs, u64 remote_addr, u32 rkey,
+		enum dma_data_direction dir);
+void rdma_rw_ctx_destroy_signature(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+		u32 port_num, struct scatterlist *sg, u32 sg_cnt,
+		struct scatterlist *prot_sg, u32 prot_sg_cnt,
+		enum dma_data_direction dir);
+
+struct ib_send_wr *rdma_rw_ctx_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+		u32 port_num, struct ib_cqe *cqe, struct ib_send_wr *chain_wr);
+int rdma_rw_ctx_post(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u32 port_num,
+		struct ib_cqe *cqe, struct ib_send_wr *chain_wr);
+
+unsigned int rdma_rw_mr_factor(struct ib_device *device, u32 port_num,
+		unsigned int maxpages);
+unsigned int rdma_rw_max_send_wr(struct ib_device *dev, u32 port_num,
+		unsigned int max_rdma_ctxs, u32 create_flags);
+void rdma_rw_init_qp(struct ib_device *dev, struct ib_qp_init_attr *attr);
+int rdma_rw_init_mrs(struct ib_qp *qp, struct ib_qp_init_attr *attr);
+void rdma_rw_cleanup_mrs(struct ib_qp *qp);
+
+#endif /* _RDMA_RW_H */