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, 218 insertions, 0 deletions

diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c
new file mode 100644
index 000000000..5edbffd4e
--- /dev/null
+++ b/drivers/firmware/efi/memattr.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2016 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#define pr_fmt(fmt)	"efi: memattr: " fmt
+
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
+
+#include <asm/early_ioremap.h>
+
+static int __initdata tbl_size;
+unsigned long __ro_after_init efi_mem_attr_table = EFI_INVALID_TABLE_ADDR;
+
+/*
+ * Reserve the memory associated with the Memory Attributes configuration
+ * table, if it exists.
+ */
+void __init efi_memattr_init(void)
+{
+	efi_memory_attributes_table_t *tbl;
+
+	if (efi_mem_attr_table == EFI_INVALID_TABLE_ADDR)
+		return;
+
+	tbl = early_memremap(efi_mem_attr_table, sizeof(*tbl));
+	if (!tbl) {
+		pr_err("Failed to map EFI Memory Attributes table @ 0x%lx\n",
+		       efi_mem_attr_table);
+		return;
+	}
+
+	if (tbl->version > 2) {
+		pr_warn("Unexpected EFI Memory Attributes table version %d\n",
+			tbl->version);
+		goto unmap;
+	}
+
+	/*
+	 * The EFI memory attributes table descriptors might potentially be
+	 * smaller than those used by the EFI memory map, as long as they can
+	 * fit a efi_memory_desc_t. However, a larger descriptor size makes no
+	 * sense, and might be an indication that the table is corrupted.
+	 *
+	 * The only exception is kexec_load(), where the EFI memory map is
+	 * reconstructed by user space, and may use a smaller descriptor size
+	 * than the original. Given that, ignoring this companion table is
+	 * still the right thing to do here, but don't complain too loudly when
+	 * this happens.
+	 */
+	if (tbl->desc_size < sizeof(efi_memory_desc_t) ||
+	    tbl->desc_size > efi.memmap.desc_size) {
+		pr_warn("Unexpected EFI Memory Attributes descriptor size %u (expected: %lu)\n",
+			tbl->desc_size, efi.memmap.desc_size);
+		goto unmap;
+	}
+
+	/*
+	 * Sanity check: the Memory Attributes Table contains multiple entries
+	 * for each EFI runtime services code or data region in the EFI memory
+	 * map, each with the permission attributes that may be applied when
+	 * mapping the region.  There is no upper bound for the number of
+	 * entries, as it could conceivably contain more entries than the EFI
+	 * memory map itself. So pick an arbitrary limit of 64k, which is
+	 * ludicrously high. This prevents a corrupted table from eating all
+	 * system RAM.
+	 */
+	if (tbl->num_entries > SZ_64K) {
+		pr_warn(FW_BUG "Corrupted EFI Memory Attributes Table detected! (version == %u, desc_size == %u, num_entries == %u)\n",
+			tbl->version, tbl->desc_size, tbl->num_entries);
+		goto unmap;
+	}
+
+	tbl_size = sizeof(*tbl) + tbl->num_entries * tbl->desc_size;
+	memblock_reserve(efi_mem_attr_table, tbl_size);
+	set_bit(EFI_MEM_ATTR, &efi.flags);
+
+unmap:
+	early_memunmap(tbl, sizeof(*tbl));
+}
+
+/*
+ * Returns a copy @out of the UEFI memory descriptor @in if it is covered
+ * entirely by a UEFI memory map entry with matching attributes. The virtual
+ * address of @out is set according to the matching entry that was found.
+ */
+static bool entry_is_valid(const efi_memory_desc_t *in, efi_memory_desc_t *out)
+{
+	u64 in_paddr = in->phys_addr;
+	u64 in_size = in->num_pages << EFI_PAGE_SHIFT;
+	efi_memory_desc_t *md;
+
+	*out = *in;
+
+	if (in->type != EFI_RUNTIME_SERVICES_CODE &&
+	    in->type != EFI_RUNTIME_SERVICES_DATA) {
+		pr_warn("Entry type should be RuntimeServiceCode/Data\n");
+		return false;
+	}
+
+	if (PAGE_SIZE > EFI_PAGE_SIZE &&
+	    (!PAGE_ALIGNED(in->phys_addr) ||
+	     !PAGE_ALIGNED(in->num_pages << EFI_PAGE_SHIFT))) {
+		/*
+		 * Since arm64 may execute with page sizes of up to 64 KB, the
+		 * UEFI spec mandates that RuntimeServices memory regions must
+		 * be 64 KB aligned. We need to validate this here since we will
+		 * not be able to tighten permissions on such regions without
+		 * affecting adjacent regions.
+		 */
+		pr_warn("Entry address region misaligned\n");
+		return false;
+	}
+
+	for_each_efi_memory_desc(md) {
+		u64 md_paddr = md->phys_addr;
+		u64 md_size = md->num_pages << EFI_PAGE_SHIFT;
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME))
+			continue;
+		if (md->virt_addr == 0 && md->phys_addr != 0) {
+			/* no virtual mapping has been installed by the stub */
+			break;
+		}
+
+		if (md_paddr > in_paddr || (in_paddr - md_paddr) >= md_size)
+			continue;
+
+		/*
+		 * This entry covers the start of @in, check whether
+		 * it covers the end as well.
+		 */
+		if (md_paddr + md_size < in_paddr + in_size) {
+			pr_warn("Entry covers multiple EFI memory map regions\n");
+			return false;
+		}
+
+		if (md->type != in->type) {
+			pr_warn("Entry type deviates from EFI memory map region type\n");
+			return false;
+		}
+
+		out->virt_addr = in_paddr + (md->virt_addr - md_paddr);
+
+		return true;
+	}
+
+	pr_warn("No matching entry found in the EFI memory map\n");
+	return false;
+}
+
+/*
+ * To be called after the EFI page tables have been populated. If a memory
+ * attributes table is available, its contents will be used to update the
+ * mappings with tightened permissions as described by the table.
+ * This requires the UEFI memory map to have already been populated with
+ * virtual addresses.
+ */
+int __init efi_memattr_apply_permissions(struct mm_struct *mm,
+					 efi_memattr_perm_setter fn)
+{
+	efi_memory_attributes_table_t *tbl;
+	bool has_bti = false;
+	int i, ret;
+
+	if (tbl_size <= sizeof(*tbl))
+		return 0;
+
+	/*
+	 * We need the EFI memory map to be setup so we can use it to
+	 * lookup the virtual addresses of all entries in the  of EFI
+	 * Memory Attributes table. If it isn't available, this
+	 * function should not be called.
+	 */
+	if (WARN_ON(!efi_enabled(EFI_MEMMAP)))
+		return 0;
+
+	tbl = memremap(efi_mem_attr_table, tbl_size, MEMREMAP_WB);
+	if (!tbl) {
+		pr_err("Failed to map EFI Memory Attributes table @ 0x%lx\n",
+		       efi_mem_attr_table);
+		return -ENOMEM;
+	}
+
+	if (tbl->version > 1 &&
+	    (tbl->flags & EFI_MEMORY_ATTRIBUTES_FLAGS_RT_FORWARD_CONTROL_FLOW_GUARD))
+		has_bti = true;
+
+	if (efi_enabled(EFI_DBG))
+		pr_info("Processing EFI Memory Attributes table:\n");
+
+	for (i = ret = 0; ret == 0 && i < tbl->num_entries; i++) {
+		efi_memory_desc_t md;
+		unsigned long size;
+		bool valid;
+		char buf[64];
+
+		valid = entry_is_valid(efi_memdesc_ptr(tbl->entry, tbl->desc_size, i),
+				       &md);
+		size = md.num_pages << EFI_PAGE_SHIFT;
+		if (efi_enabled(EFI_DBG) || !valid)
+			pr_info("%s 0x%012llx-0x%012llx %s\n",
+				valid ? "" : "!", md.phys_addr,
+				md.phys_addr + size - 1,
+				efi_md_typeattr_format(buf, sizeof(buf), &md));
+
+		if (valid) {
+			ret = fn(mm, &md, has_bti);
+			if (ret)
+				pr_err("Error updating mappings, skipping subsequent md's\n");
+		}
+	}
+	memunmap(tbl);
+	return ret;
+}