[RFC PATCH 3/3] acpi/numa: add CONFIG_ACPI_NUMA_ADD_CFMWS_NODES

[Gregory Price]

CXL is intended to be a programmable topology, and a single CXL Fixed
Memory Window (CFMWS) may back memory that a driver wants to split across
multiple NUMA nodes for tiering or isolation.

Those nodes must exist at __init time to be usable later.

Add CONFIG_ACPI_NUMA_ADD_CFMWS_NODES, the number of additional standby
NUMA nodes to reserve per CEDT CFMWS entry.

acpi_parse_cfmws() records the per-window count, which is folded into
the standby request on successful acpi_numa_init().

Signed-off-by: Gregory Price <gourry@xxxxxxxxxx>
---
 drivers/acpi/numa/Kconfig | 20 ++++++++++++++++++++
 drivers/acpi/numa/srat.c  | 13 +++++++++++--
 2 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/numa/Kconfig b/drivers/acpi/numa/Kconfig
index ecf27bf45e5b..65d7eb9a4022 100644
--- a/drivers/acpi/numa/Kconfig
+++ b/drivers/acpi/numa/Kconfig
@@ -14,6 +14,26 @@ config ACPI_HMAT
 	 performance attributes through the node's sysfs device if
 	 provided.
 
+config ACPI_NUMA_ADD_CFMWS_NODES
+	int "Additional standby NUMA nodes per CEDT CFMWS entry"
+	depends on ACPI_NUMA
+	range 0 4
+	default 0
+	help
+	  Number of additional standby NUMA nodes to reserve per CEDT
+	  CXL Fixed Memory Window Structure (CFMWS) entry.
+
+	  By default ACPI reserves 1 NUMA node per unique PXM entry in
+	  the SRAT, or 1 node for a CFMWS without SRAT mappings.
+
+	  Setting this > 0 reserves additional standby nodes per CFMWS
+	  that drivers can claim at runtime via
+	  numa_request_exclusive_node(). This is useful for CXL drivers
+	  that want to place memory on distinct NUMA nodes within the
+	  same CXL Fixed Memory Window.
+
+	  Set to 0 (default) to disable.
+
 config ACPI_NUMA_STANDBY_NODES
 	int "Additional standby NUMA nodes for runtime claiming"
 	depends on ACPI_NUMA
diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index d7b0e4ece610..6c54d5f0cf0a 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -354,6 +354,7 @@ static int __init acpi_parse_slit(struct acpi_table_header *table)
 }
 
 static int parsed_numa_memblks __initdata;
+static int cfmws_standby_count __initdata;
 
 static int __init
 acpi_parse_memory_affinity(union acpi_subtable_headers *header,
@@ -454,7 +455,7 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
 	 * window.
 	 */
 	if (!numa_fill_memblks(start, end))
-		return 0;
+		goto standby_nodes;
 
 	/* No SRAT description. Create a new node. */
 	node = acpi_map_pxm_to_node(*fake_pxm);
@@ -473,6 +474,11 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
 
 	/* Set the next available fake_pxm value */
 	(*fake_pxm)++;
+
+standby_nodes:
+	/* Request any standby nodes (created after numa_emulation runs) */
+	cfmws_standby_count += CONFIG_ACPI_NUMA_ADD_CFMWS_NODES;
+
 	return 0;
 }
 
@@ -607,6 +613,8 @@ int __init acpi_numa_init(void)
 	if (acpi_disabled)
 		return -EINVAL;
 
+	cfmws_standby_count = 0;
+
 	/*
 	 * Should not limit number with cpu num that is from NR_CPUS or nr_cpus=
 	 * SRAT cpu entries could have different order with that in MADT.
@@ -666,7 +674,8 @@ int __init acpi_numa_init(void)
 		return -ENOENT;
 
 	/* Request any standby nodes (created after numa emulation) */
-	numa_request_standby_count(CONFIG_ACPI_NUMA_STANDBY_NODES);
+	numa_request_standby_count(CONFIG_ACPI_NUMA_STANDBY_NODES +
+				   cfmws_standby_count);
 	return 0;
 }
 
-- 
2.54.0