@@ -50,6 +50,8 @@ config DEV_DAX_HMEM
config DEV_DAX_HMEM_DEVICES
depends on DEV_DAX_HMEM
+ # requires phys_to_target_node() support
+ depends on X86_NUMA_KEEP_MEMINFO || MEMBLOCK_NUMA_INFO
def_bool y
config DEV_DAX_KMEM
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
-obj-$(CONFIG_DEV_DAX_HMEM_DEVICES) += device.o
+obj-$(CONFIG_DEV_DAX_HMEM_DEVICES) += device_hmem.o
+device_hmem-y := device.o
dax_hmem-y := hmem.o
@@ -5,6 +5,9 @@
#include <linux/dax.h>
#include <linux/mm.h>
+static bool nohmem;
+module_param_named(disable, nohmem, bool, 0444);
+
void hmem_register_device(int target_nid, struct resource *r)
{
/* define a clean / non-busy resource for the platform device */
@@ -17,6 +20,9 @@ void hmem_register_device(int target_nid, struct resource *r)
struct memregion_info info;
int rc, id;
+ if (nohmem)
+ return;
+
rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
IORES_DESC_SOFT_RESERVED);
if (rc != REGION_INTERSECTS)
@@ -63,3 +69,32 @@ void hmem_register_device(int target_nid, struct resource *r)
out_pdev:
memregion_free(id);
}
+
+static __init int hmem_register_one(struct resource *res, void *data)
+{
+ /*
+ * If the resource is not a top-level resource it was already
+ * assigned to a device by the HMAT parsing.
+ */
+ if (res->parent != &iomem_resource) {
+ pr_info("HMEM: skip %pr, already claimed\n", res);
+ return 0;
+ }
+
+ hmem_register_device(phys_to_target_node(res->start), res);
+
+ return 0;
+}
+
+static __init int hmem_init(void)
+{
+ walk_iomem_res_desc(IORES_DESC_SOFT_RESERVED,
+ IORESOURCE_MEM, 0, -1, NULL, hmem_register_one);
+ return 0;
+}
+
+/*
+ * As this is a fallback for address ranges unclaimed by the ACPI HMAT
+ * parsing it must be at an initcall level greater than hmat_init().
+ */
+late_initcall(hmem_init);
The hmem enabling in commit 'cf8741ac57ed ("ACPI: NUMA: HMAT: Register "soft reserved" memory as an "hmem" device")' only registered ranges to the hmem driver for each soft-reservation that also appeared in the HMAT. While this is meant to encourage platform firmware to "do the right thing" and publish an HMAT, the corollary is that platforms that fail to publish an accurate HMAT will strand memory from Linux usage. Additionally, the "efi_fake_mem" kernel command line option enabling will strand memory by default without an HMAT. Arrange for "soft reserved" memory that goes unclaimed by HMAT entries to be published as raw resource ranges for the hmem driver to consume. Include a module parameter to disable either this fallback behavior, or the hmat enabling from creating hmem devices. The module parameter requires the hmem device enabling to have unique name in the module namespace: "device_hmem". The driver depends on the architecture providing phys_to_target_node() which is only x86 via numa_meminfo() and arm64 via a generic memblock implementation. Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Joao Martins <joao.m.martins@oracle.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> --- drivers/dax/Kconfig | 2 ++ drivers/dax/hmem/Makefile | 3 ++- drivers/dax/hmem/device.c | 35 +++++++++++++++++++++++++++++++++++ 3 files changed, 39 insertions(+), 1 deletion(-)