From 5ccac54f3e124a49789c3773d5a351e87470cf12 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 13 Oct 2020 16:49:28 -0700 Subject: [PATCH] ACPI: HMAT: attach a device for each soft-reserved range MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit 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. [joao.m.martins@oracle.com: require NUMA_KEEP_MEMINFO for phys_to_target_node()] Link: https://lkml.kernel.org/r/aaae71a7-4846-f5cc-5acf-cf05fdb1f2dc@oracle.com Signed-off-by: Dan Williams Signed-off-by: Joao Martins Signed-off-by: Andrew Morton Reviewed-by: Joao Martins Cc: Jonathan Cameron Cc: Brice Goglin Cc: Jeff Moyer Cc: Catalin Marinas Cc: Will Deacon Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Benjamin Herrenschmidt Cc: Ben Skeggs Cc: Borislav Petkov Cc: Daniel Vetter Cc: Dave Hansen Cc: Dave Jiang Cc: David Airlie Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Ira Weiny Cc: Jason Gunthorpe Cc: Jia He Cc: Michael Ellerman Cc: Mike Rapoport Cc: Paul Mackerras Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: Tom Lendacky Cc: Vishal Verma Cc: Wei Yang Cc: Ard Biesheuvel Cc: Bjorn Helgaas Cc: Boris Ostrovsky Cc: Hulk Robot Cc: Jason Yan Cc: "Jérôme Glisse" Cc: Juergen Gross Cc: kernel test robot Cc: Randy Dunlap Cc: Stefano Stabellini Cc: Vivek Goyal Link: https://lkml.kernel.org/r/159643098298.4062302.17587338161136144730.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds --- drivers/dax/Kconfig | 2 ++ drivers/dax/hmem/Makefile | 3 ++- drivers/dax/hmem/device.c | 35 +++++++++++++++++++++++++++++++++++ 3 files changed, 39 insertions(+), 1 deletion(-) diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index a66dff7..567428e 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -35,6 +35,7 @@ config DEV_DAX_PMEM config DEV_DAX_HMEM tristate "HMEM DAX: direct access to 'specific purpose' memory" depends on EFI_SOFT_RESERVE + select NUMA_KEEP_MEMINFO if (NUMA && X86) default DEV_DAX help EFI 2.8 platforms, and others, may advertise 'specific purpose' @@ -49,6 +50,7 @@ config DEV_DAX_HMEM Say M if unsure. config DEV_DAX_HMEM_DEVICES + depends on NUMA_KEEP_MEMINFO # for phys_to_target_node() depends on DEV_DAX_HMEM && DAX=y def_bool y diff --git a/drivers/dax/hmem/Makefile b/drivers/dax/hmem/Makefile index a9d353d..57377b4 100644 --- a/drivers/dax/hmem/Makefile +++ b/drivers/dax/hmem/Makefile @@ -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 diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c index b9dd6b2..cb6401c 100644 --- a/drivers/dax/hmem/device.c +++ b/drivers/dax/hmem/device.c @@ -5,6 +5,9 @@ #include #include +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 @@ out_resource: 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); -- 2.7.4