Merge branch 'acpi-mm'

* acpi-mm:
  ACPI: HMAT: use %u instead of %d to print u32 values
  ACPI: NUMA: HMAT: fix a section mismatch
  ACPI: HMAT: don't mix pxm and nid when setting memory target processor_pxm
  ACPI: NUMA: HMAT: Register "soft reserved" memory as an "hmem" device
  ACPI: NUMA: HMAT: Register HMAT at device_initcall level
  device-dax: Add a driver for "hmem" devices
  dax: Fix alloc_dax_region() compile warning
  lib: Uplevel the pmem "region" ida to a global allocator
  x86/efi: Add efi_fake_mem support for EFI_MEMORY_SP
  arm/efi: EFI soft reservation to memblock
  x86/efi: EFI soft reservation to E820 enumeration
  efi: Common enable/disable infrastructure for EFI soft reservation
  x86/efi: Push EFI_MEMMAP check into leaf routines
  efi: Enumerate EFI_MEMORY_SP
  ACPI: NUMA: Establish a new drivers/acpi/numa/ directory

Documentation/admin-guide/kernel-parameters.txt

@@ -1168,7 +1168,8 @@
 			Format: {"off" | "on" | "skip[mbr]"}
 
 	efi=		[EFI]
-			Format: { "old_map", "nochunk", "noruntime", "debug" }
+			Format: { "old_map", "nochunk", "noruntime", "debug",
+				  "nosoftreserve" }
 			old_map [X86-64]: switch to the old ioremap-based EFI
 			runtime services mapping. 32-bit still uses this one by
 			default.
@@ -1177,6 +1178,12 @@
 			firmware implementations.
 			noruntime : disable EFI runtime services support
 			debug: enable misc debug output
+			nosoftreserve: The EFI_MEMORY_SP (Specific Purpose)
+			attribute may cause the kernel to reserve the
+			memory range for a memory mapping driver to
+			claim. Specify efi=nosoftreserve to disable this
+			reservation and treat the memory by its base type
+			(i.e. EFI_CONVENTIONAL_MEMORY / "System RAM").
 
 	efi_no_storage_paranoia [EFI; X86]
 			Using this parameter you can use more than 50% of
@@ -1189,15 +1196,21 @@
 			updating original EFI memory map.
 			Region of memory which aa attribute is added to is
 			from ss to ss+nn.
+
 			If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000
 			is specified, EFI_MEMORY_MORE_RELIABLE(0x10000)
 			attribute is added to range 0x100000000-0x180000000 and
 			0x10a0000000-0x1120000000.
 
+			If efi_fake_mem=8G@9G:0x40000 is specified, the
+			EFI_MEMORY_SP(0x40000) attribute is added to
+			range 0x240000000-0x43fffffff.
+
 			Using this parameter you can do debugging of EFI memmap
-			related feature. For example, you can do debugging of
+			related features. For example, you can do debugging of
 			Address Range Mirroring feature even if your box
-			doesn't support it.
+			doesn't support it, or mark specific memory as
+			"soft reserved".
 
 	efivar_ssdt=	[EFI; X86] Name of an EFI variable that contains an SSDT
 			that is to be dynamically loaded by Linux. If there are

arch/arm64/mm/mmu.c

@@ -1061,6 +1061,8 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
 			     size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
 
+	memblock_clear_nomap(start, size);
+
 	return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
 			   restrictions);
 }

arch/x86/boot/compressed/eboot.c

@@ -554,7 +554,11 @@ setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_s
 		case EFI_BOOT_SERVICES_CODE:
 		case EFI_BOOT_SERVICES_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
-			e820_type = E820_TYPE_RAM;
+			if (efi_soft_reserve_enabled() &&
+			    (d->attribute & EFI_MEMORY_SP))
+				e820_type = E820_TYPE_SOFT_RESERVED;
+			else
+				e820_type = E820_TYPE_RAM;
 			break;
 
 		case EFI_ACPI_MEMORY_NVS:

arch/x86/boot/compressed/kaslr.c

@@ -132,8 +132,14 @@ char *skip_spaces(const char *str)
 #include "../../../../lib/ctype.c"
 #include "../../../../lib/cmdline.c"
 
+enum parse_mode {
+	PARSE_MEMMAP,
+	PARSE_EFI,
+};
+
 static int
-parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
+parse_memmap(char *p, unsigned long long *start, unsigned long long *size,
+		enum parse_mode mode)
 {
 	char *oldp;
 
@@ -156,8 +162,29 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
 		*start = memparse(p + 1, &p);
 		return 0;
 	case '@':
-		/* memmap=nn@ss specifies usable region, should be skipped */
-		*size = 0;
+		if (mode == PARSE_MEMMAP) {
+			/*
+			 * memmap=nn@ss specifies usable region, should
+			 * be skipped
+			 */
+			*size = 0;
+		} else {
+			unsigned long long flags;
+
+			/*
+			 * efi_fake_mem=nn@ss:attr the attr specifies
+			 * flags that might imply a soft-reservation.
+			 */
+			*start = memparse(p + 1, &p);
+			if (p && *p == ':') {
+				p++;
+				if (kstrtoull(p, 0, &flags) < 0)
+					*size = 0;
+				else if (flags & EFI_MEMORY_SP)
+					return 0;
+			}
+			*size = 0;
+		}
 		/* Fall through */
 	default:
 		/*
@@ -172,7 +199,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
 	return -EINVAL;
 }
 
-static void mem_avoid_memmap(char *str)
+static void mem_avoid_memmap(enum parse_mode mode, char *str)
 {
 	static int i;
 
@@ -187,7 +214,7 @@ static void mem_avoid_memmap(char *str)
 		if (k)
 			*k++ = 0;
 
-		rc = parse_memmap(str, &start, &size);
+		rc = parse_memmap(str, &start, &size, mode);
 		if (rc < 0)
 			break;
 		str = k;
@@ -238,7 +265,6 @@ static void parse_gb_huge_pages(char *param, char *val)
 	}
 }
 
-
 static void handle_mem_options(void)
 {
 	char *args = (char *)get_cmd_line_ptr();
@@ -271,7 +297,7 @@ static void handle_mem_options(void)
 		}
 
 		if (!strcmp(param, "memmap")) {
-			mem_avoid_memmap(val);
+			mem_avoid_memmap(PARSE_MEMMAP, val);
 		} else if (strstr(param, "hugepages")) {
 			parse_gb_huge_pages(param, val);
 		} else if (!strcmp(param, "mem")) {
@@ -284,6 +310,8 @@ static void handle_mem_options(void)
 				goto out;
 
 			mem_limit = mem_size;
+		} else if (!strcmp(param, "efi_fake_mem")) {
+			mem_avoid_memmap(PARSE_EFI, val);
 		}
 	}
 
@@ -760,6 +788,10 @@ process_efi_entries(unsigned long minimum, unsigned long image_size)
 		if (md->type != EFI_CONVENTIONAL_MEMORY)
 			continue;
 
+		if (efi_soft_reserve_enabled() &&
+		    (md->attribute & EFI_MEMORY_SP))
+			continue;
+
 		if (efi_mirror_found &&
 		    !(md->attribute & EFI_MEMORY_MORE_RELIABLE))
 			continue;

arch/x86/include/asm/e820/types.h

@@ -28,6 +28,14 @@ enum e820_type {
 	 */
 	E820_TYPE_PRAM		= 12,
 
+	/*
+	 * Special-purpose memory is indicated to the system via the
+	 * EFI_MEMORY_SP attribute. Define an e820 translation of this
+	 * memory type for the purpose of reserving this range and
+	 * marking it with the IORES_DESC_SOFT_RESERVED designation.
+	 */
+	E820_TYPE_SOFT_RESERVED	= 0xefffffff,
+
 	/*
 	 * Reserved RAM used by the kernel itself if
 	 * CONFIG_INTEL_TXT=y is enabled, memory of this type

arch/x86/include/asm/efi.h

@@ -140,7 +140,6 @@ extern void efi_delete_dummy_variable(void);
 extern void efi_switch_mm(struct mm_struct *mm);
 extern void efi_recover_from_page_fault(unsigned long phys_addr);
 extern void efi_free_boot_services(void);
-extern void efi_reserve_boot_services(void);
 
 struct efi_setup_data {
 	u64 fw_vendor;
@@ -244,6 +243,8 @@ static inline bool efi_is_64bit(void)
 extern bool efi_reboot_required(void);
 extern bool efi_is_table_address(unsigned long phys_addr);
 
+extern void efi_find_mirror(void);
+extern void efi_reserve_boot_services(void);
 #else
 static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
 static inline bool efi_reboot_required(void)
@@ -254,6 +255,20 @@ static inline  bool efi_is_table_address(unsigned long phys_addr)
 {
 	return false;
 }
+static inline void efi_find_mirror(void)
+{
+}
+static inline void efi_reserve_boot_services(void)
+{
+}
 #endif /* CONFIG_EFI */
 
+#ifdef CONFIG_EFI_FAKE_MEMMAP
+extern void __init efi_fake_memmap_early(void);
+#else
+static inline void efi_fake_memmap_early(void)
+{
+}
+#endif
+
 #endif /* _ASM_X86_EFI_H */

arch/x86/kernel/e820.c

@@ -190,6 +190,7 @@ static void __init e820_print_type(enum e820_type type)
 	case E820_TYPE_RAM:		/* Fall through: */
 	case E820_TYPE_RESERVED_KERN:	pr_cont("usable");			break;
 	case E820_TYPE_RESERVED:	pr_cont("reserved");			break;
+	case E820_TYPE_SOFT_RESERVED:	pr_cont("soft reserved");		break;
 	case E820_TYPE_ACPI:		pr_cont("ACPI data");			break;
 	case E820_TYPE_NVS:		pr_cont("ACPI NVS");			break;
 	case E820_TYPE_UNUSABLE:	pr_cont("unusable");			break;
@@ -1037,6 +1038,7 @@ static const char *__init e820_type_to_string(struct e820_entry *entry)
 	case E820_TYPE_PRAM:		return "Persistent Memory (legacy)";
 	case E820_TYPE_PMEM:		return "Persistent Memory";
 	case E820_TYPE_RESERVED:	return "Reserved";
+	case E820_TYPE_SOFT_RESERVED:	return "Soft Reserved";
 	default:			return "Unknown E820 type";
 	}
 }
@@ -1052,6 +1054,7 @@ static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry)
 	case E820_TYPE_PRAM:		/* Fall-through: */
 	case E820_TYPE_PMEM:		/* Fall-through: */
 	case E820_TYPE_RESERVED:	/* Fall-through: */
+	case E820_TYPE_SOFT_RESERVED:	/* Fall-through: */
 	default:			return IORESOURCE_MEM;
 	}
 }
@@ -1064,6 +1067,7 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
 	case E820_TYPE_PMEM:		return IORES_DESC_PERSISTENT_MEMORY;
 	case E820_TYPE_PRAM:		return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
 	case E820_TYPE_RESERVED:	return IORES_DESC_RESERVED;
+	case E820_TYPE_SOFT_RESERVED:	return IORES_DESC_SOFT_RESERVED;
 	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
 	case E820_TYPE_RAM:		/* Fall-through: */
 	case E820_TYPE_UNUSABLE:	/* Fall-through: */
@@ -1078,11 +1082,12 @@ static bool __init do_mark_busy(enum e820_type type, struct resource *res)
 		return true;
 
 	/*
-	 * Treat persistent memory like device memory, i.e. reserve it
-	 * for exclusive use of a driver
+	 * Treat persistent memory and other special memory ranges like
+	 * device memory, i.e. reserve it for exclusive use of a driver
 	 */
 	switch (type) {
 	case E820_TYPE_RESERVED:
+	case E820_TYPE_SOFT_RESERVED:
 	case E820_TYPE_PRAM:
 	case E820_TYPE_PMEM:
 		return false;
@@ -1285,6 +1290,9 @@ void __init e820__memblock_setup(void)
 		if (end != (resource_size_t)end)
 			continue;
 
+		if (entry->type == E820_TYPE_SOFT_RESERVED)
+			memblock_reserve(entry->addr, entry->size);
+
 		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
 			continue;
 

arch/x86/kernel/setup.c

@@ -1122,17 +1122,15 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_bios_regions();
 
-	if (efi_enabled(EFI_MEMMAP)) {
-		efi_fake_memmap();
-		efi_find_mirror();
-		efi_esrt_init();
+	efi_fake_memmap();
+	efi_find_mirror();
+	efi_esrt_init();
 
-		/*
-		 * The EFI specification says that boot service code won't be
-		 * called after ExitBootServices(). This is, in fact, a lie.
-		 */
-		efi_reserve_boot_services();
-	}
+	/*
+	 * The EFI specification says that boot service code won't be
+	 * called after ExitBootServices(). This is, in fact, a lie.
+	 */
+	efi_reserve_boot_services();
 
 	/* preallocate 4k for mptable mpc */
 	e820__memblock_alloc_reserved_mpc_new();

arch/x86/platform/efi/efi.c

@@ -128,6 +128,9 @@ void __init efi_find_mirror(void)
 	efi_memory_desc_t *md;
 	u64 mirror_size = 0, total_size = 0;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
 	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
@@ -145,14 +148,18 @@ void __init efi_find_mirror(void)
 
 /*
  * Tell the kernel about the EFI memory map.  This might include
- * more than the max 128 entries that can fit in the e820 legacy
- * (zeropage) memory map.
+ * more than the max 128 entries that can fit in the passed in e820
+ * legacy (zeropage) memory map, but the kernel's e820 table can hold
+ * E820_MAX_ENTRIES.
  */
 
 static void __init do_add_efi_memmap(void)
 {
 	efi_memory_desc_t *md;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
 	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
@@ -164,7 +171,10 @@ static void __init do_add_efi_memmap(void)
 		case EFI_BOOT_SERVICES_CODE:
 		case EFI_BOOT_SERVICES_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
-			if (md->attribute & EFI_MEMORY_WB)
+			if (efi_soft_reserve_enabled()
+			    && (md->attribute & EFI_MEMORY_SP))
+				e820_type = E820_TYPE_SOFT_RESERVED;
+			else if (md->attribute & EFI_MEMORY_WB)
 				e820_type = E820_TYPE_RAM;
 			else
 				e820_type = E820_TYPE_RESERVED;
@@ -190,11 +200,36 @@ static void __init do_add_efi_memmap(void)
 			e820_type = E820_TYPE_RESERVED;
 			break;
 		}
+
 		e820__range_add(start, size, e820_type);
 	}
 	e820__update_table(e820_table);
 }
 
+/*
+ * Given add_efi_memmap defaults to 0 and there there is no alternative
+ * e820 mechanism for soft-reserved memory, import the full EFI memory
+ * map if soft reservations are present and enabled. Otherwise, the
+ * mechanism to disable the kernel's consideration of EFI_MEMORY_SP is
+ * the efi=nosoftreserve option.
+ */
+static bool do_efi_soft_reserve(void)
+{
+	efi_memory_desc_t *md;
+
+	if (!efi_enabled(EFI_MEMMAP))
+		return false;
+
+	if (!efi_soft_reserve_enabled())
+		return false;
+
+	for_each_efi_memory_desc(md)
+		if (md->type == EFI_CONVENTIONAL_MEMORY &&
+		    (md->attribute & EFI_MEMORY_SP))
+			return true;
+	return false;
+}
+
 int __init efi_memblock_x86_reserve_range(void)
 {
 	struct efi_info *e = &boot_params.efi_info;
@@ -224,9 +259,11 @@ int __init efi_memblock_x86_reserve_range(void)
 	if (rv)
 		return rv;
 
-	if (add_efi_memmap)
+	if (add_efi_memmap || do_efi_soft_reserve())
 		do_add_efi_memmap();
 
+	efi_fake_memmap_early();
+
 	WARN(efi.memmap.desc_version != 1,
 	     "Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
 	     efi.memmap.desc_version);
@@ -778,6 +815,15 @@ static bool should_map_region(efi_memory_desc_t *md)
 	if (IS_ENABLED(CONFIG_X86_32))
 		return false;
 
+	/*
+	 * EFI specific purpose memory may be reserved by default
+	 * depending on kernel config and boot options.
+	 */
+	if (md->type == EFI_CONVENTIONAL_MEMORY &&
+	    efi_soft_reserve_enabled() &&
+	    (md->attribute & EFI_MEMORY_SP))
+		return false;
+
 	/*
 	 * Map all of RAM so that we can access arguments in the 1:1
 	 * mapping when making EFI runtime calls.

arch/x86/platform/efi/quirks.c

@@ -320,6 +320,9 @@ void __init efi_reserve_boot_services(void)
 {
 	efi_memory_desc_t *md;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
 	for_each_efi_memory_desc(md) {
 		u64 start = md->phys_addr;
 		u64 size = md->num_pages << EFI_PAGE_SHIFT;

drivers/acpi/Kconfig

@@ -319,12 +319,6 @@ config ACPI_THERMAL
 	  To compile this driver as a module, choose M here:
 	  the module will be called thermal.
 
-config ACPI_NUMA
-	bool "NUMA support"
-	depends on NUMA
-	depends on (X86 || IA64 || ARM64)
-	default y if IA64 || ARM64
-
 config ACPI_CUSTOM_DSDT_FILE
 	string "Custom DSDT Table file to include"
 	default ""
@@ -473,8 +467,7 @@ config ACPI_REDUCED_HARDWARE_ONLY
 	  If you are unsure what to do, do not enable this option.
 
 source "drivers/acpi/nfit/Kconfig"
-source "drivers/acpi/hmat/Kconfig"
-
+source "drivers/acpi/numa/Kconfig"
 source "drivers/acpi/apei/Kconfig"
 source "drivers/acpi/dptf/Kconfig"
 

drivers/acpi/Makefile

@@ -55,7 +55,6 @@ acpi-$(CONFIG_X86)		+= acpi_cmos_rtc.o
 acpi-$(CONFIG_X86)		+= x86/apple.o
 acpi-$(CONFIG_X86)		+= x86/utils.o
 acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
-acpi-$(CONFIG_ACPI_NUMA)	+= numa.o
 acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o
 acpi-y				+= acpi_lpat.o
 acpi-$(CONFIG_ACPI_LPIT)	+= acpi_lpit.o
@@ -80,7 +79,7 @@ obj-$(CONFIG_ACPI_PROCESSOR)	+= processor.o
 obj-$(CONFIG_ACPI)		+= container.o
 obj-$(CONFIG_ACPI_THERMAL)	+= thermal.o
 obj-$(CONFIG_ACPI_NFIT)		+= nfit/
-obj-$(CONFIG_ACPI_HMAT)		+= hmat/
+obj-$(CONFIG_ACPI_NUMA)		+= numa/
 obj-$(CONFIG_ACPI)		+= acpi_memhotplug.o
 obj-$(CONFIG_ACPI_HOTPLUG_IOAPIC) += ioapic.o
 obj-$(CONFIG_ACPI_BATTERY)	+= battery.o

drivers/acpi/hmat/Kconfig → drivers/acpi/numa/Kconfig

 # SPDX-License-Identifier: GPL-2.0
+config ACPI_NUMA
+	bool "NUMA support"
+	depends on NUMA
+	depends on (X86 || IA64 || ARM64)
+	default y if IA64 || ARM64
+
 config ACPI_HMAT
 	bool "ACPI Heterogeneous Memory Attribute Table Support"
 	depends on ACPI_NUMA
 	select HMEM_REPORTING
+	select MEMREGION
 	help
 	 If set, this option has the kernel parse and report the
 	 platform's ACPI HMAT (Heterogeneous Memory Attributes Table),

drivers/acpi/hmat/Makefile → drivers/acpi/numa/Makefile

 # SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_ACPI_HMAT) := hmat.o
+obj-$(CONFIG_ACPI_NUMA) += srat.o
+obj-$(CONFIG_ACPI_HMAT) += hmat.o

drivers/acpi/hmat/hmat.c → drivers/acpi/numa/hmat.c

@@ -8,12 +8,18 @@
  * the applicable attributes with the node's interfaces.
  */
 
+#define pr_fmt(fmt) "acpi/hmat: " fmt
+#define dev_fmt(fmt) "acpi/hmat: " fmt
+
 #include <linux/acpi.h>
 #include <linux/bitops.h>
 #include <linux/device.h>
 #include <linux/init.h>
 #include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/platform_device.h>
 #include <linux/list_sort.h>
+#include <linux/memregion.h>
 #include <linux/memory.h>
 #include <linux/mutex.h>
 #include <linux/node.h>
@@ -49,6 +55,7 @@ struct memory_target {
 	struct list_head node;
 	unsigned int memory_pxm;
 	unsigned int processor_pxm;
+	struct resource memregions;
 	struct node_hmem_attrs hmem_attrs;
 	struct list_head caches;
 	struct node_cache_attrs cache_attrs;
@@ -104,22 +111,36 @@ static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 	list_add_tail(&initiator->node, &initiators);
 }
 
-static __init void alloc_memory_target(unsigned int mem_pxm)
+static __init void alloc_memory_target(unsigned int mem_pxm,
+		resource_size_t start, resource_size_t len)
 {
 	struct memory_target *target;
 
 	target = find_mem_target(mem_pxm);
-	if (target)
-		return;
-
-	target = kzalloc(sizeof(*target), GFP_KERNEL);
-	if (!target)
-		return;
+	if (!target) {
+		target = kzalloc(sizeof(*target), GFP_KERNEL);
+		if (!target)
+			return;
+		target->memory_pxm = mem_pxm;
+		target->processor_pxm = PXM_INVAL;
+		target->memregions = (struct resource) {
+			.name	= "ACPI mem",
+			.start	= 0,
+			.end	= -1,
+			.flags	= IORESOURCE_MEM,
+		};
+		list_add_tail(&target->node, &targets);
+		INIT_LIST_HEAD(&target->caches);
+	}
 
-	target->memory_pxm = mem_pxm;
-	target->processor_pxm = PXM_INVAL;
-	list_add_tail(&target->node, &targets);
-	INIT_LIST_HEAD(&target->caches);
+	/*
+	 * There are potentially multiple ranges per PXM, so record each
+	 * in the per-target memregions resource tree.
+	 */
+	if (!__request_region(&target->memregions, start, len, "memory target",
+				IORESOURCE_MEM))
+		pr_warn("failed to reserve %#llx - %#llx in pxm: %d\n",
+				start, start + len, mem_pxm);
 }
 
 static __init const char *hmat_data_type(u8 type)
@@ -272,7 +293,7 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 	u8 type, mem_hier;
 
 	if (hmat_loc->header.length < sizeof(*hmat_loc)) {
-		pr_notice("HMAT: Unexpected locality header length: %d\n",
+		pr_notice("HMAT: Unexpected locality header length: %u\n",
 			 hmat_loc->header.length);
 		return -EINVAL;
 	}
@@ -284,12 +305,12 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 	total_size = sizeof(*hmat_loc) + sizeof(*entries) * ipds * tpds +
 		     sizeof(*inits) * ipds + sizeof(*targs) * tpds;
 	if (hmat_loc->header.length < total_size) {
-		pr_notice("HMAT: Unexpected locality header length:%d, minimum required:%d\n",
+		pr_notice("HMAT: Unexpected locality header length:%u, minimum required:%u\n",
 			 hmat_loc->header.length, total_size);
 		return -EINVAL;
 	}
 
-	pr_info("HMAT: Locality: Flags:%02x Type:%s Initiator Domains:%d Target Domains:%d Base:%lld\n",
+	pr_info("HMAT: Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n",
 		hmat_loc->flags, hmat_data_type(type), ipds, tpds,
 		hmat_loc->entry_base_unit);
 
@@ -302,7 +323,7 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 			value = hmat_normalize(entries[init * tpds + targ],
 					       hmat_loc->entry_base_unit,
 					       type);
-			pr_info("  Initiator-Target[%d-%d]:%d%s\n",
+			pr_info("  Initiator-Target[%u-%u]:%u%s\n",
 				inits[init], targs[targ], value,
 				hmat_data_type_suffix(type));
 
@@ -329,13 +350,13 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header,
 	u32 attrs;
 
 	if (cache->header.length < sizeof(*cache)) {
-		pr_notice("HMAT: Unexpected cache header length: %d\n",
+		pr_notice("HMAT: Unexpected cache header length: %u\n",
 			 cache->header.length);
 		return -EINVAL;
 	}
 
 	attrs = cache->cache_attributes;
-	pr_info("HMAT: Cache: Domain:%d Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
+	pr_info("HMAT: Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
 		cache->memory_PD, cache->cache_size, attrs,
 		cache->number_of_SMBIOShandles);
 
@@ -390,17 +411,17 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 	struct memory_target *target = NULL;
 
 	if (p->header.length != sizeof(*p)) {
-		pr_notice("HMAT: Unexpected address range header length: %d\n",
+		pr_notice("HMAT: Unexpected address range header length: %u\n",
 			 p->header.length);
 		return -EINVAL;
 	}
 
 	if (hmat_revision == 1)
-		pr_info("HMAT: Memory (%#llx length %#llx) Flags:%04x Processor Domain:%d Memory Domain:%d\n",
+		pr_info("HMAT: Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n",
 			p->reserved3, p->reserved4, p->flags, p->processor_PD,
 			p->memory_PD);
 	else
-		pr_info("HMAT: Memory Flags:%04x Processor Domain:%d Memory Domain:%d\n",
+		pr_info("HMAT: Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n",
 			p->flags, p->processor_PD, p->memory_PD);
 
 	if (p->flags & ACPI_HMAT_MEMORY_PD_VALID && hmat_revision == 1) {
@@ -417,7 +438,7 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 			pr_debug("HMAT: Invalid Processor Domain\n");
 			return -EINVAL;
 		}
-		target->processor_pxm = p_node;
+		target->processor_pxm = p->processor_PD;
 	}
 
 	return 0;
@@ -452,7 +473,7 @@ static __init int srat_parse_mem_affinity(union acpi_subtable_headers *header,
 		return -EINVAL;
 	if (!(ma->flags & ACPI_SRAT_MEM_ENABLED))
 		return 0;
-	alloc_memory_target(ma->proximity_domain);
+	alloc_memory_target(ma->proximity_domain, ma->base_address, ma->length);
 	return 0;
 }
 
@@ -613,10 +634,91 @@ static void hmat_register_target_perf(struct memory_target *target)
 	node_set_perf_attrs(mem_nid, &target->hmem_attrs, 0);
 }
 
+static void hmat_register_target_device(struct memory_target *target,
+		struct resource *r)
+{
+	/* define a clean / non-busy resource for the platform device */
+	struct resource res = {
+		.start = r->start,
+		.end = r->end,
+		.flags = IORESOURCE_MEM,
+	};
+	struct platform_device *pdev;
+	struct memregion_info info;
+	int rc, id;
+
+	rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
+			IORES_DESC_SOFT_RESERVED);
+	if (rc != REGION_INTERSECTS)
+		return;
+
+	id = memregion_alloc(GFP_KERNEL);
+	if (id < 0) {
+		pr_err("memregion allocation failure for %pr\n", &res);
+		return;
+	}
+
+	pdev = platform_device_alloc("hmem", id);
+	if (!pdev) {
+		pr_err("hmem device allocation failure for %pr\n", &res);
+		goto out_pdev;
+	}
+
+	pdev->dev.numa_node = acpi_map_pxm_to_online_node(target->memory_pxm);
+	info = (struct memregion_info) {
+		.target_node = acpi_map_pxm_to_node(target->memory_pxm),
+	};
+	rc = platform_device_add_data(pdev, &info, sizeof(info));
+	if (rc < 0) {
+		pr_err("hmem memregion_info allocation failure for %pr\n", &res);
+		goto out_pdev;
+	}
+
+	rc = platform_device_add_resources(pdev, &res, 1);
+	if (rc < 0) {
+		pr_err("hmem resource allocation failure for %pr\n", &res);
+		goto out_resource;
+	}
+
+	rc = platform_device_add(pdev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "device add failed for %pr\n", &res);
+		goto out_resource;
+	}
+
+	return;
+
+out_resource:
+	put_device(&pdev->dev);
+out_pdev:
+	memregion_free(id);
+}
+
+static void hmat_register_target_devices(struct memory_target *target)
+{
+	struct resource *res;
+
+	/*
+	 * Do not bother creating devices if no driver is available to
+	 * consume them.
+	 */
+	if (!IS_ENABLED(CONFIG_DEV_DAX_HMEM))
+		return;
+
+	for (res = target->memregions.child; res; res = res->sibling)
+		hmat_register_target_device(target, res);
+}
+
 static void hmat_register_target(struct memory_target *target)
 {
 	int nid = pxm_to_node(target->memory_pxm);
 
+	/*
+	 * Devices may belong to either an offline or online
+	 * node, so unconditionally add them.
+	 */
+	hmat_register_target_devices(target);
+
 	/*
 	 * Skip offline nodes. This can happen when memory
 	 * marked EFI_MEMORY_SP, "specific purpose", is applied
@@ -677,11 +779,21 @@ static __init void hmat_free_structures(void)
 	struct target_cache *tcache, *cnext;
 
 	list_for_each_entry_safe(target, tnext, &targets, node) {
+		struct resource *res, *res_next;
+
 		list_for_each_entry_safe(tcache, cnext, &target->caches, node) {
 			list_del(&tcache->node);
 			kfree(tcache);
 		}
+
 		list_del(&target->node);
+		res = target->memregions.child;
+		while (res) {
+			res_next = res->sibling;
+			__release_region(&target->memregions, res->start,
+					resource_size(res));
+			res = res_next;
+		}
 		kfree(target);
 	}
 
@@ -748,4 +860,4 @@ static __init int hmat_init(void)
 	acpi_put_table(tbl);
 	return 0;
 }
-subsys_initcall(hmat_init);
+device_initcall(hmat_init);

drivers/dax/Kconfig

@@ -32,19 +32,36 @@ config DEV_DAX_PMEM
 
 	  Say M if unsure
 
+config DEV_DAX_HMEM
+	tristate "HMEM DAX: direct access to 'specific purpose' memory"
+	depends on EFI_SOFT_RESERVE
+	default DEV_DAX
+	help
+	  EFI 2.8 platforms, and others, may advertise 'specific purpose'
+	  memory. For example, a high bandwidth memory pool. The
+	  indication from platform firmware is meant to reserve the
+	  memory from typical usage by default. This driver creates
+	  device-dax instances for these memory ranges, and that also
+	  enables the possibility to assign them to the DEV_DAX_KMEM
+	  driver to override the reservation and add them to kernel
+	  "System RAM" pool.
+
+	  Say M if unsure.
+
 config DEV_DAX_KMEM
 	tristate "KMEM DAX: volatile-use of persistent memory"
 	default DEV_DAX
 	depends on DEV_DAX
 	depends on MEMORY_HOTPLUG # for add_memory() and friends
 	help
-	  Support access to persistent memory as if it were RAM.  This
-	  allows easier use of persistent memory by unmodified
-	  applications.
+	  Support access to persistent, or other performance
+	  differentiated memory as if it were System RAM. This allows
+	  easier use of persistent memory by unmodified applications, or
+	  adds core kernel memory services to heterogeneous memory types
+	  (HMEM) marked "reserved" by platform firmware.
 
 	  To use this feature, a DAX device must be unbound from the
-	  device_dax driver (PMEM DAX) and bound to this kmem driver
-	  on each boot.
+	  device_dax driver and bound to this kmem driver on each boot.
 
 	  Say N if unsure.
 

drivers/dax/Makefile

@@ -2,9 +2,11 @@
 obj-$(CONFIG_DAX) += dax.o
 obj-$(CONFIG_DEV_DAX) += device_dax.o
 obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o
+obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
 
 dax-y := super.o
 dax-y += bus.o
 device_dax-y := device.o
+dax_hmem-y := hmem.o
 
 obj-y += pmem/

drivers/dax/bus.c

@@ -227,7 +227,7 @@ static void dax_region_unregister(void *region)
 
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		struct resource *res, int target_node, unsigned int align,
-		unsigned long pfn_flags)
+		unsigned long long pfn_flags)
 {
 	struct dax_region *dax_region;
 

drivers/dax/bus.h

@@ -11,7 +11,7 @@ struct dax_region;
 void dax_region_put(struct dax_region *dax_region);
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		struct resource *res, int target_node, unsigned int align,
-		unsigned long flags);
+		unsigned long long flags);
 
 enum dev_dax_subsys {
 	DEV_DAX_BUS,

drivers/dax/dax-private.h

@@ -32,7 +32,7 @@ struct dax_region {
 	struct device *dev;
 	unsigned int align;
 	struct resource res;
-	unsigned long pfn_flags;
+	unsigned long long pfn_flags;
 };
 
 /**

drivers/dax/hmem.c

+// SPDX-License-Identifier: GPL-2.0
+#include <linux/platform_device.h>
+#include <linux/memregion.h>
+#include <linux/module.h>
+#include <linux/pfn_t.h>
+#include "bus.h"
+
+static int dax_hmem_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct dev_pagemap pgmap = { };
+	struct dax_region *dax_region;
+	struct memregion_info *mri;
+	struct dev_dax *dev_dax;
+	struct resource *res;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENOMEM;
+
+	mri = dev->platform_data;
+	memcpy(&pgmap.res, res, sizeof(*res));
+
+	dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
+			PMD_SIZE, PFN_DEV|PFN_MAP);
+	if (!dax_region)
+		return -ENOMEM;
+
+	dev_dax = devm_create_dev_dax(dax_region, 0, &pgmap);
+	if (IS_ERR(dev_dax))
+		return PTR_ERR(dev_dax);
+
+	/* child dev_dax instances now own the lifetime of the dax_region */
+	dax_region_put(dax_region);
+	return 0;
+}
+
+static int dax_hmem_remove(struct platform_device *pdev)
+{
+	/* devm handles teardown */
+	return 0;
+}
+
+static struct platform_driver dax_hmem_driver = {
+	.probe = dax_hmem_probe,
+	.remove = dax_hmem_remove,
+	.driver = {
+		.name = "hmem",
+	},
+};
+
+module_platform_driver(dax_hmem_driver);
+
+MODULE_ALIAS("platform:hmem*");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");

drivers/firmware/efi/Kconfig

@@ -75,6 +75,27 @@ config EFI_MAX_FAKE_MEM
 	  Ranges can be set up to this value using comma-separated list.
 	  The default value is 8.
 
+config EFI_SOFT_RESERVE
+	bool "Reserve EFI Specific Purpose Memory"
+	depends on EFI && EFI_STUB && ACPI_HMAT
+	default ACPI_HMAT
+	help
+	  On systems that have mixed performance classes of memory EFI
+	  may indicate specific purpose memory with an attribute (See
+	  EFI_MEMORY_SP in UEFI 2.8). A memory range tagged with this
+	  attribute may have unique performance characteristics compared
+	  to the system's general purpose "System RAM" pool. On the
+	  expectation that such memory has application specific usage,
+	  and its base EFI memory type is "conventional" answer Y to
+	  arrange for the kernel to reserve it as a "Soft Reserved"
+	  resource, and set aside for direct-access (device-dax) by
+	  default. The memory range can later be optionally assigned to
+	  the page allocator by system administrator policy via the
+	  device-dax kmem facility. Say N to have the kernel treat this
+	  memory as "System RAM" by default.
+
+	  If unsure, say Y.
+
 config EFI_PARAMS_FROM_FDT
 	bool
 	help

drivers/firmware/efi/Makefile

@@ -20,13 +20,16 @@ obj-$(CONFIG_UEFI_CPER)			+= cper.o
 obj-$(CONFIG_EFI_RUNTIME_MAP)		+= runtime-map.o
 obj-$(CONFIG_EFI_RUNTIME_WRAPPERS)	+= runtime-wrappers.o
 obj-$(CONFIG_EFI_STUB)			+= libstub/
-obj-$(CONFIG_EFI_FAKE_MEMMAP)		+= fake_mem.o
+obj-$(CONFIG_EFI_FAKE_MEMMAP)		+= fake_map.o
 obj-$(CONFIG_EFI_BOOTLOADER_CONTROL)	+= efibc.o
 obj-$(CONFIG_EFI_TEST)			+= test/
 obj-$(CONFIG_EFI_DEV_PATH_PARSER)	+= dev-path-parser.o
 obj-$(CONFIG_APPLE_PROPERTIES)		+= apple-properties.o
 obj-$(CONFIG_EFI_RCI2_TABLE)		+= rci2-table.o
 
+fake_map-y				+= fake_mem.o
+fake_map-$(CONFIG_X86)			+= x86_fake_mem.o
+
 arm-obj-$(CONFIG_EFI)			:= arm-init.o arm-runtime.o
 obj-$(CONFIG_ARM)			+= $(arm-obj-y)
 obj-$(CONFIG_ARM64)			+= $(arm-obj-y)

drivers/firmware/efi/arm-init.c

@@ -163,6 +163,15 @@ static __init int is_usable_memory(efi_memory_desc_t *md)
 	case EFI_BOOT_SERVICES_DATA:
 	case EFI_CONVENTIONAL_MEMORY:
 	case EFI_PERSISTENT_MEMORY:
+		/*
+		 * Special purpose memory is 'soft reserved', which means it
+		 * is set aside initially, but can be hotplugged back in or
+		 * be assigned to the dax driver after boot.
+		 */
+		if (efi_soft_reserve_enabled() &&
+		    (md->attribute & EFI_MEMORY_SP))
+			return false;
+
 		/*
 		 * According to the spec, these regions are no longer reserved
 		 * after calling ExitBootServices(). However, we can only use

drivers/firmware/efi/arm-runtime.c

@@ -121,6 +121,30 @@ static int __init arm_enable_runtime_services(void)
 		return 0;
 	}
 
+	if (efi_soft_reserve_enabled()) {
+		efi_memory_desc_t *md;
+
+		for_each_efi_memory_desc(md) {
+			int md_size = md->num_pages << EFI_PAGE_SHIFT;
+			struct resource *res;
+
+			if (!(md->attribute & EFI_MEMORY_SP))
+				continue;
+
+			res = kzalloc(sizeof(*res), GFP_KERNEL);
+			if (WARN_ON(!res))
+				break;
+
+			res->start	= md->phys_addr;
+			res->end	= md->phys_addr + md_size - 1;
+			res->name	= "Soft Reserved";
+			res->flags	= IORESOURCE_MEM;
+			res->desc	= IORES_DESC_SOFT_RESERVED;
+
+			insert_resource(&iomem_resource, res);
+		}
+	}
+
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
 		return 0;

drivers/firmware/efi/efi.c

@@ -81,6 +81,11 @@ bool efi_runtime_disabled(void)
 	return disable_runtime;
 }
 
+bool __pure __efi_soft_reserve_enabled(void)
+{
+	return !efi_enabled(EFI_MEM_NO_SOFT_RESERVE);
+}
+
 static int __init parse_efi_cmdline(char *str)
 {
 	if (!str) {
@@ -94,6 +99,9 @@ static int __init parse_efi_cmdline(char *str)
 	if (parse_option_str(str, "noruntime"))
 		disable_runtime = true;
 
+	if (parse_option_str(str, "nosoftreserve"))
+		set_bit(EFI_MEM_NO_SOFT_RESERVE, &efi.flags);
+
 	return 0;
 }
 early_param("efi", parse_efi_cmdline);
@@ -842,15 +850,16 @@ char * __init efi_md_typeattr_format(char *buf, size_t size,
 	if (attr & ~(EFI_MEMORY_UC | EFI_MEMORY_WC | EFI_MEMORY_WT |
 		     EFI_MEMORY_WB | EFI_MEMORY_UCE | EFI_MEMORY_RO |
 		     EFI_MEMORY_WP | EFI_MEMORY_RP | EFI_MEMORY_XP |
-		     EFI_MEMORY_NV |
+		     EFI_MEMORY_NV | EFI_MEMORY_SP |
 		     EFI_MEMORY_RUNTIME | EFI_MEMORY_MORE_RELIABLE))
 		snprintf(pos, size, "|attr=0x%016llx]",
 			 (unsigned long long)attr);
 	else
 		snprintf(pos, size,
-			 "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
+			 "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
 			 attr & EFI_MEMORY_RUNTIME ? "RUN" : "",
 			 attr & EFI_MEMORY_MORE_RELIABLE ? "MR" : "",
+			 attr & EFI_MEMORY_SP      ? "SP"  : "",
 			 attr & EFI_MEMORY_NV      ? "NV"  : "",
 			 attr & EFI_MEMORY_XP      ? "XP"  : "",
 			 attr & EFI_MEMORY_RP      ? "RP"  : "",

drivers/firmware/efi/esrt.c

@@ -246,6 +246,9 @@ void __init efi_esrt_init(void)
 	int rc;
 	phys_addr_t end;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
 	pr_debug("esrt-init: loading.\n");
 	if (!esrt_table_exists())
 		return;

drivers/firmware/efi/fake_mem.c

@@ -17,12 +17,10 @@
 #include <linux/memblock.h>
 #include <linux/types.h>
 #include <linux/sort.h>
-#include <asm/efi.h>
+#include "fake_mem.h"
 
-#define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM
-
-static struct efi_mem_range fake_mems[EFI_MAX_FAKEMEM];
-static int nr_fake_mem;
+struct efi_mem_range efi_fake_mems[EFI_MAX_FAKEMEM];
+int nr_fake_mem;
 
 static int __init cmp_fake_mem(const void *x1, const void *x2)
 {
@@ -44,13 +42,13 @@ void __init efi_fake_memmap(void)
 	void *new_memmap;
 	int i;
 
-	if (!nr_fake_mem)
+	if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
 		return;
 
 	/* count up the number of EFI memory descriptor */
 	for (i = 0; i < nr_fake_mem; i++) {
 		for_each_efi_memory_desc(md) {
-			struct range *r = &fake_mems[i].range;
+			struct range *r = &efi_fake_mems[i].range;
 
 			new_nr_map += efi_memmap_split_count(md, r);
 		}
@@ -70,7 +68,7 @@ void __init efi_fake_memmap(void)
 	}
 
 	for (i = 0; i < nr_fake_mem; i++)
-		efi_memmap_insert(&efi.memmap, new_memmap, &fake_mems[i]);
+		efi_memmap_insert(&efi.memmap, new_memmap, &efi_fake_mems[i]);
 
 	/* swap into new EFI memmap */
 	early_memunmap(new_memmap, efi.memmap.desc_size * new_nr_map);
@@ -104,22 +102,22 @@ static int __init setup_fake_mem(char *p)
 		if (nr_fake_mem >= EFI_MAX_FAKEMEM)
 			break;
 
-		fake_mems[nr_fake_mem].range.start = start;
-		fake_mems[nr_fake_mem].range.end = start + mem_size - 1;
-		fake_mems[nr_fake_mem].attribute = attribute;
+		efi_fake_mems[nr_fake_mem].range.start = start;
+		efi_fake_mems[nr_fake_mem].range.end = start + mem_size - 1;
+		efi_fake_mems[nr_fake_mem].attribute = attribute;
 		nr_fake_mem++;
 
 		if (*p == ',')
 			p++;
 	}
 
-	sort(fake_mems, nr_fake_mem, sizeof(struct efi_mem_range),
+	sort(efi_fake_mems, nr_fake_mem, sizeof(struct efi_mem_range),
 	     cmp_fake_mem, NULL);
 
 	for (i = 0; i < nr_fake_mem; i++)
 		pr_info("efi_fake_mem: add attr=0x%016llx to [mem 0x%016llx-0x%016llx]",
-			fake_mems[i].attribute, fake_mems[i].range.start,
-			fake_mems[i].range.end);
+			efi_fake_mems[i].attribute, efi_fake_mems[i].range.start,
+			efi_fake_mems[i].range.end);
 
 	return *p == '\0' ? 0 : -EINVAL;
 }

drivers/firmware/efi/fake_mem.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __EFI_FAKE_MEM_H__
+#define __EFI_FAKE_MEM_H__
+#include <asm/efi.h>
+
+#define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM
+
+extern struct efi_mem_range efi_fake_mems[EFI_MAX_FAKEMEM];
+extern int nr_fake_mem;
+#endif /* __EFI_FAKE_MEM_H__ */

drivers/firmware/efi/libstub/arm32-stub.c

@@ -146,6 +146,11 @@ static efi_status_t reserve_kernel_base(efi_system_table_t *sys_table_arg,
 			continue;
 
 		case EFI_CONVENTIONAL_MEMORY:
+			/* Skip soft reserved conventional memory */
+			if (efi_soft_reserve_enabled() &&
+			    (desc->attribute & EFI_MEMORY_SP))
+				continue;
+
 			/*
 			 * Reserve the intersection between this entry and the
 			 * region.

drivers/firmware/efi/libstub/efi-stub-helper.c

@@ -32,6 +32,7 @@ static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE;
 static int __section(.data) __nokaslr;
 static int __section(.data) __quiet;
 static int __section(.data) __novamap;
+static bool __section(.data) efi_nosoftreserve;
 
 int __pure nokaslr(void)
 {
@@ -45,6 +46,10 @@ int __pure novamap(void)
 {
 	return __novamap;
 }
+bool __pure __efi_soft_reserve_enabled(void)
+{
+	return !efi_nosoftreserve;
+}
 
 #define EFI_MMAP_NR_SLACK_SLOTS	8
 
@@ -211,6 +216,10 @@ efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg,
 		if (desc->type != EFI_CONVENTIONAL_MEMORY)
 			continue;
 
+		if (efi_soft_reserve_enabled() &&
+		    (desc->attribute & EFI_MEMORY_SP))
+			continue;
+
 		if (desc->num_pages < nr_pages)
 			continue;
 
@@ -305,6 +314,10 @@ efi_status_t efi_low_alloc_above(efi_system_table_t *sys_table_arg,
 		if (desc->type != EFI_CONVENTIONAL_MEMORY)
 			continue;
 
+		if (efi_soft_reserve_enabled() &&
+		    (desc->attribute & EFI_MEMORY_SP))
+			continue;
+
 		if (desc->num_pages < nr_pages)
 			continue;
 
@@ -484,6 +497,12 @@ efi_status_t efi_parse_options(char const *cmdline)
 			__novamap = 1;
 		}
 
+		if (IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) &&
+		    !strncmp(str, "nosoftreserve", 7)) {
+			str += strlen("nosoftreserve");
+			efi_nosoftreserve = 1;
+		}
+
 		/* Group words together, delimited by "," */
 		while (*str && *str != ' ' && *str != ',')
 			str++;

drivers/firmware/efi/libstub/random.c

@@ -46,6 +46,10 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
 	if (md->type != EFI_CONVENTIONAL_MEMORY)
 		return 0;
 
+	if (efi_soft_reserve_enabled() &&
+	    (md->attribute & EFI_MEMORY_SP))
+		return 0;
+
 	region_end = min((u64)ULONG_MAX, md->phys_addr + md->num_pages*EFI_PAGE_SIZE - 1);
 
 	first_slot = round_up(md->phys_addr, align);

drivers/firmware/efi/x86_fake_mem.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2019 Intel Corporation. All rights reserved. */
+#include <linux/efi.h>
+#include <asm/e820/api.h>
+#include "fake_mem.h"
+
+void __init efi_fake_memmap_early(void)
+{
+	int i;
+
+	/*
+	 * The late efi_fake_mem() call can handle all requests if
+	 * EFI_MEMORY_SP support is disabled.
+	 */
+	if (!efi_soft_reserve_enabled())
+		return;
+
+	if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
+		return;
+
+	/*
+	 * Given that efi_fake_memmap() needs to perform memblock
+	 * allocations it needs to run after e820__memblock_setup().
+	 * However, if efi_fake_mem specifies EFI_MEMORY_SP for a given
+	 * address range that potentially needs to mark the memory as
+	 * reserved prior to e820__memblock_setup(). Update e820
+	 * directly if EFI_MEMORY_SP is specified for an
+	 * EFI_CONVENTIONAL_MEMORY descriptor.
+	 */
+	for (i = 0; i < nr_fake_mem; i++) {
+		struct efi_mem_range *mem = &efi_fake_mems[i];
+		efi_memory_desc_t *md;
+		u64 m_start, m_end;
+
+		if ((mem->attribute & EFI_MEMORY_SP) == 0)
+			continue;
+
+		m_start = mem->range.start;
+		m_end = mem->range.end;
+		for_each_efi_memory_desc(md) {
+			u64 start, end;
+
+			if (md->type != EFI_CONVENTIONAL_MEMORY)
+				continue;
+
+			start = md->phys_addr;
+			end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
+
+			if (m_start <= end && m_end >= start)
+				/* fake range overlaps descriptor */;
+			else
+				continue;
+
+			/*
+			 * Trim the boundary of the e820 update to the
+			 * descriptor in case the fake range overlaps
+			 * !EFI_CONVENTIONAL_MEMORY
+			 */
+			start = max(start, m_start);
+			end = min(end, m_end);
+
+			if (end <= start)
+				continue;
+			e820__range_update(start, end - start + 1, E820_TYPE_RAM,
+					E820_TYPE_SOFT_RESERVED);
+			e820__update_table(e820_table);
+		}
+	}
+}

drivers/nvdimm/Kconfig

@@ -4,6 +4,7 @@ menuconfig LIBNVDIMM
 	depends on PHYS_ADDR_T_64BIT
 	depends on HAS_IOMEM
 	depends on BLK_DEV
+	select MEMREGION
 	help
 	  Generic support for non-volatile memory devices including
 	  ACPI-6-NFIT defined resources.  On platforms that define an

drivers/nvdimm/core.c

@@ -455,7 +455,6 @@ static __exit void libnvdimm_exit(void)
 	nd_region_exit();
 	nvdimm_exit();
 	nvdimm_bus_exit();
-	nd_region_devs_exit();
 	nvdimm_devs_exit();
 }
 

drivers/nvdimm/nd-core.h

@@ -114,7 +114,6 @@ struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev);
 int __init nvdimm_bus_init(void);
 void nvdimm_bus_exit(void);
 void nvdimm_devs_exit(void);
-void nd_region_devs_exit(void);
 struct nd_region;
 void nd_region_advance_seeds(struct nd_region *nd_region, struct device *dev);
 void nd_region_create_ns_seed(struct nd_region *nd_region);

drivers/nvdimm/region_devs.c

@@ -3,6 +3,7 @@
  * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
  */
 #include <linux/scatterlist.h>
+#include <linux/memregion.h>
 #include <linux/highmem.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -19,7 +20,6 @@
  */
 #include <linux/io-64-nonatomic-hi-lo.h>
 
-static DEFINE_IDA(region_ida);
 static DEFINE_PER_CPU(int, flush_idx);
 
 static int nvdimm_map_flush(struct device *dev, struct nvdimm *nvdimm, int dimm,
@@ -133,7 +133,7 @@ static void nd_region_release(struct device *dev)
 		put_device(&nvdimm->dev);
 	}
 	free_percpu(nd_region->lane);
-	ida_simple_remove(&region_ida, nd_region->id);
+	memregion_free(nd_region->id);
 	if (is_nd_blk(dev))
 		kfree(to_nd_blk_region(dev));
 	else
@@ -985,7 +985,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 
 	if (!region_buf)
 		return NULL;
-	nd_region->id = ida_simple_get(&region_ida, 0, 0, GFP_KERNEL);
+	nd_region->id = memregion_alloc(GFP_KERNEL);
 	if (nd_region->id < 0)
 		goto err_id;
 
@@ -1044,7 +1044,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 	return nd_region;
 
  err_percpu:
-	ida_simple_remove(&region_ida, nd_region->id);
+	memregion_free(nd_region->id);
  err_id:
 	kfree(region_buf);
 	return NULL;
@@ -1216,8 +1216,3 @@ int nd_region_conflict(struct nd_region *nd_region, resource_size_t start,
 
 	return device_for_each_child(&nvdimm_bus->dev, &ctx, region_conflict);
 }
-
-void __exit nd_region_devs_exit(void)
-{
-	ida_destroy(&region_ida);
-}

include/linux/efi.h

@@ -112,6 +112,7 @@ typedef	struct {
 #define EFI_MEMORY_MORE_RELIABLE \
 				((u64)0x0000000000010000ULL)	/* higher reliability */
 #define EFI_MEMORY_RO		((u64)0x0000000000020000ULL)	/* read-only */
+#define EFI_MEMORY_SP		((u64)0x0000000000040000ULL)	/* soft reserved */
 #define EFI_MEMORY_RUNTIME	((u64)0x8000000000000000ULL)	/* range requires runtime mapping */
 #define EFI_MEMORY_DESCRIPTOR_VERSION	1
 
@@ -1044,7 +1045,6 @@ extern void efi_enter_virtual_mode (void);	/* switch EFI to virtual mode, if pos
 extern efi_status_t efi_query_variable_store(u32 attributes,
 					     unsigned long size,
 					     bool nonblocking);
-extern void efi_find_mirror(void);
 #else
 
 static inline efi_status_t efi_query_variable_store(u32 attributes,
@@ -1202,6 +1202,7 @@ extern int __init efi_setup_pcdp_console(char *);
 #define EFI_DBG			8	/* Print additional debug info at runtime */
 #define EFI_NX_PE_DATA		9	/* Can runtime data regions be mapped non-executable? */
 #define EFI_MEM_ATTR		10	/* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */
+#define EFI_MEM_NO_SOFT_RESERVE	11	/* Is the kernel configured to ignore soft reservations? */
 
 #ifdef CONFIG_EFI
 /*
@@ -1212,6 +1213,14 @@ static inline bool efi_enabled(int feature)
 	return test_bit(feature, &efi.flags) != 0;
 }
 extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused);
+
+bool __pure __efi_soft_reserve_enabled(void);
+
+static inline bool __pure efi_soft_reserve_enabled(void)
+{
+	return IS_ENABLED(CONFIG_EFI_SOFT_RESERVE)
+		&& __efi_soft_reserve_enabled();
+}
 #else
 static inline bool efi_enabled(int feature)
 {
@@ -1225,6 +1234,11 @@ efi_capsule_pending(int *reset_type)
 {
 	return false;
 }
+
+static inline bool efi_soft_reserve_enabled(void)
+{
+	return false;
+}
 #endif
 
 extern int efi_status_to_err(efi_status_t status);

include/linux/ioport.h

@@ -134,6 +134,7 @@ enum {
 	IORES_DESC_PERSISTENT_MEMORY_LEGACY	= 5,
 	IORES_DESC_DEVICE_PRIVATE_MEMORY	= 6,
 	IORES_DESC_RESERVED			= 7,
+	IORES_DESC_SOFT_RESERVED		= 8,
 };
 
 /*

include/linux/memregion.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MEMREGION_H_
+#define _MEMREGION_H_
+#include <linux/types.h>
+#include <linux/errno.h>
+
+struct memregion_info {
+	int target_node;
+};
+
+#ifdef CONFIG_MEMREGION
+int memregion_alloc(gfp_t gfp);
+void memregion_free(int id);
+#else
+static inline int memregion_alloc(gfp_t gfp)
+{
+	return -ENOMEM;
+}
+void memregion_free(int id)
+{
+}
+#endif
+#endif /* _MEMREGION_H_ */

lib/Kconfig

@@ -605,6 +605,9 @@ config ARCH_NO_SG_CHAIN
 config ARCH_HAS_PMEM_API
 	bool
 
+config MEMREGION
+	bool
+
 # use memcpy to implement user copies for nommu architectures
 config UACCESS_MEMCPY
 	bool

lib/Makefile

@@ -212,6 +212,7 @@ obj-$(CONFIG_GENERIC_NET_UTILS) += net_utils.o
 
 obj-$(CONFIG_SG_SPLIT) += sg_split.o
 obj-$(CONFIG_SG_POOL) += sg_pool.o
+obj-$(CONFIG_MEMREGION) += memregion.o
 obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
 obj-$(CONFIG_IRQ_POLL) += irq_poll.o
 

lib/memregion.c

+// SPDX-License-Identifier: GPL-2.0-only
+/* identifiers for device / performance-differentiated memory regions */
+#include <linux/idr.h>
+#include <linux/types.h>
+
+static DEFINE_IDA(memregion_ids);
+
+int memregion_alloc(gfp_t gfp)
+{
+	return ida_alloc(&memregion_ids, gfp);
+}
+EXPORT_SYMBOL(memregion_alloc);
+
+void memregion_free(int id)
+{
+	ida_free(&memregion_ids, id);
+}
+EXPORT_SYMBOL(memregion_free);