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

12 files changed, 191 insertions, 17 deletions

diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index b248870a9806..bcc378c19ebe 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/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
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 4ac2de4dfa72..554d795270d9 100644
--- a/drivers/firmware/efi/Makefile
+++ b/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)
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index 311cd349a862..904fa09e6a6b 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -164,6 +164,15 @@ static __init int is_usable_memory(efi_memory_desc_t *md)
 	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
 		 * them as System RAM if they can be mapped writeback cacheable.
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index e2ac5fa5531b..899b803842bb 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/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;
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 8a492ce16b3b..d101f072c8f8 100644
--- a/drivers/firmware/efi/efi.c
+++ b/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"  : "",
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index d6dd5f503fa2..2762e0662bf4 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/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;
diff --git a/drivers/firmware/efi/fake_mem.c b/drivers/firmware/efi/fake_mem.c
index 9501edc0fcfb..bb9fc70d0cfa 100644
--- a/drivers/firmware/efi/fake_mem.c
+++ b/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;
 }
diff --git a/drivers/firmware/efi/fake_mem.h b/drivers/firmware/efi/fake_mem.h
new file mode 100644
index 000000000000..d52791af4b18
--- /dev/null
+++ b/drivers/firmware/efi/fake_mem.h
@@ -0,0 +1,10 @@
+/* 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__ */
diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
index 41213bf5fcf5..4566640de650 100644
--- a/drivers/firmware/efi/libstub/arm32-stub.c
+++ b/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.
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 35dbc2791c97..e02579907f2e 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/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 @@ again:
 		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++;
diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c
index b4b1d1dcb5fd..6c188695e730 100644
--- a/drivers/firmware/efi/libstub/random.c
+++ b/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);
diff --git a/drivers/firmware/efi/x86_fake_mem.c b/drivers/firmware/efi/x86_fake_mem.c
new file mode 100644
index 000000000000..e5d6d5a1b240
--- /dev/null
+++ b/drivers/firmware/efi/x86_fake_mem.c
@@ -0,0 +1,69 @@
+// 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);
+		}
+	}
+}