efi: Export EFI runtime memory mapping to sysfs

kexec kernel will need exactly same mapping for EFI runtime memory
ranges. Thus here export the runtime ranges mapping to sysfs,
kexec-tools will assemble them and pass to 2nd kernel via setup_data.

Introducing a new directory /sys/firmware/efi/runtime-map just like
/sys/firmware/memmap. Containing below attribute in each file of that
directory:

attribute  num_pages  phys_addr  type  virt_addr

Signed-off-by: Dave Young <dyoung@redhat.com>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

Documentation/ABI/testing/sysfs-firmware-efi-runtime-map

@@ -0,0 +1,34 @@
+What:		/sys/firmware/efi/runtime-map/
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	Switching efi runtime services to virtual mode requires
+		that all efi memory ranges which have the runtime attribute
+		bit set to be mapped to virtual addresses.
+
+		The efi runtime services can only be switched to virtual
+		mode once without rebooting. The kexec kernel must maintain
+		the same physical to virtual address mappings as the first
+		kernel. The mappings are exported to sysfs so userspace tools
+		can reassemble them and pass them into the kexec kernel.
+
+		/sys/firmware/efi/runtime-map/ is the directory the kernel
+		exports that information in.
+
+		subdirectories are named with the number of the memory range:
+
+			/sys/firmware/efi/runtime-map/0
+			/sys/firmware/efi/runtime-map/1
+			/sys/firmware/efi/runtime-map/2
+			/sys/firmware/efi/runtime-map/3
+			...
+
+		Each subdirectory contains five files:
+
+		attribute : The attributes of the memory range.
+		num_pages : The size of the memory range in pages.
+		phys_addr : The physical address of the memory range.
+		type      : The type of the memory range.
+		virt_addr : The virtual address of the memory range.
+
+		Above values are all hexadecimal numbers with the '0x' prefix.
+Users:		Kexec

arch/x86/platform/efi/efi.c

@@ -76,6 +76,9 @@ static __initdata efi_config_table_type_t arch_tables[] = {
 	{NULL_GUID, NULL, NULL},
 };
 
+static void *efi_runtime_map;
+static int nr_efi_runtime_map;
+
 /*
  * Returns 1 if 'facility' is enabled, 0 otherwise.
  */
@@ -824,6 +827,39 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md)
 	}
 }
 
+static int __init save_runtime_map(void)
+{
+	efi_memory_desc_t *md;
+	void *tmp, *p, *q = NULL;
+	int count = 0;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) ||
+		    (md->type == EFI_BOOT_SERVICES_CODE) ||
+		    (md->type == EFI_BOOT_SERVICES_DATA))
+			continue;
+		tmp = krealloc(q, (count + 1) * memmap.desc_size, GFP_KERNEL);
+		if (!tmp)
+			goto out;
+		q = tmp;
+
+		memcpy(q + count * memmap.desc_size, md, memmap.desc_size);
+		count++;
+	}
+
+	efi_runtime_map = q;
+	nr_efi_runtime_map = count;
+	efi_runtime_map_setup(efi_runtime_map, nr_efi_runtime_map,
+			      boot_params.efi_info.efi_memdesc_size);
+
+	return 0;
+out:
+	kfree(q);
+	return -ENOMEM;
+}
+
 /*
  * Map efi memory ranges for runtime serivce and update new_memmap with virtual
  * addresses.
@@ -849,7 +885,7 @@ static void * __init efi_map_regions(int *count)
 		tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size,
 			       GFP_KERNEL);
 		if (!tmp)
-			goto out_krealloc;
+			goto out;
 		new_memmap = tmp;
 		memcpy(new_memmap + (*count * memmap.desc_size), md,
 		       memmap.desc_size);
@@ -857,7 +893,7 @@ static void * __init efi_map_regions(int *count)
 	}
 
 	return new_memmap;
-out_krealloc:
+out:
 	kfree(new_memmap);
 	return NULL;
 }
@@ -883,7 +919,7 @@ void __init efi_enter_virtual_mode(void)
 {
 	efi_status_t status;
 	void *new_memmap = NULL;
-	int count = 0;
+	int err, count = 0;
 
 	efi.systab = NULL;
 
@@ -904,6 +940,10 @@ void __init efi_enter_virtual_mode(void)
 		return;
 	}
 
+	err = save_runtime_map();
+	if (err)
+		pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+
 	BUG_ON(!efi.systab);
 
 	efi_setup_page_tables();

drivers/firmware/efi/Kconfig

@@ -39,4 +39,15 @@ config EFI_VARS_PSTORE_DEFAULT_DISABLE
 config UEFI_CPER
 	def_bool n
 
+config EFI_RUNTIME_MAP
+	bool "Export efi runtime maps to sysfs"
+	depends on X86 && EFI && KEXEC
+	default y
+	help
+	  Export efi runtime memory maps to /sys/firmware/efi/runtime-map.
+	  That memory map is used for example by kexec to set up efi virtual
+	  mapping the 2nd kernel, but can also be used for debugging purposes.
+
+	  See also Documentation/ABI/testing/sysfs-firmware-efi-runtime-map.
+
 endmenu

drivers/firmware/efi/Makefile

@@ -5,3 +5,4 @@ obj-y					+= efi.o vars.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
 obj-$(CONFIG_EFI_VARS_PSTORE)		+= efi-pstore.o
 obj-$(CONFIG_UEFI_CPER)			+= cper.o
+obj-$(CONFIG_EFI_RUNTIME_MAP)		+= runtime-map.o

drivers/firmware/efi/efi.c

@@ -167,6 +167,10 @@ static int __init efisubsys_init(void)
 		goto err_unregister;
 	}
 
+	error = efi_runtime_map_init(efi_kobj);
+	if (error)
+		goto err_remove_group;
+
 	/* and the standard mountpoint for efivarfs */
 	efivars_kobj = kobject_create_and_add("efivars", efi_kobj);
 	if (!efivars_kobj) {

drivers/firmware/efi/runtime-map.c

@@ -0,0 +1,181 @@
+/*
+ * linux/drivers/efi/runtime-map.c
+ * Copyright (C) 2013 Red Hat, Inc., Dave Young <dyoung@redhat.com>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+
+#include <asm/setup.h>
+
+static void *efi_runtime_map;
+static int nr_efi_runtime_map;
+static u32 efi_memdesc_size;
+
+struct efi_runtime_map_entry {
+	efi_memory_desc_t md;
+	struct kobject kobj;   /* kobject for each entry */
+};
+
+static struct efi_runtime_map_entry **map_entries;
+
+struct map_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct efi_runtime_map_entry *entry, char *buf);
+};
+
+static inline struct map_attribute *to_map_attr(struct attribute *attr)
+{
+	return container_of(attr, struct map_attribute, attr);
+}
+
+static ssize_t type_show(struct efi_runtime_map_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%x\n", entry->md.type);
+}
+
+#define EFI_RUNTIME_FIELD(var) entry->md.var
+
+#define EFI_RUNTIME_U64_ATTR_SHOW(name) \
+static ssize_t name##_show(struct efi_runtime_map_entry *entry, char *buf) \
+{ \
+	return snprintf(buf, PAGE_SIZE, "0x%llx\n", EFI_RUNTIME_FIELD(name)); \
+}
+
+EFI_RUNTIME_U64_ATTR_SHOW(phys_addr);
+EFI_RUNTIME_U64_ATTR_SHOW(virt_addr);
+EFI_RUNTIME_U64_ATTR_SHOW(num_pages);
+EFI_RUNTIME_U64_ATTR_SHOW(attribute);
+
+static inline struct efi_runtime_map_entry *to_map_entry(struct kobject *kobj)
+{
+	return container_of(kobj, struct efi_runtime_map_entry, kobj);
+}
+
+static ssize_t map_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct efi_runtime_map_entry *entry = to_map_entry(kobj);
+	struct map_attribute *map_attr = to_map_attr(attr);
+
+	return map_attr->show(entry, buf);
+}
+
+static struct map_attribute map_type_attr = __ATTR_RO(type);
+static struct map_attribute map_phys_addr_attr   = __ATTR_RO(phys_addr);
+static struct map_attribute map_virt_addr_attr  = __ATTR_RO(virt_addr);
+static struct map_attribute map_num_pages_attr  = __ATTR_RO(num_pages);
+static struct map_attribute map_attribute_attr  = __ATTR_RO(attribute);
+
+/*
+ * These are default attributes that are added for every memmap entry.
+ */
+static struct attribute *def_attrs[] = {
+	&map_type_attr.attr,
+	&map_phys_addr_attr.attr,
+	&map_virt_addr_attr.attr,
+	&map_num_pages_attr.attr,
+	&map_attribute_attr.attr,
+	NULL
+};
+
+static const struct sysfs_ops map_attr_ops = {
+	.show = map_attr_show,
+};
+
+static void map_release(struct kobject *kobj)
+{
+	struct efi_runtime_map_entry *entry;
+
+	entry = to_map_entry(kobj);
+	kfree(entry);
+}
+
+static struct kobj_type __refdata map_ktype = {
+	.sysfs_ops	= &map_attr_ops,
+	.default_attrs	= def_attrs,
+	.release	= map_release,
+};
+
+static struct kset *map_kset;
+
+static struct efi_runtime_map_entry *
+add_sysfs_runtime_map_entry(struct kobject *kobj, int nr)
+{
+	int ret;
+	struct efi_runtime_map_entry *entry;
+
+	if (!map_kset) {
+		map_kset = kset_create_and_add("runtime-map", NULL, kobj);
+		if (!map_kset)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		kset_unregister(map_kset);
+		return entry;
+	}
+
+	memcpy(&entry->md, efi_runtime_map + nr * efi_memdesc_size,
+	       sizeof(efi_memory_desc_t));
+
+	kobject_init(&entry->kobj, &map_ktype);
+	entry->kobj.kset = map_kset;
+	ret = kobject_add(&entry->kobj, NULL, "%d", nr);
+	if (ret) {
+		kobject_put(&entry->kobj);
+		kset_unregister(map_kset);
+		return ERR_PTR(ret);
+	}
+
+	return entry;
+}
+
+void efi_runtime_map_setup(void *map, int nr_entries, u32 desc_size)
+{
+	efi_runtime_map = map;
+	nr_efi_runtime_map = nr_entries;
+	efi_memdesc_size = desc_size;
+}
+
+int __init efi_runtime_map_init(struct kobject *efi_kobj)
+{
+	int i, j, ret = 0;
+	struct efi_runtime_map_entry *entry;
+
+	if (!efi_runtime_map)
+		return 0;
+
+	map_entries = kzalloc(nr_efi_runtime_map * sizeof(entry), GFP_KERNEL);
+	if (!map_entries) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < nr_efi_runtime_map; i++) {
+		entry = add_sysfs_runtime_map_entry(efi_kobj, i);
+		if (IS_ERR(entry)) {
+			ret = PTR_ERR(entry);
+			goto out_add_entry;
+		}
+		*(map_entries + i) = entry;
+	}
+
+	return 0;
+out_add_entry:
+	for (j = i - 1; j > 0; j--) {
+		entry = *(map_entries + j);
+		kobject_put(&entry->kobj);
+	}
+	if (map_kset)
+		kset_unregister(map_kset);
+out:
+	return ret;
+}

include/linux/efi.h

@@ -872,4 +872,17 @@ int efivars_sysfs_init(void);
 
 #endif /* CONFIG_EFI_VARS */
 
+#ifdef CONFIG_EFI_RUNTIME_MAP
+int efi_runtime_map_init(struct kobject *);
+void efi_runtime_map_setup(void *, int, u32);
+#else
+static inline int efi_runtime_map_init(struct kobject *kobj)
+{
+	return 0;
+}
+
+static inline void
+efi_runtime_map_setup(void *map, int nr_entries, u32 desc_size) {}
+#endif
+
 #endif /* _LINUX_EFI_H */