Linux-libre 4.6.2-gnu

20 files changed, 1307 insertions, 174 deletions

diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 49a3a1185..6664f1108 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -161,6 +161,26 @@ config RASPBERRYPI_FIRMWARE
 	  This option enables support for communicating with the firmware on the
 	  Raspberry Pi.
 
+config FW_CFG_SYSFS
+	tristate "QEMU fw_cfg device support in sysfs"
+	depends on SYSFS && (ARM || ARM64 || PPC_PMAC || SPARC || X86)
+	depends on HAS_IOPORT_MAP
+	default n
+	help
+	  Say Y or M here to enable the exporting of the QEMU firmware
+	  configuration (fw_cfg) file entries via sysfs. Entries are
+	  found under /sys/firmware/fw_cfg when this option is enabled
+	  and loaded.
+
+config FW_CFG_SYSFS_CMDLINE
+	bool "QEMU fw_cfg device parameter parsing"
+	depends on FW_CFG_SYSFS
+	help
+	  Allow the qemu_fw_cfg device to be initialized via the kernel
+	  command line or using a module parameter.
+	  WARNING: Using incorrect parameters (base address in particular)
+	  may crash your system.
+
 config QCOM_SCM
 	bool
 	depends on ARM || ARM64
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 48dd41752..474bada56 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_ISCSI_IBFT_FIND)	+= iscsi_ibft_find.o
 obj-$(CONFIG_ISCSI_IBFT)	+= iscsi_ibft.o
 obj-$(CONFIG_FIRMWARE_MEMMAP)	+= memmap.o
 obj-$(CONFIG_RASPBERRYPI_FIRMWARE) += raspberrypi.o
+obj-$(CONFIG_FW_CFG_SYSFS)	+= qemu_fw_cfg.o
 obj-$(CONFIG_QCOM_SCM)		+= qcom_scm.o
 obj-$(CONFIG_QCOM_SCM_64)	+= qcom_scm-64.o
 obj-$(CONFIG_QCOM_SCM_32)	+= qcom_scm-32.o
diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c
index 6174db80c..7e3e595c9 100644
--- a/drivers/firmware/arm_scpi.c
+++ b/drivers/firmware/arm_scpi.c
@@ -80,7 +80,7 @@
 #define FW_REV_MINOR(x)		(((x) & FW_REV_MINOR_MASK) >> FW_REV_MINOR_BITS)
 #define FW_REV_PATCH(x)		((x) & FW_REV_PATCH_MASK)
 
-#define MAX_RX_TIMEOUT		(msecs_to_jiffies(20))
+#define MAX_RX_TIMEOUT		(msecs_to_jiffies(30))
 
 enum scpi_error_codes {
 	SCPI_SUCCESS = 0, /* Success */
@@ -231,7 +231,8 @@ struct _scpi_sensor_info {
 };
 
 struct sensor_value {
-	__le32 val;
+	__le32 lo_val;
+	__le32 hi_val;
 } __packed;
 
 static struct scpi_drvinfo *scpi_info;
@@ -373,7 +374,7 @@ static int scpi_send_message(u8 cmd, void *tx_buf, unsigned int tx_len,
 		ret = -ETIMEDOUT;
 	else
 		/* first status word */
-		ret = le32_to_cpu(msg->status);
+		ret = msg->status;
 out:
 	if (ret < 0 && rx_buf) /* remove entry from the list if timed-out */
 		scpi_process_cmd(scpi_chan, msg->cmd);
@@ -525,15 +526,17 @@ static int scpi_sensor_get_info(u16 sensor_id, struct scpi_sensor_info *info)
 	return ret;
 }
 
-int scpi_sensor_get_value(u16 sensor, u32 *val)
+int scpi_sensor_get_value(u16 sensor, u64 *val)
 {
+	__le16 id = cpu_to_le16(sensor);
 	struct sensor_value buf;
 	int ret;
 
-	ret = scpi_send_message(SCPI_CMD_SENSOR_VALUE, &sensor, sizeof(sensor),
+	ret = scpi_send_message(SCPI_CMD_SENSOR_VALUE, &id, sizeof(id),
 				&buf, sizeof(buf));
 	if (!ret)
-		*val = le32_to_cpu(buf.val);
+		*val = (u64)le32_to_cpu(buf.hi_val) << 32 |
+			le32_to_cpu(buf.lo_val);
 
 	return ret;
 }
@@ -699,7 +702,7 @@ static int scpi_probe(struct platform_device *pdev)
 		cl->rx_callback = scpi_handle_remote_msg;
 		cl->tx_prepare = scpi_tx_prepare;
 		cl->tx_block = true;
-		cl->tx_tout = 50;
+		cl->tx_tout = 20;
 		cl->knows_txdone = false; /* controller can't ack */
 
 		INIT_LIST_HEAD(&pchan->rx_pending);
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index a76c35fc0..8714f8c27 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -61,8 +61,8 @@ static int __init uefi_init(void)
 	char vendor[100] = "unknown";
 	int i, retval;
 
-	efi.systab = early_memremap(efi_system_table,
-				    sizeof(efi_system_table_t));
+	efi.systab = early_memremap_ro(efi_system_table,
+				       sizeof(efi_system_table_t));
 	if (efi.systab == NULL) {
 		pr_warn("Unable to map EFI system table.\n");
 		return -ENOMEM;
@@ -86,8 +86,8 @@ static int __init uefi_init(void)
 			efi.systab->hdr.revision & 0xffff);
 
 	/* Show what we know for posterity */
-	c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor),
-			     sizeof(vendor) * sizeof(efi_char16_t));
+	c16 = early_memremap_ro(efi_to_phys(efi.systab->fw_vendor),
+				sizeof(vendor) * sizeof(efi_char16_t));
 	if (c16) {
 		for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
 			vendor[i] = c16[i];
@@ -100,8 +100,8 @@ static int __init uefi_init(void)
 		efi.systab->hdr.revision & 0xffff, vendor);
 
 	table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables;
-	config_tables = early_memremap(efi_to_phys(efi.systab->tables),
-				       table_size);
+	config_tables = early_memremap_ro(efi_to_phys(efi.systab->tables),
+					  table_size);
 	if (config_tables == NULL) {
 		pr_warn("Unable to map EFI config table array.\n");
 		retval = -ENOMEM;
@@ -185,7 +185,7 @@ void __init efi_init(void)
 	efi_system_table = params.system_table;
 
 	memmap.phys_map = params.mmap;
-	memmap.map = early_memremap(params.mmap, params.mmap_size);
+	memmap.map = early_memremap_ro(params.mmap, params.mmap_size);
 	if (memmap.map == NULL) {
 		/*
 		* If we are booting via UEFI, the UEFI memory map is the only
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index c51f3b2fe..3a69ed5ec 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -327,38 +327,6 @@ u64 __init efi_mem_desc_end(efi_memory_desc_t *md)
 	return end;
 }
 
-/*
- * We can't ioremap data in EFI boot services RAM, because we've already mapped
- * it as RAM.  So, look it up in the existing EFI memory map instead.  Only
- * callable after efi_enter_virtual_mode and before efi_free_boot_services.
- */
-void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
-{
-	struct efi_memory_map *map;
-	void *p;
-	map = efi.memmap;
-	if (!map)
-		return NULL;
-	if (WARN_ON(!map->map))
-		return NULL;
-	for (p = map->map; p < map->map_end; p += map->desc_size) {
-		efi_memory_desc_t *md = p;
-		u64 size = md->num_pages << EFI_PAGE_SHIFT;
-		u64 end = md->phys_addr + size;
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
-		if (!md->virt_addr)
-			continue;
-		if (phys_addr >= md->phys_addr && phys_addr < end) {
-			phys_addr += md->virt_addr - md->phys_addr;
-			return (__force void __iomem *)(unsigned long)phys_addr;
-		}
-	}
-	return NULL;
-}
-
 static __initdata efi_config_table_type_t common_tables[] = {
 	{ACPI_20_TABLE_GUID, "ACPI 2.0", &efi.acpi20},
 	{ACPI_TABLE_GUID, "ACPI", &efi.acpi},
@@ -587,7 +555,8 @@ static __initdata char memory_type_name[][20] = {
 	"ACPI Memory NVS",
 	"Memory Mapped I/O",
 	"MMIO Port Space",
-	"PAL Code"
+	"PAL Code",
+	"Persistent Memory",
 };
 
 char * __init efi_md_typeattr_format(char *buf, size_t size,
@@ -614,13 +583,16 @@ 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_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|%3s|%2s|%2s|%2s|%2s]",
+		snprintf(pos, size,
+			 "|%3s|%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_NV      ? "NV"  : "",
 			 attr & EFI_MEMORY_XP      ? "XP"  : "",
 			 attr & EFI_MEMORY_RP      ? "RP"  : "",
 			 attr & EFI_MEMORY_WP      ? "WP"  : "",
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 10e6774ab..096adcbcb 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -231,7 +231,7 @@ sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor,
 
 static inline bool is_compat(void)
 {
-	if (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())
+	if (IS_ENABLED(CONFIG_COMPAT) && in_compat_syscall())
 		return true;
 
 	return false;
@@ -386,7 +386,7 @@ static const struct sysfs_ops efivar_attr_ops = {
 
 static void efivar_release(struct kobject *kobj)
 {
-	struct efivar_entry *var = container_of(kobj, struct efivar_entry, kobj);
+	struct efivar_entry *var = to_efivar_entry(kobj);
 	kfree(var);
 }
 
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index 22c5285f7..75feb3f58 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -167,14 +167,11 @@ static struct kset *esrt_kset;
 static int esre_create_sysfs_entry(void *esre, int entry_num)
 {
 	struct esre_entry *entry;
-	char name[20];
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
 		return -ENOMEM;
 
-	sprintf(name, "entry%d", entry_num);
-
 	entry->kobj.kset = esrt_kset;
 
 	if (esrt->fw_resource_version == 1) {
@@ -182,7 +179,7 @@ static int esre_create_sysfs_entry(void *esre, int entry_num)
 
 		entry->esre.esre1 = esre;
 		rc = kobject_init_and_add(&entry->kobj, &esre1_ktype, NULL,
-					  "%s", name);
+					  "entry%d", entry_num);
 		if (rc) {
 			kfree(entry);
 			return rc;
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index aaf9c0bab..da99bbb74 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -23,6 +23,10 @@ KBUILD_CFLAGS			:= $(cflags-y) -DDISABLE_BRANCH_PROFILING \
 GCOV_PROFILE			:= n
 KASAN_SANITIZE			:= n
 UBSAN_SANITIZE			:= n
+OBJECT_FILES_NON_STANDARD	:= y
+
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT			:= n
 
 lib-y				:= efi-stub-helper.o
 
@@ -36,7 +40,7 @@ lib-$(CONFIG_EFI_ARMSTUB)	+= arm-stub.o fdt.o string.o \
 				   $(patsubst %.c,lib-%.o,$(arm-deps))
 
 lib-$(CONFIG_ARM)		+= arm32-stub.o
-lib-$(CONFIG_ARM64)		+= arm64-stub.o
+lib-$(CONFIG_ARM64)		+= arm64-stub.o random.o
 CFLAGS_arm64-stub.o 		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 
 #
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 3397902e4..414deb85c 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -18,6 +18,8 @@
 
 #include "efistub.h"
 
+bool __nokaslr;
+
 static int efi_secureboot_enabled(efi_system_table_t *sys_table_arg)
 {
 	static efi_guid_t const var_guid = EFI_GLOBAL_VARIABLE_GUID;
@@ -190,6 +192,10 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 
 	pr_efi(sys_table, "Booting Linux Kernel...\n");
 
+	status = check_platform_features(sys_table);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
 	/*
 	 * Get a handle to the loaded image protocol.  This is used to get
 	 * information about the running image, such as size and the command
@@ -207,14 +213,6 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 		pr_efi_err(sys_table, "Failed to find DRAM base\n");
 		goto fail;
 	}
-	status = handle_kernel_image(sys_table, image_addr, &image_size,
-				     &reserve_addr,
-				     &reserve_size,
-				     dram_base, image);
-	if (status != EFI_SUCCESS) {
-		pr_efi_err(sys_table, "Failed to relocate kernel\n");
-		goto fail;
-	}
 
 	/*
 	 * Get the command line from EFI, using the LOADED_IMAGE
@@ -224,7 +222,28 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 	cmdline_ptr = efi_convert_cmdline(sys_table, image, &cmdline_size);
 	if (!cmdline_ptr) {
 		pr_efi_err(sys_table, "getting command line via LOADED_IMAGE_PROTOCOL\n");
-		goto fail_free_image;
+		goto fail;
+	}
+
+	/* check whether 'nokaslr' was passed on the command line */
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+		static const u8 default_cmdline[] = CONFIG_CMDLINE;
+		const u8 *str, *cmdline = cmdline_ptr;
+
+		if (IS_ENABLED(CONFIG_CMDLINE_FORCE))
+			cmdline = default_cmdline;
+		str = strstr(cmdline, "nokaslr");
+		if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
+			__nokaslr = true;
+	}
+
+	status = handle_kernel_image(sys_table, image_addr, &image_size,
+				     &reserve_addr,
+				     &reserve_size,
+				     dram_base, image);
+	if (status != EFI_SUCCESS) {
+		pr_efi_err(sys_table, "Failed to relocate kernel\n");
+		goto fail_free_cmdline;
 	}
 
 	status = efi_parse_options(cmdline_ptr);
@@ -244,7 +263,7 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 
 		if (status != EFI_SUCCESS) {
 			pr_efi_err(sys_table, "Failed to load device tree!\n");
-			goto fail_free_cmdline;
+			goto fail_free_image;
 		}
 	}
 
@@ -286,12 +305,11 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 	efi_free(sys_table, initrd_size, initrd_addr);
 	efi_free(sys_table, fdt_size, fdt_addr);
 
-fail_free_cmdline:
-	efi_free(sys_table, cmdline_size, (unsigned long)cmdline_ptr);
-
 fail_free_image:
 	efi_free(sys_table, image_size, *image_addr);
 	efi_free(sys_table, reserve_size, reserve_addr);
+fail_free_cmdline:
+	efi_free(sys_table, cmdline_size, (unsigned long)cmdline_ptr);
 fail:
 	return EFI_ERROR;
 }
diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
index 495ebd657..6f42be4d0 100644
--- a/drivers/firmware/efi/libstub/arm32-stub.c
+++ b/drivers/firmware/efi/libstub/arm32-stub.c
@@ -9,6 +9,23 @@
 #include <linux/efi.h>
 #include <asm/efi.h>
 
+efi_status_t check_platform_features(efi_system_table_t *sys_table_arg)
+{
+	int block;
+
+	/* non-LPAE kernels can run anywhere */
+	if (!IS_ENABLED(CONFIG_ARM_LPAE))
+		return EFI_SUCCESS;
+
+	/* LPAE kernels need compatible hardware */
+	block = cpuid_feature_extract(CPUID_EXT_MMFR0, 0);
+	if (block < 5) {
+		pr_efi_err(sys_table_arg, "This LPAE kernel is not supported by your CPU\n");
+		return EFI_UNSUPPORTED;
+	}
+	return EFI_SUCCESS;
+}
+
 efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 				 unsigned long *image_addr,
 				 unsigned long *image_size,
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index 78dfbd34b..a90f6459f 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -12,37 +12,87 @@
 #include <linux/efi.h>
 #include <asm/efi.h>
 #include <asm/sections.h>
+#include <asm/sysreg.h>
 
-efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg,
-					unsigned long *image_addr,
-					unsigned long *image_size,
-					unsigned long *reserve_addr,
-					unsigned long *reserve_size,
-					unsigned long dram_base,
-					efi_loaded_image_t *image)
+#include "efistub.h"
+
+extern bool __nokaslr;
+
+efi_status_t check_platform_features(efi_system_table_t *sys_table_arg)
+{
+	u64 tg;
+
+	/* UEFI mandates support for 4 KB granularity, no need to check */
+	if (IS_ENABLED(CONFIG_ARM64_4K_PAGES))
+		return EFI_SUCCESS;
+
+	tg = (read_cpuid(ID_AA64MMFR0_EL1) >> ID_AA64MMFR0_TGRAN_SHIFT) & 0xf;
+	if (tg != ID_AA64MMFR0_TGRAN_SUPPORTED) {
+		if (IS_ENABLED(CONFIG_ARM64_64K_PAGES))
+			pr_efi_err(sys_table_arg, "This 64 KB granular kernel is not supported by your CPU\n");
+		else
+			pr_efi_err(sys_table_arg, "This 16 KB granular kernel is not supported by your CPU\n");
+		return EFI_UNSUPPORTED;
+	}
+	return EFI_SUCCESS;
+}
+
+efi_status_t handle_kernel_image(efi_system_table_t *sys_table_arg,
+				 unsigned long *image_addr,
+				 unsigned long *image_size,
+				 unsigned long *reserve_addr,
+				 unsigned long *reserve_size,
+				 unsigned long dram_base,
+				 efi_loaded_image_t *image)
 {
 	efi_status_t status;
 	unsigned long kernel_size, kernel_memsize = 0;
-	unsigned long nr_pages;
 	void *old_image_addr = (void *)*image_addr;
 	unsigned long preferred_offset;
+	u64 phys_seed = 0;
+
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+		if (!__nokaslr) {
+			status = efi_get_random_bytes(sys_table_arg,
+						      sizeof(phys_seed),
+						      (u8 *)&phys_seed);
+			if (status == EFI_NOT_FOUND) {
+				pr_efi(sys_table_arg, "EFI_RNG_PROTOCOL unavailable, no randomness supplied\n");
+			} else if (status != EFI_SUCCESS) {
+				pr_efi_err(sys_table_arg, "efi_get_random_bytes() failed\n");
+				return status;
+			}
+		} else {
+			pr_efi(sys_table_arg, "KASLR disabled on kernel command line\n");
+		}
+	}
 
 	/*
 	 * The preferred offset of the kernel Image is TEXT_OFFSET bytes beyond
 	 * a 2 MB aligned base, which itself may be lower than dram_base, as
 	 * long as the resulting offset equals or exceeds it.
 	 */
-	preferred_offset = round_down(dram_base, SZ_2M) + TEXT_OFFSET;
+	preferred_offset = round_down(dram_base, MIN_KIMG_ALIGN) + TEXT_OFFSET;
 	if (preferred_offset < dram_base)
-		preferred_offset += SZ_2M;
+		preferred_offset += MIN_KIMG_ALIGN;
 
-	/* Relocate the image, if required. */
 	kernel_size = _edata - _text;
-	if (*image_addr != preferred_offset) {
-		kernel_memsize = kernel_size + (_end - _edata);
+	kernel_memsize = kernel_size + (_end - _edata);
+
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && phys_seed != 0) {
+		/*
+		 * If KASLR is enabled, and we have some randomness available,
+		 * locate the kernel at a randomized offset in physical memory.
+		 */
+		*reserve_size = kernel_memsize + TEXT_OFFSET;
+		status = efi_random_alloc(sys_table_arg, *reserve_size,
+					  MIN_KIMG_ALIGN, reserve_addr,
+					  phys_seed);
 
+		*image_addr = *reserve_addr + TEXT_OFFSET;
+	} else {
 		/*
-		 * First, try a straight allocation at the preferred offset.
+		 * Else, try a straight allocation at the preferred offset.
 		 * This will work around the issue where, if dram_base == 0x0,
 		 * efi_low_alloc() refuses to allocate at 0x0 (to prevent the
 		 * address of the allocation to be mistaken for a FAIL return
@@ -52,27 +102,31 @@ efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg,
 		 * Mustang), we can still place the kernel at the address
 		 * 'dram_base + TEXT_OFFSET'.
 		 */
+		if (*image_addr == preferred_offset)
+			return EFI_SUCCESS;
+
 		*image_addr = *reserve_addr = preferred_offset;
-		nr_pages = round_up(kernel_memsize, EFI_ALLOC_ALIGN) /
-			   EFI_PAGE_SIZE;
+		*reserve_size = round_up(kernel_memsize, EFI_ALLOC_ALIGN);
+
 		status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS,
-					EFI_LOADER_DATA, nr_pages,
+					EFI_LOADER_DATA,
+					*reserve_size / EFI_PAGE_SIZE,
 					(efi_physical_addr_t *)reserve_addr);
-		if (status != EFI_SUCCESS) {
-			kernel_memsize += TEXT_OFFSET;
-			status = efi_low_alloc(sys_table_arg, kernel_memsize,
-					       SZ_2M, reserve_addr);
+	}
 
-			if (status != EFI_SUCCESS) {
-				pr_efi_err(sys_table_arg, "Failed to relocate kernel\n");
-				return status;
-			}
-			*image_addr = *reserve_addr + TEXT_OFFSET;
+	if (status != EFI_SUCCESS) {
+		*reserve_size = kernel_memsize + TEXT_OFFSET;
+		status = efi_low_alloc(sys_table_arg, *reserve_size,
+				       MIN_KIMG_ALIGN, reserve_addr);
+
+		if (status != EFI_SUCCESS) {
+			pr_efi_err(sys_table_arg, "Failed to relocate kernel\n");
+			*reserve_size = 0;
+			return status;
 		}
-		memcpy((void *)*image_addr, old_image_addr, kernel_size);
-		*reserve_size = kernel_memsize;
+		*image_addr = *reserve_addr + TEXT_OFFSET;
 	}
-
+	memcpy((void *)*image_addr, old_image_addr, kernel_size);
 
 	return EFI_SUCCESS;
 }
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index f07d4a67f..29ed2f9b2 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -649,6 +649,10 @@ static u8 *efi_utf16_to_utf8(u8 *dst, const u16 *src, int n)
 	return dst;
 }
 
+#ifndef MAX_CMDLINE_ADDRESS
+#define MAX_CMDLINE_ADDRESS	ULONG_MAX
+#endif
+
 /*
  * Convert the unicode UEFI command line to ASCII to pass to kernel.
  * Size of memory allocated return in *cmd_line_len.
@@ -684,7 +688,8 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg,
 
 	options_bytes++;	/* NUL termination */
 
-	status = efi_low_alloc(sys_table_arg, options_bytes, 0, &cmdline_addr);
+	status = efi_high_alloc(sys_table_arg, options_bytes, 0,
+				&cmdline_addr, MAX_CMDLINE_ADDRESS);
 	if (status != EFI_SUCCESS)
 		return NULL;
 
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 6b6548fda..ee49cd23e 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -5,6 +5,16 @@
 /* error code which can't be mistaken for valid address */
 #define EFI_ERROR	(~0UL)
 
+/*
+ * __init annotations should not be used in the EFI stub, since the code is
+ * either included in the decompressor (x86, ARM) where they have no effect,
+ * or the whole stub is __init annotated at the section level (arm64), by
+ * renaming the sections, in which case the __init annotation will be
+ * redundant, and will result in section names like .init.init.text, and our
+ * linker script does not expect that.
+ */
+#undef __init
+
 void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
 
 efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
@@ -43,4 +53,13 @@ void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size,
 		     unsigned long desc_size, efi_memory_desc_t *runtime_map,
 		     int *count);
 
+efi_status_t efi_get_random_bytes(efi_system_table_t *sys_table,
+				  unsigned long size, u8 *out);
+
+efi_status_t efi_random_alloc(efi_system_table_t *sys_table_arg,
+			      unsigned long size, unsigned long align,
+			      unsigned long *addr, unsigned long random_seed);
+
+efi_status_t check_platform_features(efi_system_table_t *sys_table_arg);
+
 #endif
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index cf7b7d463..6dba78aef 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -147,6 +147,20 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
 	if (status)
 		goto fdt_set_fail;
 
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+		efi_status_t efi_status;
+
+		efi_status = efi_get_random_bytes(sys_table, sizeof(fdt_val64),
+						  (u8 *)&fdt_val64);
+		if (efi_status == EFI_SUCCESS) {
+			status = fdt_setprop(fdt, node, "kaslr-seed",
+					     &fdt_val64, sizeof(fdt_val64));
+			if (status)
+				goto fdt_set_fail;
+		} else if (efi_status != EFI_NOT_FOUND) {
+			return efi_status;
+		}
+	}
 	return EFI_SUCCESS;
 
 fdt_set_fail:
diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c
new file mode 100644
index 000000000..53f6d3fe6
--- /dev/null
+++ b/drivers/firmware/efi/libstub/random.c
@@ -0,0 +1,135 @@
+/*
+ * Copyright (C) 2016 Linaro Ltd;  <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/efi.h>
+#include <asm/efi.h>
+
+#include "efistub.h"
+
+struct efi_rng_protocol {
+	efi_status_t (*get_info)(struct efi_rng_protocol *,
+				 unsigned long *, efi_guid_t *);
+	efi_status_t (*get_rng)(struct efi_rng_protocol *,
+				efi_guid_t *, unsigned long, u8 *out);
+};
+
+efi_status_t efi_get_random_bytes(efi_system_table_t *sys_table_arg,
+				  unsigned long size, u8 *out)
+{
+	efi_guid_t rng_proto = EFI_RNG_PROTOCOL_GUID;
+	efi_status_t status;
+	struct efi_rng_protocol *rng;
+
+	status = efi_call_early(locate_protocol, &rng_proto, NULL,
+				(void **)&rng);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	return rng->get_rng(rng, NULL, size, out);
+}
+
+/*
+ * Return the number of slots covered by this entry, i.e., the number of
+ * addresses it covers that are suitably aligned and supply enough room
+ * for the allocation.
+ */
+static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
+					 unsigned long size,
+					 unsigned long align)
+{
+	u64 start, end;
+
+	if (md->type != EFI_CONVENTIONAL_MEMORY)
+		return 0;
+
+	start = round_up(md->phys_addr, align);
+	end = round_down(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - size,
+			 align);
+
+	if (start > end)
+		return 0;
+
+	return (end - start + 1) / align;
+}
+
+/*
+ * The UEFI memory descriptors have a virtual address field that is only used
+ * when installing the virtual mapping using SetVirtualAddressMap(). Since it
+ * is unused here, we can reuse it to keep track of each descriptor's slot
+ * count.
+ */
+#define MD_NUM_SLOTS(md)	((md)->virt_addr)
+
+efi_status_t efi_random_alloc(efi_system_table_t *sys_table_arg,
+			      unsigned long size,
+			      unsigned long align,
+			      unsigned long *addr,
+			      unsigned long random_seed)
+{
+	unsigned long map_size, desc_size, total_slots = 0, target_slot;
+	efi_status_t status;
+	efi_memory_desc_t *memory_map;
+	int map_offset;
+
+	status = efi_get_memory_map(sys_table_arg, &memory_map, &map_size,
+				    &desc_size, NULL, NULL);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	if (align < EFI_ALLOC_ALIGN)
+		align = EFI_ALLOC_ALIGN;
+
+	/* count the suitable slots in each memory map entry */
+	for (map_offset = 0; map_offset < map_size; map_offset += desc_size) {
+		efi_memory_desc_t *md = (void *)memory_map + map_offset;
+		unsigned long slots;
+
+		slots = get_entry_num_slots(md, size, align);
+		MD_NUM_SLOTS(md) = slots;
+		total_slots += slots;
+	}
+
+	/* find a random number between 0 and total_slots */
+	target_slot = (total_slots * (u16)random_seed) >> 16;
+
+	/*
+	 * target_slot is now a value in the range [0, total_slots), and so
+	 * it corresponds with exactly one of the suitable slots we recorded
+	 * when iterating over the memory map the first time around.
+	 *
+	 * So iterate over the memory map again, subtracting the number of
+	 * slots of each entry at each iteration, until we have found the entry
+	 * that covers our chosen slot. Use the residual value of target_slot
+	 * to calculate the randomly chosen address, and allocate it directly
+	 * using EFI_ALLOCATE_ADDRESS.
+	 */
+	for (map_offset = 0; map_offset < map_size; map_offset += desc_size) {
+		efi_memory_desc_t *md = (void *)memory_map + map_offset;
+		efi_physical_addr_t target;
+		unsigned long pages;
+
+		if (target_slot >= MD_NUM_SLOTS(md)) {
+			target_slot -= MD_NUM_SLOTS(md);
+			continue;
+		}
+
+		target = round_up(md->phys_addr, align) + target_slot * align;
+		pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+
+		status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS,
+					EFI_LOADER_DATA, pages, &target);
+		if (status == EFI_SUCCESS)
+			*addr = target;
+		break;
+	}
+
+	efi_call_early(free_pool, memory_map);
+
+	return status;
+}
diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
index 228bbf910..de6953039 100644
--- a/drivers/firmware/efi/runtime-wrappers.c
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -61,63 +61,23 @@
  */
 static DEFINE_SPINLOCK(efi_runtime_lock);
 
-/*
- * Some runtime services calls can be reentrant under NMI, even if the table
- * above says they are not. (source: UEFI Specification v2.4A)
- *
- * Table 32. Functions that may be called after Machine Check, INIT and NMI
- * +----------------------------+------------------------------------------+
- * | Function			| Called after Machine Check, INIT and NMI |
- * +----------------------------+------------------------------------------+
- * | GetTime()			| Yes, even if previously busy.		   |
- * | GetVariable()		| Yes, even if previously busy		   |
- * | GetNextVariableName()	| Yes, even if previously busy		   |
- * | QueryVariableInfo()	| Yes, even if previously busy		   |
- * | SetVariable()		| Yes, even if previously busy		   |
- * | UpdateCapsule()		| Yes, even if previously busy		   |
- * | QueryCapsuleCapabilities()	| Yes, even if previously busy		   |
- * | ResetSystem()		| Yes, even if previously busy		   |
- * +----------------------------+------------------------------------------+
- *
- * In order to prevent deadlocks under NMI, the wrappers for these functions
- * may only grab the efi_runtime_lock or rtc_lock spinlocks if !efi_in_nmi().
- * However, not all of the services listed are reachable through NMI code paths,
- * so the the special handling as suggested by the UEFI spec is only implemented
- * for QueryVariableInfo() and SetVariable(), as these can be reached in NMI
- * context through efi_pstore_write().
- */
-
-/*
- * As per commit ef68c8f87ed1 ("x86: Serialize EFI time accesses on rtc_lock"),
- * the EFI specification requires that callers of the time related runtime
- * functions serialize with other CMOS accesses in the kernel, as the EFI time
- * functions may choose to also use the legacy CMOS RTC.
- */
-__weak DEFINE_SPINLOCK(rtc_lock);
-
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(get_time, tm, tc);
 	spin_unlock(&efi_runtime_lock);
-	spin_unlock_irqrestore(&rtc_lock, flags);
 	return status;
 }
 
 static efi_status_t virt_efi_set_time(efi_time_t *tm)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(set_time, tm);
 	spin_unlock(&efi_runtime_lock);
-	spin_unlock_irqrestore(&rtc_lock, flags);
 	return status;
 }
 
@@ -125,27 +85,21 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
 					     efi_bool_t *pending,
 					     efi_time_t *tm)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
 	spin_unlock(&efi_runtime_lock);
-	spin_unlock_irqrestore(&rtc_lock, flags);
 	return status;
 }
 
 static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(set_wakeup_time, enabled, tm);
 	spin_unlock(&efi_runtime_lock);
-	spin_unlock_irqrestore(&rtc_lock, flags);
 	return status;
 }
 
@@ -155,13 +109,12 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name,
 					  unsigned long *data_size,
 					  void *data)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(get_variable, name, vendor, attr, data_size,
 			       data);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
@@ -169,12 +122,11 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
 					       efi_char16_t *name,
 					       efi_guid_t *vendor)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(get_next_variable, name_size, name, vendor);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
@@ -184,13 +136,12 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
 					  unsigned long data_size,
 					  void *data)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(set_variable, name, vendor, attr, data_size,
 			       data);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
@@ -199,15 +150,14 @@ virt_efi_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
 				  u32 attr, unsigned long data_size,
 				  void *data)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+	if (!spin_trylock(&efi_runtime_lock))
 		return EFI_NOT_READY;
 
 	status = efi_call_virt(set_variable, name, vendor, attr, data_size,
 			       data);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
@@ -217,27 +167,45 @@ static efi_status_t virt_efi_query_variable_info(u32 attr,
 						 u64 *remaining_space,
 						 u64 *max_variable_size)
 {
-	unsigned long flags;
 	efi_status_t status;
 
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(query_variable_info, attr, storage_space,
 			       remaining_space, max_variable_size);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t
+virt_efi_query_variable_info_nonblocking(u32 attr,
+					 u64 *storage_space,
+					 u64 *remaining_space,
+					 u64 *max_variable_size)
+{
+	efi_status_t status;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	if (!spin_trylock(&efi_runtime_lock))
+		return EFI_NOT_READY;
+
+	status = efi_call_virt(query_variable_info, attr, storage_space,
+			       remaining_space, max_variable_size);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
 static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(get_next_high_mono_count, count);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
@@ -246,26 +214,23 @@ static void virt_efi_reset_system(int reset_type,
 				  unsigned long data_size,
 				  efi_char16_t *data)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	__efi_call_virt(reset_system, reset_type, status, data_size, data);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 }
 
 static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
 					    unsigned long count,
 					    unsigned long sg_list)
 {
-	unsigned long flags;
 	efi_status_t status;
 
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(update_capsule, capsules, count, sg_list);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
@@ -274,16 +239,15 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
 						u64 *max_size,
 						int *reset_type)
 {
-	unsigned long flags;
 	efi_status_t status;
 
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(query_capsule_caps, capsules, count, max_size,
 			       reset_type);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
@@ -300,6 +264,7 @@ void efi_native_runtime_setup(void)
 	efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
 	efi.reset_system = virt_efi_reset_system;
 	efi.query_variable_info = virt_efi_query_variable_info;
+	efi.query_variable_info_nonblocking = virt_efi_query_variable_info_nonblocking;
 	efi.update_capsule = virt_efi_update_capsule;
 	efi.query_capsule_caps = virt_efi_query_capsule_caps;
 }
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 6f182fd91..34b741940 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -315,7 +315,18 @@ check_var_size(u32 attributes, unsigned long size)
 	if (!fops->query_variable_store)
 		return EFI_UNSUPPORTED;
 
-	return fops->query_variable_store(attributes, size);
+	return fops->query_variable_store(attributes, size, false);
+}
+
+static efi_status_t
+check_var_size_nonblocking(u32 attributes, unsigned long size)
+{
+	const struct efivar_operations *fops = __efivars->ops;
+
+	if (!fops->query_variable_store)
+		return EFI_UNSUPPORTED;
+
+	return fops->query_variable_store(attributes, size, true);
 }
 
 static int efi_status_to_err(efi_status_t status)
@@ -696,7 +707,8 @@ efivar_entry_set_nonblocking(efi_char16_t *name, efi_guid_t vendor,
 	if (!spin_trylock_irqsave(&__efivars->lock, flags))
 		return -EBUSY;
 
-	status = check_var_size(attributes, size + ucs2_strsize(name, 1024));
+	status = check_var_size_nonblocking(attributes,
+					    size + ucs2_strsize(name, 1024));
 	if (status != EFI_SUCCESS) {
 		spin_unlock_irqrestore(&__efivars->lock, flags);
 		return -ENOSPC;
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index 72791232e..81037e5fe 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -319,6 +319,9 @@ static ssize_t ibft_attr_show_nic(void *data, int type, char *buf)
 		val = cpu_to_be32(~((1 << (32-nic->subnet_mask_prefix))-1));
 		str += sprintf(str, "%pI4", &val);
 		break;
+	case ISCSI_BOOT_ETH_PREFIX_LEN:
+		str += sprintf(str, "%d\n", nic->subnet_mask_prefix);
+		break;
 	case ISCSI_BOOT_ETH_ORIGIN:
 		str += sprintf(str, "%d\n", nic->origin);
 		break;
@@ -460,6 +463,7 @@ static umode_t ibft_check_nic_for(void *data, int type)
 		if (address_not_null(nic->ip_addr))
 			rc = S_IRUGO;
 		break;
+	case ISCSI_BOOT_ETH_PREFIX_LEN:
 	case ISCSI_BOOT_ETH_SUBNET_MASK:
 		if (nic->subnet_mask_prefix)
 			rc = S_IRUGO;
diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c
index f25cd79c8..b5d05807e 100644
--- a/drivers/firmware/psci.c
+++ b/drivers/firmware/psci.c
@@ -14,6 +14,7 @@
 #define pr_fmt(fmt) "psci: " fmt
 
 #include <linux/arm-smccc.h>
+#include <linux/cpuidle.h>
 #include <linux/errno.h>
 #include <linux/linkage.h>
 #include <linux/of.h>
@@ -21,10 +22,12 @@
 #include <linux/printk.h>
 #include <linux/psci.h>
 #include <linux/reboot.h>
+#include <linux/slab.h>
 #include <linux/suspend.h>
 
 #include <uapi/linux/psci.h>
 
+#include <asm/cpuidle.h>
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
 #include <asm/smp_plat.h>
@@ -244,6 +247,123 @@ static int __init psci_features(u32 psci_func_id)
 			      psci_func_id, 0, 0);
 }
 
+#ifdef CONFIG_CPU_IDLE
+static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state);
+
+static int psci_dt_cpu_init_idle(struct device_node *cpu_node, int cpu)
+{
+	int i, ret, count = 0;
+	u32 *psci_states;
+	struct device_node *state_node;
+
+	/*
+	 * If the PSCI cpu_suspend function hook has not been initialized
+	 * idle states must not be enabled, so bail out
+	 */
+	if (!psci_ops.cpu_suspend)
+		return -EOPNOTSUPP;
+
+	/* Count idle states */
+	while ((state_node = of_parse_phandle(cpu_node, "cpu-idle-states",
+					      count))) {
+		count++;
+		of_node_put(state_node);
+	}
+
+	if (!count)
+		return -ENODEV;
+
+	psci_states = kcalloc(count, sizeof(*psci_states), GFP_KERNEL);
+	if (!psci_states)
+		return -ENOMEM;
+
+	for (i = 0; i < count; i++) {
+		u32 state;
+
+		state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
+
+		ret = of_property_read_u32(state_node,
+					   "arm,psci-suspend-param",
+					   &state);
+		if (ret) {
+			pr_warn(" * %s missing arm,psci-suspend-param property\n",
+				state_node->full_name);
+			of_node_put(state_node);
+			goto free_mem;
+		}
+
+		of_node_put(state_node);
+		pr_debug("psci-power-state %#x index %d\n", state, i);
+		if (!psci_power_state_is_valid(state)) {
+			pr_warn("Invalid PSCI power state %#x\n", state);
+			ret = -EINVAL;
+			goto free_mem;
+		}
+		psci_states[i] = state;
+	}
+	/* Idle states parsed correctly, initialize per-cpu pointer */
+	per_cpu(psci_power_state, cpu) = psci_states;
+	return 0;
+
+free_mem:
+	kfree(psci_states);
+	return ret;
+}
+
+int psci_cpu_init_idle(unsigned int cpu)
+{
+	struct device_node *cpu_node;
+	int ret;
+
+	cpu_node = of_get_cpu_node(cpu, NULL);
+	if (!cpu_node)
+		return -ENODEV;
+
+	ret = psci_dt_cpu_init_idle(cpu_node, cpu);
+
+	of_node_put(cpu_node);
+
+	return ret;
+}
+
+static int psci_suspend_finisher(unsigned long index)
+{
+	u32 *state = __this_cpu_read(psci_power_state);
+
+	return psci_ops.cpu_suspend(state[index - 1],
+				    virt_to_phys(cpu_resume));
+}
+
+int psci_cpu_suspend_enter(unsigned long index)
+{
+	int ret;
+	u32 *state = __this_cpu_read(psci_power_state);
+	/*
+	 * idle state index 0 corresponds to wfi, should never be called
+	 * from the cpu_suspend operations
+	 */
+	if (WARN_ON_ONCE(!index))
+		return -EINVAL;
+
+	if (!psci_power_state_loses_context(state[index - 1]))
+		ret = psci_ops.cpu_suspend(state[index - 1], 0);
+	else
+		ret = cpu_suspend(index, psci_suspend_finisher);
+
+	return ret;
+}
+
+/* ARM specific CPU idle operations */
+#ifdef CONFIG_ARM
+static struct cpuidle_ops psci_cpuidle_ops __initdata = {
+	.suspend = psci_cpu_suspend_enter,
+	.init = psci_dt_cpu_init_idle,
+};
+
+CPUIDLE_METHOD_OF_DECLARE(psci, "psci", &psci_cpuidle_ops);
+#endif
+#endif
+
 static int psci_system_suspend(unsigned long unused)
 {
 	return invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND),
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
new file mode 100644
index 000000000..1b95475b6
--- /dev/null
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -0,0 +1,773 @@
+/*
+ * drivers/firmware/qemu_fw_cfg.c
+ *
+ * Copyright 2015 Carnegie Mellon University
+ *
+ * Expose entries from QEMU's firmware configuration (fw_cfg) device in
+ * sysfs (read-only, under "/sys/firmware/qemu_fw_cfg/...").
+ *
+ * The fw_cfg device may be instantiated via either an ACPI node (on x86
+ * and select subsets of aarch64), a Device Tree node (on arm), or using
+ * a kernel module (or command line) parameter with the following syntax:
+ *
+ *      [fw_cfg.]ioport=<size>@<base>[:<ctrl_off>:<data_off>]
+ * or
+ *      [fw_cfg.]mmio=<size>@<base>[:<ctrl_off>:<data_off>]
+ *
+ * where:
+ *      <size>     := size of ioport or mmio range
+ *      <base>     := physical base address of ioport or mmio range
+ *      <ctrl_off> := (optional) offset of control register
+ *      <data_off> := (optional) offset of data register
+ *
+ * e.g.:
+ *      fw_cfg.ioport=2@0x510:0:1		(the default on x86)
+ * or
+ *      fw_cfg.mmio=0xA@0x9020000:8:0		(the default on arm)
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/acpi.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+
+MODULE_AUTHOR("Gabriel L. Somlo <somlo@cmu.edu>");
+MODULE_DESCRIPTION("QEMU fw_cfg sysfs support");
+MODULE_LICENSE("GPL");
+
+/* selector key values for "well-known" fw_cfg entries */
+#define FW_CFG_SIGNATURE  0x00
+#define FW_CFG_ID         0x01
+#define FW_CFG_FILE_DIR   0x19
+
+/* size in bytes of fw_cfg signature */
+#define FW_CFG_SIG_SIZE 4
+
+/* fw_cfg "file name" is up to 56 characters (including terminating nul) */
+#define FW_CFG_MAX_FILE_PATH 56
+
+/* fw_cfg file directory entry type */
+struct fw_cfg_file {
+	u32 size;
+	u16 select;
+	u16 reserved;
+	char name[FW_CFG_MAX_FILE_PATH];
+};
+
+/* fw_cfg device i/o register addresses */
+static bool fw_cfg_is_mmio;
+static phys_addr_t fw_cfg_p_base;
+static resource_size_t fw_cfg_p_size;
+static void __iomem *fw_cfg_dev_base;
+static void __iomem *fw_cfg_reg_ctrl;
+static void __iomem *fw_cfg_reg_data;
+
+/* atomic access to fw_cfg device (potentially slow i/o, so using mutex) */
+static DEFINE_MUTEX(fw_cfg_dev_lock);
+
+/* pick appropriate endianness for selector key */
+static inline u16 fw_cfg_sel_endianness(u16 key)
+{
+	return fw_cfg_is_mmio ? cpu_to_be16(key) : cpu_to_le16(key);
+}
+
+/* read chunk of given fw_cfg blob (caller responsible for sanity-check) */
+static inline void fw_cfg_read_blob(u16 key,
+				    void *buf, loff_t pos, size_t count)
+{
+	u32 glk = -1U;
+	acpi_status status;
+
+	/* If we have ACPI, ensure mutual exclusion against any potential
+	 * device access by the firmware, e.g. via AML methods:
+	 */
+	status = acpi_acquire_global_lock(ACPI_WAIT_FOREVER, &glk);
+	if (ACPI_FAILURE(status) && status != AE_NOT_CONFIGURED) {
+		/* Should never get here */
+		WARN(1, "fw_cfg_read_blob: Failed to lock ACPI!\n");
+		memset(buf, 0, count);
+		return;
+	}
+
+	mutex_lock(&fw_cfg_dev_lock);
+	iowrite16(fw_cfg_sel_endianness(key), fw_cfg_reg_ctrl);
+	while (pos-- > 0)
+		ioread8(fw_cfg_reg_data);
+	ioread8_rep(fw_cfg_reg_data, buf, count);
+	mutex_unlock(&fw_cfg_dev_lock);
+
+	acpi_release_global_lock(glk);
+}
+
+/* clean up fw_cfg device i/o */
+static void fw_cfg_io_cleanup(void)
+{
+	if (fw_cfg_is_mmio) {
+		iounmap(fw_cfg_dev_base);
+		release_mem_region(fw_cfg_p_base, fw_cfg_p_size);
+	} else {
+		ioport_unmap(fw_cfg_dev_base);
+		release_region(fw_cfg_p_base, fw_cfg_p_size);
+	}
+}
+
+/* arch-specific ctrl & data register offsets are not available in ACPI, DT */
+#if !(defined(FW_CFG_CTRL_OFF) && defined(FW_CFG_DATA_OFF))
+# if (defined(CONFIG_ARM) || defined(CONFIG_ARM64))
+#  define FW_CFG_CTRL_OFF 0x08
+#  define FW_CFG_DATA_OFF 0x00
+# elif (defined(CONFIG_PPC_PMAC) || defined(CONFIG_SPARC32)) /* ppc/mac,sun4m */
+#  define FW_CFG_CTRL_OFF 0x00
+#  define FW_CFG_DATA_OFF 0x02
+# elif (defined(CONFIG_X86) || defined(CONFIG_SPARC64)) /* x86, sun4u */
+#  define FW_CFG_CTRL_OFF 0x00
+#  define FW_CFG_DATA_OFF 0x01
+# else
+#  warning "QEMU FW_CFG may not be available on this architecture!"
+#  define FW_CFG_CTRL_OFF 0x00
+#  define FW_CFG_DATA_OFF 0x01
+# endif
+#endif
+
+/* initialize fw_cfg device i/o from platform data */
+static int fw_cfg_do_platform_probe(struct platform_device *pdev)
+{
+	char sig[FW_CFG_SIG_SIZE];
+	struct resource *range, *ctrl, *data;
+
+	/* acquire i/o range details */
+	fw_cfg_is_mmio = false;
+	range = platform_get_resource(pdev, IORESOURCE_IO, 0);
+	if (!range) {
+		fw_cfg_is_mmio = true;
+		range = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		if (!range)
+			return -EINVAL;
+	}
+	fw_cfg_p_base = range->start;
+	fw_cfg_p_size = resource_size(range);
+
+	if (fw_cfg_is_mmio) {
+		if (!request_mem_region(fw_cfg_p_base,
+					fw_cfg_p_size, "fw_cfg_mem"))
+			return -EBUSY;
+		fw_cfg_dev_base = ioremap(fw_cfg_p_base, fw_cfg_p_size);
+		if (!fw_cfg_dev_base) {
+			release_mem_region(fw_cfg_p_base, fw_cfg_p_size);
+			return -EFAULT;
+		}
+	} else {
+		if (!request_region(fw_cfg_p_base,
+				    fw_cfg_p_size, "fw_cfg_io"))
+			return -EBUSY;
+		fw_cfg_dev_base = ioport_map(fw_cfg_p_base, fw_cfg_p_size);
+		if (!fw_cfg_dev_base) {
+			release_region(fw_cfg_p_base, fw_cfg_p_size);
+			return -EFAULT;
+		}
+	}
+
+	/* were custom register offsets provided (e.g. on the command line)? */
+	ctrl = platform_get_resource_byname(pdev, IORESOURCE_REG, "ctrl");
+	data = platform_get_resource_byname(pdev, IORESOURCE_REG, "data");
+	if (ctrl && data) {
+		fw_cfg_reg_ctrl = fw_cfg_dev_base + ctrl->start;
+		fw_cfg_reg_data = fw_cfg_dev_base + data->start;
+	} else {
+		/* use architecture-specific offsets */
+		fw_cfg_reg_ctrl = fw_cfg_dev_base + FW_CFG_CTRL_OFF;
+		fw_cfg_reg_data = fw_cfg_dev_base + FW_CFG_DATA_OFF;
+	}
+
+	/* verify fw_cfg device signature */
+	fw_cfg_read_blob(FW_CFG_SIGNATURE, sig, 0, FW_CFG_SIG_SIZE);
+	if (memcmp(sig, "QEMU", FW_CFG_SIG_SIZE) != 0) {
+		fw_cfg_io_cleanup();
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+/* fw_cfg revision attribute, in /sys/firmware/qemu_fw_cfg top-level dir. */
+static u32 fw_cfg_rev;
+
+static ssize_t fw_cfg_showrev(struct kobject *k, struct attribute *a, char *buf)
+{
+	return sprintf(buf, "%u\n", fw_cfg_rev);
+}
+
+static const struct {
+	struct attribute attr;
+	ssize_t (*show)(struct kobject *k, struct attribute *a, char *buf);
+} fw_cfg_rev_attr = {
+	.attr = { .name = "rev", .mode = S_IRUSR },
+	.show = fw_cfg_showrev,
+};
+
+/* fw_cfg_sysfs_entry type */
+struct fw_cfg_sysfs_entry {
+	struct kobject kobj;
+	struct fw_cfg_file f;
+	struct list_head list;
+};
+
+/* get fw_cfg_sysfs_entry from kobject member */
+static inline struct fw_cfg_sysfs_entry *to_entry(struct kobject *kobj)
+{
+	return container_of(kobj, struct fw_cfg_sysfs_entry, kobj);
+}
+
+/* fw_cfg_sysfs_attribute type */
+struct fw_cfg_sysfs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct fw_cfg_sysfs_entry *entry, char *buf);
+};
+
+/* get fw_cfg_sysfs_attribute from attribute member */
+static inline struct fw_cfg_sysfs_attribute *to_attr(struct attribute *attr)
+{
+	return container_of(attr, struct fw_cfg_sysfs_attribute, attr);
+}
+
+/* global cache of fw_cfg_sysfs_entry objects */
+static LIST_HEAD(fw_cfg_entry_cache);
+
+/* kobjects removed lazily by kernel, mutual exclusion needed */
+static DEFINE_SPINLOCK(fw_cfg_cache_lock);
+
+static inline void fw_cfg_sysfs_cache_enlist(struct fw_cfg_sysfs_entry *entry)
+{
+	spin_lock(&fw_cfg_cache_lock);
+	list_add_tail(&entry->list, &fw_cfg_entry_cache);
+	spin_unlock(&fw_cfg_cache_lock);
+}
+
+static inline void fw_cfg_sysfs_cache_delist(struct fw_cfg_sysfs_entry *entry)
+{
+	spin_lock(&fw_cfg_cache_lock);
+	list_del(&entry->list);
+	spin_unlock(&fw_cfg_cache_lock);
+}
+
+static void fw_cfg_sysfs_cache_cleanup(void)
+{
+	struct fw_cfg_sysfs_entry *entry, *next;
+
+	list_for_each_entry_safe(entry, next, &fw_cfg_entry_cache, list) {
+		/* will end up invoking fw_cfg_sysfs_cache_delist()
+		 * via each object's release() method (i.e. destructor)
+		 */
+		kobject_put(&entry->kobj);
+	}
+}
+
+/* default_attrs: per-entry attributes and show methods */
+
+#define FW_CFG_SYSFS_ATTR(_attr) \
+struct fw_cfg_sysfs_attribute fw_cfg_sysfs_attr_##_attr = { \
+	.attr = { .name = __stringify(_attr), .mode = S_IRUSR }, \
+	.show = fw_cfg_sysfs_show_##_attr, \
+}
+
+static ssize_t fw_cfg_sysfs_show_size(struct fw_cfg_sysfs_entry *e, char *buf)
+{
+	return sprintf(buf, "%u\n", e->f.size);
+}
+
+static ssize_t fw_cfg_sysfs_show_key(struct fw_cfg_sysfs_entry *e, char *buf)
+{
+	return sprintf(buf, "%u\n", e->f.select);
+}
+
+static ssize_t fw_cfg_sysfs_show_name(struct fw_cfg_sysfs_entry *e, char *buf)
+{
+	return sprintf(buf, "%s\n", e->f.name);
+}
+
+static FW_CFG_SYSFS_ATTR(size);
+static FW_CFG_SYSFS_ATTR(key);
+static FW_CFG_SYSFS_ATTR(name);
+
+static struct attribute *fw_cfg_sysfs_entry_attrs[] = {
+	&fw_cfg_sysfs_attr_size.attr,
+	&fw_cfg_sysfs_attr_key.attr,
+	&fw_cfg_sysfs_attr_name.attr,
+	NULL,
+};
+
+/* sysfs_ops: find fw_cfg_[entry, attribute] and call appropriate show method */
+static ssize_t fw_cfg_sysfs_attr_show(struct kobject *kobj, struct attribute *a,
+				      char *buf)
+{
+	struct fw_cfg_sysfs_entry *entry = to_entry(kobj);
+	struct fw_cfg_sysfs_attribute *attr = to_attr(a);
+
+	return attr->show(entry, buf);
+}
+
+static const struct sysfs_ops fw_cfg_sysfs_attr_ops = {
+	.show = fw_cfg_sysfs_attr_show,
+};
+
+/* release: destructor, to be called via kobject_put() */
+static void fw_cfg_sysfs_release_entry(struct kobject *kobj)
+{
+	struct fw_cfg_sysfs_entry *entry = to_entry(kobj);
+
+	fw_cfg_sysfs_cache_delist(entry);
+	kfree(entry);
+}
+
+/* kobj_type: ties together all properties required to register an entry */
+static struct kobj_type fw_cfg_sysfs_entry_ktype = {
+	.default_attrs = fw_cfg_sysfs_entry_attrs,
+	.sysfs_ops = &fw_cfg_sysfs_attr_ops,
+	.release = fw_cfg_sysfs_release_entry,
+};
+
+/* raw-read method and attribute */
+static ssize_t fw_cfg_sysfs_read_raw(struct file *filp, struct kobject *kobj,
+				     struct bin_attribute *bin_attr,
+				     char *buf, loff_t pos, size_t count)
+{
+	struct fw_cfg_sysfs_entry *entry = to_entry(kobj);
+
+	if (pos > entry->f.size)
+		return -EINVAL;
+
+	if (count > entry->f.size - pos)
+		count = entry->f.size - pos;
+
+	fw_cfg_read_blob(entry->f.select, buf, pos, count);
+	return count;
+}
+
+static struct bin_attribute fw_cfg_sysfs_attr_raw = {
+	.attr = { .name = "raw", .mode = S_IRUSR },
+	.read = fw_cfg_sysfs_read_raw,
+};
+
+/*
+ * Create a kset subdirectory matching each '/' delimited dirname token
+ * in 'name', starting with sysfs kset/folder 'dir'; At the end, create
+ * a symlink directed at the given 'target'.
+ * NOTE: We do this on a best-effort basis, since 'name' is not guaranteed
+ * to be a well-behaved path name. Whenever a symlink vs. kset directory
+ * name collision occurs, the kernel will issue big scary warnings while
+ * refusing to add the offending link or directory. We follow up with our
+ * own, slightly less scary error messages explaining the situation :)
+ */
+static int fw_cfg_build_symlink(struct kset *dir,
+				struct kobject *target, const char *name)
+{
+	int ret;
+	struct kset *subdir;
+	struct kobject *ko;
+	char *name_copy, *p, *tok;
+
+	if (!dir || !target || !name || !*name)
+		return -EINVAL;
+
+	/* clone a copy of name for parsing */
+	name_copy = p = kstrdup(name, GFP_KERNEL);
+	if (!name_copy)
+		return -ENOMEM;
+
+	/* create folders for each dirname token, then symlink for basename */
+	while ((tok = strsep(&p, "/")) && *tok) {
+
+		/* last (basename) token? If so, add symlink here */
+		if (!p || !*p) {
+			ret = sysfs_create_link(&dir->kobj, target, tok);
+			break;
+		}
+
+		/* does the current dir contain an item named after tok ? */
+		ko = kset_find_obj(dir, tok);
+		if (ko) {
+			/* drop reference added by kset_find_obj */
+			kobject_put(ko);
+
+			/* ko MUST be a kset - we're about to use it as one ! */
+			if (ko->ktype != dir->kobj.ktype) {
+				ret = -EINVAL;
+				break;
+			}
+
+			/* descend into already existing subdirectory */
+			dir = to_kset(ko);
+		} else {
+			/* create new subdirectory kset */
+			subdir = kzalloc(sizeof(struct kset), GFP_KERNEL);
+			if (!subdir) {
+				ret = -ENOMEM;
+				break;
+			}
+			subdir->kobj.kset = dir;
+			subdir->kobj.ktype = dir->kobj.ktype;
+			ret = kobject_set_name(&subdir->kobj, "%s", tok);
+			if (ret) {
+				kfree(subdir);
+				break;
+			}
+			ret = kset_register(subdir);
+			if (ret) {
+				kfree(subdir);
+				break;
+			}
+
+			/* descend into newly created subdirectory */
+			dir = subdir;
+		}
+	}
+
+	/* we're done with cloned copy of name */
+	kfree(name_copy);
+	return ret;
+}
+
+/* recursively unregister fw_cfg/by_name/ kset directory tree */
+static void fw_cfg_kset_unregister_recursive(struct kset *kset)
+{
+	struct kobject *k, *next;
+
+	list_for_each_entry_safe(k, next, &kset->list, entry)
+		/* all set members are ksets too, but check just in case... */
+		if (k->ktype == kset->kobj.ktype)
+			fw_cfg_kset_unregister_recursive(to_kset(k));
+
+	/* symlinks are cleanly and automatically removed with the directory */
+	kset_unregister(kset);
+}
+
+/* kobjects & kset representing top-level, by_key, and by_name folders */
+static struct kobject *fw_cfg_top_ko;
+static struct kobject *fw_cfg_sel_ko;
+static struct kset *fw_cfg_fname_kset;
+
+/* register an individual fw_cfg file */
+static int fw_cfg_register_file(const struct fw_cfg_file *f)
+{
+	int err;
+	struct fw_cfg_sysfs_entry *entry;
+
+	/* allocate new entry */
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	/* set file entry information */
+	memcpy(&entry->f, f, sizeof(struct fw_cfg_file));
+
+	/* register entry under "/sys/firmware/qemu_fw_cfg/by_key/" */
+	err = kobject_init_and_add(&entry->kobj, &fw_cfg_sysfs_entry_ktype,
+				   fw_cfg_sel_ko, "%d", entry->f.select);
+	if (err)
+		goto err_register;
+
+	/* add raw binary content access */
+	err = sysfs_create_bin_file(&entry->kobj, &fw_cfg_sysfs_attr_raw);
+	if (err)
+		goto err_add_raw;
+
+	/* try adding "/sys/firmware/qemu_fw_cfg/by_name/" symlink */
+	fw_cfg_build_symlink(fw_cfg_fname_kset, &entry->kobj, entry->f.name);
+
+	/* success, add entry to global cache */
+	fw_cfg_sysfs_cache_enlist(entry);
+	return 0;
+
+err_add_raw:
+	kobject_del(&entry->kobj);
+err_register:
+	kfree(entry);
+	return err;
+}
+
+/* iterate over all fw_cfg directory entries, registering each one */
+static int fw_cfg_register_dir_entries(void)
+{
+	int ret = 0;
+	u32 count, i;
+	struct fw_cfg_file *dir;
+	size_t dir_size;
+
+	fw_cfg_read_blob(FW_CFG_FILE_DIR, &count, 0, sizeof(count));
+	count = be32_to_cpu(count);
+	dir_size = count * sizeof(struct fw_cfg_file);
+
+	dir = kmalloc(dir_size, GFP_KERNEL);
+	if (!dir)
+		return -ENOMEM;
+
+	fw_cfg_read_blob(FW_CFG_FILE_DIR, dir, sizeof(count), dir_size);
+
+	for (i = 0; i < count; i++) {
+		dir[i].size = be32_to_cpu(dir[i].size);
+		dir[i].select = be16_to_cpu(dir[i].select);
+		ret = fw_cfg_register_file(&dir[i]);
+		if (ret)
+			break;
+	}
+
+	kfree(dir);
+	return ret;
+}
+
+/* unregister top-level or by_key folder */
+static inline void fw_cfg_kobj_cleanup(struct kobject *kobj)
+{
+	kobject_del(kobj);
+	kobject_put(kobj);
+}
+
+static int fw_cfg_sysfs_probe(struct platform_device *pdev)
+{
+	int err;
+
+	/* NOTE: If we supported multiple fw_cfg devices, we'd first create
+	 * a subdirectory named after e.g. pdev->id, then hang per-device
+	 * by_key (and by_name) subdirectories underneath it. However, only
+	 * one fw_cfg device exist system-wide, so if one was already found
+	 * earlier, we might as well stop here.
+	 */
+	if (fw_cfg_sel_ko)
+		return -EBUSY;
+
+	/* create by_key and by_name subdirs of /sys/firmware/qemu_fw_cfg/ */
+	err = -ENOMEM;
+	fw_cfg_sel_ko = kobject_create_and_add("by_key", fw_cfg_top_ko);
+	if (!fw_cfg_sel_ko)
+		goto err_sel;
+	fw_cfg_fname_kset = kset_create_and_add("by_name", NULL, fw_cfg_top_ko);
+	if (!fw_cfg_fname_kset)
+		goto err_name;
+
+	/* initialize fw_cfg device i/o from platform data */
+	err = fw_cfg_do_platform_probe(pdev);
+	if (err)
+		goto err_probe;
+
+	/* get revision number, add matching top-level attribute */
+	fw_cfg_read_blob(FW_CFG_ID, &fw_cfg_rev, 0, sizeof(fw_cfg_rev));
+	fw_cfg_rev = le32_to_cpu(fw_cfg_rev);
+	err = sysfs_create_file(fw_cfg_top_ko, &fw_cfg_rev_attr.attr);
+	if (err)
+		goto err_rev;
+
+	/* process fw_cfg file directory entry, registering each file */
+	err = fw_cfg_register_dir_entries();
+	if (err)
+		goto err_dir;
+
+	/* success */
+	pr_debug("fw_cfg: loaded.\n");
+	return 0;
+
+err_dir:
+	fw_cfg_sysfs_cache_cleanup();
+	sysfs_remove_file(fw_cfg_top_ko, &fw_cfg_rev_attr.attr);
+err_rev:
+	fw_cfg_io_cleanup();
+err_probe:
+	fw_cfg_kset_unregister_recursive(fw_cfg_fname_kset);
+err_name:
+	fw_cfg_kobj_cleanup(fw_cfg_sel_ko);
+err_sel:
+	return err;
+}
+
+static int fw_cfg_sysfs_remove(struct platform_device *pdev)
+{
+	pr_debug("fw_cfg: unloading.\n");
+	fw_cfg_sysfs_cache_cleanup();
+	fw_cfg_kset_unregister_recursive(fw_cfg_fname_kset);
+	fw_cfg_kobj_cleanup(fw_cfg_sel_ko);
+	fw_cfg_io_cleanup();
+	return 0;
+}
+
+static const struct of_device_id fw_cfg_sysfs_mmio_match[] = {
+	{ .compatible = "qemu,fw-cfg-mmio", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, fw_cfg_sysfs_mmio_match);
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id fw_cfg_sysfs_acpi_match[] = {
+	{ "QEMU0002", },
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, fw_cfg_sysfs_acpi_match);
+#endif
+
+static struct platform_driver fw_cfg_sysfs_driver = {
+	.probe = fw_cfg_sysfs_probe,
+	.remove = fw_cfg_sysfs_remove,
+	.driver = {
+		.name = "fw_cfg",
+		.of_match_table = fw_cfg_sysfs_mmio_match,
+		.acpi_match_table = ACPI_PTR(fw_cfg_sysfs_acpi_match),
+	},
+};
+
+#ifdef CONFIG_FW_CFG_SYSFS_CMDLINE
+
+static struct platform_device *fw_cfg_cmdline_dev;
+
+/* this probably belongs in e.g. include/linux/types.h,
+ * but right now we are the only ones doing it...
+ */
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+#define __PHYS_ADDR_PREFIX "ll"
+#else
+#define __PHYS_ADDR_PREFIX ""
+#endif
+
+/* use special scanf/printf modifier for phys_addr_t, resource_size_t */
+#define PH_ADDR_SCAN_FMT "@%" __PHYS_ADDR_PREFIX "i%n" \
+			 ":%" __PHYS_ADDR_PREFIX "i" \
+			 ":%" __PHYS_ADDR_PREFIX "i%n"
+
+#define PH_ADDR_PR_1_FMT "0x%" __PHYS_ADDR_PREFIX "x@" \
+			 "0x%" __PHYS_ADDR_PREFIX "x"
+
+#define PH_ADDR_PR_3_FMT PH_ADDR_PR_1_FMT \
+			 ":%" __PHYS_ADDR_PREFIX "u" \
+			 ":%" __PHYS_ADDR_PREFIX "u"
+
+static int fw_cfg_cmdline_set(const char *arg, const struct kernel_param *kp)
+{
+	struct resource res[3] = {};
+	char *str;
+	phys_addr_t base;
+	resource_size_t size, ctrl_off, data_off;
+	int processed, consumed = 0;
+
+	/* only one fw_cfg device can exist system-wide, so if one
+	 * was processed on the command line already, we might as
+	 * well stop here.
+	 */
+	if (fw_cfg_cmdline_dev) {
+		/* avoid leaking previously registered device */
+		platform_device_unregister(fw_cfg_cmdline_dev);
+		return -EINVAL;
+	}
+
+	/* consume "<size>" portion of command line argument */
+	size = memparse(arg, &str);
+
+	/* get "@<base>[:<ctrl_off>:<data_off>]" chunks */
+	processed = sscanf(str, PH_ADDR_SCAN_FMT,
+			   &base, &consumed,
+			   &ctrl_off, &data_off, &consumed);
+
+	/* sscanf() must process precisely 1 or 3 chunks:
+	 * <base> is mandatory, optionally followed by <ctrl_off>
+	 * and <data_off>;
+	 * there must be no extra characters after the last chunk,
+	 * so str[consumed] must be '\0'.
+	 */
+	if (str[consumed] ||
+	    (processed != 1 && processed != 3))
+		return -EINVAL;
+
+	res[0].start = base;
+	res[0].end = base + size - 1;
+	res[0].flags = !strcmp(kp->name, "mmio") ? IORESOURCE_MEM :
+						   IORESOURCE_IO;
+
+	/* insert register offsets, if provided */
+	if (processed > 1) {
+		res[1].name = "ctrl";
+		res[1].start = ctrl_off;
+		res[1].flags = IORESOURCE_REG;
+		res[2].name = "data";
+		res[2].start = data_off;
+		res[2].flags = IORESOURCE_REG;
+	}
+
+	/* "processed" happens to nicely match the number of resources
+	 * we need to pass in to this platform device.
+	 */
+	fw_cfg_cmdline_dev = platform_device_register_simple("fw_cfg",
+					PLATFORM_DEVID_NONE, res, processed);
+	if (IS_ERR(fw_cfg_cmdline_dev))
+		return PTR_ERR(fw_cfg_cmdline_dev);
+
+	return 0;
+}
+
+static int fw_cfg_cmdline_get(char *buf, const struct kernel_param *kp)
+{
+	/* stay silent if device was not configured via the command
+	 * line, or if the parameter name (ioport/mmio) doesn't match
+	 * the device setting
+	 */
+	if (!fw_cfg_cmdline_dev ||
+	    (!strcmp(kp->name, "mmio") ^
+	     (fw_cfg_cmdline_dev->resource[0].flags == IORESOURCE_MEM)))
+		return 0;
+
+	switch (fw_cfg_cmdline_dev->num_resources) {
+	case 1:
+		return snprintf(buf, PAGE_SIZE, PH_ADDR_PR_1_FMT,
+				resource_size(&fw_cfg_cmdline_dev->resource[0]),
+				fw_cfg_cmdline_dev->resource[0].start);
+	case 3:
+		return snprintf(buf, PAGE_SIZE, PH_ADDR_PR_3_FMT,
+				resource_size(&fw_cfg_cmdline_dev->resource[0]),
+				fw_cfg_cmdline_dev->resource[0].start,
+				fw_cfg_cmdline_dev->resource[1].start,
+				fw_cfg_cmdline_dev->resource[2].start);
+	}
+
+	/* Should never get here */
+	WARN(1, "Unexpected number of resources: %d\n",
+		fw_cfg_cmdline_dev->num_resources);
+	return 0;
+}
+
+static const struct kernel_param_ops fw_cfg_cmdline_param_ops = {
+	.set = fw_cfg_cmdline_set,
+	.get = fw_cfg_cmdline_get,
+};
+
+device_param_cb(ioport, &fw_cfg_cmdline_param_ops, NULL, S_IRUSR);
+device_param_cb(mmio, &fw_cfg_cmdline_param_ops, NULL, S_IRUSR);
+
+#endif /* CONFIG_FW_CFG_SYSFS_CMDLINE */
+
+static int __init fw_cfg_sysfs_init(void)
+{
+	int ret;
+
+	/* create /sys/firmware/qemu_fw_cfg/ top level directory */
+	fw_cfg_top_ko = kobject_create_and_add("qemu_fw_cfg", firmware_kobj);
+	if (!fw_cfg_top_ko)
+		return -ENOMEM;
+
+	ret = platform_driver_register(&fw_cfg_sysfs_driver);
+	if (ret)
+		fw_cfg_kobj_cleanup(fw_cfg_top_ko);
+
+	return ret;
+}
+
+static void __exit fw_cfg_sysfs_exit(void)
+{
+	platform_driver_unregister(&fw_cfg_sysfs_driver);
+
+#ifdef CONFIG_FW_CFG_SYSFS_CMDLINE
+	platform_device_unregister(fw_cfg_cmdline_dev);
+#endif
+
+	/* clean up /sys/firmware/qemu_fw_cfg/ */
+	fw_cfg_kobj_cleanup(fw_cfg_top_ko);
+}
+
+module_init(fw_cfg_sysfs_init);
+module_exit(fw_cfg_sysfs_exit);