Merge tag 'driver-core-4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core

Pull driver core updates from Greg KH:
 "Just a few patches this time around for the 4.6-rc1 merge window.
  Largest is a new firmware driver, but there are some other updates to
  the driver core in here as well, the shortlog has the details.

  All have been in linux-next for a while with no reported issues"

* tag 'driver-core-4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
  Revert "driver-core: platform: probe of-devices only using list of compatibles"
  firmware: qemu config needs I/O ports
  firmware: qemu_fw_cfg.c: fix typo FW_CFG_DATA_OFF
  driver-core: platform: probe of-devices only using list of compatibles
  driver-core: platform: fix typo in documentation for multi-driver helper
  component: remove impossible condition
  drivers: dma-coherent: simplify dma_init_coherent_memory return value
  devicetree: update documentation for fw_cfg ARM bindings
  firmware: create directory hierarchy for sysfs fw_cfg entries
  firmware: introduce sysfs driver for QEMU's fw_cfg device
  kobject: export kset_find_obj() for module use
  driver core: bus: use to_subsys_private and to_device_private_bus
  driver core: bus: use list_for_each_entry*
  debugfs: Add stub function for debugfs_create_automount().
  kernfs: make kernfs_walk_ns() use kernfs_pr_cont_buf[]

Documentation/ABI/testing/sysfs-firmware-qemu_fw_cfg

+What:		/sys/firmware/qemu_fw_cfg/
+Date:		August 2015
+Contact:	Gabriel Somlo <somlo@cmu.edu>
+Description:
+		Several different architectures supported by QEMU (x86, arm,
+		sun4*, ppc/mac) are provisioned with a firmware configuration
+		(fw_cfg) device, originally intended as a way for the host to
+		provide configuration data to the guest firmware. Starting
+		with QEMU v2.4, arbitrary fw_cfg file entries may be specified
+		by the user on the command line, which makes fw_cfg additionally
+		useful as an out-of-band, asynchronous mechanism for providing
+		configuration data to the guest userspace.
+
+		The authoritative guest-side hardware interface documentation
+		to the fw_cfg device can be found in "docs/specs/fw_cfg.txt"
+		in the QEMU source tree.
+
+		=== SysFS fw_cfg Interface ===
+
+		The fw_cfg sysfs interface described in this document is only
+		intended to display discoverable blobs (i.e., those registered
+		with the file directory), as there is no way to determine the
+		presence or size of "legacy" blobs (with selector keys between
+		0x0002 and 0x0018) programmatically.
+
+		All fw_cfg information is shown under:
+
+			/sys/firmware/qemu_fw_cfg/
+
+		The only legacy blob displayed is the fw_cfg device revision:
+
+			/sys/firmware/qemu_fw_cfg/rev
+
+		--- Discoverable fw_cfg blobs by selector key ---
+
+		All discoverable blobs listed in the fw_cfg file directory are
+		displayed as entries named after their unique selector key
+		value, e.g.:
+
+			/sys/firmware/qemu_fw_cfg/by_key/32
+			/sys/firmware/qemu_fw_cfg/by_key/33
+			/sys/firmware/qemu_fw_cfg/by_key/34
+			...
+
+		Each such fw_cfg sysfs entry has the following values exported
+		as attributes:
+
+		name  	: The 56-byte nul-terminated ASCII string used as the
+			  blob's 'file name' in the fw_cfg directory.
+		size  	: The length of the blob, as given in the fw_cfg
+			  directory.
+		key	: The value of the blob's selector key as given in the
+			  fw_cfg directory. This value is the same as used in
+			  the parent directory name.
+		raw	: The raw bytes of the blob, obtained by selecting the
+			  entry via the control register, and reading a number
+			  of bytes equal to the blob size from the data
+			  register.
+
+		--- Listing fw_cfg blobs by file name ---
+
+		While the fw_cfg device does not impose any specific naming
+		convention on the blobs registered in the file directory,
+		QEMU developers have traditionally used path name semantics
+		to give each blob a descriptive name. For example:
+
+			"bootorder"
+			"genroms/kvmvapic.bin"
+			"etc/e820"
+			"etc/boot-fail-wait"
+			"etc/system-states"
+			"etc/table-loader"
+			"etc/acpi/rsdp"
+			"etc/acpi/tables"
+			"etc/smbios/smbios-tables"
+			"etc/smbios/smbios-anchor"
+			...
+
+		In addition to the listing by unique selector key described
+		above, the fw_cfg sysfs driver also attempts to build a tree
+		of directories matching the path name components of fw_cfg
+		blob names, ending in symlinks to the by_key entry for each
+		"basename", as illustrated below (assume current directory is
+		/sys/firmware):
+
+		    qemu_fw_cfg/by_name/bootorder -> ../by_key/38
+		    qemu_fw_cfg/by_name/etc/e820 -> ../../by_key/35
+		    qemu_fw_cfg/by_name/etc/acpi/rsdp -> ../../../by_key/41
+		    ...
+
+		Construction of the directory tree and symlinks is done on a
+		"best-effort" basis, as there is no guarantee that components
+		of fw_cfg blob names are always "well behaved". I.e., there is
+		the possibility that a symlink (basename) will conflict with
+		a dirname component of another fw_cfg blob, in which case the
+		creation of the offending /sys/firmware/qemu_fw_cfg/by_name
+		entry will be skipped.
+
+		The authoritative list of entries will continue to be found
+		under the /sys/firmware/qemu_fw_cfg/by_key directory.

Documentation/devicetree/bindings/arm/fw-cfg.txt

@@ -11,43 +11,9 @@ QEMU exposes the control and data register to ARM guests as memory mapped
 registers; their location is communicated to the guest's UEFI firmware in the
 DTB that QEMU places at the bottom of the guest's DRAM.
 
-The guest writes a selector value (a key) to the selector register, and then
-can read the corresponding data (produced by QEMU) via the data register. If
-the selected entry is writable, the guest can rewrite it through the data
-register.
+The authoritative guest-side hardware interface documentation to the fw_cfg
+device can be found in "docs/specs/fw_cfg.txt" in the QEMU source tree.
 
-The selector register takes keys in big endian byte order.
-
-The data register allows accesses with 8, 16, 32 and 64-bit width (only at
-offset 0 of the register). Accesses larger than a byte are interpreted as
-arrays, bundled together only for better performance. The bytes constituting
-such a word, in increasing address order, correspond to the bytes that would
-have been transferred by byte-wide accesses in chronological order.
-
-The interface allows guest firmware to download various parameters and blobs
-that affect how the firmware works and what tables it installs for the guest
-OS. For example, boot order of devices, ACPI tables, SMBIOS tables, kernel and
-initrd images for direct kernel booting, virtual machine UUID, SMP information,
-virtual NUMA topology, and so on.
-
-The authoritative registry of the valid selector values and their meanings is
-the QEMU source code; the structure of the data blobs corresponding to the
-individual key values is also defined in the QEMU source code.
-
-The presence of the registers can be verified by selecting the "signature" blob
-with key 0x0000, and reading four bytes from the data register. The returned
-signature is "QEMU".
-
-The outermost protocol (involving the write / read sequences of the control and
-data registers) is expected to be versioned, and/or described by feature bits.
-The interface revision / feature bitmap can be retrieved with key 0x0001. The
-blob to be read from the data register has size 4, and it is to be interpreted
-as a uint32_t value in little endian byte order. The current value
-(corresponding to the above outer protocol) is zero.
-
-The guest kernel is not expected to use these registers (although it is
-certainly allowed to); the device tree bindings are documented here because
-this is where device tree bindings reside in general.
 
 Required properties:
 

Documentation/driver-model/platform.txt

@@ -75,7 +75,7 @@ If one of the drivers fails to register, all drivers registered up to that
 point will be unregistered in reverse order. Note that there is a convenience
 macro that passes THIS_MODULE as owner parameter:
 
-	#define platform_register_driver(drivers, count)
+	#define platform_register_drivers(drivers, count)
 
 
 Device Enumeration

drivers/base/bus.c

@@ -149,8 +149,7 @@ EXPORT_SYMBOL_GPL(bus_remove_file);
 
 static void bus_release(struct kobject *kobj)
 {
-	struct subsys_private *priv =
-		container_of(kobj, typeof(*priv), subsys.kobj);
+	struct subsys_private *priv = to_subsys_private(kobj);
 	struct bus_type *bus = priv->bus;
 
 	kfree(priv);
@@ -1019,13 +1018,11 @@ static void device_insertion_sort_klist(struct device *a, struct list_head *list
 					int (*compare)(const struct device *a,
 							const struct device *b))
 {
-	struct list_head *pos;
 	struct klist_node *n;
 	struct device_private *dev_prv;
 	struct device *b;
 
-	list_for_each(pos, list) {
-		n = container_of(pos, struct klist_node, n_node);
+	list_for_each_entry(n, list, n_node) {
 		dev_prv = to_device_private_bus(n);
 		b = dev_prv->device;
 		if (compare(a, b) <= 0) {
@@ -1042,8 +1039,7 @@ void bus_sort_breadthfirst(struct bus_type *bus,
 					  const struct device *b))
 {
 	LIST_HEAD(sorted_devices);
-	struct list_head *pos, *tmp;
-	struct klist_node *n;
+	struct klist_node *n, *tmp;
 	struct device_private *dev_prv;
 	struct device *dev;
 	struct klist *device_klist;
@@ -1051,8 +1047,7 @@ void bus_sort_breadthfirst(struct bus_type *bus,
 	device_klist = bus_get_device_klist(bus);
 
 	spin_lock(&device_klist->k_lock);
-	list_for_each_safe(pos, tmp, &device_klist->k_list) {
-		n = container_of(pos, struct klist_node, n_node);
+	list_for_each_entry_safe(n, tmp, &device_klist->k_list, n_node) {
 		dev_prv = to_device_private_bus(n);
 		dev = dev_prv->device;
 		device_insertion_sort_klist(dev, &sorted_devices, compare);
@@ -1107,7 +1102,7 @@ struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter)
 		knode = klist_next(&iter->ki);
 		if (!knode)
 			return NULL;
-		dev = container_of(knode, struct device_private, knode_bus)->device;
+		dev = to_device_private_bus(knode)->device;
 		if (!iter->type || iter->type == dev->type)
 			return dev;
 	}

drivers/base/component.c

@@ -267,7 +267,7 @@ void component_match_add_release(struct device *master,
 	}
 
 	if (match->num == match->alloc) {
-		size_t new_size = match ? match->alloc + 16 : 15;
+		size_t new_size = match->alloc + 16;
 		int ret;
 
 		ret = component_match_realloc(master, match, new_size);

drivers/base/dma-coherent.c

@@ -17,8 +17,8 @@ struct dma_coherent_mem {
 	spinlock_t	spinlock;
 };
 
-static int dma_init_coherent_memory(phys_addr_t phys_addr, dma_addr_t device_addr,
-			     size_t size, int flags,
+static bool dma_init_coherent_memory(
+	phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags,
 	struct dma_coherent_mem **mem)
 {
 	struct dma_coherent_mem *dma_mem = NULL;
@@ -50,17 +50,13 @@ static int dma_init_coherent_memory(phys_addr_t phys_addr, dma_addr_t device_add
 	spin_lock_init(&dma_mem->spinlock);
 
 	*mem = dma_mem;
-
-	if (flags & DMA_MEMORY_MAP)
-		return DMA_MEMORY_MAP;
-
-	return DMA_MEMORY_IO;
+	return true;
 
 out:
 	kfree(dma_mem);
 	if (mem_base)
 		iounmap(mem_base);
-	return 0;
+	return false;
 }
 
 static void dma_release_coherent_memory(struct dma_coherent_mem *mem)
@@ -88,15 +84,13 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 				dma_addr_t device_addr, size_t size, int flags)
 {
 	struct dma_coherent_mem *mem;
-	int ret;
 
-	ret = dma_init_coherent_memory(phys_addr, device_addr, size, flags,
-				       &mem);
-	if (ret == 0)
+	if (!dma_init_coherent_memory(phys_addr, device_addr, size, flags,
+				      &mem))
 		return 0;
 
 	if (dma_assign_coherent_memory(dev, mem) == 0)
-		return ret;
+		return flags & DMA_MEMORY_MAP ? DMA_MEMORY_MAP : DMA_MEMORY_IO;
 
 	dma_release_coherent_memory(mem);
 	return 0;
@@ -281,9 +275,9 @@ static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
 	struct dma_coherent_mem *mem = rmem->priv;
 
 	if (!mem &&
-	    dma_init_coherent_memory(rmem->base, rmem->base, rmem->size,
+	    !dma_init_coherent_memory(rmem->base, rmem->base, rmem->size,
 				      DMA_MEMORY_MAP | DMA_MEMORY_EXCLUSIVE,
-				     &mem) != DMA_MEMORY_MAP) {
+				      &mem)) {
 		pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
 			&rmem->base, (unsigned long)rmem->size / SZ_1M);
 		return -ENODEV;

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

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

drivers/firmware/qemu_fw_cfg.c

+/*
+ * 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)
+{
+	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);
+}
+
+/* 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)
+{
+	/* 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;
+
+	return platform_driver_register(&fw_cfg_sysfs_driver);
+}
+
+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);

fs/kernfs/dir.c

@@ -691,15 +691,22 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 					  const unsigned char *path,
 					  const void *ns)
 {
-	static char path_buf[PATH_MAX];	/* protected by kernfs_mutex */
-	size_t len = strlcpy(path_buf, path, PATH_MAX);
-	char *p = path_buf;
-	char *name;
+	size_t len;
+	char *p, *name;
 
 	lockdep_assert_held(&kernfs_mutex);
 
-	if (len >= PATH_MAX)
+	/* grab kernfs_rename_lock to piggy back on kernfs_pr_cont_buf */
+	spin_lock_irq(&kernfs_rename_lock);
+
+	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
+
+	if (len >= sizeof(kernfs_pr_cont_buf)) {
+		spin_unlock_irq(&kernfs_rename_lock);
 		return NULL;
+	}
+
+	p = kernfs_pr_cont_buf;
 
 	while ((name = strsep(&p, "/")) && parent) {
 		if (*name == '\0')
@@ -707,6 +714,8 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 		parent = kernfs_find_ns(parent, name, ns);
 	}
 
+	spin_unlock_irq(&kernfs_rename_lock);
+
 	return parent;
 }
 

include/linux/debugfs.h

@@ -162,6 +162,14 @@ static inline struct dentry *debugfs_create_symlink(const char *name,
 	return ERR_PTR(-ENODEV);
 }
 
+static inline struct dentry *debugfs_create_automount(const char *name,
+					struct dentry *parent,
+					struct vfsmount *(*f)(void *),
+					void *data)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 static inline void debugfs_remove(struct dentry *dentry)
 { }
 

lib/kobject.c

@@ -861,6 +861,7 @@ struct kobject *kset_find_obj(struct kset *kset, const char *name)
 	spin_unlock(&kset->list_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(kset_find_obj);
 
 static void kset_release(struct kobject *kobj)
 {