Merge branch 'driver-core-next' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6

* 'driver-core-next' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6: (50 commits) printk: do not mangle valid userspace syslog prefixes efivars: Add Documentation efivars: Expose efivars functionality to external drivers. efivars: Parameterize operations. efivars: Split out variable registration efivars: parameterize efivars efivars: Make efivars bin_attributes dynamic efivars: move efivars globals into struct efivars drivers:misc: ti-st: fix debugging code kref: Fix typo in kref documentation UIO: add PRUSS UIO driver support Fix spelling mistakes in Documentation/zh_CN/SubmittingPatches firmware: Fix unaligned memory accesses in dmi-sysfs firmware: Add documentation for /sys/firmware/dmi firmware: Expose DMI type 15 System Event Log firmware: Break out system_event_log in dmi-sysfs firmware: Basic dmi-sysfs support firmware: Add DMI entry types to the headers Driver core: convert platform_{get,set}_drvdata to static inline functions Translate linux-2.6/Documentation/magic-number.txt into Chinese ...
2026-05-01 15:00:59 -07:00 · 2011-03-16 15:05:40 -07:00
parent 971f115a50 9d90c8d9cd
commit a5e6b135bd
44 changed files with 2891 additions and 914 deletions
@@ -0,0 +1,75 @@
+What:		/sys/firmware/efi/vars
+Date:		April 2004
+Contact:	Matt Domsch <Matt_Domsch@dell.com>
+Description:
+		This directory exposes interfaces for interactive with
+		EFI variables.  For more information on EFI variables,
+		see 'Variable Services' in the UEFI specification
+		(section 7.2 in specification version 2.3 Errata D).
+
+		In summary, EFI variables are named, and are classified
+		into separate namespaces through the use of a vendor
+		GUID.  They also have an arbitrary binary value
+		associated with them.
+
+		The efivars module enumerates these variables and
+		creates a separate directory for each one found.  Each
+		directory has a name of the form "<key>-<vendor guid>"
+		and contains the following files:
+
+		attributes:	A read-only text file enumerating the
+				EFI variable flags.  Potential values
+				include:
+
+				EFI_VARIABLE_NON_VOLATILE
+				EFI_VARIABLE_BOOTSERVICE_ACCESS
+				EFI_VARIABLE_RUNTIME_ACCESS
+				EFI_VARIABLE_HARDWARE_ERROR_RECORD
+				EFI_VARIABLE_AUTHENTICATED_WRITE_ACCESS
+
+				See the EFI documentation for an
+				explanation of each of these variables.
+
+		data:		A read-only binary file that can be read
+				to attain the value of the EFI variable
+
+		guid:		The vendor GUID of the variable.  This
+				should always match the GUID in the
+				variable's name.
+
+		raw_var:	A binary file that can be read to obtain
+				a structure that contains everything
+				there is to know about the variable.
+				For structure definition see "struct
+				efi_variable" in the kernel sources.
+
+				This file can also be written to in
+				order to update the value of a variable.
+				For this to work however, all fields of
+				the "struct efi_variable" passed must
+				match byte for byte with the structure
+				read out of the file, save for the value
+				portion.
+
+				**Note** the efi_variable structure
+				read/written with this file contains a
+				'long' type that may change widths
+				depending on your underlying
+				architecture.
+
+		size:		As ASCII representation of the size of
+				the variable's value.
+
+
+		In addition, two other magic binary files are provided
+		in the top-level directory and are used for adding and
+		removing variables:
+
+		new_var:	Takes a "struct efi_variable" and
+				instructs the EFI firmware to create a
+				new variable.
+
+		del_var:	Takes a "struct efi_variable" and
+				instructs the EFI firmware to remove any
+				variable that has a matching vendor GUID
+				and variable key name.
@@ -0,0 +1,110 @@
+What:		/sys/firmware/dmi/
+Date:		February 2011
+Contact:	Mike Waychison <mikew@google.com>
+Description:
+		Many machines' firmware (x86 and ia64) export DMI /
+		SMBIOS tables to the operating system.  Getting at this
+		information is often valuable to userland, especially in
+		cases where there are OEM extensions used.
+
+		The kernel itself does not rely on the majority of the
+		information in these tables being correct.  It equally
+		cannot ensure that the data as exported to userland is
+		without error either.
+
+		DMI is structured as a large table of entries, where
+		each entry has a common header indicating the type and
+		length of the entry, as well as 'handle' that is
+		supposed to be unique amongst all entries.
+
+		Some entries are required by the specification, but many
+		others are optional.  In general though, users should
+		never expect to find a specific entry type on their
+		system unless they know for certain what their firmware
+		is doing.  Machine to machine will vary.
+
+		Multiple entries of the same type are allowed.  In order
+		to handle these duplicate entry types, each entry is
+		assigned by the operating system an 'instance', which is
+		derived from an entry type's ordinal position.  That is
+		to say, if there are 'N' multiple entries with the same type
+		'T' in the DMI tables (adjacent or spread apart, it
+		doesn't matter), they will be represented in sysfs as
+		entries "T-0" through "T-(N-1)":
+
+		Example entry directories:
+
+			/sys/firmware/dmi/entries/17-0
+			/sys/firmware/dmi/entries/17-1
+			/sys/firmware/dmi/entries/17-2
+			/sys/firmware/dmi/entries/17-3
+			...
+
+		Instance numbers are used in lieu of the firmware
+		assigned entry handles as the kernel itself makes no
+		guarantees that handles as exported are unique, and
+		there are likely firmware images that get this wrong in
+		the wild.
+
+		Each DMI entry in sysfs has the common header values
+		exported as attributes:
+
+		handle	: The 16bit 'handle' that is assigned to this
+			  entry by the firmware.  This handle may be
+			  referred to by other entries.
+		length	: The length of the entry, as presented in the
+			  entry itself.  Note that this is _not the
+			  total count of bytes associated with the
+			  entry_.  This value represents the length of
+			  the "formatted" portion of the entry.  This
+			  "formatted" region is sometimes followed by
+			  the "unformatted" region composed of nul
+			  terminated strings, with termination signalled
+			  by a two nul characters in series.
+		raw	: The raw bytes of the entry. This includes the
+			  "formatted" portion of the entry, the
+			  "unformatted" strings portion of the entry,
+			  and the two terminating nul characters.
+		type	: The type of the entry.  This value is the same
+			  as found in the directory name.  It indicates
+			  how the rest of the entry should be
+			  interpreted.
+		instance: The instance ordinal of the entry for the
+			  given type.  This value is the same as found
+			  in the parent directory name.
+		position: The position of the entry within the entirety
+			  of the entirety.
+
+		=== Entry Specialization ===
+
+		Some entry types may have other information available in
+		sysfs.
+
+		--- Type 15 - System Event Log ---
+
+		This entry allows the firmware to export a log of
+		events the system has taken.  This information is
+		typically backed by nvram, but the implementation
+		details are abstracted by this table.  This entries data
+		is exported in the directory:
+
+		/sys/firmware/dmi/entries/15-0/system_event_log
+
+		and has the following attributes (documented in the
+		SMBIOS / DMI specification under "System Event Log (Type 15)":
+
+		area_length
+		header_start_offset
+		data_start_offset
+		access_method
+		status
+		change_token
+		access_method_address
+		header_format
+		per_log_type_descriptor_length
+		type_descriptors_supported_count
+
+		As well, the kernel exports the binary attribute:
+
+		raw_event_log	: The raw binary bits of the event log
+				  as described by the DMI entry.
@@ -0,0 +1,48 @@
+What:		/sys/devices/platform/kim/dev_name
+Date:		January 2010
+KernelVersion:	2.6.38
+Contact:	"Pavan Savoy" <pavan_savoy@ti.com>
+Description:
+		Name of the UART device at which the WL128x chip
+		is connected. example: "/dev/ttyS0".
+		The device name flows down to architecture specific board
+		initialization file from the SFI/ATAGS bootloader
+		firmware. The name exposed is read from the user-space
+		dameon and opens the device when install is requested.
+
+What:		/sys/devices/platform/kim/baud_rate
+Date:		January 2010
+KernelVersion:	2.6.38
+Contact:	"Pavan Savoy" <pavan_savoy@ti.com>
+Description:
+		The maximum reliable baud-rate the host can support.
+		Different platforms tend to have different high-speed
+		UART configurations, so the baud-rate needs to be set
+		locally and also sent across to the WL128x via a HCI-VS
+		command. The entry is read and made use by the user-space
+		daemon when the ldisc install is requested.
+
+What:		/sys/devices/platform/kim/flow_cntrl
+Date:		January 2010
+KernelVersion:	2.6.38
+Contact:	"Pavan Savoy" <pavan_savoy@ti.com>
+Description:
+		The WL128x makes use of flow control mechanism, and this
+		entry most often should be 1, the host's UART is required
+		to have the capability of flow-control, or else this
+		entry can be made use of for exceptions.
+
+What:		/sys/devices/platform/kim/install
+Date:		January 2010
+KernelVersion:	2.6.38
+Contact:	"Pavan Savoy" <pavan_savoy@ti.com>
+Description:
+		When one of the protocols Bluetooth, FM or GPS wants to make
+		use of the shared UART transport, it registers to the shared
+		transport driver, which will signal the user-space for opening,
+		configuring baud and install line discipline via this sysfs
+		entry. This entry would be polled upon by the user-space
+		daemon managing the UART, and is notified about the change
+		by the sysfs_notify. The value would be '1' when UART needs
+		to be opened/ldisc installed, and would be '0' when UART
+		is no more required and needs to be closed.
@@ -205,12 +205,20 @@ of the characters:

 The flags are:

+f
+    Include the function name in the printed message
+l
+    Include line number in the printed message
+m
+    Include module name in the printed message
 p
    Causes a printk() message to be emitted to dmesg
+t
+    Include thread ID in messages not generated from interrupt context

-Note the regexp ^[-+=][scp]+$ matches a flags specification.
+Note the regexp ^[-+=][flmpt]+$ matches a flags specification.
 Note also that there is no convenient syntax to remove all
-the flags at once, you need to use "-psc".
+the flags at once, you need to use "-flmpt".


 Debug messages during boot process
@@ -39,10 +39,12 @@ userspace. Top-level directories in sysfs represent the common
 ancestors of object hierarchies; i.e. the subsystems the objects
 belong to. 

-Sysfs internally stores the kobject that owns the directory in the
->d_fsdata pointer of the directory's dentry. This allows sysfs to do
-reference counting directly on the kobject when the file is opened and
-closed. 
+Sysfs internally stores a pointer to the kobject that implements a
+directory in the sysfs_dirent object associated with the directory. In
+the past this kobject pointer has been used by sysfs to do reference
+counting directly on the kobject whenever the file is opened or closed.
+With the current sysfs implementation the kobject reference count is
+only modified directly by the function sysfs_schedule_callback().


 Attributes
@@ -208,9 +210,9 @@ Other notes:
  is 4096. 

 - show() methods should return the number of bytes printed into the
-  buffer. This is the return value of snprintf().
+  buffer. This is the return value of scnprintf().

- show() should always use snprintf(). 
+- show() should always use scnprintf().

 - store() should return the number of bytes used from the buffer. If the
  entire buffer has been used, just return the count argument.
@@ -229,7 +231,7 @@ A very simple (and naive) implementation of a device attribute is:
 static ssize_t show_name(struct device *dev, struct device_attribute *attr,
                         char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%s\n", dev->name);
+	return scnprintf(buf, PAGE_SIZE, "%s\n", dev->name);
 }

 static ssize_t store_name(struct device *dev, struct device_attribute *attr,
@@ -156,7 +156,7 @@ static struct my_data *get_entry()
 	struct my_data *entry = NULL;
 	mutex_lock(&mutex);
 	if (!list_empty(&q)) {
-		entry = container_of(q.next, struct my_q_entry, link);
+		entry = container_of(q.next, struct my_data, link);
 		kref_get(&entry->refcount);
 	}
 	mutex_unlock(&mutex);
@@ -126,36 +126,51 @@ config options.
 --------------------------------
 4 sysfs files for memory hotplug
 --------------------------------
-All sections have their device information under /sys/devices/system/memory as
+All sections have their device information in sysfs.  Each section is part of
+a memory block under /sys/devices/system/memory as

 /sys/devices/system/memory/memoryXXX
-(XXX is section id.)
+(XXX is the section id.)

-Now, XXX is defined as start_address_of_section / section_size.
+Now, XXX is defined as (start_address_of_section / section_size) of the first
+section contained in the memory block.  The files 'phys_index' and
+'end_phys_index' under each directory report the beginning and end section id's
+for the memory block covered by the sysfs directory.  It is expected that all
+memory sections in this range are present and no memory holes exist in the
+range. Currently there is no way to determine if there is a memory hole, but
+the existence of one should not affect the hotplug capabilities of the memory
+block.

 For example, assume 1GiB section size. A device for a memory starting at
 0x100000000 is /sys/device/system/memory/memory4
 (0x100000000 / 1Gib = 4)
 This device covers address range [0x100000000 ... 0x140000000)

-Under each section, you can see 4 files.
+Under each section, you can see 4 or 5 files, the end_phys_index file being
+a recent addition and not present on older kernels.

-/sys/devices/system/memory/memoryXXX/phys_index
+/sys/devices/system/memory/memoryXXX/start_phys_index
+/sys/devices/system/memory/memoryXXX/end_phys_index
 /sys/devices/system/memory/memoryXXX/phys_device
 /sys/devices/system/memory/memoryXXX/state
 /sys/devices/system/memory/memoryXXX/removable

-'phys_index' : read-only and contains section id, same as XXX.
-'state'      : read-write
-               at read:  contains online/offline state of memory.
-               at write: user can specify "online", "offline" command
-'phys_device': read-only: designed to show the name of physical memory device.
-               This is not well implemented now.
-'removable'  : read-only: contains an integer value indicating
-               whether the memory section is removable or not
-               removable.  A value of 1 indicates that the memory
-               section is removable and a value of 0 indicates that
-               it is not removable.
+'phys_index'      : read-only and contains section id of the first section
+		    in the memory block, same as XXX.
+'end_phys_index'  : read-only and contains section id of the last section
+		    in the memory block.
+'state'           : read-write
+                    at read:  contains online/offline state of memory.
+                    at write: user can specify "online", "offline" command
+                    which will be performed on al sections in the block.
+'phys_device'     : read-only: designed to show the name of physical memory
+                    device.  This is not well implemented now.
+'removable'       : read-only: contains an integer value indicating
+                    whether the memory block is removable or not
+                    removable.  A value of 1 indicates that the memory
+                    block is removable and a value of 0 indicates that
+                    it is not removable. A memory block is removable only if
+                    every section in the block is removable.

 NOTE:
  These directories/files appear after physical memory hotplug phase.
@@ -0,0 +1,50 @@
+Chinese translated version of Documentation/SecurityBugs
+
+If you have any comment or update to the content, please contact the
+original document maintainer directly.  However, if you have a problem
+communicating in English you can also ask the Chinese maintainer for
+help.  Contact the Chinese maintainer if this translation is outdated
+or if there is a problem with the translation.
+
+Chinese maintainer: Harry Wei <harryxiyou@gmail.com>
+---------------------------------------------------------------------
+Documentation/SecurityBugs 的中文翻译
+
+如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
+交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
+译存在问题，请联系中文版维护者。
+
+中文版维护者： 贾威威 Harry Wei <harryxiyou@gmail.com>
+中文版翻译者： 贾威威 Harry Wei <harryxiyou@gmail.com>
+中文版校译者： 贾威威 Harry Wei <harryxiyou@gmail.com>
+
+
+以下为正文
+---------------------------------------------------------------------
+Linux内核开发者认为安全非常重要。因此，我们想要知道当一个有关于
+安全的漏洞被发现的时候，并且它可能会被尽快的修复或者公开。请把这个安全
+漏洞报告给Linux内核安全团队。
+
+1) 联系
+
+linux内核安全团队可以通过email<security@kernel.org>来联系。这是
+一组独立的安全工作人员，可以帮助改善漏洞报告并且公布和取消一个修复。安
+全团队有可能会从部分的维护者那里引进额外的帮助来了解并且修复安全漏洞。
+当遇到任何漏洞，所能提供的信息越多就越能诊断和修复。如果你不清楚什么
+是有帮助的信息，那就请重温一下REPORTING-BUGS文件中的概述过程。任
+何攻击性的代码都是非常有用的，未经报告者的同意不会被取消，除非它已经
+被公布于众。
+
+2) 公开
+
+Linux内核安全团队的宗旨就是和漏洞提交者一起处理漏洞的解决方案直
+到公开。我们喜欢尽快地完全公开漏洞。当一个漏洞或者修复还没有被完全地理
+解，解决方案没有通过测试或者供应商协调，可以合理地延迟公开。然而，我们
+期望这些延迟尽可能的短些，是可数的几天，而不是几个星期或者几个月。公开
+日期是通过安全团队和漏洞提供者以及供应商洽谈后的结果。公开时间表是从很
+短（特殊的，它已经被公众所知道）到几个星期。作为一个基本的默认政策，我
+们所期望通知公众的日期是7天的安排。
+
+3) 保密协议
+
+Linux内核安全团队不是一个正式的团体，因此不能加入任何的保密协议。
@@ -0,0 +1,109 @@
+Chinese translated version of Documentation/SubmitChecklist
+
+If you have any comment or update to the content, please contact the
+original document maintainer directly.  However, if you have a problem
+communicating in English you can also ask the Chinese maintainer for
+help.  Contact the Chinese maintainer if this translation is outdated
+or if there is a problem with the translation.
+
+Chinese maintainer: Harry Wei <harryxiyou@gmail.com>
+---------------------------------------------------------------------
+Documentation/SubmitChecklist 的中文翻译
+
+如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
+交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
+译存在问题，请联系中文版维护者。
+
+中文版维护者： 贾威威 Harry Wei <harryxiyou@gmail.com>
+中文版翻译者： 贾威威 Harry Wei <harryxiyou@gmail.com>
+中文版校译者： 贾威威 Harry Wei <harryxiyou@gmail.com>
+
+
+以下为正文
+---------------------------------------------------------------------
+Linux内核提交清单
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+这里有一些内核开发者应该做的基本事情，如果他们想看到自己的内核补丁提交
+被接受的更快。
+
+这些都是超出Documentation/SubmittingPatches文档里所提供的以及其他
+关于提交Linux内核补丁的说明。
+
+1：如果你使用了一个功能那么就#include定义/声明那个功能的那个文件。
+   不要依靠其他间接引入定义/声明那个功能的头文件。
+
+2：构建简洁适用或者更改CONFIG选项 =y，=m，或者=n。
+   不要有编译警告/错误， 不要有链接警告/错误。
+
+2b：通过 allnoconfig, allmodconfig
+
+2c：当使用 0=builddir 成功地构建
+
+3：通过使用本地交叉编译工具或者其他一些构建产所，在多CPU框架上构建。
+
+4：ppc64 是一个很好的检查交叉编译的框架，因为它往往把‘unsigned long’
+   当64位值来使用。
+
+5：按照Documentation/CodingStyle文件里的详细描述，检查你补丁的整体风格。
+   使用补丁风格检查琐碎的违规(scripts/checkpatch.pl)，审核员优先提交。
+   你应该调整遗留在你补丁中的所有违规。
+
+6：任何更新或者改动CONFIG选项都不能打乱配置菜单。
+
+7：所有的Kconfig选项更新都要有说明文字。
+
+8：已经认真地总结了相关的Kconfig组合。这是很难通过测试做好的--脑力在这里下降。
+
+9：检查具有简洁性。
+
+10：使用'make checkstack'和'make namespacecheck'检查，然后修改所找到的问题。
+    注意：堆栈检查不会明确地出现问题，但是任何的一个函数在堆栈上使用多于512字节
+    都要准备修改。
+
+11：包含kernel-doc到全局内核APIs文件。（不要求静态的函数，但是包含也无所谓。）
+    使用'make htmldocs'或者'make mandocs'来检查kernel-doc，然后修改任何
+    发现的问题。
+
+12：已经通过CONFIG_PREEMPT, CONFIG_DEBUG_PREEMPT,
+    CONFIG_DEBUG_SLAB, CONFIG_DEBUG_PAGEALLOC, CONFIG_DEBUG_MUTEXES,
+    CONFIG_DEBUG_SPINLOCK, CONFIG_DEBUG_SPINLOCK_SLEEP测试，并且同时都
+    使能。
+
+13：已经都构建并且使用或者不使用 CONFIG_SMP 和 CONFIG_PREEMPT测试执行时间。
+
+14：如果补丁影响IO/Disk，等等：已经通过使用或者不使用 CONFIG_LBDAF 测试。
+
+15：所有的codepaths已经行使所有lockdep启用功能。
+
+16：所有的/proc记录更新都要作成文件放在Documentation/目录下。
+
+17：所有的内核启动参数更新都被记录到Documentation/kernel-parameters.txt文件中。
+
+18：所有的模块参数更新都用MODULE_PARM_DESC()记录。
+
+19：所有的用户空间接口更新都被记录到Documentation/ABI/。查看Documentation/ABI/README
+    可以获得更多的信息。改变用户空间接口的补丁应该被邮件抄送给linux-api@vger.kernel.org。
+
+20：检查它是不是都通过`make headers_check'。
+
+21：已经通过至少引入slab和page-allocation失败检查。查看Documentation/fault-injection/。
+
+22：新加入的源码已经通过`gcc -W'（使用"make EXTRA_CFLAGS=-W"）编译。这样将产生很多烦恼，
+    但是对于寻找漏洞很有益处，例如:"warning: comparison between signed and unsigned"。
+
+23：当它被合并到-mm补丁集后再测试，用来确定它是否还和补丁队列中的其他补丁一起工作以及在VM，VFS
+    和其他子系统中各个变化。
+
+24：所有的内存屏障{e.g., barrier(), rmb(), wmb()}需要在源代码中的一个注释来解释他们都是干什么的
+    以及原因。
+
+25：如果有任何输入输出控制的补丁被添加，也要更新Documentation/ioctl/ioctl-number.txt。
+
+26：如果你的更改代码依靠或者使用任何的内核APIs或者与下面的kconfig符号有关系的功能，你就要
+    使用相关的kconfig符号关闭， and/or =m（如果选项提供）[在同一时间不是所用的都启用，仅仅各个或者自由
+    组合他们]：
+
+    CONFIG_SMP, CONFIG_SYSFS, CONFIG_PROC_FS, CONFIG_INPUT, CONFIG_PCI,
+    CONFIG_BLOCK, CONFIG_PM, CONFIG_HOTPLUG, CONFIG_MAGIC_SYSRQ,
+    CONFIG_NET, CONFIG_INET=n (后一个使用 CONFIG_NET=y)
@@ -100,7 +100,7 @@ http://userweb.kernel.org/~akpm/stuff/patch-scripts.tar.gz

 将改动拆分，逻辑类似的放到同一个补丁文件里。

-例如，如果你的改动里同时有bug修正和性能优化，那么把这些改动才分到两个或
+例如，如果你的改动里同时有bug修正和性能优化，那么把这些改动拆分到两个或
 者更多的补丁文件中。如果你的改动包含对API的修改，并且修改了驱动程序来适
 应这些新的API，那么把这些修改分成两个补丁。

@@ -230,7 +230,7 @@ pref("mailnews.display.disable_format_flowed_support", true);
 些原因，修正错误，重新提交更新后的改动，是你自己的工作。

 Linus不给出任何评论就“丢弃”你的补丁是常见的事情。在系统中这样的事情很
-平常。如果他没有接受你的补丁，也许是由于以下原本：
+平常。如果他没有接受你的补丁，也许是由于以下原因：
 * 你的补丁不能在最新版本的内核上干净的打上。
 * 你的补丁在 linux-kernel 邮件列表中没有得到充分的讨论。
 * 风格问题（参照第2小节）
@@ -0,0 +1,167 @@
+Chinese translated version of Documentation/magic-number.txt
+
+If you have any comment or update to the content, please post to LKML directly.
+However, if you have problem communicating in English you can also ask the
+Chinese maintainer for help.  Contact the Chinese maintainer, if this
+translation is outdated or there is problem with translation.
+
+Chinese maintainer: Jia Wei Wei <harryxiyou@gmail.com>
+---------------------------------------------------------------------
+Documentation/magic-number.txt的中文翻译
+
+如果想评论或更新本文的内容，请直接发信到LKML。如果你使用英文交流有困难的话，也可
+以向中文版维护者求助。如果本翻译更新不及时或者翻译存在问题，请联系中文版维护者。
+
+中文版维护者： 贾威威 Jia Wei Wei <harryxiyou@gmail.com>
+中文版翻译者： 贾威威 Jia Wei Wei <harryxiyou@gmail.com>
+中文版校译者： 贾威威 Jia Wei Wei <harryxiyou@gmail.com>
+
+以下为正文
+---------------------------------------------------------------------
+这个文件是有关当前使用的魔术值注册表。当你给一个结构添加了一个魔术值，你也应该把这个魔术值添加到这个文件，因为我们最好把用于各种结构的魔术值统一起来。
+
+使用魔术值来保护内核数据结构是一个非常好的主意。这就允许你在运行期检查(a)一个结构是否已经被攻击，或者(b)你已经给一个例行程序通过了一个错误的结构。后一种情况特别地有用---特别是当你通过一个空指针指向结构体的时候。tty源码，例如，经常通过特定驱动使用这种方法并且反复地排列特定方面的结构。
+
+使用魔术值的方法是在结构的开始处声明的，如下：
+
+struct tty_ldisc {
+	int	magic;
+	...
+};
+
+当你以后给内核添加增强功能的时候，请遵守这条规则！这样就会节省数不清的调试时间，特别是一些古怪的情况，例如，数组超出范围并且重新写了超出部分。遵守这个规则，‪这些情况可以被快速地，安全地避免。
+
+		Theodore Ts'o
+		  31 Mar 94
+
+给当前的Linux 2.1.55添加魔术表。
+
+		Michael Chastain
+		<mailto:mec@shout.net>
+		22 Sep 1997
+
+现在应该最新的Linux 2.1.112.因为在特性冻结期间，不能在2.2.x前改变任何东西。这些条目被数域所排序。
+
+		Krzysztof G.Baranowski
+	        <mailto: kgb@knm.org.pl>
+		29 Jul 1998
+
+更新魔术表到Linux 2.5.45。刚好越过特性冻结，但是有可能还会有一些新的魔术值在2.6.x之前融入到内核中。
+
+		Petr Baudis
+		<pasky@ucw.cz>
+		03 Nov 2002
+
+更新魔术表到Linux 2.5.74。
+
+		Fabian Frederick
+                <ffrederick@users.sourceforge.net>
+		09 Jul 2003
+
+魔术名                 地址         结构               所在文件
+===========================================================================
+PG_MAGIC              'P'         pg_{read,write}_hdr include/linux/pg.h
+CMAGIC                0x0111      user              include/linux/a.out.h
+MKISS_DRIVER_MAGIC    0x04bf      mkiss_channel     drivers/net/mkiss.h
+RISCOM8_MAGIC         0x0907      riscom_port       drivers/char/riscom8.h
+SPECIALIX_MAGIC       0x0907      specialix_port    drivers/char/specialix_io8.h
+HDLC_MAGIC            0x239e      n_hdlc            drivers/char/n_hdlc.c
+APM_BIOS_MAGIC        0x4101      apm_user          arch/i386/kernel/apm.c
+CYCLADES_MAGIC        0x4359      cyclades_port     include/linux/cyclades.h
+DB_MAGIC              0x4442      fc_info           drivers/net/iph5526_novram.c
+DL_MAGIC              0x444d      fc_info           drivers/net/iph5526_novram.c
+FASYNC_MAGIC          0x4601      fasync_struct     include/linux/fs.h
+FF_MAGIC              0x4646      fc_info           drivers/net/iph5526_novram.c
+ISICOM_MAGIC          0x4d54      isi_port          include/linux/isicom.h
+PTY_MAGIC             0x5001                        drivers/char/pty.c
+PPP_MAGIC             0x5002      ppp               include/linux/if_pppvar.h
+SERIAL_MAGIC          0x5301      async_struct      include/linux/serial.h
+SSTATE_MAGIC          0x5302      serial_state      include/linux/serial.h
+SLIP_MAGIC            0x5302      slip              drivers/net/slip.h
+STRIP_MAGIC           0x5303      strip             drivers/net/strip.c
+X25_ASY_MAGIC         0x5303      x25_asy           drivers/net/x25_asy.h
+SIXPACK_MAGIC         0x5304      sixpack           drivers/net/hamradio/6pack.h
+AX25_MAGIC            0x5316      ax_disp           drivers/net/mkiss.h
+ESP_MAGIC             0x53ee      esp_struct        drivers/char/esp.h
+TTY_MAGIC             0x5401      tty_struct        include/linux/tty.h
+MGSL_MAGIC            0x5401      mgsl_info         drivers/char/synclink.c
+TTY_DRIVER_MAGIC      0x5402      tty_driver        include/linux/tty_driver.h
+MGSLPC_MAGIC          0x5402      mgslpc_info       drivers/char/pcmcia/synclink_cs.c
+TTY_LDISC_MAGIC       0x5403      tty_ldisc         include/linux/tty_ldisc.h
+USB_SERIAL_MAGIC      0x6702      usb_serial        drivers/usb/serial/usb-serial.h
+FULL_DUPLEX_MAGIC     0x6969                        drivers/net/tulip/de2104x.c
+USB_BLUETOOTH_MAGIC   0x6d02      usb_bluetooth     drivers/usb/class/bluetty.c
+RFCOMM_TTY_MAGIC      0x6d02                        net/bluetooth/rfcomm/tty.c
+USB_SERIAL_PORT_MAGIC 0x7301      usb_serial_port   drivers/usb/serial/usb-serial.h
+CG_MAGIC              0x00090255  ufs_cylinder_group include/linux/ufs_fs.h
+A2232_MAGIC           0x000a2232  gs_port           drivers/char/ser_a2232.h
+RPORT_MAGIC           0x00525001  r_port            drivers/char/rocket_int.h
+LSEMAGIC              0x05091998  lse               drivers/fc4/fc.c
+GDTIOCTL_MAGIC        0x06030f07  gdth_iowr_str     drivers/scsi/gdth_ioctl.h
+RIEBL_MAGIC           0x09051990                    drivers/net/atarilance.c
+RIO_MAGIC             0x12345678  gs_port           drivers/char/rio/rio_linux.c
+SX_MAGIC              0x12345678  gs_port           drivers/char/sx.h
+NBD_REQUEST_MAGIC     0x12560953  nbd_request       include/linux/nbd.h
+RED_MAGIC2            0x170fc2a5  (any)             mm/slab.c
+BAYCOM_MAGIC          0x19730510  baycom_state      drivers/net/baycom_epp.c
+ISDN_X25IFACE_MAGIC   0x1e75a2b9  isdn_x25iface_proto_data
+                                                    drivers/isdn/isdn_x25iface.h
+ECP_MAGIC             0x21504345  cdkecpsig         include/linux/cdk.h
+LSOMAGIC              0x27091997  lso               drivers/fc4/fc.c
+LSMAGIC               0x2a3b4d2a  ls                drivers/fc4/fc.c
+WANPIPE_MAGIC         0x414C4453  sdla_{dump,exec}  include/linux/wanpipe.h
+CS_CARD_MAGIC         0x43525553  cs_card           sound/oss/cs46xx.c
+LABELCL_MAGIC         0x4857434c  labelcl_info_s    include/asm/ia64/sn/labelcl.h
+ISDN_ASYNC_MAGIC      0x49344C01  modem_info        include/linux/isdn.h
+CTC_ASYNC_MAGIC       0x49344C01  ctc_tty_info      drivers/s390/net/ctctty.c
+ISDN_NET_MAGIC        0x49344C02  isdn_net_local_s  drivers/isdn/i4l/isdn_net_lib.h
+SAVEKMSG_MAGIC2       0x4B4D5347  savekmsg          arch/*/amiga/config.c
+STLI_BOARDMAGIC       0x4bc6c825  stlibrd           include/linux/istallion.h
+CS_STATE_MAGIC        0x4c4f4749  cs_state          sound/oss/cs46xx.c
+SLAB_C_MAGIC          0x4f17a36d  kmem_cache        mm/slab.c
+COW_MAGIC             0x4f4f4f4d  cow_header_v1     arch/um/drivers/ubd_user.c
+I810_CARD_MAGIC       0x5072696E  i810_card         sound/oss/i810_audio.c
+TRIDENT_CARD_MAGIC    0x5072696E  trident_card      sound/oss/trident.c
+ROUTER_MAGIC          0x524d4157  wan_device        include/linux/wanrouter.h
+SCC_MAGIC             0x52696368  gs_port           drivers/char/scc.h
+SAVEKMSG_MAGIC1       0x53415645  savekmsg          arch/*/amiga/config.c
+GDA_MAGIC             0x58464552  gda               arch/mips/include/asm/sn/gda.h
+RED_MAGIC1            0x5a2cf071  (any)             mm/slab.c
+STL_PORTMAGIC         0x5a7182c9  stlport           include/linux/stallion.h
+EEPROM_MAGIC_VALUE    0x5ab478d2  lanai_dev         drivers/atm/lanai.c
+HDLCDRV_MAGIC         0x5ac6e778  hdlcdrv_state     include/linux/hdlcdrv.h
+EPCA_MAGIC            0x5c6df104  channel           include/linux/epca.h
+PCXX_MAGIC            0x5c6df104  channel           drivers/char/pcxx.h
+KV_MAGIC              0x5f4b565f  kernel_vars_s     arch/mips/include/asm/sn/klkernvars.h
+I810_STATE_MAGIC      0x63657373  i810_state        sound/oss/i810_audio.c
+TRIDENT_STATE_MAGIC   0x63657373  trient_state      sound/oss/trident.c
+M3_CARD_MAGIC         0x646e6f50  m3_card           sound/oss/maestro3.c
+FW_HEADER_MAGIC       0x65726F66  fw_header         drivers/atm/fore200e.h
+SLOT_MAGIC            0x67267321  slot              drivers/hotplug/cpqphp.h
+SLOT_MAGIC            0x67267322  slot              drivers/hotplug/acpiphp.h
+LO_MAGIC              0x68797548  nbd_device        include/linux/nbd.h
+OPROFILE_MAGIC        0x6f70726f  super_block       drivers/oprofile/oprofilefs.h
+M3_STATE_MAGIC        0x734d724d  m3_state          sound/oss/maestro3.c
+STL_PANELMAGIC        0x7ef621a1  stlpanel          include/linux/stallion.h
+VMALLOC_MAGIC         0x87654320  snd_alloc_track   sound/core/memory.c
+KMALLOC_MAGIC         0x87654321  snd_alloc_track   sound/core/memory.c
+PWC_MAGIC             0x89DC10AB  pwc_device        drivers/usb/media/pwc.h
+NBD_REPLY_MAGIC       0x96744668  nbd_reply         include/linux/nbd.h
+STL_BOARDMAGIC        0xa2267f52  stlbrd            include/linux/stallion.h
+ENI155_MAGIC          0xa54b872d  midway_eprom	    drivers/atm/eni.h
+SCI_MAGIC             0xbabeface  gs_port           drivers/char/sh-sci.h
+CODA_MAGIC            0xC0DAC0DA  coda_file_info    include/linux/coda_fs_i.h
+DPMEM_MAGIC           0xc0ffee11  gdt_pci_sram      drivers/scsi/gdth.h
+STLI_PORTMAGIC        0xe671c7a1  stliport          include/linux/istallion.h
+YAM_MAGIC             0xF10A7654  yam_port          drivers/net/hamradio/yam.c
+CCB_MAGIC             0xf2691ad2  ccb               drivers/scsi/ncr53c8xx.c
+QUEUE_MAGIC_FREE      0xf7e1c9a3  queue_entry       drivers/scsi/arm/queue.c
+QUEUE_MAGIC_USED      0xf7e1cc33  queue_entry       drivers/scsi/arm/queue.c
+HTB_CMAGIC            0xFEFAFEF1  htb_class         net/sched/sch_htb.c
+NMI_MAGIC             0x48414d4d455201 nmi_s        arch/mips/include/asm/sn/nmi.h
+
+请注意，在声音记忆管理中仍然有每一些被定义的驱动魔术值。查看include/sound/sndmagic.h来获取他们完整的列表信息。很多OSS声音驱动拥有自己从声卡PCI ID构建的魔术值-他们也没有被列在这里。
+
+IrDA子系统也使用了大量的自己的魔术值，查看include/net/irda/irda.h来获取他们完整的信息。
+
+HFS是另外一个比较大的使用魔术值的文件系统-你可以在fs/hfs/hfs.h中找到他们。
@@ -17,6 +17,54 @@
 #include <asm/pSeries_reconfig.h>
 #include <asm/sparsemem.h>

+static unsigned long get_memblock_size(void)
+{
+	struct device_node *np;
+	unsigned int memblock_size = 0;
+
+	np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
+	if (np) {
+		const unsigned long *size;
+
+		size = of_get_property(np, "ibm,lmb-size", NULL);
+		memblock_size = size ? *size : 0;
+
+		of_node_put(np);
+	} else {
+		unsigned int memzero_size = 0;
+		const unsigned int *regs;
+
+		np = of_find_node_by_path("/memory@0");
+		if (np) {
+			regs = of_get_property(np, "reg", NULL);
+			memzero_size = regs ? regs[3] : 0;
+			of_node_put(np);
+		}
+
+		if (memzero_size) {
+			/* We now know the size of memory@0, use this to find
+			 * the first memoryblock and get its size.
+			 */
+			char buf[64];
+
+			sprintf(buf, "/memory@%x", memzero_size);
+			np = of_find_node_by_path(buf);
+			if (np) {
+				regs = of_get_property(np, "reg", NULL);
+				memblock_size = regs ? regs[3] : 0;
+				of_node_put(np);
+			}
+		}
+	}
+
+	return memblock_size;
+}
+
+unsigned long memory_block_size_bytes(void)
+{
+	return get_memblock_size();
+}
+
 static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size)
 {
 	unsigned long start, start_pfn;
@@ -127,30 +175,22 @@ static int pseries_add_memory(struct device_node *np)

 static int pseries_drconf_memory(unsigned long *base, unsigned int action)
 {
-	struct device_node *np;
-	const unsigned long *lmb_size;
+	unsigned long memblock_size;
 	int rc;

-	np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
-	if (!np)
+	memblock_size = get_memblock_size();
+	if (!memblock_size)
 		return -EINVAL;

-	lmb_size = of_get_property(np, "ibm,lmb-size", NULL);
-	if (!lmb_size) {
-		of_node_put(np);
-		return -EINVAL;
-	}
-
 	if (action == PSERIES_DRCONF_MEM_ADD) {
-		rc = memblock_add(*base, *lmb_size);
+		rc = memblock_add(*base, memblock_size);
 		rc = (rc < 0) ? -EINVAL : 0;
 	} else if (action == PSERIES_DRCONF_MEM_REMOVE) {
-		rc = pseries_remove_memblock(*base, *lmb_size);
+		rc = pseries_remove_memblock(*base, memblock_size);
 	} else {
 		rc = -EINVAL;
 	}

-	of_node_put(np);
 	return rc;
 }

@@ -51,6 +51,7 @@
 #include <asm/numa.h>
 #include <asm/cacheflush.h>
 #include <asm/init.h>
+#include <asm/uv/uv.h>

 static int __init parse_direct_gbpages_off(char *arg)
 {
@@ -898,6 +899,19 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 	return NULL;
 }

+#ifdef CONFIG_X86_UV
+#define MIN_MEMORY_BLOCK_SIZE   (1 << SECTION_SIZE_BITS)
+
+unsigned long memory_block_size_bytes(void)
+{
+	if (is_uv_system()) {
+		printk(KERN_INFO "UV: memory block size 2GB\n");
+		return 2UL * 1024 * 1024 * 1024;
+	}
+	return MIN_MEMORY_BLOCK_SIZE;
+}
+#endif
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
 * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
@@ -1320,7 +1320,10 @@ struct root_device
 	struct module *owner;
 };

-#define to_root_device(dev) container_of(dev, struct root_device, dev)
+inline struct root_device *to_root_device(struct device *d)
+{
+	return container_of(d, struct root_device, dev);
+}

 static void root_device_release(struct device *dev)
 {
@@ -1551,7 +1554,34 @@ EXPORT_SYMBOL_GPL(device_destroy);
 * on the same device to ensure that new_name is valid and
 * won't conflict with other devices.
 *
- * "Never use this function, bad things will happen" - gregkh
+ * Note: Don't call this function.  Currently, the networking layer calls this
+ * function, but that will change.  The following text from Kay Sievers offers
+ * some insight:
+ *
+ * Renaming devices is racy at many levels, symlinks and other stuff are not
+ * replaced atomically, and you get a "move" uevent, but it's not easy to
+ * connect the event to the old and new device. Device nodes are not renamed at
+ * all, there isn't even support for that in the kernel now.
+ *
+ * In the meantime, during renaming, your target name might be taken by another
+ * driver, creating conflicts. Or the old name is taken directly after you
+ * renamed it -- then you get events for the same DEVPATH, before you even see
+ * the "move" event. It's just a mess, and nothing new should ever rely on
+ * kernel device renaming. Besides that, it's not even implemented now for
+ * other things than (driver-core wise very simple) network devices.
+ *
+ * We are currently about to change network renaming in udev to completely
+ * disallow renaming of devices in the same namespace as the kernel uses,
+ * because we can't solve the problems properly, that arise with swapping names
+ * of multiple interfaces without races. Means, renaming of eth[0-9]* will only
+ * be allowed to some other name than eth[0-9]*, for the aforementioned
+ * reasons.
+ *
+ * Make up a "real" name in the driver before you register anything, or add
+ * some other attributes for userspace to find the device, or use udev to add
+ * symlinks -- but never rename kernel devices later, it's a complete mess. We
+ * don't even want to get into that and try to implement the missing pieces in
+ * the core. We really have other pieces to fix in the driver core mess. :)
 */
 int device_rename(struct device *dev, const char *new_name)
 {
@@ -593,8 +593,7 @@ int
 request_firmware(const struct firmware **firmware_p, const char *name,
                 struct device *device)
 {
-        int uevent = 1;
-        return _request_firmware(firmware_p, name, device, uevent, false);
+        return _request_firmware(firmware_p, name, device, true, false);
 }

 /**
@@ -618,7 +617,7 @@ struct firmware_work {
 	struct device *device;
 	void *context;
 	void (*cont)(const struct firmware *fw, void *context);
-	int uevent;
+	bool uevent;
 };

 static int request_firmware_work_func(void *arg)
@@ -661,7 +660,7 @@ static int request_firmware_work_func(void *arg)
 **/
 int
 request_firmware_nowait(
-	struct module *module, int uevent,
+	struct module *module, bool uevent,
 	const char *name, struct device *device, gfp_t gfp, void *context,
 	void (*cont)(const struct firmware *fw, void *context))
 {
@@ -30,6 +30,14 @@
 static DEFINE_MUTEX(mem_sysfs_mutex);

 #define MEMORY_CLASS_NAME	"memory"
+#define MIN_MEMORY_BLOCK_SIZE	(1 << SECTION_SIZE_BITS)
+
+static int sections_per_block;
+
+static inline int base_memory_block_id(int section_nr)
+{
+	return section_nr / sections_per_block;
+}

 static struct sysdev_class memory_sysdev_class = {
 	.name = MEMORY_CLASS_NAME,
@@ -84,39 +92,72 @@ EXPORT_SYMBOL(unregister_memory_isolate_notifier);
 * register_memory - Setup a sysfs device for a memory block
 */
 static
-int register_memory(struct memory_block *memory, struct mem_section *section)
+int register_memory(struct memory_block *memory)
 {
 	int error;

 	memory->sysdev.cls = &memory_sysdev_class;
-	memory->sysdev.id = __section_nr(section);
+	memory->sysdev.id = memory->start_section_nr / sections_per_block;

 	error = sysdev_register(&memory->sysdev);
 	return error;
 }

 static void
-unregister_memory(struct memory_block *memory, struct mem_section *section)
+unregister_memory(struct memory_block *memory)
 {
 	BUG_ON(memory->sysdev.cls != &memory_sysdev_class);
-	BUG_ON(memory->sysdev.id != __section_nr(section));

 	/* drop the ref. we got in remove_memory_block() */
 	kobject_put(&memory->sysdev.kobj);
 	sysdev_unregister(&memory->sysdev);
 }

+unsigned long __weak memory_block_size_bytes(void)
+{
+	return MIN_MEMORY_BLOCK_SIZE;
+}
+
+static unsigned long get_memory_block_size(void)
+{
+	unsigned long block_sz;
+
+	block_sz = memory_block_size_bytes();
+
+	/* Validate blk_sz is a power of 2 and not less than section size */
+	if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) {
+		WARN_ON(1);
+		block_sz = MIN_MEMORY_BLOCK_SIZE;
+	}
+
+	return block_sz;
+}
+
 /*
 * use this as the physical section index that this memsection
 * uses.
 */

-static ssize_t show_mem_phys_index(struct sys_device *dev,
+static ssize_t show_mem_start_phys_index(struct sys_device *dev,
 			struct sysdev_attribute *attr, char *buf)
 {
 	struct memory_block *mem =
 		container_of(dev, struct memory_block, sysdev);
-	return sprintf(buf, "%08lx\n", mem->phys_index);
+	unsigned long phys_index;
+
+	phys_index = mem->start_section_nr / sections_per_block;
+	return sprintf(buf, "%08lx\n", phys_index);
+}
+
+static ssize_t show_mem_end_phys_index(struct sys_device *dev,
+			struct sysdev_attribute *attr, char *buf)
+{
+	struct memory_block *mem =
+		container_of(dev, struct memory_block, sysdev);
+	unsigned long phys_index;
+
+	phys_index = mem->end_section_nr / sections_per_block;
+	return sprintf(buf, "%08lx\n", phys_index);
 }

 /*
@@ -125,13 +166,16 @@ static ssize_t show_mem_phys_index(struct sys_device *dev,
 static ssize_t show_mem_removable(struct sys_device *dev,
 			struct sysdev_attribute *attr, char *buf)
 {
-	unsigned long start_pfn;
-	int ret;
+	unsigned long i, pfn;
+	int ret = 1;
 	struct memory_block *mem =
 		container_of(dev, struct memory_block, sysdev);

-	start_pfn = section_nr_to_pfn(mem->phys_index);
-	ret = is_mem_section_removable(start_pfn, PAGES_PER_SECTION);
+	for (i = 0; i < sections_per_block; i++) {
+		pfn = section_nr_to_pfn(mem->start_section_nr + i);
+		ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
+	}
+
 	return sprintf(buf, "%d\n", ret);
 }

@@ -184,17 +228,14 @@ int memory_isolate_notify(unsigned long val, void *v)
 * OK to have direct references to sparsemem variables in here.
 */
 static int
-memory_block_action(struct memory_block *mem, unsigned long action)
+memory_section_action(unsigned long phys_index, unsigned long action)
 {
 	int i;
-	unsigned long psection;
 	unsigned long start_pfn, start_paddr;
 	struct page *first_page;
 	int ret;
-	int old_state = mem->state;

-	psection = mem->phys_index;
-	first_page = pfn_to_page(psection << PFN_SECTION_SHIFT);
+	first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT);

 	/*
 	 * The probe routines leave the pages reserved, just
@@ -207,8 +248,8 @@ memory_block_action(struct memory_block *mem, unsigned long action)
 				continue;

 			printk(KERN_WARNING "section number %ld page number %d "
-				"not reserved, was it already online? \n",
-				psection, i);
+				"not reserved, was it already online?\n",
+				phys_index, i);
 			return -EBUSY;
 		}
 	}
@@ -219,18 +260,13 @@ memory_block_action(struct memory_block *mem, unsigned long action)
 			ret = online_pages(start_pfn, PAGES_PER_SECTION);
 			break;
 		case MEM_OFFLINE:
-			mem->state = MEM_GOING_OFFLINE;
 			start_paddr = page_to_pfn(first_page) << PAGE_SHIFT;
 			ret = remove_memory(start_paddr,
 					    PAGES_PER_SECTION << PAGE_SHIFT);
-			if (ret) {
-				mem->state = old_state;
-				break;
-			}
 			break;
 		default:
-			WARN(1, KERN_WARNING "%s(%p, %ld) unknown action: %ld\n",
-					__func__, mem, action, action);
+			WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
+			     "%ld\n", __func__, phys_index, action, action);
 			ret = -EINVAL;
 	}

@@ -240,7 +276,8 @@ memory_block_action(struct memory_block *mem, unsigned long action)
 static int memory_block_change_state(struct memory_block *mem,
 		unsigned long to_state, unsigned long from_state_req)
 {
-	int ret = 0;
+	int i, ret = 0;
+
 	mutex_lock(&mem->state_mutex);

 	if (mem->state != from_state_req) {
@@ -248,8 +285,23 @@ static int memory_block_change_state(struct memory_block *mem,
 		goto out;
 	}

-	ret = memory_block_action(mem, to_state);
-	if (!ret)
+	if (to_state == MEM_OFFLINE)
+		mem->state = MEM_GOING_OFFLINE;
+
+	for (i = 0; i < sections_per_block; i++) {
+		ret = memory_section_action(mem->start_section_nr + i,
+					    to_state);
+		if (ret)
+			break;
+	}
+
+	if (ret) {
+		for (i = 0; i < sections_per_block; i++)
+			memory_section_action(mem->start_section_nr + i,
+					      from_state_req);
+
+		mem->state = from_state_req;
+	} else
 		mem->state = to_state;

 out:
@@ -262,20 +314,15 @@ store_mem_state(struct sys_device *dev,
 		struct sysdev_attribute *attr, const char *buf, size_t count)
 {
 	struct memory_block *mem;
-	unsigned int phys_section_nr;
 	int ret = -EINVAL;

 	mem = container_of(dev, struct memory_block, sysdev);
-	phys_section_nr = mem->phys_index;
-
-	if (!present_section_nr(phys_section_nr))
-		goto out;

 	if (!strncmp(buf, "online", min((int)count, 6)))
 		ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
 	else if(!strncmp(buf, "offline", min((int)count, 7)))
 		ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
-out:
+
 	if (ret)
 		return ret;
 	return count;
@@ -298,7 +345,8 @@ static ssize_t show_phys_device(struct sys_device *dev,
 	return sprintf(buf, "%d\n", mem->phys_device);
 }

-static SYSDEV_ATTR(phys_index, 0444, show_mem_phys_index, NULL);
+static SYSDEV_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
+static SYSDEV_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
 static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state);
 static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL);
 static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL);
@@ -315,7 +363,7 @@ static ssize_t
 print_block_size(struct sysdev_class *class, struct sysdev_class_attribute *attr,
 		 char *buf)
 {
-	return sprintf(buf, "%lx\n", (unsigned long)PAGES_PER_SECTION * PAGE_SIZE);
+	return sprintf(buf, "%lx\n", get_memory_block_size());
 }

 static SYSDEV_CLASS_ATTR(block_size_bytes, 0444, print_block_size, NULL);
@@ -339,12 +387,19 @@ memory_probe_store(struct class *class, struct class_attribute *attr,
 {
 	u64 phys_addr;
 	int nid;
-	int ret;
+	int i, ret;

 	phys_addr = simple_strtoull(buf, NULL, 0);

-	nid = memory_add_physaddr_to_nid(phys_addr);
-	ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
+	for (i = 0; i < sections_per_block; i++) {
+		nid = memory_add_physaddr_to_nid(phys_addr);
+		ret = add_memory(nid, phys_addr,
+				 PAGES_PER_SECTION << PAGE_SHIFT);
+		if (ret)
+			break;
+
+		phys_addr += MIN_MEMORY_BLOCK_SIZE;
+	}

 	if (ret)
 		count = ret;
@@ -444,6 +499,7 @@ struct memory_block *find_memory_block_hinted(struct mem_section *section,
 	struct sys_device *sysdev;
 	struct memory_block *mem;
 	char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1];
+	int block_id = base_memory_block_id(__section_nr(section));

 	kobj = hint ? &hint->sysdev.kobj : NULL;

@@ -451,7 +507,7 @@ struct memory_block *find_memory_block_hinted(struct mem_section *section,
 	 * This only works because we know that section == sysdev->id
 	 * slightly redundant with sysdev_register()
 	 */
-	sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, __section_nr(section));
+	sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, block_id);

 	kobj = kset_find_obj_hinted(&memory_sysdev_class.kset, name, kobj);
 	if (!kobj)
@@ -476,36 +532,62 @@ struct memory_block *find_memory_block(struct mem_section *section)
 	return find_memory_block_hinted(section, NULL);
 }

-static int add_memory_block(int nid, struct mem_section *section,
-			unsigned long state, enum mem_add_context context)
+static int init_memory_block(struct memory_block **memory,
+			     struct mem_section *section, unsigned long state)
 {
-	struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+	struct memory_block *mem;
 	unsigned long start_pfn;
+	int scn_nr;
 	int ret = 0;

+	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
 	if (!mem)
 		return -ENOMEM;

-	mutex_lock(&mem_sysfs_mutex);
-
-	mem->phys_index = __section_nr(section);
+	scn_nr = __section_nr(section);
+	mem->start_section_nr =
+			base_memory_block_id(scn_nr) * sections_per_block;
+	mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
 	mem->state = state;
 	mem->section_count++;
 	mutex_init(&mem->state_mutex);
-	start_pfn = section_nr_to_pfn(mem->phys_index);
+	start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	mem->phys_device = arch_get_memory_phys_device(start_pfn);

-	ret = register_memory(mem, section);
+	ret = register_memory(mem);
 	if (!ret)
 		ret = mem_create_simple_file(mem, phys_index);
+	if (!ret)
+		ret = mem_create_simple_file(mem, end_phys_index);
 	if (!ret)
 		ret = mem_create_simple_file(mem, state);
 	if (!ret)
 		ret = mem_create_simple_file(mem, phys_device);
 	if (!ret)
 		ret = mem_create_simple_file(mem, removable);
+
+	*memory = mem;
+	return ret;
+}
+
+static int add_memory_section(int nid, struct mem_section *section,
+			unsigned long state, enum mem_add_context context)
+{
+	struct memory_block *mem;
+	int ret = 0;
+
+	mutex_lock(&mem_sysfs_mutex);
+
+	mem = find_memory_block(section);
+	if (mem) {
+		mem->section_count++;
+		kobject_put(&mem->sysdev.kobj);
+	} else
+		ret = init_memory_block(&mem, section, state);
+
 	if (!ret) {
-		if (context == HOTPLUG)
+		if (context == HOTPLUG &&
+		    mem->section_count == sections_per_block)
 			ret = register_mem_sect_under_node(mem, nid);
 	}

@@ -520,16 +602,19 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,

 	mutex_lock(&mem_sysfs_mutex);
 	mem = find_memory_block(section);
+	unregister_mem_sect_under_nodes(mem, __section_nr(section));

 	mem->section_count--;
 	if (mem->section_count == 0) {
-		unregister_mem_sect_under_nodes(mem);
 		mem_remove_simple_file(mem, phys_index);
+		mem_remove_simple_file(mem, end_phys_index);
 		mem_remove_simple_file(mem, state);
 		mem_remove_simple_file(mem, phys_device);
 		mem_remove_simple_file(mem, removable);
-		unregister_memory(mem, section);
-	}
+		unregister_memory(mem);
+		kfree(mem);
+	} else
+		kobject_put(&mem->sysdev.kobj);

 	mutex_unlock(&mem_sysfs_mutex);
 	return 0;
@@ -541,7 +626,7 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
 */
 int register_new_memory(int nid, struct mem_section *section)
 {
-	return add_memory_block(nid, section, MEM_OFFLINE, HOTPLUG);
+	return add_memory_section(nid, section, MEM_OFFLINE, HOTPLUG);
 }

 int unregister_memory_section(struct mem_section *section)
@@ -560,12 +645,16 @@ int __init memory_dev_init(void)
 	unsigned int i;
 	int ret;
 	int err;
+	unsigned long block_sz;

 	memory_sysdev_class.kset.uevent_ops = &memory_uevent_ops;
 	ret = sysdev_class_register(&memory_sysdev_class);
 	if (ret)
 		goto out;

+	block_sz = get_memory_block_size();
+	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
+
 	/*
 	 * Create entries for memory sections that were found
 	 * during boot and have been initialized
@@ -573,8 +662,8 @@ int __init memory_dev_init(void)
 	for (i = 0; i < NR_MEM_SECTIONS; i++) {
 		if (!present_section_nr(i))
 			continue;
-		err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE,
-				       BOOT);
+		err = add_memory_section(0, __nr_to_section(i), MEM_ONLINE,
+					 BOOT);
 		if (!ret)
 			ret = err;
 	}
@@ -375,8 +375,10 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 		return -EFAULT;
 	if (!node_online(nid))
 		return 0;
-	sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
-	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
+
+	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
+	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
+	sect_end_pfn += PAGES_PER_SECTION - 1;
 	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int page_nid;

@@ -400,7 +402,8 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 }

 /* unregister memory section under all nodes that it spans */
-int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
+int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
+				    unsigned long phys_index)
 {
 	NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL);
 	unsigned long pfn, sect_start_pfn, sect_end_pfn;
@@ -412,7 +415,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
 	if (!unlinked_nodes)
 		return -ENOMEM;
 	nodes_clear(*unlinked_nodes);
-	sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
+
+	sect_start_pfn = section_nr_to_pfn(phys_index);
 	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
 	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int nid;
@@ -166,6 +166,36 @@ EXPORT_SYMBOL_GPL(sysdev_class_unregister);

 static DEFINE_MUTEX(sysdev_drivers_lock);

+/*
+ * @dev != NULL means that we're unwinding because some drv->add()
+ * failed for some reason. You need to grab sysdev_drivers_lock before
+ * calling this.
+ */
+static void __sysdev_driver_remove(struct sysdev_class *cls,
+				   struct sysdev_driver *drv,
+				   struct sys_device *from_dev)
+{
+	struct sys_device *dev = from_dev;
+
+	list_del_init(&drv->entry);
+	if (!cls)
+		return;
+
+	if (!drv->remove)
+		goto kset_put;
+
+	if (dev)
+		list_for_each_entry_continue_reverse(dev, &cls->kset.list,
+						     kobj.entry)
+			drv->remove(dev);
+	else
+		list_for_each_entry(dev, &cls->kset.list, kobj.entry)
+			drv->remove(dev);
+
+kset_put:
+	kset_put(&cls->kset);
+}
+
 /**
 *	sysdev_driver_register - Register auxillary driver
 *	@cls:	Device class driver belongs to.
@@ -175,14 +205,14 @@ static DEFINE_MUTEX(sysdev_drivers_lock);
 *	called on each operation on devices of that class. The refcount
 *	of @cls is incremented.
 */
-
 int sysdev_driver_register(struct sysdev_class *cls, struct sysdev_driver *drv)
 {
+	struct sys_device *dev = NULL;
 	int err = 0;

 	if (!cls) {
-		WARN(1, KERN_WARNING "sysdev: invalid class passed to "
-			"sysdev_driver_register!\n");
+		WARN(1, KERN_WARNING "sysdev: invalid class passed to %s!\n",
+			__func__);
 		return -EINVAL;
 	}

@@ -198,19 +228,27 @@ int sysdev_driver_register(struct sysdev_class *cls, struct sysdev_driver *drv)

 		/* If devices of this class already exist, tell the driver */
 		if (drv->add) {
-			struct sys_device *dev;
-			list_for_each_entry(dev, &cls->kset.list, kobj.entry)
-				drv->add(dev);
+			list_for_each_entry(dev, &cls->kset.list, kobj.entry) {
+				err = drv->add(dev);
+				if (err)
+					goto unwind;
+			}
 		}
 	} else {
 		err = -EINVAL;
 		WARN(1, KERN_ERR "%s: invalid device class\n", __func__);
 	}
+
+	goto unlock;
+
+unwind:
+	__sysdev_driver_remove(cls, drv, dev);
+
+unlock:
 	mutex_unlock(&sysdev_drivers_lock);
 	return err;
 }

-
 /**
 *	sysdev_driver_unregister - Remove an auxillary driver.
 *	@cls:	Class driver belongs to.
@@ -220,23 +258,12 @@ void sysdev_driver_unregister(struct sysdev_class *cls,
 			      struct sysdev_driver *drv)
 {
 	mutex_lock(&sysdev_drivers_lock);
-	list_del_init(&drv->entry);
-	if (cls) {
-		if (drv->remove) {
-			struct sys_device *dev;
-			list_for_each_entry(dev, &cls->kset.list, kobj.entry)
-				drv->remove(dev);
-		}
-		kset_put(&cls->kset);
-	}
+	__sysdev_driver_remove(cls, drv, NULL);
 	mutex_unlock(&sysdev_drivers_lock);
 }
-
 EXPORT_SYMBOL_GPL(sysdev_driver_register);
 EXPORT_SYMBOL_GPL(sysdev_driver_unregister);

-
-
 /**
 *	sysdev_register - add a system device to the tree
 *	@sysdev:	device in question
@@ -113,6 +113,17 @@ config DMIID
 	  information from userspace through /sys/class/dmi/id/ or if you want
 	  DMI-based module auto-loading.

+config DMI_SYSFS
+	tristate "DMI table support in sysfs"
+	depends on SYSFS && DMI
+	default n
+	help
+	  Say Y or M here to enable the exporting of the raw DMI table
+	  data via sysfs.  This is useful for consuming the data without
+	  requiring any access to /dev/mem at all.  Tables are found
+	  under /sys/firmware/dmi when this option is enabled and
+	  loaded.
+
 config ISCSI_IBFT_FIND
 	bool "iSCSI Boot Firmware Table Attributes"
 	depends on X86
@@ -2,6 +2,7 @@
 # Makefile for the linux kernel.
 #
 obj-$(CONFIG_DMI)		+= dmi_scan.o
+obj-$(CONFIG_DMI_SYSFS)		+= dmi-sysfs.o
 obj-$(CONFIG_EDD)		+= edd.o
 obj-$(CONFIG_EFI_VARS)		+= efivars.o
 obj-$(CONFIG_EFI_PCDP)		+= pcdp.o
--- a/Show More
+++ b/Show More