diff options
Diffstat (limited to 'Documentation')
42 files changed, 1590 insertions, 1681 deletions
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone b/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone index 063bda7fe707..698b8081c473 100644 --- a/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone +++ b/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone @@ -1,4 +1,4 @@ -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/actual_dpi +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/kone/roccatkone<minor>/actual_dpi Date: March 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: It is possible to switch the dpi setting of the mouse with the @@ -17,13 +17,13 @@ Description: It is possible to switch the dpi setting of the mouse with the This file is readonly. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/actual_profile +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/kone/roccatkone<minor>/actual_profile Date: March 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: When read, this file returns the number of the actual profile. This file is readonly. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/firmware_version +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/kone/roccatkone<minor>/firmware_version Date: March 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: When read, this file returns the raw integer version number of the @@ -33,7 +33,7 @@ Description: When read, this file returns the raw integer version number of the left. E.g. a returned value of 138 means 1.38 This file is readonly. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile[1-5] +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/kone/roccatkone<minor>/profile[1-5] Date: March 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: The mouse can store 5 profiles which can be switched by the @@ -48,7 +48,7 @@ Description: The mouse can store 5 profiles which can be switched by the stored in the profile doesn't need to fit the number of the store. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/settings +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/kone/roccatkone<minor>/settings Date: March 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: When read, this file returns the settings stored in the mouse. @@ -58,7 +58,7 @@ Description: When read, this file returns the settings stored in the mouse. The data has to be 36 bytes long. The mouse will reject invalid data. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/startup_profile +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/kone/roccatkone<minor>/startup_profile Date: March 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: The integer value of this attribute ranges from 1 to 5. @@ -67,7 +67,7 @@ Description: The integer value of this attribute ranges from 1 to 5. When written, this file sets the number of the startup profile and the mouse activates this profile immediately. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/tcu +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/kone/roccatkone<minor>/tcu Date: March 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: The mouse has a "Tracking Control Unit" which lets the user @@ -78,7 +78,7 @@ Description: The mouse has a "Tracking Control Unit" which lets the user Writing 1 in this file will start the calibration which takes around 6 seconds to complete and activates the TCU. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/weight +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/kone/roccatkone<minor>/weight Date: March 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: The mouse can be equipped with one of four supplied weights diff --git a/Documentation/ABI/testing/sysfs-driver-hid-roccat-koneplus b/Documentation/ABI/testing/sysfs-driver-hid-roccat-koneplus new file mode 100644 index 000000000000..0f9f30eb1742 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-driver-hid-roccat-koneplus @@ -0,0 +1,108 @@ +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/koneplus/roccatkoneplus<minor>/actual_profile +Date: October 2010 +Contact: Stefan Achatz <erazor_de@users.sourceforge.net> +Description: When read, this file returns the number of the actual profile in + range 0-4. + This file is readonly. + +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/koneplus/roccatkoneplus<minor>/firmware_version +Date: October 2010 +Contact: Stefan Achatz <erazor_de@users.sourceforge.net> +Description: When read, this file returns the raw integer version number of the + firmware reported by the mouse. Using the integer value eases + further usage in other programs. To receive the real version + number the decimal point has to be shifted 2 positions to the + left. E.g. a returned value of 121 means 1.21 + This file is readonly. + +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/koneplus/roccatkoneplus<minor>/macro +Date: October 2010 +Contact: Stefan Achatz <erazor_de@users.sourceforge.net> +Description: The mouse can store a macro with max 500 key/button strokes + internally. + When written, this file lets one set the sequence for a specific + button for a specific profile. Button and profile numbers are + included in written data. The data has to be 2082 bytes long. + This file is writeonly. + +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/koneplus/roccatkoneplus<minor>/profile_buttons +Date: August 2010 +Contact: Stefan Achatz <erazor_de@users.sourceforge.net> +Description: The mouse can store 5 profiles which can be switched by the + press of a button. A profile is split in settings and buttons. + profile_buttons holds informations about button layout. + When written, this file lets one write the respective profile + buttons back to the mouse. The data has to be 77 bytes long. + The mouse will reject invalid data. + Which profile to write is determined by the profile number + contained in the data. + This file is writeonly. + +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/koneplus/roccatkoneplus<minor>/profile[1-5]_buttons +Date: August 2010 +Contact: Stefan Achatz <erazor_de@users.sourceforge.net> +Description: The mouse can store 5 profiles which can be switched by the + press of a button. A profile is split in settings and buttons. + profile_buttons holds informations about button layout. + When read, these files return the respective profile buttons. + The returned data is 77 bytes in size. + This file is readonly. + +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/koneplus/roccatkoneplus<minor>/profile_settings +Date: October 2010 +Contact: Stefan Achatz <erazor_de@users.sourceforge.net> +Description: The mouse can store 5 profiles which can be switched by the + press of a button. A profile is split in settings and buttons. + profile_settings holds informations like resolution, sensitivity + and light effects. + When written, this file lets one write the respective profile + settings back to the mouse. The data has to be 43 bytes long. + The mouse will reject invalid data. + Which profile to write is determined by the profile number + contained in the data. + This file is writeonly. + +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/koneplus/roccatkoneplus<minor>/profile[1-5]_settings +Date: August 2010 +Contact: Stefan Achatz <erazor_de@users.sourceforge.net> +Description: The mouse can store 5 profiles which can be switched by the + press of a button. A profile is split in settings and buttons. + profile_settings holds informations like resolution, sensitivity + and light effects. + When read, these files return the respective profile settings. + The returned data is 43 bytes in size. + This file is readonly. + +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/koneplus/roccatkoneplus<minor>/sensor +Date: October 2010 +Contact: Stefan Achatz <erazor_de@users.sourceforge.net> +Description: The mouse has a tracking- and a distance-control-unit. These + can be activated/deactivated and the lift-off distance can be + set. The data has to be 6 bytes long. + This file is writeonly. + +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/koneplus/roccatkoneplus<minor>/startup_profile +Date: October 2010 +Contact: Stefan Achatz <erazor_de@users.sourceforge.net> +Description: The integer value of this attribute ranges from 0-4. + When read, this attribute returns the number of the profile + that's active when the mouse is powered on. + When written, this file sets the number of the startup profile + and the mouse activates this profile immediately. + +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/koneplus/roccatkoneplus<minor>/tcu +Date: October 2010 +Contact: Stefan Achatz <erazor_de@users.sourceforge.net> +Description: When written a calibration process for the tracking control unit + can be initiated/cancelled. + The data has to be 3 bytes long. + This file is writeonly. + +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/koneplus/roccatkoneplus<minor>/tcu_image +Date: October 2010 +Contact: Stefan Achatz <erazor_de@users.sourceforge.net> +Description: When read the mouse returns a 30x30 pixel image of the + sampled underground. This works only in the course of a + calibration process initiated with tcu. + The returned data is 1028 bytes in size. + This file is readonly. diff --git a/Documentation/ABI/testing/sysfs-driver-hid-roccat-pyra b/Documentation/ABI/testing/sysfs-driver-hid-roccat-pyra index ad1125b02ff4..1c37b823f142 100644 --- a/Documentation/ABI/testing/sysfs-driver-hid-roccat-pyra +++ b/Documentation/ABI/testing/sysfs-driver-hid-roccat-pyra @@ -1,4 +1,4 @@ -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/actual_cpi +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/pyra/roccatpyra<minor>/actual_cpi Date: August 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: It is possible to switch the cpi setting of the mouse with the @@ -14,14 +14,14 @@ Description: It is possible to switch the cpi setting of the mouse with the This file is readonly. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/actual_profile +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/pyra/roccatpyra<minor>/actual_profile Date: August 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: When read, this file returns the number of the actual profile in range 0-4. This file is readonly. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/firmware_version +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/pyra/roccatpyra<minor>/firmware_version Date: August 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: When read, this file returns the raw integer version number of the @@ -31,7 +31,7 @@ Description: When read, this file returns the raw integer version number of the left. E.g. a returned value of 138 means 1.38 This file is readonly. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile_settings +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/pyra/roccatpyra<minor>/profile_settings Date: August 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: The mouse can store 5 profiles which can be switched by the @@ -45,7 +45,7 @@ Description: The mouse can store 5 profiles which can be switched by the contained in the data. This file is writeonly. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile[1-5]_settings +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/pyra/roccatpyra<minor>/profile[1-5]_settings Date: August 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: The mouse can store 5 profiles which can be switched by the @@ -56,7 +56,7 @@ Description: The mouse can store 5 profiles which can be switched by the The returned data is 13 bytes in size. This file is readonly. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile_buttons +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/pyra/roccatpyra<minor>/profile_buttons Date: August 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: The mouse can store 5 profiles which can be switched by the @@ -69,7 +69,7 @@ Description: The mouse can store 5 profiles which can be switched by the contained in the data. This file is writeonly. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile[1-5]_buttons +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/pyra/roccatpyra<minor>/profile[1-5]_buttons Date: August 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: The mouse can store 5 profiles which can be switched by the @@ -79,7 +79,7 @@ Description: The mouse can store 5 profiles which can be switched by the The returned data is 19 bytes in size. This file is readonly. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/startup_profile +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/pyra/roccatpyra<minor>/startup_profile Date: August 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: The integer value of this attribute ranges from 0-4. @@ -87,7 +87,7 @@ Description: The integer value of this attribute ranges from 0-4. that's active when the mouse is powered on. This file is readonly. -What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/settings +What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/pyra/roccatpyra<minor>/settings Date: August 2010 Contact: Stefan Achatz <erazor_de@users.sourceforge.net> Description: When read, this file returns the settings stored in the mouse. diff --git a/Documentation/ABI/testing/sysfs-platform-ideapad-laptop b/Documentation/ABI/testing/sysfs-platform-ideapad-laptop new file mode 100644 index 000000000000..807fca2ae2a4 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-platform-ideapad-laptop @@ -0,0 +1,6 @@ +What: /sys/devices/platform/ideapad/camera_power +Date: Dec 2010 +KernelVersion: 2.6.37 +Contact: "Ike Panhc <ike.pan@canonical.com>" +Description: + Control the power of camera module. 1 means on, 0 means off. diff --git a/Documentation/ABI/testing/sysfs-tty b/Documentation/ABI/testing/sysfs-tty new file mode 100644 index 000000000000..b138b663bf54 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-tty @@ -0,0 +1,19 @@ +What: /sys/class/tty/console/active +Date: Nov 2010 +Contact: Kay Sievers <kay.sievers@vrfy.org> +Description: + Shows the list of currently configured + console devices, like 'tty1 ttyS0'. + The last entry in the file is the active + device connected to /dev/console. + The file supports poll() to detect virtual + console switches. + +What: /sys/class/tty/tty0/active +Date: Nov 2010 +Contact: Kay Sievers <kay.sievers@vrfy.org> +Description: + Shows the currently active virtual console + device, like 'tty1'. + The file supports poll() to detect virtual + console switches. diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index 22edcbb9ddaf..35447e081736 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -304,6 +304,10 @@ X!Idrivers/video/console/fonts.c !Edrivers/input/ff-core.c !Edrivers/input/ff-memless.c </sect1> + <sect1><title>Multitouch Library</title> +!Iinclude/linux/input/mt.h +!Edrivers/input/input-mt.c + </sect1> <sect1><title>Polled input devices</title> !Iinclude/linux/input-polldev.h !Edrivers/input/input-polldev.c diff --git a/Documentation/arm/OMAP/omap_pm b/Documentation/arm/OMAP/omap_pm index 5389440aade3..9012bb039094 100644 --- a/Documentation/arm/OMAP/omap_pm +++ b/Documentation/arm/OMAP/omap_pm @@ -127,3 +127,28 @@ implementation needs: 10. (*pdata->cpu_set_freq)(unsigned long f) 11. (*pdata->cpu_get_freq)(void) + +Customizing OPP for platform +============================ +Defining CONFIG_PM should enable OPP layer for the silicon +and the registration of OPP table should take place automatically. +However, in special cases, the default OPP table may need to be +tweaked, for e.g.: + * enable default OPPs which are disabled by default, but which + could be enabled on a platform + * Disable an unsupported OPP on the platform + * Define and add a custom opp table entry +in these cases, the board file needs to do additional steps as follows: +arch/arm/mach-omapx/board-xyz.c + #include "pm.h" + .... + static void __init omap_xyz_init_irq(void) + { + .... + /* Initialize the default table */ + omapx_opp_init(); + /* Do customization to the defaults */ + .... + } +NOTE: omapx_opp_init will be omap3_opp_init or as required +based on the omap family. diff --git a/Documentation/coccinelle.txt b/Documentation/coccinelle.txt index 4a276ea7001c..96b690348ba1 100644 --- a/Documentation/coccinelle.txt +++ b/Documentation/coccinelle.txt @@ -36,6 +36,10 @@ as a regular user, and install it with sudo make install +The semantic patches in the kernel will work best with Coccinelle version +0.2.4 or later. Using earlier versions may incur some parse errors in the +semantic patch code, but any results that are obtained should still be +correct. Using Coccinelle on the Linux kernel ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index f2742e115b09..22f10818c2b3 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -566,3 +566,13 @@ Why: This field is deprecated. I2C device drivers shouldn't change their Who: Jean Delvare <khali@linux-fr.org> ---------------------------- + +What: cancel_rearming_delayed_work[queue]() +When: 2.6.39 + +Why: The functions have been superceded by cancel_delayed_work_sync() + quite some time ago. The conversion is trivial and there is no + in-kernel user left. +Who: Tejun Heo <tj@kernel.org> + +---------------------------- diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 33fa3e5d38fd..977d8919cc69 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -9,22 +9,25 @@ be able to use diff(1). --------------------------- dentry_operations -------------------------- prototypes: - int (*d_revalidate)(struct dentry *, int); - int (*d_hash) (struct dentry *, struct qstr *); - int (*d_compare) (struct dentry *, struct qstr *, struct qstr *); + int (*d_revalidate)(struct dentry *, struct nameidata *); + int (*d_hash)(const struct dentry *, const struct inode *, + struct qstr *); + int (*d_compare)(const struct dentry *, const struct inode *, + const struct dentry *, const struct inode *, + unsigned int, const char *, const struct qstr *); int (*d_delete)(struct dentry *); void (*d_release)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen); locking rules: - dcache_lock rename_lock ->d_lock may block -d_revalidate: no no no yes -d_hash no no no yes -d_compare: no yes no no -d_delete: yes no yes no -d_release: no no no yes -d_iput: no no no yes + rename_lock ->d_lock may block rcu-walk +d_revalidate: no no yes (ref-walk) maybe +d_hash no no no maybe +d_compare: yes no no maybe +d_delete: no yes no no +d_release: no no yes no +d_iput: no no yes no d_dname: no no no no --------------------------- inode_operations --------------------------- @@ -44,8 +47,8 @@ ata *); void * (*follow_link) (struct dentry *, struct nameidata *); void (*put_link) (struct dentry *, struct nameidata *, void *); void (*truncate) (struct inode *); - int (*permission) (struct inode *, int, struct nameidata *); - int (*check_acl)(struct inode *, int); + int (*permission) (struct inode *, int, unsigned int); + int (*check_acl)(struct inode *, int, unsigned int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); @@ -73,7 +76,7 @@ follow_link: no put_link: no truncate: yes (see below) setattr: yes -permission: no +permission: no (may not block if called in rcu-walk mode) check_acl: no getattr: no setxattr: yes diff --git a/Documentation/filesystems/dentry-locking.txt b/Documentation/filesystems/dentry-locking.txt deleted file mode 100644 index 79334ed5daa7..000000000000 --- a/Documentation/filesystems/dentry-locking.txt +++ /dev/null @@ -1,174 +0,0 @@ -RCU-based dcache locking model -============================== - -On many workloads, the most common operation on dcache is to look up a -dentry, given a parent dentry and the name of the child. Typically, -for every open(), stat() etc., the dentry corresponding to the -pathname will be looked up by walking the tree starting with the first -component of the pathname and using that dentry along with the next -component to look up the next level and so on. Since it is a frequent -operation for workloads like multiuser environments and web servers, -it is important to optimize this path. - -Prior to 2.5.10, dcache_lock was acquired in d_lookup and thus in -every component during path look-up. Since 2.5.10 onwards, fast-walk -algorithm changed this by holding the dcache_lock at the beginning and -walking as many cached path component dentries as possible. This -significantly decreases the number of acquisition of -dcache_lock. However it also increases the lock hold time -significantly and affects performance in large SMP machines. Since -2.5.62 kernel, dcache has been using a new locking model that uses RCU -to make dcache look-up lock-free. - -The current dcache locking model is not very different from the -existing dcache locking model. Prior to 2.5.62 kernel, dcache_lock -protected the hash chain, d_child, d_alias, d_lru lists as well as -d_inode and several other things like mount look-up. RCU-based changes -affect only the way the hash chain is protected. For everything else -the dcache_lock must be taken for both traversing as well as -updating. The hash chain updates too take the dcache_lock. The -significant change is the way d_lookup traverses the hash chain, it -doesn't acquire the dcache_lock for this and rely on RCU to ensure -that the dentry has not been *freed*. - - -Dcache locking details -====================== - -For many multi-user workloads, open() and stat() on files are very -frequently occurring operations. Both involve walking of path names to -find the dentry corresponding to the concerned file. In 2.4 kernel, -dcache_lock was held during look-up of each path component. Contention -and cache-line bouncing of this global lock caused significant -scalability problems. With the introduction of RCU in Linux kernel, -this was worked around by making the look-up of path components during -path walking lock-free. - - -Safe lock-free look-up of dcache hash table -=========================================== - -Dcache is a complex data structure with the hash table entries also -linked together in other lists. In 2.4 kernel, dcache_lock protected -all the lists. We applied RCU only on hash chain walking. The rest of -the lists are still protected by dcache_lock. Some of the important -changes are : - -1. The deletion from hash chain is done using hlist_del_rcu() macro - which doesn't initialize next pointer of the deleted dentry and - this allows us to walk safely lock-free while a deletion is - happening. - -2. Insertion of a dentry into the hash table is done using - hlist_add_head_rcu() which take care of ordering the writes - the - writes to the dentry must be visible before the dentry is - inserted. This works in conjunction with hlist_for_each_rcu(), - which has since been replaced by hlist_for_each_entry_rcu(), while - walking the hash chain. The only requirement is that all - initialization to the dentry must be done before - hlist_add_head_rcu() since we don't have dcache_lock protection - while traversing the hash chain. This isn't different from the - existing code. - -3. The dentry looked up without holding dcache_lock by cannot be - returned for walking if it is unhashed. It then may have a NULL - d_inode or other bogosity since RCU doesn't protect the other - fields in the dentry. We therefore use a flag DCACHE_UNHASHED to - indicate unhashed dentries and use this in conjunction with a - per-dentry lock (d_lock). Once looked up without the dcache_lock, - we acquire the per-dentry lock (d_lock) and check if the dentry is - unhashed. If so, the look-up is failed. If not, the reference count - of the dentry is increased and the dentry is returned. - -4. Once a dentry is looked up, it must be ensured during the path walk - for that component it doesn't go away. In pre-2.5.10 code, this was - done holding a reference to the dentry. dcache_rcu does the same. - In some sense, dcache_rcu path walking looks like the pre-2.5.10 - version. - -5. All dentry hash chain updates must take the dcache_lock as well as - the per-dentry lock in that order. dput() does this to ensure that - a dentry that has just been looked up in another CPU doesn't get - deleted before dget() can be done on it. - -6. There are several ways to do reference counting of RCU protected - objects. One such example is in ipv4 route cache where deferred - freeing (using call_rcu()) is done as soon as the reference count - goes to zero. This cannot be done in the case of dentries because - tearing down of dentries require blocking (dentry_iput()) which - isn't supported from RCU callbacks. Instead, tearing down of - dentries happen synchronously in dput(), but actual freeing happens - later when RCU grace period is over. This allows safe lock-free - walking of the hash chains, but a matched dentry may have been - partially torn down. The checking of DCACHE_UNHASHED flag with - d_lock held detects such dentries and prevents them from being - returned from look-up. - - -Maintaining POSIX rename semantics -================================== - -Since look-up of dentries is lock-free, it can race against a -concurrent rename operation. For example, during rename of file A to -B, look-up of either A or B must succeed. So, if look-up of B happens -after A has been removed from the hash chain but not added to the new -hash chain, it may fail. Also, a comparison while the name is being -written concurrently by a rename may result in false positive matches -violating rename semantics. Issues related to race with rename are -handled as described below : - -1. Look-up can be done in two ways - d_lookup() which is safe from - simultaneous renames and __d_lookup() which is not. If - __d_lookup() fails, it must be followed up by a d_lookup() to - correctly determine whether a dentry is in the hash table or - not. d_lookup() protects look-ups using a sequence lock - (rename_lock). - -2. The name associated with a dentry (d_name) may be changed if a - rename is allowed to happen simultaneously. To avoid memcmp() in - __d_lookup() go out of bounds due to a rename and false positive - comparison, the name comparison is done while holding the - per-dentry lock. This prevents concurrent renames during this - operation. - -3. Hash table walking during look-up may move to a different bucket as - the current dentry is moved to a different bucket due to rename. - But we use hlists in dcache hash table and they are - null-terminated. So, even if a dentry moves to a different bucket, - hash chain walk will terminate. [with a list_head list, it may not - since termination is when the list_head in the original bucket is - reached]. Since we redo the d_parent check and compare name while - holding d_lock, lock-free look-up will not race against d_move(). - -4. There can be a theoretical race when a dentry keeps coming back to - original bucket due to double moves. Due to this look-up may - consider that it has never moved and can end up in a infinite loop. - But this is not any worse that theoretical livelocks we already - have in the kernel. - - -Important guidelines for filesystem developers related to dcache_rcu -==================================================================== - -1. Existing dcache interfaces (pre-2.5.62) exported to filesystem - don't change. Only dcache internal implementation changes. However - filesystems *must not* delete from the dentry hash chains directly - using the list macros like allowed earlier. They must use dcache - APIs like d_drop() or __d_drop() depending on the situation. - -2. d_flags is now protected by a per-dentry lock (d_lock). All access - to d_flags must be protected by it. - -3. For a hashed dentry, checking of d_count needs to be protected by - d_lock. - - -Papers and other documentation on dcache locking -================================================ - -1. Scaling dcache with RCU (http://linuxjournal.com/article.php?sid=7124). - -2. http://lse.sourceforge.net/locking/dcache/dcache.html - - - diff --git a/Documentation/filesystems/ntfs.txt b/Documentation/filesystems/ntfs.txt index ac2a261c5f7d..6ef8cf3bc9a3 100644 --- a/Documentation/filesystems/ntfs.txt +++ b/Documentation/filesystems/ntfs.txt @@ -457,6 +457,9 @@ ChangeLog Note, a technical ChangeLog aimed at kernel hackers is in fs/ntfs/ChangeLog. +2.1.30: + - Fix writev() (it kept writing the first segment over and over again + instead of moving onto subsequent segments). 2.1.29: - Fix a deadlock when mounting read-write. 2.1.28: diff --git a/Documentation/filesystems/path-lookup.txt b/Documentation/filesystems/path-lookup.txt new file mode 100644 index 000000000000..eb59c8b44be9 --- /dev/null +++ b/Documentation/filesystems/path-lookup.txt @@ -0,0 +1,382 @@ +Path walking and name lookup locking +==================================== + +Path resolution is the finding a dentry corresponding to a path name string, by +performing a path walk. Typically, for every open(), stat() etc., the path name +will be resolved. Paths are resolved by walking the namespace tree, starting +with the first component of the pathname (eg. root or cwd) with a known dentry, +then finding the child of that dentry, which is named the next component in the +path string. Then repeating the lookup from the child dentry and finding its +child with the next element, and so on. + +Since it is a frequent operation for workloads like multiuser environments and +web servers, it is important to optimize this code. + +Path walking synchronisation history: +Prior to 2.5.10, dcache_lock was acquired in d_lookup (dcache hash lookup) and +thus in every component during path look-up. Since 2.5.10 onwards, fast-walk +algorithm changed this by holding the dcache_lock at the beginning and walking +as many cached path component dentries as possible. This significantly +decreases the number of acquisition of dcache_lock. However it also increases +the lock hold time significantly and affects performance in large SMP machines. +Since 2.5.62 kernel, dcache has been using a new locking model that uses RCU to +make dcache look-up lock-free. + +All the above algorithms required taking a lock and reference count on the +dentry that was looked up, so that may be used as the basis for walking the +next path element. This is inefficient and unscalable. It is inefficient +because of the locks and atomic operations required for every dentry element +slows things down. It is not scalable because many parallel applications that +are path-walk intensive tend to do path lookups starting from a common dentry +(usually, the root "/" or current working directory). So contention on these +common path elements causes lock and cacheline queueing. + +Since 2.6.38, RCU is used to make a significant part of the entire path walk +(including dcache look-up) completely "store-free" (so, no locks, atomics, or +even stores into cachelines of common dentries). This is known as "rcu-walk" +path walking. + +Path walking overview +===================== + +A name string specifies a start (root directory, cwd, fd-relative) and a +sequence of elements (directory entry names), which together refer to a path in +the namespace. A path is represented as a (dentry, vfsmount) tuple. The name +elements are sub-strings, seperated by '/'. + +Name lookups will want to find a particular path that a name string refers to +(usually the final element, or parent of final element). This is done by taking +the path given by the name's starting point (which we know in advance -- eg. +current->fs->cwd or current->fs->root) as the first parent of the lookup. Then +iteratively for each subsequent name element, look up the child of the current +parent with the given name and if it is not the desired entry, make it the +parent for the next lookup. + +A parent, of course, must be a directory, and we must have appropriate +permissions on the parent inode to be able to walk into it. + +Turning the child into a parent for the next lookup requires more checks and +procedures. Symlinks essentially substitute the symlink name for the target +name in the name string, and require some recursive path walking. Mount points +must be followed into (thus changing the vfsmount that subsequent path elements +refer to), switching from the mount point path to the root of the particular +mounted vfsmount. These behaviours are variously modified depending on the +exact path walking flags. + +Path walking then must, broadly, do several particular things: +- find the start point of the walk; +- perform permissions and validity checks on inodes; +- perform dcache hash name lookups on (parent, name element) tuples; +- traverse mount points; +- traverse symlinks; +- lookup and create missing parts of the path on demand. + +Safe store-free look-up of dcache hash table +============================================ + +Dcache name lookup +------------------ +In order to lookup a dcache (parent, name) tuple, we take a hash on the tuple +and use that to select a bucket in the dcache-hash table. The list of entries +in that bucket is then walked, and we do a full comparison of each entry +against our (parent, name) tuple. + +The hash lists are RCU protected, so list walking is not serialised with +concurrent updates (insertion, deletion from the hash). This is a standard RCU +list application with the exception of renames, which will be covered below. + +Parent and name members of a dentry, as well as its membership in the dcache +hash, and its inode are protected by the per-dentry d_lock spinlock. A +reference is taken on the dentry (while the fields are verified under d_lock), +and this stabilises its d_inode pointer and actual inode. This gives a stable +point to perform the next step of our path walk against. + +These members are also protected by d_seq seqlock, although this offers +read-only protection and no durability of results, so care must be taken when +using d_seq for synchronisation (see seqcount based lookups, below). + +Renames +------- +Back to the rename case. In usual RCU protected lists, the only operations that +will happen to an object is insertion, and then eventually removal from the +list. The object will not be reused until an RCU grace period is complete. +This ensures the RCU list traversal primitives can run over the object without +problems (see RCU documentation for how this works). + +However when a dentry is renamed, its hash value can change, requiring it to be +moved to a new hash list. Allocating and inserting a new alias would be +expensive and also problematic for directory dentries. Latency would be far to +high to wait for a grace period after removing the dentry and before inserting +it in the new hash bucket. So what is done is to insert the dentry into the +new list immediately. + +However, when the dentry's list pointers are updated to point to objects in the +new list before waiting for a grace period, this can result in a concurrent RCU +lookup of the old list veering off into the new (incorrect) list and missing +the remaining dentries on the list. + +There is no fundamental problem with walking down the wrong list, because the +dentry comparisons will never match. However it is fatal to miss a matching +dentry. So a seqlock is used to detect when a rename has occurred, and so the +lookup can be retried. + + 1 2 3 + +---+ +---+ +---+ +hlist-->| N-+->| N-+->| N-+-> +head <--+-P |<-+-P |<-+-P | + +---+ +---+ +---+ + +Rename of dentry 2 may require it deleted from the above list, and inserted +into a new list. Deleting 2 gives the following list. + + 1 3 + +---+ +---+ (don't worry, the longer pointers do not +hlist-->| N-+-------->| N-+-> impose a measurable performance overhead +head <--+-P |<--------+-P | on modern CPUs) + +---+ +---+ + ^ 2 ^ + | +---+ | + | | N-+----+ + +----+-P | + +---+ + +This is a standard RCU-list deletion, which leaves the deleted object's +pointers intact, so a concurrent list walker that is currently looking at +object 2 will correctly continue to object 3 when it is time to traverse the +next object. + +However, when inserting object 2 onto a new list, we end up with this: + + 1 3 + +---+ +---+ +hlist-->| N-+-------->| N-+-> +head <--+-P |<--------+-P | + +---+ +---+ + 2 + +---+ + | N-+----> + <----+-P | + +---+ + +Because we didn't wait for a grace period, there may be a concurrent lookup +still at 2. Now when it follows 2's 'next' pointer, it will walk off into +another list without ever having checked object 3. + +A related, but distinctly different, issue is that of rename atomicity versus +lookup operations. If a file is renamed from 'A' to 'B', a lookup must only +find either 'A' or 'B'. So if a lookup of 'A' returns NULL, a subsequent lookup +of 'B' must succeed (note the reverse is not true). + +Between deleting the dentry from the old hash list, and inserting it on the new +hash list, a lookup may find neither 'A' nor 'B' matching the dentry. The same +rename seqlock is also used to cover this race in much the same way, by +retrying a negative lookup result if a rename was in progress. + +Seqcount based lookups +---------------------- +In refcount based dcache lookups, d_lock is used to serialise access to +the dentry, stabilising it while comparing its name and parent and then +taking a reference count (the reference count then gives a stable place to +start the next part of the path walk from). + +As explained above, we would like to do path walking without taking locks or +reference counts on intermediate dentries along the path. To do this, a per +dentry seqlock (d_seq) is used to take a "coherent snapshot" of what the dentry +looks like (its name, parent, and inode). That snapshot is then used to start +the next part of the path walk. When loading the coherent snapshot under d_seq, +care must be taken to load the members up-front, and use those pointers rather +than reloading from the dentry later on (otherwise we'd have interesting things +like d_inode going NULL underneath us, if the name was unlinked). + +Also important is to avoid performing any destructive operations (pretty much: +no non-atomic stores to shared data), and to recheck the seqcount when we are +"done" with the operation. Retry or abort if the seqcount does not match. +Avoiding destructive or changing operations means we can easily unwind from +failure. + +What this means is that a caller, provided they are holding RCU lock to +protect the dentry object from disappearing, can perform a seqcount based +lookup which does not increment the refcount on the dentry or write to +it in any way. This returned dentry can be used for subsequent operations, +provided that d_seq is rechecked after that operation is complete. + +Inodes are also rcu freed, so the seqcount lookup dentry's inode may also be +queried for permissions. + +With this two parts of the puzzle, we can do path lookups without taking +locks or refcounts on dentry elements. + +RCU-walk path walking design +============================ + +Path walking code now has two distinct modes, ref-walk and rcu-walk. ref-walk +is the traditional[*] way of performing dcache lookups using d_lock to +serialise concurrent modifications to the dentry and take a reference count on +it. ref-walk is simple and obvious, and may sleep, take locks, etc while path +walking is operating on each dentry. rcu-walk uses seqcount based dentry +lookups, and can perform lookup of intermediate elements without any stores to +shared data in the dentry or inode. rcu-walk can not be applied to all cases, +eg. if the filesystem must sleep or perform non trivial operations, rcu-walk +must be switched to ref-walk mode. + +[*] RCU is still used for the dentry hash lookup in ref-walk, but not the full + path walk. + +Where ref-walk uses a stable, refcounted ``parent'' to walk the remaining +path string, rcu-walk uses a d_seq protected snapshot. When looking up a +child of this parent snapshot, we open d_seq critical section on the child +before closing d_seq critical section on the parent. This gives an interlocking +ladder of snapshots to walk down. + + + proc 101 + /----------------\ + / comm: "vi" \ + / fs.root: dentry0 \ + \ fs.cwd: dentry2 / + \ / + \----------------/ + +So when vi wants to open("/home/npiggin/test.c", O_RDWR), then it will +start from current->fs->root, which is a pinned dentry. Alternatively, +"./test.c" would start from cwd; both names refer to the same path in +the context of proc101. + + dentry 0 + +---------------------+ rcu-walk begins here, we note d_seq, check the + | name: "/" | inode's permission, and then look up the next + | inode: 10 | path element which is "home"... + | children:"home", ...| + +---------------------+ + | + dentry 1 V + +---------------------+ ... which brings us here. We find dentry1 via + | name: "home" | hash lookup, then note d_seq and compare name + | inode: 678 | string and parent pointer. When we have a match, + | children:"npiggin" | we now recheck the d_seq of dentry0. Then we + +---------------------+ check inode and look up the next element. + | + dentry2 V + +---------------------+ Note: if dentry0 is now modified, lookup is + | name: "npiggin" | not necessarily invalid, so we need only keep a + | inode: 543 | parent for d_seq verification, and grandparents + | children:"a.c", ... | can be forgotten. + +---------------------+ + | + dentry3 V + +---------------------+ At this point we have our destination dentry. + | name: "a.c" | We now take its d_lock, verify d_seq of this + | inode: 14221 | dentry. If that checks out, we can increment + | children:NULL | its refcount because we're holding d_lock. + +---------------------+ + +Taking a refcount on a dentry from rcu-walk mode, by taking its d_lock, +re-checking its d_seq, and then incrementing its refcount is called +"dropping rcu" or dropping from rcu-walk into ref-walk mode. + +It is, in some sense, a bit of a house of cards. If the seqcount check of the +parent snapshot fails, the house comes down, because we had closed the d_seq +section on the grandparent, so we have nothing left to stand on. In that case, +the path walk must be fully restarted (which we do in ref-walk mode, to avoid +live locks). It is costly to have a full restart, but fortunately they are +quite rare. + +When we reach a point where sleeping is required, or a filesystem callout +requires ref-walk, then instead of restarting the walk, we attempt to drop rcu +at the last known good dentry we have. Avoiding a full restart in ref-walk in +these cases is fundamental for performance and scalability because blocking +operations such as creates and unlinks are not uncommon. + +The detailed design for rcu-walk is like this: +* LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. +* Take the RCU lock for the entire path walk, starting with the acquiring + of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are + not required for dentry persistence. +* synchronize_rcu is called when unregistering a filesystem, so we can + access d_ops and i_ops during rcu-walk. +* Similarly take the vfsmount lock for the entire path walk. So now mnt + refcounts are not required for persistence. Also we are free to perform mount + lookups, and to assume dentry mount points and mount roots are stable up and + down the path. +* Have a per-dentry seqlock to protect the dentry name, parent, and inode, + so we can load this tuple atomically, and also check whether any of its + members have changed. +* Dentry lookups (based on parent, candidate string tuple) recheck the parent + sequence after the child is found in case anything changed in the parent + during the path walk. +* inode is also RCU protected so we can load d_inode and use the inode for + limited things. +* i_mode, i_uid, i_gid can be tested for exec permissions during path walk. +* i_op can be loaded. +* When the destination dentry is reached, drop rcu there (ie. take d_lock, + verify d_seq, increment refcount). +* If seqlock verification fails anywhere along the path, do a full restart + of the path lookup in ref-walk mode. -ECHILD tends to be used (for want of + a better errno) to signal an rcu-walk failure. + +The cases where rcu-walk cannot continue are: +* NULL dentry (ie. any uncached path element) +* Following links + +It may be possible eventually to make following links rcu-walk aware. + +Uncached path elements will always require dropping to ref-walk mode, at the +very least because i_mutex needs to be grabbed, and objects allocated. + +Final note: +"store-free" path walking is not strictly store free. We take vfsmount lock +and refcounts (both of which can be made per-cpu), and we also store to the +stack (which is essentially CPU-local), and we also have to take locks and +refcount on final dentry. + +The point is that shared data, where practically possible, is not locked +or stored into. The result is massive improvements in performance and +scalability of path resolution. + + +Interesting statistics +====================== + +The following table gives rcu lookup statistics for a few simple workloads +(2s12c24t Westmere, debian non-graphical system). Ungraceful are attempts to +drop rcu that fail due to d_seq failure and requiring the entire path lookup +again. Other cases are successful rcu-drops that are required before the final +element, nodentry for missing dentry, revalidate for filesystem revalidate +routine requiring rcu drop, permission for permission check requiring drop, +and link for symlink traversal requiring drop. + + rcu-lookups restart nodentry link revalidate permission +bootup 47121 0 4624 1010 10283 7852 +dbench 25386793 0 6778659(26.7%) 55 549 1156 +kbuild 2696672 10 64442(2.3%) 108764(4.0%) 1 1590 +git diff 39605 0 28 2 0 106 +vfstest 24185492 4945 708725(2.9%) 1076136(4.4%) 0 2651 + +What this shows is that failed rcu-walk lookups, ie. ones that are restarted +entirely with ref-walk, are quite rare. Even the "vfstest" case which +specifically has concurrent renames/mkdir/rmdir/ creat/unlink/etc to excercise +such races is not showing a huge amount of restarts. + +Dropping from rcu-walk to ref-walk mean that we have encountered a dentry where +the reference count needs to be taken for some reason. This is either because +we have reached the target of the path walk, or because we have encountered a +condition that can't be resolved in rcu-walk mode. Ideally, we drop rcu-walk +only when we have reached the target dentry, so the other statistics show where +this does not happen. + +Note that a graceful drop from rcu-walk mode due to something such as the +dentry not existing (which can be common) is not necessarily a failure of +rcu-walk scheme, because some elements of the path may have been walked in +rcu-walk mode. The further we get from common path elements (such as cwd or +root), the less contended the dentry is likely to be. The closer we are to +common path elements, the more likely they will exist in dentry cache. + + +Papers and other documentation on dcache locking +================================================ + +1. Scaling dcache with RCU (http://linuxjournal.com/article.php?sid=7124). + +2. http://lse.sourceforge.net/locking/dcache/dcache.html + + diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index b12c89538680..07a32b42cf9c 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -216,7 +216,6 @@ had ->revalidate()) add calls in ->follow_link()/->readlink(). ->d_parent changes are not protected by BKL anymore. Read access is safe if at least one of the following is true: * filesystem has no cross-directory rename() - * dcache_lock is held * we know that parent had been locked (e.g. we are looking at ->d_parent of ->lookup() argument). * we are called from ->rename(). @@ -318,3 +317,71 @@ if it's zero is not *and* *never* *had* *been* enough. Final unlink() and iput( may happen while the inode is in the middle of ->write_inode(); e.g. if you blindly free the on-disk inode, you may end up doing that while ->write_inode() is writing to it. + +--- +[mandatory] + + .d_delete() now only advises the dcache as to whether or not to cache +unreferenced dentries, and is now only called when the dentry refcount goes to +0. Even on 0 refcount transition, it must be able to tolerate being called 0, +1, or more times (eg. constant, idempotent). + +--- +[mandatory] + + .d_compare() calling convention and locking rules are significantly +changed. Read updated documentation in Documentation/filesystems/vfs.txt (and +look at examples of other filesystems) for guidance. + +--- +[mandatory] + + .d_hash() calling convention and locking rules are significantly +changed. Read updated documentation in Documentation/filesystems/vfs.txt (and +look at examples of other filesystems) for guidance. + +--- +[mandatory] + dcache_lock is gone, replaced by fine grained locks. See fs/dcache.c +for details of what locks to replace dcache_lock with in order to protect +particular things. Most of the time, a filesystem only needs ->d_lock, which +protects *all* the dcache state of a given dentry. + +-- +[mandatory] + + Filesystems must RCU-free their inodes, if they can have been accessed +via rcu-walk path walk (basically, if the file can have had a path name in the +vfs namespace). + + i_dentry and i_rcu share storage in a union, and the vfs expects +i_dentry to be reinitialized before it is freed, so an: + + INIT_LIST_HEAD(&inode->i_dentry); + +must be done in the RCU callback. + +-- +[recommended] + vfs now tries to do path walking in "rcu-walk mode", which avoids +atomic operations and scalability hazards on dentries and inodes (see +Documentation/filesystems/path-walk.txt). d_hash and d_compare changes (above) +are examples of the changes required to support this. For more complex +filesystem callbacks, the vfs drops out of rcu-walk mode before the fs call, so +no changes are required to the filesystem. However, this is costly and loses +the benefits of rcu-walk mode. We will begin to add filesystem callbacks that +are rcu-walk aware, shown below. Filesystems should take advantage of this +where possible. + +-- +[mandatory] + d_revalidate is a callback that is made on every path element (if +the filesystem provides it), which requires dropping out of rcu-walk mode. This +may now be called in rcu-walk mode (nd->flags & LOOKUP_RCU). -ECHILD should be +returned if the filesystem cannot handle rcu-walk. See +Documentation/filesystems/vfs.txt for more details. + + permission and check_acl are inode permission checks that are called +on many or all directory inodes on the way down a path walk (to check for +exec permission). These must now be rcu-walk aware (flags & IPERM_RCU). See +Documentation/filesystems/vfs.txt for more details. diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index e73df2722ff3..9471225212c4 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1181,6 +1181,30 @@ Table 1-12: Files in /proc/fs/ext4/<devname> mb_groups details of multiblock allocator buddy cache of free blocks .............................................................................. +2.0 /proc/consoles +------------------ +Shows registered system console lines. + +To see which character device lines are currently used for the system console +/dev/console, you may simply look into the file /proc/consoles: + + > cat /proc/consoles + tty0 -WU (ECp) 4:7 + ttyS0 -W- (Ep) 4:64 + +The columns are: + + device name of the device + operations R = can do read operations + W = can do write operations + U = can do unblank + flags E = it is enabled + C = it is prefered console + B = it is primary boot console + p = it is used for printk buffer + b = it is not a TTY but a Braille device + a = it is safe to use when cpu is offline + major:minor major and minor number of the device separated by a colon ------------------------------------------------------------------------------ Summary diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 20899e095e7e..fbb324e2bd43 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -325,7 +325,8 @@ struct inode_operations { void * (*follow_link) (struct dentry *, struct nameidata *); void (*put_link) (struct dentry *, struct nameidata *, void *); void (*truncate) (struct inode *); - int (*permission) (struct inode *, int, struct nameidata *); + int (*permission) (struct inode *, int, unsigned int); + int (*check_acl)(struct inode *, int, unsigned int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); @@ -414,6 +415,13 @@ otherwise noted. permission: called by the VFS to check for access rights on a POSIX-like filesystem. + May be called in rcu-walk mode (flags & IPERM_RCU). If in rcu-walk + mode, the filesystem must check the permission without blocking or + storing to the inode. + + If a situation is encountered that rcu-walk cannot handle, return + -ECHILD and it will be called again in ref-walk mode. + setattr: called by the VFS to set attributes for a file. This method is called by chmod(2) and related system calls. @@ -847,9 +855,12 @@ defined: struct dentry_operations { int (*d_revalidate)(struct dentry *, struct nameidata *); - int (*d_hash) (struct dentry *, struct qstr *); - int (*d_compare) (struct dentry *, struct qstr *, struct qstr *); - int (*d_delete)(struct dentry *); + int (*d_hash)(const struct dentry *, const struct inode *, + struct qstr *); + int (*d_compare)(const struct dentry *, const struct inode *, + const struct dentry *, const struct inode *, + unsigned int, const char *, const struct qstr *); + int (*d_delete)(const struct dentry *); void (*d_release)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); @@ -860,13 +871,45 @@ struct dentry_operations { dcache. Most filesystems leave this as NULL, because all their dentries in the dcache are valid - d_hash: called when the VFS adds a dentry to the hash table + d_revalidate may be called in rcu-walk mode (nd->flags & LOOKUP_RCU). + If in rcu-walk mode, the filesystem must revalidate the dentry without + blocking or storing to the dentry, d_parent and d_inode should not be + used without care (because they can go NULL), instead nd->inode should + be used. + + If a situation is encountered that rcu-walk cannot handle, return + -ECHILD and it will be called again in ref-walk mode. + + d_hash: called when the VFS adds a dentry to the hash table. The first + dentry passed to d_hash is the parent directory that the name is + to be hashed into. The inode is the dentry's inode. + + Same locking and synchronisation rules as d_compare regarding + what is safe to dereference etc. + + d_compare: called to compare a dentry name with a given name. The first + dentry is the parent of the dentry to be compared, the second is + the parent's inode, then the dentry and inode (may be NULL) of the + child dentry. len and name string are properties of the dentry to be + compared. qstr is the name to compare it with. + + Must be constant and idempotent, and should not take locks if + possible, and should not or store into the dentry or inodes. + Should not dereference pointers outside the dentry or inodes without + lots of care (eg. d_parent, d_inode, d_name should not be used). + + However, our vfsmount is pinned, and RCU held, so the dentries and + inodes won't disappear, neither will our sb or filesystem module. + ->i_sb and ->d_sb may be used. - d_compare: called when a dentry should be compared with another + It is a tricky calling convention because it needs to be called under + "rcu-walk", ie. without any locks or references on things. - d_delete: called when the last reference to a dentry is - deleted. This means no-one is using the dentry, however it is - still valid and in the dcache + d_delete: called when the last reference to a dentry is dropped and the + dcache is deciding whether or not to cache it. Return 1 to delete + immediately, or 0 to cache the dentry. Default is NULL which means to + always cache a reachable dentry. d_delete must be constant and + idempotent. d_release: called when a dentry is really deallocated @@ -910,14 +953,11 @@ manipulate dentries: the usage count) dput: close a handle for a dentry (decrements the usage count). If - the usage count drops to 0, the "d_delete" method is called - and the dentry is placed on the unused list if the dentry is - still in its parents hash list. Putting the dentry on the - unused list just means that if the system needs some RAM, it - goes through the unused list of dentries and deallocates them. - If the dentry has already been unhashed and the usage count - drops to 0, in this case the dentry is deallocated after the - "d_delete" method is called + the usage count drops to 0, and the dentry is still in its + parent's hash, the "d_delete" method is called to check whether + it should be cached. If it should not be cached, or if the dentry + is not hashed, it is deleted. Otherwise cached dentries are put + into an LRU list to be reclaimed on memory shortage. d_drop: this unhashes a dentry from its parents hash list. A subsequent call to dput() will deallocate the dentry if its diff --git a/Documentation/hwmon/ds620 b/Documentation/hwmon/ds620 new file mode 100644 index 000000000000..1fbe3cd916cc --- /dev/null +++ b/Documentation/hwmon/ds620 @@ -0,0 +1,34 @@ +Kernel driver ds620 +=================== + +Supported chips: + * Dallas Semiconductor DS620 + Prefix: 'ds620' + Datasheet: Publicly available at the Dallas Semiconductor website + http://www.dalsemi.com/ + +Authors: + Roland Stigge <stigge@antcom.de> + based on ds1621.c by + Christian W. Zuckschwerdt <zany@triq.net> + +Description +----------- + +The DS620 is a (one instance) digital thermometer and thermostat. It has both +high and low temperature limits which can be user defined (i.e. programmed +into non-volatile on-chip registers). Temperature range is -55 degree Celsius +to +125. Between 0 and 70 degree Celsius, accuracy is 0.5 Kelvin. The value +returned via sysfs displays post decimal positions. + +The thermostat function works as follows: When configured via platform_data +(struct ds620_platform_data) .pomode == 0 (default), the thermostat output pin +PO is always low. If .pomode == 1, the thermostat is in PO_LOW mode. I.e., the +output pin PO becomes active when the temperature falls below temp1_min and +stays active until the temperature goes above temp1_max. + +Likewise, with .pomode == 2, the thermostat is in PO_HIGH mode. I.e., the PO +output pin becomes active when the temperature goes above temp1_max and stays +active until the temperature falls below temp1_min. + +The PO output pin of the DS620 operates active-low. diff --git a/Documentation/hwmon/sht21 b/Documentation/hwmon/sht21 new file mode 100644 index 000000000000..db17fda45c3e --- /dev/null +++ b/Documentation/hwmon/sht21 @@ -0,0 +1,49 @@ +Kernel driver sht21 +=================== + +Supported chips: + * Sensirion SHT21 + Prefix: 'sht21' + Addresses scanned: none + Datasheet: Publicly available at the Sensirion website + http://www.sensirion.com/en/pdf/product_information/Datasheet-humidity-sensor-SHT21.pdf + + * Sensirion SHT25 + Prefix: 'sht21' + Addresses scanned: none + Datasheet: Publicly available at the Sensirion website + http://www.sensirion.com/en/pdf/product_information/Datasheet-humidity-sensor-SHT25.pdf + +Author: + Urs Fleisch <urs.fleisch@sensirion.com> + +Description +----------- + +The SHT21 and SHT25 are humidity and temperature sensors in a DFN package of +only 3 x 3 mm footprint and 1.1 mm height. The difference between the two +devices is the higher level of precision of the SHT25 (1.8% relative humidity, +0.2 degree Celsius) compared with the SHT21 (2.0% relative humidity, +0.3 degree Celsius). + +The devices communicate with the I2C protocol. All sensors are set to the same +I2C address 0x40, so an entry with I2C_BOARD_INFO("sht21", 0x40) can be used +in the board setup code. + +sysfs-Interface +--------------- + +temp1_input - temperature input +humidity1_input - humidity input + +Notes +----- + +The driver uses the default resolution settings of 12 bit for humidity and 14 +bit for temperature, which results in typical measurement times of 22 ms for +humidity and 66 ms for temperature. To keep self heating below 0.1 degree +Celsius, the device should not be active for more than 10% of the time, +e.g. maximum two measurements per second at the given resolution. + +Different resolutions, the on-chip heater, using the CRC checksum and reading +the serial number are not supported yet. diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface index 645699010551..c6559f153589 100644 --- a/Documentation/hwmon/sysfs-interface +++ b/Documentation/hwmon/sysfs-interface @@ -384,10 +384,20 @@ curr[1-*]_min Current min value. Unit: milliampere RW +curr[1-*]_lcrit Current critical low value + Unit: milliampere + RW + +curr[1-*]_crit Current critical high value. + Unit: milliampere + RW + curr[1-*]_input Current input value Unit: milliampere RO +Also see the Alarms section for status flags associated with currents. + ********* * Power * ********* @@ -450,13 +460,6 @@ power[1-*]_accuracy Accuracy of the power meter. Unit: Percent RO -power[1-*]_alarm 1 if the system is drawing more power than the - cap allows; 0 otherwise. A poll notification is - sent to this file when the power use exceeds the - cap. This file only appears if the cap is known - to be enforced by hardware. - RO - power[1-*]_cap If power use rises above this limit, the system should take action to reduce power use. A poll notification is sent to this file if the @@ -479,6 +482,20 @@ power[1-*]_cap_min Minimum cap that can be set. Unit: microWatt RO +power[1-*]_max Maximum power. + Unit: microWatt + RW + +power[1-*]_crit Critical maximum power. + If power rises to or above this limit, the + system is expected take drastic action to reduce + power consumption, such as a system shutdown or + a forced powerdown of some devices. + Unit: microWatt + RW + +Also see the Alarms section for status flags associated with power readings. + ********** * Energy * ********** @@ -488,6 +505,15 @@ energy[1-*]_input Cumulative energy use RO +************ +* Humidity * +************ + +humidity[1-*]_input Humidity + Unit: milli-percent (per cent mille, pcm) + RO + + ********** * Alarms * ********** @@ -501,6 +527,7 @@ implementation. in[0-*]_alarm curr[1-*]_alarm +power[1-*]_alarm fan[1-*]_alarm temp[1-*]_alarm Channel alarm @@ -512,12 +539,20 @@ OR in[0-*]_min_alarm in[0-*]_max_alarm +in[0-*]_lcrit_alarm +in[0-*]_crit_alarm curr[1-*]_min_alarm curr[1-*]_max_alarm +curr[1-*]_lcrit_alarm +curr[1-*]_crit_alarm +power[1-*]_cap_alarm +power[1-*]_max_alarm +power[1-*]_crit_alarm fan[1-*]_min_alarm fan[1-*]_max_alarm temp[1-*]_min_alarm temp[1-*]_max_alarm +temp[1-*]_lcrit_alarm temp[1-*]_crit_alarm temp[1-*]_emergency_alarm Limit alarm diff --git a/Documentation/i2c/muxes/gpio-i2cmux b/Documentation/i2c/muxes/gpio-i2cmux new file mode 100644 index 000000000000..811cd78d4cdc --- /dev/null +++ b/Documentation/i2c/muxes/gpio-i2cmux @@ -0,0 +1,65 @@ +Kernel driver gpio-i2cmux + +Author: Peter Korsgaard <peter.korsgaard@barco.com> + +Description +----------- + +gpio-i2cmux is an i2c mux driver providing access to I2C bus segments +from a master I2C bus and a hardware MUX controlled through GPIO pins. + +E.G.: + + ---------- ---------- Bus segment 1 - - - - - + | | SCL/SDA | |-------------- | | + | |------------| | + | | | | Bus segment 2 | | + | Linux | GPIO 1..N | MUX |--------------- Devices + | |------------| | | | + | | | | Bus segment M + | | | |---------------| | + ---------- ---------- - - - - - + +SCL/SDA of the master I2C bus is multiplexed to bus segment 1..M +according to the settings of the GPIO pins 1..N. + +Usage +----- + +gpio-i2cmux uses the platform bus, so you need to provide a struct +platform_device with the platform_data pointing to a struct +gpio_i2cmux_platform_data with the I2C adapter number of the master +bus, the number of bus segments to create and the GPIO pins used +to control it. See include/linux/gpio-i2cmux.h for details. + +E.G. something like this for a MUX providing 4 bus segments +controlled through 3 GPIO pins: + +#include <linux/gpio-i2cmux.h> +#include <linux/platform_device.h> + +static const unsigned myboard_gpiomux_gpios[] = { + AT91_PIN_PC26, AT91_PIN_PC25, AT91_PIN_PC24 +}; + +static const unsigned myboard_gpiomux_values[] = { + 0, 1, 2, 3 +}; + +static struct gpio_i2cmux_platform_data myboard_i2cmux_data = { + .parent = 1, + .base_nr = 2, /* optional */ + .values = myboard_gpiomux_values, + .n_values = ARRAY_SIZE(myboard_gpiomux_values), + .gpios = myboard_gpiomux_gpios, + .n_gpios = ARRAY_SIZE(myboard_gpiomux_gpios), + .idle = 4, /* optional */ +}; + +static struct platform_device myboard_i2cmux = { + .name = "gpio-i2cmux", + .id = 0, + .dev = { + .platform_data = &myboard_i2cmux_data, + }, +}; diff --git a/Documentation/input/cma3000_d0x.txt b/Documentation/input/cma3000_d0x.txt new file mode 100644 index 000000000000..29d088db4afd --- /dev/null +++ b/Documentation/input/cma3000_d0x.txt @@ -0,0 +1,115 @@ +Kernel driver for CMA3000-D0x +============================ + +Supported chips: +* VTI CMA3000-D0x +Datasheet: + CMA3000-D0X Product Family Specification 8281000A.02.pdf + <http://www.vti.fi/en/> + +Author: Hemanth V <hemanthv@ti.com> + + +Description +----------- +CMA3000 Tri-axis accelerometer supports Motion detect, Measurement and +Free fall modes. + +Motion Detect Mode: Its the low power mode where interrupts are generated only +when motion exceeds the defined thresholds. + +Measurement Mode: This mode is used to read the acceleration data on X,Y,Z +axis and supports 400, 100, 40 Hz sample frequency. + +Free fall Mode: This mode is intended to save system resources. + +Threshold values: Chip supports defining threshold values for above modes +which includes time and g value. Refer product specifications for more details. + +CMA3000 chip supports mutually exclusive I2C and SPI interfaces for +communication, currently the driver supports I2C based communication only. +Initial configuration for bus mode is set in non volatile memory and can later +be modified through bus interface command. + +Driver reports acceleration data through input subsystem. It generates ABS_MISC +event with value 1 when free fall is detected. + +Platform data need to be configured for initial default values. + +Platform Data +------------- +fuzz_x: Noise on X Axis + +fuzz_y: Noise on Y Axis + +fuzz_z: Noise on Z Axis + +g_range: G range in milli g i.e 2000 or 8000 + +mode: Default Operating mode + +mdthr: Motion detect g range threshold value + +mdfftmr: Motion detect and free fall time threshold value + +ffthr: Free fall g range threshold value + +Input Interface +-------------- +Input driver version is 1.0.0 +Input device ID: bus 0x18 vendor 0x0 product 0x0 version 0x0 +Input device name: "cma3000-accelerometer" +Supported events: + Event type 0 (Sync) + Event type 3 (Absolute) + Event code 0 (X) + Value 47 + Min -8000 + Max 8000 + Fuzz 200 + Event code 1 (Y) + Value -28 + Min -8000 + Max 8000 + Fuzz 200 + Event code 2 (Z) + Value 905 + Min -8000 + Max 8000 + Fuzz 200 + Event code 40 (Misc) + Value 0 + Min 0 + Max 1 + Event type 4 (Misc) + + +Register/Platform parameters Description +---------------------------------------- + +mode: + 0: power down mode + 1: 100 Hz Measurement mode + 2: 400 Hz Measurement mode + 3: 40 Hz Measurement mode + 4: Motion Detect mode (default) + 5: 100 Hz Free fall mode + 6: 40 Hz Free fall mode + 7: Power off mode + +grange: + 2000: 2000 mg or 2G Range + 8000: 8000 mg or 8G Range + +mdthr: + X: X * 71mg (8G Range) + X: X * 18mg (2G Range) + +mdfftmr: + X: (X & 0x70) * 100 ms (MDTMR) + (X & 0x0F) * 2.5 ms (FFTMR 400 Hz) + (X & 0x0F) * 10 ms (FFTMR 100 Hz) + +ffthr: + X: (X >> 2) * 18mg (2G Range) + X: (X & 0x0F) * 71 mg (8G Range) diff --git a/Documentation/input/multi-touch-protocol.txt b/Documentation/input/multi-touch-protocol.txt index bdcba154b83e..71536e78406f 100644 --- a/Documentation/input/multi-touch-protocol.txt +++ b/Documentation/input/multi-touch-protocol.txt @@ -1,6 +1,6 @@ Multi-touch (MT) Protocol ------------------------- - Copyright (C) 2009 Henrik Rydberg <rydberg@euromail.se> + Copyright (C) 2009-2010 Henrik Rydberg <rydberg@euromail.se> Introduction @@ -161,19 +161,24 @@ against the glass. The inner region will increase, and in general, the ratio ABS_MT_TOUCH_MAJOR / ABS_MT_WIDTH_MAJOR, which is always smaller than unity, is related to the contact pressure. For pressure-based devices, ABS_MT_PRESSURE may be used to provide the pressure on the contact area -instead. +instead. Devices capable of contact hovering can use ABS_MT_DISTANCE to +indicate the distance between the contact and the surface. In addition to the MAJOR parameters, the oval shape of the contact can be described by adding the MINOR parameters, such that MAJOR and MINOR are the major and minor axis of an ellipse. Finally, the orientation of the oval shape can be describe with the ORIENTATION parameter. +For type A devices, further specification of the touch shape is possible +via ABS_MT_BLOB_ID. + The ABS_MT_TOOL_TYPE may be used to specify whether the touching tool is a -contact or a pen or something else. Devices with more granular information -may specify general shapes as blobs, i.e., as a sequence of rectangular -shapes grouped together by an ABS_MT_BLOB_ID. Finally, for the few devices -that currently support it, the ABS_MT_TRACKING_ID event may be used to -report contact tracking from hardware [5]. +finger or a pen or something else. Finally, the ABS_MT_TRACKING_ID event +may be used to track identified contacts over time [5]. + +In the type B protocol, ABS_MT_TOOL_TYPE and ABS_MT_TRACKING_ID are +implicitly handled by input core; drivers should instead call +input_mt_report_slot_state(). Event Semantics @@ -213,6 +218,12 @@ The pressure, in arbitrary units, on the contact area. May be used instead of TOUCH and WIDTH for pressure-based devices or any device with a spatial signal intensity distribution. +ABS_MT_DISTANCE + +The distance, in surface units, between the contact and the surface. Zero +distance means the contact is touching the surface. A positive number means +the contact is hovering above the surface. + ABS_MT_ORIENTATION The orientation of the ellipse. The value should describe a signed quarter @@ -240,21 +251,24 @@ ABS_MT_TOOL_TYPE The type of approaching tool. A lot of kernel drivers cannot distinguish between different tool types, such as a finger or a pen. In such cases, the event should be omitted. The protocol currently supports MT_TOOL_FINGER and -MT_TOOL_PEN [2]. +MT_TOOL_PEN [2]. For type B devices, this event is handled by input core; +drivers should instead use input_mt_report_slot_state(). ABS_MT_BLOB_ID The BLOB_ID groups several packets together into one arbitrarily shaped -contact. This is a low-level anonymous grouping for type A devices, and +contact. The sequence of points forms a polygon which defines the shape of +the contact. This is a low-level anonymous grouping for type A devices, and should not be confused with the high-level trackingID [5]. Most type A devices do not have blob capability, so drivers can safely omit this event. ABS_MT_TRACKING_ID The TRACKING_ID identifies an initiated contact throughout its life cycle -[5]. This event is mandatory for type B devices. The value range of the -TRACKING_ID should be large enough to ensure unique identification of a -contact maintained over an extended period of time. +[5]. The value range of the TRACKING_ID should be large enough to ensure +unique identification of a contact maintained over an extended period of +time. For type B devices, this event is handled by input core; drivers +should instead use input_mt_report_slot_state(). Event Computation @@ -301,18 +315,19 @@ and with ORIENTATION, one can detect twisting of fingers. Notes ----- -In order to stay compatible with existing applications, the data -reported in a finger packet must not be recognized as single-touch -events. In addition, all finger data must bypass input filtering, -since subsequent events of the same type refer to different fingers. +In order to stay compatible with existing applications, the data reported +in a finger packet must not be recognized as single-touch events. + +For type A devices, all finger data bypasses input filtering, since +subsequent events of the same type refer to different fingers. -The first kernel driver to utilize the MT protocol is the bcm5974 driver, -where examples can be found. +For example usage of the type A protocol, see the bcm5974 driver. For +example usage of the type B protocol, see the hid-egalax driver. [1] With the extension ABS_MT_APPROACH_X and ABS_MT_APPROACH_Y, the difference between the contact position and the approaching tool position could be used to derive tilt. [2] The list can of course be extended. -[3] Multitouch X driver project: http://bitmath.org/code/multitouch/. +[3] The mtdev project: http://bitmath.org/code/mtdev/. [4] See the section on event computation. [5] See the section on finger tracking. diff --git a/Documentation/kbuild/kbuild.txt b/Documentation/kbuild/kbuild.txt index 1e5165aa9e4e..4a990317b84a 100644 --- a/Documentation/kbuild/kbuild.txt +++ b/Documentation/kbuild/kbuild.txt @@ -73,6 +73,14 @@ Specify the output directory when building the kernel. The output directory can also be specified using "O=...". Setting "O=..." takes precedence over KBUILD_OUTPUT. +KBUILD_DEBARCH +-------------------------------------------------- +For the deb-pkg target, allows overriding the normal heuristics deployed by +deb-pkg. Normally deb-pkg attempts to guess the right architecture based on +the UTS_MACHINE variable, and on some architectures also the kernel config. +The value of KBUILD_DEBARCH is assumed (not checked) to be a valid Debian +architecture. + ARCH -------------------------------------------------- Set ARCH to the architecture to be built. diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt index 2fe93ca7c77c..b507d61fd41c 100644 --- a/Documentation/kbuild/kconfig-language.txt +++ b/Documentation/kbuild/kconfig-language.txt @@ -112,7 +112,6 @@ applicable everywhere (see syntax). (no prompts anywhere) and for symbols with no dependencies. That will limit the usefulness but on the other hand avoid the illegal configurations all over. - kconfig should one day warn about such things. - numerical ranges: "range" <symbol> <symbol> ["if" <expr>] This allows to limit the range of possible input values for int @@ -268,7 +267,7 @@ separate list of options. choices: - "choice" + "choice" [symbol] <choice options> <choice block> "endchoice" @@ -282,6 +281,10 @@ single driver can be compiled/loaded into the kernel, but all drivers can be compiled as modules. A choice accepts another option "optional", which allows to set the choice to 'n' and no entry needs to be selected. +If no [symbol] is associated with a choice, then you can not have multiple +definitions of that choice. If a [symbol] is associated to the choice, +then you may define the same choice (ie. with the same entries) in another +place. comment: diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt index 0ef00bd6e54d..86e3cd0d26a0 100644 --- a/Documentation/kbuild/makefiles.txt +++ b/Documentation/kbuild/makefiles.txt @@ -1136,6 +1136,21 @@ When kbuild executes, the following steps are followed (roughly): resulting in the target file being recompiled for no obvious reason. + dtc + Create flattend device tree blob object suitable for linking + into vmlinux. Device tree blobs linked into vmlinux are placed + in an init section in the image. Platform code *must* copy the + blob to non-init memory prior to calling unflatten_device_tree(). + + Example: + #arch/x86/platform/ce4100/Makefile + clean-files := *dtb.S + + DTC_FLAGS := -p 1024 + obj-y += foo.dtb.o + + $(obj)/%.dtb: $(src)/%.dts + $(call cmd,dtc) --- 6.7 Custom kbuild commands diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index f3dc951e949f..ed3708f8d0db 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -403,6 +403,10 @@ and is between 256 and 4096 characters. It is defined in the file bttv.pll= See Documentation/video4linux/bttv/Insmod-options bttv.tuner= and Documentation/video4linux/bttv/CARDLIST + bulk_remove=off [PPC] This parameter disables the use of the pSeries + firmware feature for flushing multiple hpte entries + at a time. + c101= [NET] Moxa C101 synchronous serial card cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection. @@ -1490,6 +1494,10 @@ and is between 256 and 4096 characters. It is defined in the file mtdparts= [MTD] See drivers/mtd/cmdlinepart.c. + multitce=off [PPC] This parameter disables the use of the pSeries + firmware feature for updating multiple TCE entries + at a time. + onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock] diff --git a/Documentation/keys-trusted-encrypted.txt b/Documentation/keys-trusted-encrypted.txt new file mode 100644 index 000000000000..8fb79bc1ac4b --- /dev/null +++ b/Documentation/keys-trusted-encrypted.txt @@ -0,0 +1,145 @@ + Trusted and Encrypted Keys + +Trusted and Encrypted Keys are two new key types added to the existing kernel +key ring service. Both of these new types are variable length symmetic keys, +and in both cases all keys are created in the kernel, and user space sees, +stores, and loads only encrypted blobs. Trusted Keys require the availability +of a Trusted Platform Module (TPM) chip for greater security, while Encrypted +Keys can be used on any system. All user level blobs, are displayed and loaded +in hex ascii for convenience, and are integrity verified. + +Trusted Keys use a TPM both to generate and to seal the keys. Keys are sealed +under a 2048 bit RSA key in the TPM, and optionally sealed to specified PCR +(integrity measurement) values, and only unsealed by the TPM, if PCRs and blob +integrity verifications match. A loaded Trusted Key can be updated with new +(future) PCR values, so keys are easily migrated to new pcr values, such as +when the kernel and initramfs are updated. The same key can have many saved +blobs under different PCR values, so multiple boots are easily supported. + +By default, trusted keys are sealed under the SRK, which has the default +authorization value (20 zeros). This can be set at takeownership time with the +trouser's utility: "tpm_takeownership -u -z". + +Usage: + keyctl add trusted name "new keylen [options]" ring + keyctl add trusted name "load hex_blob [pcrlock=pcrnum]" ring + keyctl update key "update [options]" + keyctl print keyid + + options: + keyhandle= ascii hex value of sealing key default 0x40000000 (SRK) + keyauth= ascii hex auth for sealing key default 0x00...i + (40 ascii zeros) + blobauth= ascii hex auth for sealed data default 0x00... + (40 ascii zeros) + blobauth= ascii hex auth for sealed data default 0x00... + (40 ascii zeros) + pcrinfo= ascii hex of PCR_INFO or PCR_INFO_LONG (no default) + pcrlock= pcr number to be extended to "lock" blob + migratable= 0|1 indicating permission to reseal to new PCR values, + default 1 (resealing allowed) + +"keyctl print" returns an ascii hex copy of the sealed key, which is in standard +TPM_STORED_DATA format. The key length for new keys are always in bytes. +Trusted Keys can be 32 - 128 bytes (256 - 1024 bits), the upper limit is to fit +within the 2048 bit SRK (RSA) keylength, with all necessary structure/padding. + +Encrypted keys do not depend on a TPM, and are faster, as they use AES for +encryption/decryption. New keys are created from kernel generated random +numbers, and are encrypted/decrypted using a specified 'master' key. The +'master' key can either be a trusted-key or user-key type. The main +disadvantage of encrypted keys is that if they are not rooted in a trusted key, +they are only as secure as the user key encrypting them. The master user key +should therefore be loaded in as secure a way as possible, preferably early in +boot. + +Usage: + keyctl add encrypted name "new key-type:master-key-name keylen" ring + keyctl add encrypted name "load hex_blob" ring + keyctl update keyid "update key-type:master-key-name" + +where 'key-type' is either 'trusted' or 'user'. + +Examples of trusted and encrypted key usage: + +Create and save a trusted key named "kmk" of length 32 bytes: + + $ keyctl add trusted kmk "new 32" @u + 440502848 + + $ keyctl show + Session Keyring + -3 --alswrv 500 500 keyring: _ses + 97833714 --alswrv 500 -1 \_ keyring: _uid.500 + 440502848 --alswrv 500 500 \_ trusted: kmk + + $ keyctl print 440502848 + 0101000000000000000001005d01b7e3f4a6be5709930f3b70a743cbb42e0cc95e18e915 + 3f60da455bbf1144ad12e4f92b452f966929f6105fd29ca28e4d4d5a031d068478bacb0b + 27351119f822911b0a11ba3d3498ba6a32e50dac7f32894dd890eb9ad578e4e292c83722 + a52e56a097e6a68b3f56f7a52ece0cdccba1eb62cad7d817f6dc58898b3ac15f36026fec + d568bd4a706cb60bb37be6d8f1240661199d640b66fb0fe3b079f97f450b9ef9c22c6d5d + dd379f0facd1cd020281dfa3c70ba21a3fa6fc2471dc6d13ecf8298b946f65345faa5ef0 + f1f8fff03ad0acb083725535636addb08d73dedb9832da198081e5deae84bfaf0409c22b + e4a8aea2b607ec96931e6f4d4fe563ba + + $ keyctl pipe 440502848 > kmk.blob + +Load a trusted key from the saved blob: + + $ keyctl add trusted kmk "load `cat kmk.blob`" @u + 268728824 + + $ keyctl print 268728824 + 0101000000000000000001005d01b7e3f4a6be5709930f3b70a743cbb42e0cc95e18e915 + 3f60da455bbf1144ad12e4f92b452f966929f6105fd29ca28e4d4d5a031d068478bacb0b + 27351119f822911b0a11ba3d3498ba6a32e50dac7f32894dd890eb9ad578e4e292c83722 + a52e56a097e6a68b3f56f7a52ece0cdccba1eb62cad7d817f6dc58898b3ac15f36026fec + d568bd4a706cb60bb37be6d8f1240661199d640b66fb0fe3b079f97f450b9ef9c22c6d5d + dd379f0facd1cd020281dfa3c70ba21a3fa6fc2471dc6d13ecf8298b946f65345faa5ef0 + f1f8fff03ad0acb083725535636addb08d73dedb9832da198081e5deae84bfaf0409c22b + e4a8aea2b607ec96931e6f4d4fe563ba + +Reseal a trusted key under new pcr values: + + $ keyctl update 268728824 "update pcrinfo=`cat pcr.blob`" + $ keyctl print 268728824 + 010100000000002c0002800093c35a09b70fff26e7a98ae786c641e678ec6ffb6b46d805 + 77c8a6377aed9d3219c6dfec4b23ffe3000001005d37d472ac8a44023fbb3d18583a4f73 + d3a076c0858f6f1dcaa39ea0f119911ff03f5406df4f7f27f41da8d7194f45c9f4e00f2e + df449f266253aa3f52e55c53de147773e00f0f9aca86c64d94c95382265968c354c5eab4 + 9638c5ae99c89de1e0997242edfb0b501744e11ff9762dfd951cffd93227cc513384e7e6 + e782c29435c7ec2edafaa2f4c1fe6e7a781b59549ff5296371b42133777dcc5b8b971610 + 94bc67ede19e43ddb9dc2baacad374a36feaf0314d700af0a65c164b7082401740e489c9 + 7ef6a24defe4846104209bf0c3eced7fa1a672ed5b125fc9d8cd88b476a658a4434644ef + df8ae9a178e9f83ba9f08d10fa47e4226b98b0702f06b3b8 + +Create and save an encrypted key "evm" using the above trusted key "kmk": + + $ keyctl add encrypted evm "new trusted:kmk 32" @u + 159771175 + + $ keyctl print 159771175 + trusted:kmk 32 2375725ad57798846a9bbd240de8906f006e66c03af53b1b382dbbc55 + be2a44616e4959430436dc4f2a7a9659aa60bb4652aeb2120f149ed197c564e024717c64 + 5972dcb82ab2dde83376d82b2e3c09ffc + + $ keyctl pipe 159771175 > evm.blob + +Load an encrypted key "evm" from saved blob: + + $ keyctl add encrypted evm "load `cat evm.blob`" @u + 831684262 + + $ keyctl print 831684262 + trusted:kmk 32 2375725ad57798846a9bbd240de8906f006e66c03af53b1b382dbbc55 + be2a44616e4959430436dc4f2a7a9659aa60bb4652aeb2120f149ed197c564e024717c64 + 5972dcb82ab2dde83376d82b2e3c09ffc + + +The initial consumer of trusted keys is EVM, which at boot time needs a high +quality symmetric key for HMAC protection of file metadata. The use of a +trusted key provides strong guarantees that the EVM key has not been +compromised by a user level problem, and when sealed to specific boot PCR +values, protects against boot and offline attacks. Other uses for trusted and +encrypted keys, such as for disk and file encryption are anticipated. diff --git a/Documentation/make/headers_install.txt b/Documentation/make/headers_install.txt index f2481cabffcb..951eb9f1e040 100644 --- a/Documentation/make/headers_install.txt +++ b/Documentation/make/headers_install.txt @@ -39,8 +39,9 @@ INSTALL_HDR_PATH indicates where to install the headers. It defaults to The command "make headers_install_all" exports headers for all architectures simultaneously. (This is mostly of interest to distribution maintainers, who create an architecture-independent tarball from the resulting include -directory.) Remember to provide the appropriate linux/asm directory via "mv" -or "ln -s" before building a C library with headers exported this way. +directory.) You also can use HDR_ARCH_LIST to specify list of architectures. +Remember to provide the appropriate linux/asm directory via "mv" or "ln -s" +before building a C library with headers exported this way. The kernel header export infrastructure is maintained by David Woodhouse <dwmw2@infradead.org>. diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt index b395ca6a49f2..811872b45bee 100644 --- a/Documentation/networking/dccp.txt +++ b/Documentation/networking/dccp.txt @@ -167,6 +167,7 @@ rx_ccid = 2 seq_window = 100 The initial sequence window (sec. 7.5.2) of the sender. This influences the local ackno validity and the remote seqno validity windows (7.5.1). + Values in the range Wmin = 32 (RFC 4340, 7.5.2) up to 2^32-1 can be set. tx_qlen = 5 The size of the transmit buffer in packets. A value of 0 corresponds diff --git a/Documentation/power/drivers-testing.txt b/Documentation/power/drivers-testing.txt index 7f7a737f7f9f..638afdf4d6b8 100644 --- a/Documentation/power/drivers-testing.txt +++ b/Documentation/power/drivers-testing.txt @@ -23,10 +23,10 @@ Once you have resolved the suspend/resume-related problems with your test system without the new driver, you are ready to test it: a) Build the driver as a module, load it and try the test modes of hibernation - (see: Documents/power/basic-pm-debugging.txt, 1). + (see: Documentation/power/basic-pm-debugging.txt, 1). b) Load the driver and attempt to hibernate in the "reboot", "shutdown" and - "platform" modes (see: Documents/power/basic-pm-debugging.txt, 1). + "platform" modes (see: Documentation/power/basic-pm-debugging.txt, 1). c) Compile the driver directly into the kernel and try the test modes of hibernation. @@ -34,12 +34,12 @@ c) Compile the driver directly into the kernel and try the test modes of d) Attempt to hibernate with the driver compiled directly into the kernel in the "reboot", "shutdown" and "platform" modes. -e) Try the test modes of suspend (see: Documents/power/basic-pm-debugging.txt, +e) Try the test modes of suspend (see: Documentation/power/basic-pm-debugging.txt, 2). [As far as the STR tests are concerned, it should not matter whether or not the driver is built as a module.] f) Attempt to suspend to RAM using the s2ram tool with the driver loaded - (see: Documents/power/basic-pm-debugging.txt, 2). + (see: Documentation/power/basic-pm-debugging.txt, 2). Each of the above tests should be repeated several times and the STD tests should be mixed with the STR tests. If any of them fails, the driver cannot be diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt index 41cc7b30d7dd..ffe55ffa540a 100644 --- a/Documentation/power/runtime_pm.txt +++ b/Documentation/power/runtime_pm.txt @@ -50,6 +50,15 @@ type's callbacks are not defined) of given device. The bus type, device type and device class callbacks are referred to as subsystem-level callbacks in what follows. +By default, the callbacks are always invoked in process context with interrupts +enabled. However, subsystems can use the pm_runtime_irq_safe() helper function +to tell the PM core that a device's ->runtime_suspend() and ->runtime_resume() +callbacks should be invoked in atomic context with interrupts disabled +(->runtime_idle() is still invoked the default way). This implies that these +callback routines must not block or sleep, but it also means that the +synchronous helper functions listed at the end of Section 4 can be used within +an interrupt handler or in an atomic context. + The subsystem-level suspend callback is _entirely_ _responsible_ for handling the suspend of the device as appropriate, which may, but need not include executing the device driver's own ->runtime_suspend() callback (from the @@ -237,6 +246,10 @@ defined in include/linux/pm.h: Section 8); it may be modified only by the pm_runtime_no_callbacks() helper function + unsigned int irq_safe; + - indicates that the ->runtime_suspend() and ->runtime_resume() callbacks + will be invoked with the spinlock held and interrupts disabled + unsigned int use_autosuspend; - indicates that the device's driver supports delayed autosuspend (see Section 9); it may be modified only by the @@ -344,6 +357,10 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: - decrement the device's usage counter; if the result is 0 then run pm_runtime_idle(dev) and return its result + int pm_runtime_put_sync_suspend(struct device *dev); + - decrement the device's usage counter; if the result is 0 then run + pm_runtime_suspend(dev) and return its result + int pm_runtime_put_sync_autosuspend(struct device *dev); - decrement the device's usage counter; if the result is 0 then run pm_runtime_autosuspend(dev) and return its result @@ -397,6 +414,11 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: PM attributes from /sys/devices/.../power (or prevent them from being added when the device is registered) + void pm_runtime_irq_safe(struct device *dev); + - set the power.irq_safe flag for the device, causing the runtime-PM + suspend and resume callbacks (but not the idle callback) to be invoked + with interrupts disabled + void pm_runtime_mark_last_busy(struct device *dev); - set the power.last_busy field to the current time @@ -438,6 +460,15 @@ pm_runtime_suspended() pm_runtime_mark_last_busy() pm_runtime_autosuspend_expiration() +If pm_runtime_irq_safe() has been called for a device then the following helper +functions may also be used in interrupt context: + +pm_runtime_suspend() +pm_runtime_autosuspend() +pm_runtime_resume() +pm_runtime_get_sync() +pm_runtime_put_sync_suspend() + 5. Run-time PM Initialization, Device Probing and Removal Initially, the run-time PM is disabled for all devices, which means that the diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt index 302db5da49b3..3272ed59dec7 100644 --- a/Documentation/powerpc/booting-without-of.txt +++ b/Documentation/powerpc/booting-without-of.txt @@ -131,7 +131,7 @@ order to avoid the degeneration that had become the ppc32 kernel entry point and the way a new platform should be added to the kernel. The legacy iSeries platform breaks those rules as it predates this scheme, but no new board support will be accepted in the main tree that -doesn't follows them properly. In addition, since the advent of the +doesn't follow them properly. In addition, since the advent of the arch/powerpc merged architecture for ppc32 and ppc64, new 32-bit platforms and 32-bit platforms which move into arch/powerpc will be required to use these rules as well. @@ -1025,7 +1025,7 @@ dtc source code can be found at WARNING: This version is still in early development stage; the resulting device-tree "blobs" have not yet been validated with the -kernel. The current generated bloc lacks a useful reserve map (it will +kernel. The current generated block lacks a useful reserve map (it will be fixed to generate an empty one, it's up to the bootloader to fill it up) among others. The error handling needs work, bugs are lurking, etc... diff --git a/Documentation/powerpc/dts-bindings/4xx/cpm.txt b/Documentation/powerpc/dts-bindings/4xx/cpm.txt new file mode 100644 index 000000000000..ee459806d35e --- /dev/null +++ b/Documentation/powerpc/dts-bindings/4xx/cpm.txt @@ -0,0 +1,52 @@ +PPC4xx Clock Power Management (CPM) node + +Required properties: + - compatible : compatible list, currently only "ibm,cpm" + - dcr-access-method : "native" + - dcr-reg : < DCR register range > + +Optional properties: + - er-offset : All 4xx SoCs with a CPM controller have + one of two different order for the CPM + registers. Some have the CPM registers + in the following order (ER,FR,SR). The + others have them in the following order + (SR,ER,FR). For the second case set + er-offset = <1>. + - unused-units : specifier consist of one cell. For each + bit in the cell, the corresponding bit + in CPM will be set to turn off unused + devices. + - idle-doze : specifier consist of one cell. For each + bit in the cell, the corresponding bit + in CPM will be set to turn off unused + devices. This is usually just CPM[CPU]. + - standby : specifier consist of one cell. For each + bit in the cell, the corresponding bit + in CPM will be set on standby and + restored on resume. + - suspend : specifier consist of one cell. For each + bit in the cell, the corresponding bit + in CPM will be set on suspend (mem) and + restored on resume. Note, for standby + and suspend the corresponding bits can + be different or the same. Usually for + standby only class 2 and 3 units are set. + However, the interface does not care. + If they are the same, the additional + power saving will be seeing if support + is available to put the DDR in self + refresh mode and any additional power + saving techniques for the specific SoC. + +Example: + CPM0: cpm { + compatible = "ibm,cpm"; + dcr-access-method = "native"; + dcr-reg = <0x160 0x003>; + er-offset = <0>; + unused-units = <0x00000100>; + idle-doze = <0x02000000>; + standby = <0xfeff0000>; + suspend = <0xfeff791d>; +}; diff --git a/Documentation/powerpc/dts-bindings/eeprom.txt b/Documentation/powerpc/dts-bindings/eeprom.txt new file mode 100644 index 000000000000..4342c10de1bf --- /dev/null +++ b/Documentation/powerpc/dts-bindings/eeprom.txt @@ -0,0 +1,28 @@ +EEPROMs (I2C) + +Required properties: + + - compatible : should be "<manufacturer>,<type>" + If there is no specific driver for <manufacturer>, a generic + driver based on <type> is selected. Possible types are: + 24c00, 24c01, 24c02, 24c04, 24c08, 24c16, 24c32, 24c64, + 24c128, 24c256, 24c512, 24c1024, spd + + - reg : the I2C address of the EEPROM + +Optional properties: + + - pagesize : the length of the pagesize for writing. Please consult the + manual of your device, that value varies a lot. A wrong value + may result in data loss! If not specified, a safety value of + '1' is used which will be very slow. + + - read-only: this parameterless property disables writes to the eeprom + +Example: + +eeprom@52 { + compatible = "atmel,24c32"; + reg = <0x52>; + pagesize = <32>; +}; diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas index 00301ed9c371..b64d10d221ec 100644 --- a/Documentation/scsi/ChangeLog.megaraid_sas +++ b/Documentation/scsi/ChangeLog.megaraid_sas @@ -1,3 +1,25 @@ +Release Date : Tues. Dec 14, 2010 17:00:00 PST 2010 - + (emaild-id:megaraidlinux@lsi.com) + Adam Radford +Current Version : 00.00.05.29-rc1 +Old Version : 00.00.04.31-rc1 + 1. Rename megaraid_sas.c to megaraid_sas_base.c. + 2. Update GPL headers. + 3. Add MSI-X support and 'msix_disable' module parameter. + 4. Use lowest memory bar (for SR-IOV VF support). + 5. Add struct megasas_instance_temlate changes, and change all code to use + new instance entries: + + irqreturn_t (*service_isr )(int irq, void *devp); + void (*tasklet)(unsigned long); + u32 (*init_adapter)(struct megasas_instance *); + u32 (*build_and_issue_cmd) (struct megasas_instance *, + struct scsi_cmnd *); + void (*issue_dcmd) (struct megasas_instance *instance, + struct megasas_cmd *cmd); + + 6. Add code to support MegaRAID 9265/9285 controllers device id (0x5b). +------------------------------------------------------------------------------- 1 Release Date : Thur. May 03, 2010 09:12:45 PST 2009 - (emaild-id:megaraidlinux@lsi.com) Bo Yang diff --git a/Documentation/serial/00-INDEX b/Documentation/serial/00-INDEX index 07dcdb0d2a36..e09468ad3cb1 100644 --- a/Documentation/serial/00-INDEX +++ b/Documentation/serial/00-INDEX @@ -14,6 +14,8 @@ riscom8.txt - notes on using the RISCom/8 multi-port serial driver. rocket.txt - info on the Comtrol RocketPort multiport serial driver. +serial-rs485.txt + - info about RS485 structures and support in the kernel. specialix.txt - info on hardware/driver for specialix IO8+ multiport serial card. stallion.txt diff --git a/Documentation/serial/serial-rs485.txt b/Documentation/serial/serial-rs485.txt new file mode 100644 index 000000000000..a4932387bbfb --- /dev/null +++ b/Documentation/serial/serial-rs485.txt @@ -0,0 +1,120 @@ + RS485 SERIAL COMMUNICATIONS + +1. INTRODUCTION + + EIA-485, also known as TIA/EIA-485 or RS-485, is a standard defining the + electrical characteristics of drivers and receivers for use in balanced + digital multipoint systems. + This standard is widely used for communications in industrial automation + because it can be used effectively over long distances and in electrically + noisy environments. + +2. HARDWARE-RELATED CONSIDERATIONS + + Some CPUs/UARTs (e.g., Atmel AT91 or 16C950 UART) contain a built-in + half-duplex mode capable of automatically controlling line direction by + toggling RTS or DTR signals. That can be used to control external + half-duplex hardware like an RS485 transceiver or any RS232-connected + half-duplex devices like some modems. + + For these microcontrollers, the Linux driver should be made capable of + working in both modes, and proper ioctls (see later) should be made + available at user-level to allow switching from one mode to the other, and + vice versa. + +3. DATA STRUCTURES ALREADY AVAILABLE IN THE KERNEL + + The Linux kernel provides the serial_rs485 structure (see [1]) to handle + RS485 communications. This data structure is used to set and configure RS485 + parameters in the platform data and in ioctls. + + Any driver for devices capable of working both as RS232 and RS485 should + provide at least the following ioctls: + + - TIOCSRS485 (typically associated with number 0x542F). This ioctl is used + to enable/disable RS485 mode from user-space + + - TIOCGRS485 (typically associated with number 0x542E). This ioctl is used + to get RS485 mode from kernel-space (i.e., driver) to user-space. + + In other words, the serial driver should contain a code similar to the next + one: + + static struct uart_ops atmel_pops = { + /* ... */ + .ioctl = handle_ioctl, + }; + + static int handle_ioctl(struct uart_port *port, + unsigned int cmd, + unsigned long arg) + { + struct serial_rs485 rs485conf; + + switch (cmd) { + case TIOCSRS485: + if (copy_from_user(&rs485conf, + (struct serial_rs485 *) arg, + sizeof(rs485conf))) + return -EFAULT; + + /* ... */ + break; + + case TIOCGRS485: + if (copy_to_user((struct serial_rs485 *) arg, + ..., + sizeof(rs485conf))) + return -EFAULT; + /* ... */ + break; + + /* ... */ + } + } + + +4. USAGE FROM USER-LEVEL + + From user-level, RS485 configuration can be get/set using the previous + ioctls. For instance, to set RS485 you can use the following code: + + #include <linux/serial.h> + + /* Driver-specific ioctls: */ + #define TIOCGRS485 0x542E + #define TIOCSRS485 0x542F + + /* Open your specific device (e.g., /dev/mydevice): */ + int fd = open ("/dev/mydevice", O_RDWR); + if (fd < 0) { + /* Error handling. See errno. */ + } + + struct serial_rs485 rs485conf; + + /* Set RS485 mode: */ + rs485conf.flags |= SER_RS485_ENABLED; + + /* Set rts delay before send, if needed: */ + rs485conf.flags |= SER_RS485_RTS_BEFORE_SEND; + rs485conf.delay_rts_before_send = ...; + + /* Set rts delay after send, if needed: */ + rs485conf.flags |= SER_RS485_RTS_AFTER_SEND; + rs485conf.delay_rts_after_send = ...; + + if (ioctl (fd, TIOCSRS485, &rs485conf) < 0) { + /* Error handling. See errno. */ + } + + /* Use read() and write() syscalls here... */ + + /* Close the device when finished: */ + if (close (fd) < 0) { + /* Error handling. See errno. */ + } + +5. REFERENCES + + [1] include/linux/serial.h diff --git a/Documentation/spi/pxa2xx b/Documentation/spi/pxa2xx index 6bb916d57c95..68a4fe3818a1 100644 --- a/Documentation/spi/pxa2xx +++ b/Documentation/spi/pxa2xx @@ -19,7 +19,7 @@ Declaring PXA2xx Master Controllers ----------------------------------- Typically a SPI master is defined in the arch/.../mach-*/board-*.c as a "platform device". The master configuration is passed to the driver via a table -found in arch/arm/mach-pxa/include/mach/pxa2xx_spi.h: +found in include/linux/spi/pxa2xx_spi.h: struct pxa2xx_spi_master { enum pxa_ssp_type ssp_type; @@ -94,7 +94,7 @@ using the "spi_board_info" structure found in "linux/spi/spi.h". See Each slave device attached to the PXA must provide slave specific configuration information via the structure "pxa2xx_spi_chip" found in -"arch/arm/mach-pxa/include/mach/pxa2xx_spi.h". The pxa2xx_spi master controller driver +"include/linux/spi/pxa2xx_spi.h". The pxa2xx_spi master controller driver will uses the configuration whenever the driver communicates with the slave device. All fields are optional. diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 209e1584c3dc..574067194f38 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -219,7 +219,7 @@ dmesg_restrict: This toggle indicates whether unprivileged users are prevented from using dmesg(8) to view messages from the kernel's log buffer. When dmesg_restrict is set to (0) there are no restrictions. When -dmesg_restrict is set set to (1), users must have CAP_SYS_ADMIN to use +dmesg_restrict is set set to (1), users must have CAP_SYSLOG to use dmesg(8). The kernel config option CONFIG_SECURITY_DMESG_RESTRICT sets the default diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt index b29d8e56cf28..c9ffa9ced7ee 100644 --- a/Documentation/usb/power-management.txt +++ b/Documentation/usb/power-management.txt @@ -2,7 +2,7 @@ Alan Stern <stern@rowland.harvard.edu> - December 11, 2009 + October 28, 2010 @@ -107,9 +107,14 @@ allowed to issue dynamic suspends. The user interface for controlling dynamic PM is located in the power/ subdirectory of each USB device's sysfs directory, that is, in /sys/bus/usb/devices/.../power/ where "..." is the device's ID. The -relevant attribute files are: wakeup, control, and autosuspend. -(There may also be a file named "level"; this file was deprecated -as of the 2.6.35 kernel and replaced by the "control" file.) +relevant attribute files are: wakeup, control, and +autosuspend_delay_ms. (There may also be a file named "level"; this +file was deprecated as of the 2.6.35 kernel and replaced by the +"control" file. In 2.6.38 the "autosuspend" file will be deprecated +and replaced by the "autosuspend_delay_ms" file. The only difference +is that the newer file expresses the delay in milliseconds whereas the +older file uses seconds. Confusingly, both files are present in 2.6.37 +but only "autosuspend" works.) power/wakeup @@ -140,33 +145,36 @@ as of the 2.6.35 kernel and replaced by the "control" file.) suspended and autoresume was not allowed. This setting is no longer supported.) - power/autosuspend + power/autosuspend_delay_ms This file contains an integer value, which is the - number of seconds the device should remain idle before - the kernel will autosuspend it (the idle-delay time). - The default is 2. 0 means to autosuspend as soon as - the device becomes idle, and negative values mean - never to autosuspend. You can write a number to the - file to change the autosuspend idle-delay time. - -Writing "-1" to power/autosuspend and writing "on" to power/control do -essentially the same thing -- they both prevent the device from being -autosuspended. Yes, this is a redundancy in the API. + number of milliseconds the device should remain idle + before the kernel will autosuspend it (the idle-delay + time). The default is 2000. 0 means to autosuspend + as soon as the device becomes idle, and negative + values mean never to autosuspend. You can write a + number to the file to change the autosuspend + idle-delay time. + +Writing "-1" to power/autosuspend_delay_ms and writing "on" to +power/control do essentially the same thing -- they both prevent the +device from being autosuspended. Yes, this is a redundancy in the +API. (In 2.6.21 writing "0" to power/autosuspend would prevent the device from being autosuspended; the behavior was changed in 2.6.22. The power/autosuspend attribute did not exist prior to 2.6.21, and the power/level attribute did not exist prior to 2.6.22. power/control -was added in 2.6.34.) +was added in 2.6.34, and power/autosuspend_delay_ms was added in +2.6.37 but did not become functional until 2.6.38.) Changing the default idle-delay time ------------------------------------ -The default autosuspend idle-delay time is controlled by a module -parameter in usbcore. You can specify the value when usbcore is -loaded. For example, to set it to 5 seconds instead of 2 you would +The default autosuspend idle-delay time (in seconds) is controlled by +a module parameter in usbcore. You can specify the value when usbcore +is loaded. For example, to set it to 5 seconds instead of 2 you would do: modprobe usbcore autosuspend=5 @@ -234,25 +242,23 @@ every device. If a driver knows that its device has proper suspend/resume support, it can enable autosuspend all by itself. For example, the video -driver for a laptop's webcam might do this, since these devices are -rarely used and so should normally be autosuspended. +driver for a laptop's webcam might do this (in recent kernels they +do), since these devices are rarely used and so should normally be +autosuspended. Sometimes it turns out that even when a device does work okay with -autosuspend there are still problems. For example, there are -experimental patches adding autosuspend support to the usbhid driver, -which manages keyboards and mice, among other things. Tests with a -number of keyboards showed that typing on a suspended keyboard, while -causing the keyboard to do a remote wakeup all right, would -nonetheless frequently result in lost keystrokes. Tests with mice -showed that some of them would issue a remote-wakeup request in -response to button presses but not to motion, and some in response to -neither. +autosuspend there are still problems. For example, the usbhid driver, +which manages keyboards and mice, has autosuspend support. Tests with +a number of keyboards show that typing on a suspended keyboard, while +causing the keyboard to do a remote wakeup all right, will nonetheless +frequently result in lost keystrokes. Tests with mice show that some +of them will issue a remote-wakeup request in response to button +presses but not to motion, and some in response to neither. The kernel will not prevent you from enabling autosuspend on devices that can't handle it. It is even possible in theory to damage a -device by suspending it at the wrong time -- for example, suspending a -USB hard disk might cause it to spin down without parking the heads. -(Highly unlikely, but possible.) Take care. +device by suspending it at the wrong time. (Highly unlikely, but +possible.) Take care. The driver interface for Power Management @@ -336,10 +342,6 @@ autosuspend the interface's device. When the usage counter is = 0 then the interface is considered to be idle, and the kernel may autosuspend the device. -(There is a similar usage counter field in struct usb_device, -associated with the device itself rather than any of its interfaces. -This counter is used only by the USB core.) - Drivers need not be concerned about balancing changes to the usage counter; the USB core will undo any remaining "get"s when a driver is unbound from its interface. As a corollary, drivers must not call @@ -409,11 +411,11 @@ during autosuspend. For example, there's not much point autosuspending a keyboard if the user can't cause the keyboard to do a remote wakeup by typing on it. If the driver sets intf->needs_remote_wakeup to 1, the kernel won't autosuspend the -device if remote wakeup isn't available or has been disabled through -the power/wakeup attribute. (If the device is already autosuspended, -though, setting this flag won't cause the kernel to autoresume it. -Normally a driver would set this flag in its probe method, at which -time the device is guaranteed not to be autosuspended.) +device if remote wakeup isn't available. (If the device is already +autosuspended, though, setting this flag won't cause the kernel to +autoresume it. Normally a driver would set this flag in its probe +method, at which time the device is guaranteed not to be +autosuspended.) If a driver does its I/O asynchronously in interrupt context, it should call usb_autopm_get_interface_async() before starting output and @@ -422,20 +424,19 @@ it receives an input event, it should call usb_mark_last_busy(struct usb_device *udev); -in the event handler. This sets udev->last_busy to the current time. -udev->last_busy is the field used for idle-delay calculations; -updating it will cause any pending autosuspend to be moved back. Most -of the usb_autopm_* routines will also set the last_busy field to the -current time. +in the event handler. This tells the PM core that the device was just +busy and therefore the next autosuspend idle-delay expiration should +be pushed back. Many of the usb_autopm_* routines also make this call, +so drivers need to worry only when interrupt-driven input arrives. Asynchronous operation is always subject to races. For example, a -driver may call one of the usb_autopm_*_interface_async() routines at -a time when the core has just finished deciding the device has been -idle for long enough but not yet gotten around to calling the driver's -suspend method. The suspend method must be responsible for -synchronizing with the output request routine and the URB completion -handler; it should cause autosuspends to fail with -EBUSY if the -driver needs to use the device. +driver may call the usb_autopm_get_interface_async() routine at a time +when the core has just finished deciding the device has been idle for +long enough but not yet gotten around to calling the driver's suspend +method. The suspend method must be responsible for synchronizing with +the I/O request routine and the URB completion handler; it should +cause autosuspends to fail with -EBUSY if the driver needs to use the +device. External suspend calls should never be allowed to fail in this way, only autosuspend calls. The driver can tell them apart by checking @@ -472,7 +473,9 @@ Firstly, a device may already be autosuspended when a system suspend occurs. Since system suspends are supposed to be as transparent as possible, the device should remain suspended following the system resume. But this theory may not work out well in practice; over time -the kernel's behavior in this regard has changed. +the kernel's behavior in this regard has changed. As of 2.6.37 the +policy is to resume all devices during a system resume and let them +handle their own runtime suspends afterward. Secondly, a dynamic power-management event may occur as a system suspend is underway. The window for this is short, since system diff --git a/Documentation/vm/Makefile b/Documentation/vm/Makefile index 9dcff328b964..3fa4d0668864 100644 --- a/Documentation/vm/Makefile +++ b/Documentation/vm/Makefile @@ -2,7 +2,7 @@ obj- := dummy.o # List of programs to build -hostprogs-y := slabinfo page-types hugepage-mmap hugepage-shm map_hugetlb +hostprogs-y := page-types hugepage-mmap hugepage-shm map_hugetlb # Tell kbuild to always build the programs always := $(hostprogs-y) diff --git a/Documentation/vm/slabinfo.c b/Documentation/vm/slabinfo.c deleted file mode 100644 index 92e729f4b676..000000000000 --- a/Documentation/vm/slabinfo.c +++ /dev/null @@ -1,1364 +0,0 @@ -/* - * Slabinfo: Tool to get reports about slabs - * - * (C) 2007 sgi, Christoph Lameter - * - * Compile by: - * - * gcc -o slabinfo slabinfo.c - */ -#include <stdio.h> -#include <stdlib.h> -#include <sys/types.h> -#include <dirent.h> -#include <strings.h> -#include <string.h> -#include <unistd.h> -#include <stdarg.h> -#include <getopt.h> -#include <regex.h> -#include <errno.h> - -#define MAX_SLABS 500 -#define MAX_ALIASES 500 -#define MAX_NODES 1024 - -struct slabinfo { - char *name; - int alias; - int refs; - int aliases, align, cache_dma, cpu_slabs, destroy_by_rcu; - int hwcache_align, object_size, objs_per_slab; - int sanity_checks, slab_size, store_user, trace; - int order, poison, reclaim_account, red_zone; - unsigned long partial, objects, slabs, objects_partial, objects_total; - unsigned long alloc_fastpath, alloc_slowpath; - unsigned long free_fastpath, free_slowpath; - unsigned long free_frozen, free_add_partial, free_remove_partial; - unsigned long alloc_from_partial, alloc_slab, free_slab, alloc_refill; - unsigned long cpuslab_flush, deactivate_full, deactivate_empty; - unsigned long deactivate_to_head, deactivate_to_tail; - unsigned long deactivate_remote_frees, order_fallback; - int numa[MAX_NODES]; - int numa_partial[MAX_NODES]; -} slabinfo[MAX_SLABS]; - -struct aliasinfo { - char *name; - char *ref; - struct slabinfo *slab; -} aliasinfo[MAX_ALIASES]; - -int slabs = 0; -int actual_slabs = 0; -int aliases = 0; -int alias_targets = 0; -int highest_node = 0; - -char buffer[4096]; - -int show_empty = 0; -int show_report = 0; -int show_alias = 0; -int show_slab = 0; -int skip_zero = 1; -int show_numa = 0; -int show_track = 0; -int show_first_alias = 0; -int validate = 0; -int shrink = 0; -int show_inverted = 0; -int show_single_ref = 0; -int show_totals = 0; -int sort_size = 0; -int sort_active = 0; -int set_debug = 0; -int show_ops = 0; -int show_activity = 0; - -/* Debug options */ -int sanity = 0; -int redzone = 0; -int poison = 0; -int tracking = 0; -int tracing = 0; - -int page_size; - -regex_t pattern; - -static void fatal(const char *x, ...) -{ - va_list ap; - - va_start(ap, x); - vfprintf(stderr, x, ap); - va_end(ap); - exit(EXIT_FAILURE); -} - -static void usage(void) -{ - printf("slabinfo 5/7/2007. (c) 2007 sgi.\n\n" - "slabinfo [-ahnpvtsz] [-d debugopts] [slab-regexp]\n" - "-a|--aliases Show aliases\n" - "-A|--activity Most active slabs first\n" - "-d<options>|--debug=<options> Set/Clear Debug options\n" - "-D|--display-active Switch line format to activity\n" - "-e|--empty Show empty slabs\n" - "-f|--first-alias Show first alias\n" - "-h|--help Show usage information\n" - "-i|--inverted Inverted list\n" - "-l|--slabs Show slabs\n" - "-n|--numa Show NUMA information\n" - "-o|--ops Show kmem_cache_ops\n" - "-s|--shrink Shrink slabs\n" - "-r|--report Detailed report on single slabs\n" - "-S|--Size Sort by size\n" - "-t|--tracking Show alloc/free information\n" - "-T|--Totals Show summary information\n" - "-v|--validate Validate slabs\n" - "-z|--zero Include empty slabs\n" - "-1|--1ref Single reference\n" - "\nValid debug options (FZPUT may be combined)\n" - "a / A Switch on all debug options (=FZUP)\n" - "- Switch off all debug options\n" - "f / F Sanity Checks (SLAB_DEBUG_FREE)\n" - "z / Z Redzoning\n" - "p / P Poisoning\n" - "u / U Tracking\n" - "t / T Tracing\n" - ); -} - -static unsigned long read_obj(const char *name) -{ - FILE *f = fopen(name, "r"); - - if (!f) - buffer[0] = 0; - else { - if (!fgets(buffer, sizeof(buffer), f)) - buffer[0] = 0; - fclose(f); - if (buffer[strlen(buffer)] == '\n') - buffer[strlen(buffer)] = 0; - } - return strlen(buffer); -} - - -/* - * Get the contents of an attribute - */ -static unsigned long get_obj(const char *name) -{ - if (!read_obj(name)) - return 0; - - return atol(buffer); -} - -static unsigned long get_obj_and_str(const char *name, char **x) -{ - unsigned long result = 0; - char *p; - - *x = NULL; - - if (!read_obj(name)) { - x = NULL; - return 0; - } - result = strtoul(buffer, &p, 10); - while (*p == ' ') - p++; - if (*p) - *x = strdup(p); - return result; -} - -static void set_obj(struct slabinfo *s, const char *name, int n) -{ - char x[100]; - FILE *f; - - snprintf(x, 100, "%s/%s", s->name, name); - f = fopen(x, "w"); - if (!f) - fatal("Cannot write to %s\n", x); - - fprintf(f, "%d\n", n); - fclose(f); -} - -static unsigned long read_slab_obj(struct slabinfo *s, const char *name) -{ - char x[100]; - FILE *f; - size_t l; - - snprintf(x, 100, "%s/%s", s->name, name); - f = fopen(x, "r"); - if (!f) { - buffer[0] = 0; - l = 0; - } else { - l = fread(buffer, 1, sizeof(buffer), f); - buffer[l] = 0; - fclose(f); - } - return l; -} - - -/* - * Put a size string together - */ -static int store_size(char *buffer, unsigned long value) -{ - unsigned long divisor = 1; - char trailer = 0; - int n; - - if (value > 1000000000UL) { - divisor = 100000000UL; - trailer = 'G'; - } else if (value > 1000000UL) { - divisor = 100000UL; - trailer = 'M'; - } else if (value > 1000UL) { - divisor = 100; - trailer = 'K'; - } - - value /= divisor; - n = sprintf(buffer, "%ld",value); - if (trailer) { - buffer[n] = trailer; - n++; - buffer[n] = 0; - } - if (divisor != 1) { - memmove(buffer + n - 2, buffer + n - 3, 4); - buffer[n-2] = '.'; - n++; - } - return n; -} - -static void decode_numa_list(int *numa, char *t) -{ - int node; - int nr; - - memset(numa, 0, MAX_NODES * sizeof(int)); - - if (!t) - return; - - while (*t == 'N') { - t++; - node = strtoul(t, &t, 10); - if (*t == '=') { - t++; - nr = strtoul(t, &t, 10); - numa[node] = nr; - if (node > highest_node) - highest_node = node; - } - while (*t == ' ') - t++; - } -} - -static void slab_validate(struct slabinfo *s) -{ - if (strcmp(s->name, "*") == 0) - return; - - set_obj(s, "validate", 1); -} - -static void slab_shrink(struct slabinfo *s) -{ - if (strcmp(s->name, "*") == 0) - return; - - set_obj(s, "shrink", 1); -} - -int line = 0; - -static void first_line(void) -{ - if (show_activity) - printf("Name Objects Alloc Free %%Fast Fallb O\n"); - else - printf("Name Objects Objsize Space " - "Slabs/Part/Cpu O/S O %%Fr %%Ef Flg\n"); -} - -/* - * Find the shortest alias of a slab - */ -static struct aliasinfo *find_one_alias(struct slabinfo *find) -{ - struct aliasinfo *a; - struct aliasinfo *best = NULL; - - for(a = aliasinfo;a < aliasinfo + aliases; a++) { - if (a->slab == find && - (!best || strlen(best->name) < strlen(a->name))) { - best = a; - if (strncmp(a->name,"kmall", 5) == 0) - return best; - } - } - return best; -} - -static unsigned long slab_size(struct slabinfo *s) -{ - return s->slabs * (page_size << s->order); -} - -static unsigned long slab_activity(struct slabinfo *s) -{ - return s->alloc_fastpath + s->free_fastpath + - s->alloc_slowpath + s->free_slowpath; -} - -static void slab_numa(struct slabinfo *s, int mode) -{ - int node; - - if (strcmp(s->name, "*") == 0) - return; - - if (!highest_node) { - printf("\n%s: No NUMA information available.\n", s->name); - return; - } - - if (skip_zero && !s->slabs) - return; - - if (!line) { - printf("\n%-21s:", mode ? "NUMA nodes" : "Slab"); - for(node = 0; node <= highest_node; node++) - printf(" %4d", node); - printf("\n----------------------"); - for(node = 0; node <= highest_node; node++) - printf("-----"); - printf("\n"); - } - printf("%-21s ", mode ? "All slabs" : s->name); - for(node = 0; node <= highest_node; node++) { - char b[20]; - - store_size(b, s->numa[node]); - printf(" %4s", b); - } - printf("\n"); - if (mode) { - printf("%-21s ", "Partial slabs"); - for(node = 0; node <= highest_node; node++) { - char b[20]; - - store_size(b, s->numa_partial[node]); - printf(" %4s", b); - } - printf("\n"); - } - line++; -} - -static void show_tracking(struct slabinfo *s) -{ - printf("\n%s: Kernel object allocation\n", s->name); - printf("-----------------------------------------------------------------------\n"); - if (read_slab_obj(s, "alloc_calls")) - printf(buffer); - else - printf("No Data\n"); - - printf("\n%s: Kernel object freeing\n", s->name); - printf("------------------------------------------------------------------------\n"); - if (read_slab_obj(s, "free_calls")) - printf(buffer); - else - printf("No Data\n"); - -} - -static void ops(struct slabinfo *s) -{ - if (strcmp(s->name, "*") == 0) - return; - - if (read_slab_obj(s, "ops")) { - printf("\n%s: kmem_cache operations\n", s->name); - printf("--------------------------------------------\n"); - printf(buffer); - } else - printf("\n%s has no kmem_cache operations\n", s->name); -} - -static const char *onoff(int x) -{ - if (x) - return "On "; - return "Off"; -} - -static void slab_stats(struct slabinfo *s) -{ - unsigned long total_alloc; - unsigned long total_free; - unsigned long total; - - if (!s->alloc_slab) - return; - - total_alloc = s->alloc_fastpath + s->alloc_slowpath; - total_free = s->free_fastpath + s->free_slowpath; - - if (!total_alloc) - return; - - printf("\n"); - printf("Slab Perf Counter Alloc Free %%Al %%Fr\n"); - printf("--------------------------------------------------\n"); - printf("Fastpath %8lu %8lu %3lu %3lu\n", - s->alloc_fastpath, s->free_fastpath, - s->alloc_fastpath * 100 / total_alloc, - s->free_fastpath * 100 / total_free); - printf("Slowpath %8lu %8lu %3lu %3lu\n", - total_alloc - s->alloc_fastpath, s->free_slowpath, - (total_alloc - s->alloc_fastpath) * 100 / total_alloc, - s->free_slowpath * 100 / total_free); - printf("Page Alloc %8lu %8lu %3lu %3lu\n", - s->alloc_slab, s->free_slab, - s->alloc_slab * 100 / total_alloc, - s->free_slab * 100 / total_free); - printf("Add partial %8lu %8lu %3lu %3lu\n", - s->deactivate_to_head + s->deactivate_to_tail, - s->free_add_partial, - (s->deactivate_to_head + s->deactivate_to_tail) * 100 / total_alloc, - s->free_add_partial * 100 / total_free); - printf("Remove partial %8lu %8lu %3lu %3lu\n", - s->alloc_from_partial, s->free_remove_partial, - s->alloc_from_partial * 100 / total_alloc, - s->free_remove_partial * 100 / total_free); - - printf("RemoteObj/SlabFrozen %8lu %8lu %3lu %3lu\n", - s->deactivate_remote_frees, s->free_frozen, - s->deactivate_remote_frees * 100 / total_alloc, - s->free_frozen * 100 / total_free); - - printf("Total %8lu %8lu\n\n", total_alloc, total_free); - - if (s->cpuslab_flush) - printf("Flushes %8lu\n", s->cpuslab_flush); - - if (s->alloc_refill) - printf("Refill %8lu\n", s->alloc_refill); - - total = s->deactivate_full + s->deactivate_empty + - s->deactivate_to_head + s->deactivate_to_tail; - - if (total) - printf("Deactivate Full=%lu(%lu%%) Empty=%lu(%lu%%) " - "ToHead=%lu(%lu%%) ToTail=%lu(%lu%%)\n", - s->deactivate_full, (s->deactivate_full * 100) / total, - s->deactivate_empty, (s->deactivate_empty * 100) / total, - s->deactivate_to_head, (s->deactivate_to_head * 100) / total, - s->deactivate_to_tail, (s->deactivate_to_tail * 100) / total); -} - -static void report(struct slabinfo *s) -{ - if (strcmp(s->name, "*") == 0) - return; - - printf("\nSlabcache: %-20s Aliases: %2d Order : %2d Objects: %lu\n", - s->name, s->aliases, s->order, s->objects); - if (s->hwcache_align) - printf("** Hardware cacheline aligned\n"); - if (s->cache_dma) - printf("** Memory is allocated in a special DMA zone\n"); - if (s->destroy_by_rcu) - printf("** Slabs are destroyed via RCU\n"); - if (s->reclaim_account) - printf("** Reclaim accounting active\n"); - - printf("\nSizes (bytes) Slabs Debug Memory\n"); - printf("------------------------------------------------------------------------\n"); - printf("Object : %7d Total : %7ld Sanity Checks : %s Total: %7ld\n", - s->object_size, s->slabs, onoff(s->sanity_checks), - s->slabs * (page_size << s->order)); - printf("SlabObj: %7d Full : %7ld Redzoning : %s Used : %7ld\n", - s->slab_size, s->slabs - s->partial - s->cpu_slabs, - onoff(s->red_zone), s->objects * s->object_size); - printf("SlabSiz: %7d Partial: %7ld Poisoning : %s Loss : %7ld\n", - page_size << s->order, s->partial, onoff(s->poison), - s->slabs * (page_size << s->order) - s->objects * s->object_size); - printf("Loss : %7d CpuSlab: %7d Tracking : %s Lalig: %7ld\n", - s->slab_size - s->object_size, s->cpu_slabs, onoff(s->store_user), - (s->slab_size - s->object_size) * s->objects); - printf("Align : %7d Objects: %7d Tracing : %s Lpadd: %7ld\n", - s->align, s->objs_per_slab, onoff(s->trace), - ((page_size << s->order) - s->objs_per_slab * s->slab_size) * - s->slabs); - - ops(s); - show_tracking(s); - slab_numa(s, 1); - slab_stats(s); -} - -static void slabcache(struct slabinfo *s) -{ - char size_str[20]; - char dist_str[40]; - char flags[20]; - char *p = flags; - - if (strcmp(s->name, "*") == 0) - return; - - if (actual_slabs == 1) { - report(s); - return; - } - - if (skip_zero && !show_empty && !s->slabs) - return; - - if (show_empty && s->slabs) - return; - - store_size(size_str, slab_size(s)); - snprintf(dist_str, 40, "%lu/%lu/%d", s->slabs - s->cpu_slabs, - s->partial, s->cpu_slabs); - - if (!line++) - first_line(); - - if (s->aliases) - *p++ = '*'; - if (s->cache_dma) - *p++ = 'd'; - if (s->hwcache_align) - *p++ = 'A'; - if (s->poison) - *p++ = 'P'; - if (s->reclaim_account) - *p++ = 'a'; - if (s->red_zone) - *p++ = 'Z'; - if (s->sanity_checks) - *p++ = 'F'; - if (s->store_user) - *p++ = 'U'; - if (s->trace) - *p++ = 'T'; - - *p = 0; - if (show_activity) { - unsigned long total_alloc; - unsigned long total_free; - - total_alloc = s->alloc_fastpath + s->alloc_slowpath; - total_free = s->free_fastpath + s->free_slowpath; - - printf("%-21s %8ld %10ld %10ld %3ld %3ld %5ld %1d\n", - s->name, s->objects, - total_alloc, total_free, - total_alloc ? (s->alloc_fastpath * 100 / total_alloc) : 0, - total_free ? (s->free_fastpath * 100 / total_free) : 0, - s->order_fallback, s->order); - } - else - printf("%-21s %8ld %7d %8s %14s %4d %1d %3ld %3ld %s\n", - s->name, s->objects, s->object_size, size_str, dist_str, - s->objs_per_slab, s->order, - s->slabs ? (s->partial * 100) / s->slabs : 100, - s->slabs ? (s->objects * s->object_size * 100) / - (s->slabs * (page_size << s->order)) : 100, - flags); -} - -/* - * Analyze debug options. Return false if something is amiss. - */ -static int debug_opt_scan(char *opt) -{ - if (!opt || !opt[0] || strcmp(opt, "-") == 0) - return 1; - - if (strcasecmp(opt, "a") == 0) { - sanity = 1; - poison = 1; - redzone = 1; - tracking = 1; - return 1; - } - - for ( ; *opt; opt++) - switch (*opt) { - case 'F' : case 'f': - if (sanity) - return 0; - sanity = 1; - break; - case 'P' : case 'p': - if (poison) - return 0; - poison = 1; - break; - - case 'Z' : case 'z': - if (redzone) - return 0; - redzone = 1; - break; - - case 'U' : case 'u': - if (tracking) - return 0; - tracking = 1; - break; - - case 'T' : case 't': - if (tracing) - return 0; - tracing = 1; - break; - default: - return 0; - } - return 1; -} - -static int slab_empty(struct slabinfo *s) -{ - if (s->objects > 0) - return 0; - - /* - * We may still have slabs even if there are no objects. Shrinking will - * remove them. - */ - if (s->slabs != 0) - set_obj(s, "shrink", 1); - - return 1; -} - -static void slab_debug(struct slabinfo *s) -{ - if (strcmp(s->name, "*") == 0) - return; - - if (sanity && !s->sanity_checks) { - set_obj(s, "sanity", 1); - } - if (!sanity && s->sanity_checks) { - if (slab_empty(s)) - set_obj(s, "sanity", 0); - else - fprintf(stderr, "%s not empty cannot disable sanity checks\n", s->name); - } - if (redzone && !s->red_zone) { - if (slab_empty(s)) - set_obj(s, "red_zone", 1); - else - fprintf(stderr, "%s not empty cannot enable redzoning\n", s->name); - } - if (!redzone && s->red_zone) { - if (slab_empty(s)) - set_obj(s, "red_zone", 0); - else - fprintf(stderr, "%s not empty cannot disable redzoning\n", s->name); - } - if (poison && !s->poison) { - if (slab_empty(s)) - set_obj(s, "poison", 1); - else - fprintf(stderr, "%s not empty cannot enable poisoning\n", s->name); - } - if (!poison && s->poison) { - if (slab_empty(s)) - set_obj(s, "poison", 0); - else - fprintf(stderr, "%s not empty cannot disable poisoning\n", s->name); - } - if (tracking && !s->store_user) { - if (slab_empty(s)) - set_obj(s, "store_user", 1); - else - fprintf(stderr, "%s not empty cannot enable tracking\n", s->name); - } - if (!tracking && s->store_user) { - if (slab_empty(s)) - set_obj(s, "store_user", 0); - else - fprintf(stderr, "%s not empty cannot disable tracking\n", s->name); - } - if (tracing && !s->trace) { - if (slabs == 1) - set_obj(s, "trace", 1); - else - fprintf(stderr, "%s can only enable trace for one slab at a time\n", s->name); - } - if (!tracing && s->trace) - set_obj(s, "trace", 1); -} - -static void totals(void) -{ - struct slabinfo *s; - - int used_slabs = 0; - char b1[20], b2[20], b3[20], b4[20]; - unsigned long long max = 1ULL << 63; - - /* Object size */ - unsigned long long min_objsize = max, max_objsize = 0, avg_objsize; - - /* Number of partial slabs in a slabcache */ - unsigned long long min_partial = max, max_partial = 0, - avg_partial, total_partial = 0; - - /* Number of slabs in a slab cache */ - unsigned long long min_slabs = max, max_slabs = 0, - avg_slabs, total_slabs = 0; - - /* Size of the whole slab */ - unsigned long long min_size = max, max_size = 0, - avg_size, total_size = 0; - - /* Bytes used for object storage in a slab */ - unsigned long long min_used = max, max_used = 0, - avg_used, total_used = 0; - - /* Waste: Bytes used for alignment and padding */ - unsigned long long min_waste = max, max_waste = 0, - avg_waste, total_waste = 0; - /* Number of objects in a slab */ - unsigned long long min_objects = max, max_objects = 0, - avg_objects, total_objects = 0; - /* Waste per object */ - unsigned long long min_objwaste = max, - max_objwaste = 0, avg_objwaste, - total_objwaste = 0; - - /* Memory per object */ - unsigned long long min_memobj = max, - max_memobj = 0, avg_memobj, - total_objsize = 0; - - /* Percentage of partial slabs per slab */ - unsigned long min_ppart = 100, max_ppart = 0, - avg_ppart, total_ppart = 0; - - /* Number of objects in partial slabs */ - unsigned long min_partobj = max, max_partobj = 0, - avg_partobj, total_partobj = 0; - - /* Percentage of partial objects of all objects in a slab */ - unsigned long min_ppartobj = 100, max_ppartobj = 0, - avg_ppartobj, total_ppartobj = 0; - - - for (s = slabinfo; s < slabinfo + slabs; s++) { - unsigned long long size; - unsigned long used; - unsigned long long wasted; - unsigned long long objwaste; - unsigned long percentage_partial_slabs; - unsigned long percentage_partial_objs; - - if (!s->slabs || !s->objects) - continue; - - used_slabs++; - - size = slab_size(s); - used = s->objects * s->object_size; - wasted = size - used; - objwaste = s->slab_size - s->object_size; - - percentage_partial_slabs = s->partial * 100 / s->slabs; - if (percentage_partial_slabs > 100) - percentage_partial_slabs = 100; - - percentage_partial_objs = s->objects_partial * 100 - / s->objects; - - if (percentage_partial_objs > 100) - percentage_partial_objs = 100; - - if (s->object_size < min_objsize) - min_objsize = s->object_size; - if (s->partial < min_partial) - min_partial = s->partial; - if (s->slabs < min_slabs) - min_slabs = s->slabs; - if (size < min_size) - min_size = size; - if (wasted < min_waste) - min_waste = wasted; - if (objwaste < min_objwaste) - min_objwaste = objwaste; - if (s->objects < min_objects) - min_objects = s->objects; - if (used < min_used) - min_used = used; - if (s->objects_partial < min_partobj) - min_partobj = s->objects_partial; - if (percentage_partial_slabs < min_ppart) - min_ppart = percentage_partial_slabs; - if (percentage_partial_objs < min_ppartobj) - min_ppartobj = percentage_partial_objs; - if (s->slab_size < min_memobj) - min_memobj = s->slab_size; - - if (s->object_size > max_objsize) - max_objsize = s->object_size; - if (s->partial > max_partial) - max_partial = s->partial; - if (s->slabs > max_slabs) - max_slabs = s->slabs; - if (size > max_size) - max_size = size; - if (wasted > max_waste) - max_waste = wasted; - if (objwaste > max_objwaste) - max_objwaste = objwaste; - if (s->objects > max_objects) - max_objects = s->objects; - if (used > max_used) - max_used = used; - if (s->objects_partial > max_partobj) - max_partobj = s->objects_partial; - if (percentage_partial_slabs > max_ppart) - max_ppart = percentage_partial_slabs; - if (percentage_partial_objs > max_ppartobj) - max_ppartobj = percentage_partial_objs; - if (s->slab_size > max_memobj) - max_memobj = s->slab_size; - - total_partial += s->partial; - total_slabs += s->slabs; - total_size += size; - total_waste += wasted; - - total_objects += s->objects; - total_used += used; - total_partobj += s->objects_partial; - total_ppart += percentage_partial_slabs; - total_ppartobj += percentage_partial_objs; - - total_objwaste += s->objects * objwaste; - total_objsize += s->objects * s->slab_size; - } - - if (!total_objects) { - printf("No objects\n"); - return; - } - if (!used_slabs) { - printf("No slabs\n"); - return; - } - - /* Per slab averages */ - avg_partial = total_partial / used_slabs; - avg_slabs = total_slabs / used_slabs; - avg_size = total_size / used_slabs; - avg_waste = total_waste / used_slabs; - - avg_objects = total_objects / used_slabs; - avg_used = total_used / used_slabs; - avg_partobj = total_partobj / used_slabs; - avg_ppart = total_ppart / used_slabs; - avg_ppartobj = total_ppartobj / used_slabs; - - /* Per object object sizes */ - avg_objsize = total_used / total_objects; - avg_objwaste = total_objwaste / total_objects; - avg_partobj = total_partobj * 100 / total_objects; - avg_memobj = total_objsize / total_objects; - - printf("Slabcache Totals\n"); - printf("----------------\n"); - printf("Slabcaches : %3d Aliases : %3d->%-3d Active: %3d\n", - slabs, aliases, alias_targets, used_slabs); - - store_size(b1, total_size);store_size(b2, total_waste); - store_size(b3, total_waste * 100 / total_used); - printf("Memory used: %6s # Loss : %6s MRatio:%6s%%\n", b1, b2, b3); - - store_size(b1, total_objects);store_size(b2, total_partobj); - store_size(b3, total_partobj * 100 / total_objects); - printf("# Objects : %6s # PartObj: %6s ORatio:%6s%%\n", b1, b2, b3); - - printf("\n"); - printf("Per Cache Average Min Max Total\n"); - printf("---------------------------------------------------------\n"); - - store_size(b1, avg_objects);store_size(b2, min_objects); - store_size(b3, max_objects);store_size(b4, total_objects); - printf("#Objects %10s %10s %10s %10s\n", - b1, b2, b3, b4); - - store_size(b1, avg_slabs);store_size(b2, min_slabs); - store_size(b3, max_slabs);store_size(b4, total_slabs); - printf("#Slabs %10s %10s %10s %10s\n", - b1, b2, b3, b4); - - store_size(b1, avg_partial);store_size(b2, min_partial); - store_size(b3, max_partial);store_size(b4, total_partial); - printf("#PartSlab %10s %10s %10s %10s\n", - b1, b2, b3, b4); - store_size(b1, avg_ppart);store_size(b2, min_ppart); - store_size(b3, max_ppart); - store_size(b4, total_partial * 100 / total_slabs); - printf("%%PartSlab%10s%% %10s%% %10s%% %10s%%\n", - b1, b2, b3, b4); - - store_size(b1, avg_partobj);store_size(b2, min_partobj); - store_size(b3, max_partobj); - store_size(b4, total_partobj); - printf("PartObjs %10s %10s %10s %10s\n", - b1, b2, b3, b4); - - store_size(b1, avg_ppartobj);store_size(b2, min_ppartobj); - store_size(b3, max_ppartobj); - store_size(b4, total_partobj * 100 / total_objects); - printf("%% PartObj%10s%% %10s%% %10s%% %10s%%\n", - b1, b2, b3, b4); - - store_size(b1, avg_size);store_size(b2, min_size); - store_size(b3, max_size);store_size(b4, total_size); - printf("Memory %10s %10s %10s %10s\n", - b1, b2, b3, b4); - - store_size(b1, avg_used);store_size(b2, min_used); - store_size(b3, max_used);store_size(b4, total_used); - printf("Used %10s %10s %10s %10s\n", - b1, b2, b3, b4); - - store_size(b1, avg_waste);store_size(b2, min_waste); - store_size(b3, max_waste);store_size(b4, total_waste); - printf("Loss %10s %10s %10s %10s\n", - b1, b2, b3, b4); - - printf("\n"); - printf("Per Object Average Min Max\n"); - printf("---------------------------------------------\n"); - - store_size(b1, avg_memobj);store_size(b2, min_memobj); - store_size(b3, max_memobj); - printf("Memory %10s %10s %10s\n", - b1, b2, b3); - store_size(b1, avg_objsize);store_size(b2, min_objsize); - store_size(b3, max_objsize); - printf("User %10s %10s %10s\n", - b1, b2, b3); - - store_size(b1, avg_objwaste);store_size(b2, min_objwaste); - store_size(b3, max_objwaste); - printf("Loss %10s %10s %10s\n", - b1, b2, b3); -} - -static void sort_slabs(void) -{ - struct slabinfo *s1,*s2; - - for (s1 = slabinfo; s1 < slabinfo + slabs; s1++) { - for (s2 = s1 + 1; s2 < slabinfo + slabs; s2++) { - int result; - - if (sort_size) - result = slab_size(s1) < slab_size(s2); - else if (sort_active) - result = slab_activity(s1) < slab_activity(s2); - else - result = strcasecmp(s1->name, s2->name); - - if (show_inverted) - result = -result; - - if (result > 0) { - struct slabinfo t; - - memcpy(&t, s1, sizeof(struct slabinfo)); - memcpy(s1, s2, sizeof(struct slabinfo)); - memcpy(s2, &t, sizeof(struct slabinfo)); - } - } - } -} - -static void sort_aliases(void) -{ - struct aliasinfo *a1,*a2; - - for (a1 = aliasinfo; a1 < aliasinfo + aliases; a1++) { - for (a2 = a1 + 1; a2 < aliasinfo + aliases; a2++) { - char *n1, *n2; - - n1 = a1->name; - n2 = a2->name; - if (show_alias && !show_inverted) { - n1 = a1->ref; - n2 = a2->ref; - } - if (strcasecmp(n1, n2) > 0) { - struct aliasinfo t; - - memcpy(&t, a1, sizeof(struct aliasinfo)); - memcpy(a1, a2, sizeof(struct aliasinfo)); - memcpy(a2, &t, sizeof(struct aliasinfo)); - } - } - } -} - -static void link_slabs(void) -{ - struct aliasinfo *a; - struct slabinfo *s; - - for (a = aliasinfo; a < aliasinfo + aliases; a++) { - - for (s = slabinfo; s < slabinfo + slabs; s++) - if (strcmp(a->ref, s->name) == 0) { - a->slab = s; - s->refs++; - break; - } - if (s == slabinfo + slabs) - fatal("Unresolved alias %s\n", a->ref); - } -} - -static void alias(void) -{ - struct aliasinfo *a; - char *active = NULL; - - sort_aliases(); - link_slabs(); - - for(a = aliasinfo; a < aliasinfo + aliases; a++) { - - if (!show_single_ref && a->slab->refs == 1) - continue; - - if (!show_inverted) { - if (active) { - if (strcmp(a->slab->name, active) == 0) { - printf(" %s", a->name); - continue; - } - } - printf("\n%-12s <- %s", a->slab->name, a->name); - active = a->slab->name; - } - else - printf("%-20s -> %s\n", a->name, a->slab->name); - } - if (active) - printf("\n"); -} - - -static void rename_slabs(void) -{ - struct slabinfo *s; - struct aliasinfo *a; - - for (s = slabinfo; s < slabinfo + slabs; s++) { - if (*s->name != ':') - continue; - - if (s->refs > 1 && !show_first_alias) - continue; - - a = find_one_alias(s); - - if (a) - s->name = a->name; - else { - s->name = "*"; - actual_slabs--; - } - } -} - -static int slab_mismatch(char *slab) -{ - return regexec(&pattern, slab, 0, NULL, 0); -} - -static void read_slab_dir(void) -{ - DIR *dir; - struct dirent *de; - struct slabinfo *slab = slabinfo; - struct aliasinfo *alias = aliasinfo; - char *p; - char *t; - int count; - - if (chdir("/sys/kernel/slab") && chdir("/sys/slab")) - fatal("SYSFS support for SLUB not active\n"); - - dir = opendir("."); - while ((de = readdir(dir))) { - if (de->d_name[0] == '.' || - (de->d_name[0] != ':' && slab_mismatch(de->d_name))) - continue; - switch (de->d_type) { - case DT_LNK: - alias->name = strdup(de->d_name); - count = readlink(de->d_name, buffer, sizeof(buffer)); - - if (count < 0) - fatal("Cannot read symlink %s\n", de->d_name); - - buffer[count] = 0; - p = buffer + count; - while (p > buffer && p[-1] != '/') - p--; - alias->ref = strdup(p); - alias++; - break; - case DT_DIR: - if (chdir(de->d_name)) - fatal("Unable to access slab %s\n", slab->name); - slab->name = strdup(de->d_name); - slab->alias = 0; - slab->refs = 0; - slab->aliases = get_obj("aliases"); - slab->align = get_obj("align"); - slab->cache_dma = get_obj("cache_dma"); - slab->cpu_slabs = get_obj("cpu_slabs"); - slab->destroy_by_rcu = get_obj("destroy_by_rcu"); - slab->hwcache_align = get_obj("hwcache_align"); - slab->object_size = get_obj("object_size"); - slab->objects = get_obj("objects"); - slab->objects_partial = get_obj("objects_partial"); - slab->objects_total = get_obj("objects_total"); - slab->objs_per_slab = get_obj("objs_per_slab"); - slab->order = get_obj("order"); - slab->partial = get_obj("partial"); - slab->partial = get_obj_and_str("partial", &t); - decode_numa_list(slab->numa_partial, t); - free(t); - slab->poison = get_obj("poison"); - slab->reclaim_account = get_obj("reclaim_account"); - slab->red_zone = get_obj("red_zone"); - slab->sanity_checks = get_obj("sanity_checks"); - slab->slab_size = get_obj("slab_size"); - slab->slabs = get_obj_and_str("slabs", &t); - decode_numa_list(slab->numa, t); - free(t); - slab->store_user = get_obj("store_user"); - slab->trace = get_obj("trace"); - slab->alloc_fastpath = get_obj("alloc_fastpath"); - slab->alloc_slowpath = get_obj("alloc_slowpath"); - slab->free_fastpath = get_obj("free_fastpath"); - slab->free_slowpath = get_obj("free_slowpath"); - slab->free_frozen= get_obj("free_frozen"); - slab->free_add_partial = get_obj("free_add_partial"); - slab->free_remove_partial = get_obj("free_remove_partial"); - slab->alloc_from_partial = get_obj("alloc_from_partial"); - slab->alloc_slab = get_obj("alloc_slab"); - slab->alloc_refill = get_obj("alloc_refill"); - slab->free_slab = get_obj("free_slab"); - slab->cpuslab_flush = get_obj("cpuslab_flush"); - slab->deactivate_full = get_obj("deactivate_full"); - slab->deactivate_empty = get_obj("deactivate_empty"); - slab->deactivate_to_head = get_obj("deactivate_to_head"); - slab->deactivate_to_tail = get_obj("deactivate_to_tail"); - slab->deactivate_remote_frees = get_obj("deactivate_remote_frees"); - slab->order_fallback = get_obj("order_fallback"); - chdir(".."); - if (slab->name[0] == ':') - alias_targets++; - slab++; - break; - default : - fatal("Unknown file type %lx\n", de->d_type); - } - } - closedir(dir); - slabs = slab - slabinfo; - actual_slabs = slabs; - aliases = alias - aliasinfo; - if (slabs > MAX_SLABS) - fatal("Too many slabs\n"); - if (aliases > MAX_ALIASES) - fatal("Too many aliases\n"); -} - -static void output_slabs(void) -{ - struct slabinfo *slab; - - for (slab = slabinfo; slab < slabinfo + slabs; slab++) { - - if (slab->alias) - continue; - - - if (show_numa) - slab_numa(slab, 0); - else if (show_track) - show_tracking(slab); - else if (validate) - slab_validate(slab); - else if (shrink) - slab_shrink(slab); - else if (set_debug) - slab_debug(slab); - else if (show_ops) - ops(slab); - else if (show_slab) - slabcache(slab); - else if (show_report) - report(slab); - } -} - -struct option opts[] = { - { "aliases", 0, NULL, 'a' }, - { "activity", 0, NULL, 'A' }, - { "debug", 2, NULL, 'd' }, - { "display-activity", 0, NULL, 'D' }, - { "empty", 0, NULL, 'e' }, - { "first-alias", 0, NULL, 'f' }, - { "help", 0, NULL, 'h' }, - { "inverted", 0, NULL, 'i'}, - { "numa", 0, NULL, 'n' }, - { "ops", 0, NULL, 'o' }, - { "report", 0, NULL, 'r' }, - { "shrink", 0, NULL, 's' }, - { "slabs", 0, NULL, 'l' }, - { "track", 0, NULL, 't'}, - { "validate", 0, NULL, 'v' }, - { "zero", 0, NULL, 'z' }, - { "1ref", 0, NULL, '1'}, - { NULL, 0, NULL, 0 } -}; - -int main(int argc, char *argv[]) -{ - int c; - int err; - char *pattern_source; - - page_size = getpagesize(); - - while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTS", - opts, NULL)) != -1) - switch (c) { - case '1': - show_single_ref = 1; - break; - case 'a': - show_alias = 1; - break; - case 'A': - sort_active = 1; - break; - case 'd': - set_debug = 1; - if (!debug_opt_scan(optarg)) - fatal("Invalid debug option '%s'\n", optarg); - break; - case 'D': - show_activity = 1; - break; - case 'e': - show_empty = 1; - break; - case 'f': - show_first_alias = 1; - break; - case 'h': - usage(); - return 0; - case 'i': - show_inverted = 1; - break; - case 'n': - show_numa = 1; - break; - case 'o': - show_ops = 1; - break; - case 'r': - show_report = 1; - break; - case 's': - shrink = 1; - break; - case 'l': - show_slab = 1; - break; - case 't': - show_track = 1; - break; - case 'v': - validate = 1; - break; - case 'z': - skip_zero = 0; - break; - case 'T': - show_totals = 1; - break; - case 'S': - sort_size = 1; - break; - - default: - fatal("%s: Invalid option '%c'\n", argv[0], optopt); - - } - - if (!show_slab && !show_alias && !show_track && !show_report - && !validate && !shrink && !set_debug && !show_ops) - show_slab = 1; - - if (argc > optind) - pattern_source = argv[optind]; - else - pattern_source = ".*"; - - err = regcomp(&pattern, pattern_source, REG_ICASE|REG_NOSUB); - if (err) - fatal("%s: Invalid pattern '%s' code %d\n", - argv[0], pattern_source, err); - read_slab_dir(); - if (show_alias) - alias(); - else - if (show_totals) - totals(); - else { - link_slabs(); - rename_slabs(); - sort_slabs(); - output_slabs(); - } - return 0; -} |