diff options
Diffstat (limited to 'Documentation')
205 files changed, 6467 insertions, 2369 deletions
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX index 06b982affe76..dd10b51b4e65 100644 --- a/Documentation/00-INDEX +++ b/Documentation/00-INDEX @@ -250,6 +250,8 @@ numastat.txt - info on how to read Numa policy hit/miss statistics in sysfs. oops-tracing.txt - how to decode those nasty internal kernel error dump messages. +padata.txt + - An introduction to the "padata" parallel execution API parisc/ - directory with info on using Linux on PA-RISC architecture. parport.txt diff --git a/Documentation/ABI/obsolete/sysfs-bus-usb b/Documentation/ABI/obsolete/sysfs-bus-usb new file mode 100644 index 000000000000..bd096d33fbc7 --- /dev/null +++ b/Documentation/ABI/obsolete/sysfs-bus-usb @@ -0,0 +1,31 @@ +What: /sys/bus/usb/devices/.../power/level +Date: March 2007 +KernelVersion: 2.6.21 +Contact: Alan Stern <stern@rowland.harvard.edu> +Description: + Each USB device directory will contain a file named + power/level. This file holds a power-level setting for + the device, either "on" or "auto". + + "on" means that the device is not allowed to autosuspend, + although normal suspends for system sleep will still + be honored. "auto" means the device will autosuspend + and autoresume in the usual manner, according to the + capabilities of its driver. + + During normal use, devices should be left in the "auto" + level. The "on" level is meant for administrative uses. + If you want to suspend a device immediately but leave it + free to wake up in response to I/O requests, you should + write "0" to power/autosuspend. + + Device not capable of proper suspend and resume should be + left in the "on" level. Although the USB spec requires + devices to support suspend/resume, many of them do not. + In fact so many don't that by default, the USB core + initializes all non-hub devices in the "on" level. Some + drivers may change this setting when they are bound. + + This file is deprecated and will be removed after 2010. + Use the power/control file instead; it does exactly the + same thing. diff --git a/Documentation/ABI/obsolete/sysfs-class-rfkill b/Documentation/ABI/obsolete/sysfs-class-rfkill new file mode 100644 index 000000000000..4201d5b05515 --- /dev/null +++ b/Documentation/ABI/obsolete/sysfs-class-rfkill @@ -0,0 +1,29 @@ +rfkill - radio frequency (RF) connector kill switch support + +For details to this subsystem look at Documentation/rfkill.txt. + +What: /sys/class/rfkill/rfkill[0-9]+/state +Date: 09-Jul-2007 +KernelVersion v2.6.22 +Contact: linux-wireless@vger.kernel.org +Description: Current state of the transmitter. + This file is deprecated and sheduled to be removed in 2014, + because its not possible to express the 'soft and hard block' + state of the rfkill driver. +Values: A numeric value. + 0: RFKILL_STATE_SOFT_BLOCKED + transmitter is turned off by software + 1: RFKILL_STATE_UNBLOCKED + transmitter is (potentially) active + 2: RFKILL_STATE_HARD_BLOCKED + transmitter is forced off by something outside of + the driver's control. + +What: /sys/class/rfkill/rfkill[0-9]+/claim +Date: 09-Jul-2007 +KernelVersion v2.6.22 +Contact: linux-wireless@vger.kernel.org +Description: This file is deprecated because there no longer is a way to + claim just control over a single rfkill instance. + This file is scheduled to be removed in 2012. +Values: 0: Kernel handles events diff --git a/Documentation/ABI/stable/sysfs-class-rfkill b/Documentation/ABI/stable/sysfs-class-rfkill new file mode 100644 index 000000000000..097f522c33bb --- /dev/null +++ b/Documentation/ABI/stable/sysfs-class-rfkill @@ -0,0 +1,67 @@ +rfkill - radio frequency (RF) connector kill switch support + +For details to this subsystem look at Documentation/rfkill.txt. + +For the deprecated /sys/class/rfkill/*/state and +/sys/class/rfkill/*/claim knobs of this interface look in +Documentation/ABI/obsolete/sysfs-class-rfkill. + +What: /sys/class/rfkill +Date: 09-Jul-2007 +KernelVersion: v2.6.22 +Contact: linux-wireless@vger.kernel.org, +Description: The rfkill class subsystem folder. + Each registered rfkill driver is represented by an rfkillX + subfolder (X being an integer > 0). + + +What: /sys/class/rfkill/rfkill[0-9]+/name +Date: 09-Jul-2007 +KernelVersion v2.6.22 +Contact: linux-wireless@vger.kernel.org +Description: Name assigned by driver to this key (interface or driver name). +Values: arbitrary string. + + +What: /sys/class/rfkill/rfkill[0-9]+/type +Date: 09-Jul-2007 +KernelVersion v2.6.22 +Contact: linux-wireless@vger.kernel.org +Description: Driver type string ("wlan", "bluetooth", etc). +Values: See include/linux/rfkill.h. + + +What: /sys/class/rfkill/rfkill[0-9]+/persistent +Date: 09-Jul-2007 +KernelVersion v2.6.22 +Contact: linux-wireless@vger.kernel.org +Description: Whether the soft blocked state is initialised from non-volatile + storage at startup. +Values: A numeric value. + 0: false + 1: true + + +What: /sys/class/rfkill/rfkill[0-9]+/hard +Date: 12-March-2010 +KernelVersion v2.6.34 +Contact: linux-wireless@vger.kernel.org +Description: Current hardblock state. This file is read only. +Values: A numeric value. + 0: inactive + The transmitter is (potentially) active. + 1: active + The transmitter is forced off by something outside of + the driver's control. + + +What: /sys/class/rfkill/rfkill[0-9]+/soft +Date: 12-March-2010 +KernelVersion v2.6.34 +Contact: linux-wireless@vger.kernel.org +Description: Current softblock state. This file is read and write. +Values: A numeric value. + 0: inactive + The transmitter is (potentially) active. + 1: active + The transmitter is turned off by software. diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb index a986e9bbba3d..294aa864a60a 100644 --- a/Documentation/ABI/testing/sysfs-bus-usb +++ b/Documentation/ABI/testing/sysfs-bus-usb @@ -14,34 +14,6 @@ Description: The autosuspend delay for newly-created devices is set to the value of the usbcore.autosuspend module parameter. -What: /sys/bus/usb/devices/.../power/level -Date: March 2007 -KernelVersion: 2.6.21 -Contact: Alan Stern <stern@rowland.harvard.edu> -Description: - Each USB device directory will contain a file named - power/level. This file holds a power-level setting for - the device, either "on" or "auto". - - "on" means that the device is not allowed to autosuspend, - although normal suspends for system sleep will still - be honored. "auto" means the device will autosuspend - and autoresume in the usual manner, according to the - capabilities of its driver. - - During normal use, devices should be left in the "auto" - level. The "on" level is meant for administrative uses. - If you want to suspend a device immediately but leave it - free to wake up in response to I/O requests, you should - write "0" to power/autosuspend. - - Device not capable of proper suspend and resume should be - left in the "on" level. Although the USB spec requires - devices to support suspend/resume, many of them do not. - In fact so many don't that by default, the USB core - initializes all non-hub devices in the "on" level. Some - drivers may change this setting when they are bound. - What: /sys/bus/usb/devices/.../power/persist Date: May 2007 KernelVersion: 2.6.23 @@ -160,7 +132,7 @@ Description: match the driver to the device. For example: # echo "046d c315" > /sys/bus/usb/drivers/foo/remove_id -What: /sys/bus/usb/device/.../avoid_reset +What: /sys/bus/usb/device/.../avoid_reset_quirk Date: December 2009 Contact: Oliver Neukum <oliver@neukum.org> Description: diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory index bf1627b02a03..aba7d989208c 100644 --- a/Documentation/ABI/testing/sysfs-devices-memory +++ b/Documentation/ABI/testing/sysfs-devices-memory @@ -43,7 +43,7 @@ Date: September 2008 Contact: Badari Pulavarty <pbadari@us.ibm.com> Description: The file /sys/devices/system/memory/memoryX/state - is read-write. When read, it's contents show the + is read-write. When read, its contents show the online/offline state of the memory section. When written, root can toggle the the online/offline state of a removable memory section (see removable file description above) diff --git a/Documentation/ABI/testing/sysfs-devices-platform-_UDC_-gadget b/Documentation/ABI/testing/sysfs-devices-platform-_UDC_-gadget new file mode 100644 index 000000000000..34034027b13c --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-platform-_UDC_-gadget @@ -0,0 +1,9 @@ +What: /sys/devices/platform/_UDC_/gadget/suspended +Date: April 2010 +Contact: Fabien Chouteau <fabien.chouteau@barco.com> +Description: + Show the suspend state of an USB composite gadget. + 1 -> suspended + 0 -> resumed + + (_UDC_ is the name of the USB Device Controller driver) diff --git a/Documentation/Changes b/Documentation/Changes index f08b313cd235..eca9f6e6fbe6 100644 --- a/Documentation/Changes +++ b/Documentation/Changes @@ -49,7 +49,7 @@ o oprofile 0.9 # oprofiled --version o udev 081 # udevinfo -V o grub 0.93 # grub --version o mcelog 0.6 -o iptables 1.4.1 # iptables -V +o iptables 1.4.2 # iptables -V Kernel compilation diff --git a/Documentation/PCI/PCI-DMA-mapping.txt b/Documentation/DMA-API-HOWTO.txt index ecad88d9fe59..2e435adfbd6b 100644 --- a/Documentation/PCI/PCI-DMA-mapping.txt +++ b/Documentation/DMA-API-HOWTO.txt @@ -1,12 +1,12 @@ - Dynamic DMA mapping - =================== + Dynamic DMA mapping Guide + ========================= David S. Miller <davem@redhat.com> Richard Henderson <rth@cygnus.com> Jakub Jelinek <jakub@redhat.com> -This document describes the DMA mapping system in terms of the pci_ -API. For a similar API that works for generic devices, see +This is a guide to device driver writers on how to use the DMA API +with example pseudo-code. For a concise description of the API, see DMA-API.txt. Most of the 64bit platforms have special hardware that translates bus @@ -26,12 +26,15 @@ mapped only for the time they are actually used and unmapped after the DMA transfer. The following API will work of course even on platforms where no such -hardware exists, see e.g. arch/x86/include/asm/pci.h for how it is implemented on -top of the virt_to_bus interface. +hardware exists. + +Note that the DMA API works with any bus independent of the underlying +microprocessor architecture. You should use the DMA API rather than +the bus specific DMA API (e.g. pci_dma_*). First of all, you should make sure -#include <linux/pci.h> +#include <linux/dma-mapping.h> is in your driver. This file will obtain for you the definition of the dma_addr_t (which can hold any valid DMA address for the platform) @@ -78,44 +81,43 @@ for you to DMA from/to. DMA addressing limitations Does your device have any DMA addressing limitations? For example, is -your device only capable of driving the low order 24-bits of address -on the PCI bus for SAC DMA transfers? If so, you need to inform the -PCI layer of this fact. +your device only capable of driving the low order 24-bits of address? +If so, you need to inform the kernel of this fact. By default, the kernel assumes that your device can address the full -32-bits in a SAC cycle. For a 64-bit DAC capable device, this needs -to be increased. And for a device with limitations, as discussed in -the previous paragraph, it needs to be decreased. - -pci_alloc_consistent() by default will return 32-bit DMA addresses. -PCI-X specification requires PCI-X devices to support 64-bit -addressing (DAC) for all transactions. And at least one platform (SGI -SN2) requires 64-bit consistent allocations to operate correctly when -the IO bus is in PCI-X mode. Therefore, like with pci_set_dma_mask(), -it's good practice to call pci_set_consistent_dma_mask() to set the -appropriate mask even if your device only supports 32-bit DMA -(default) and especially if it's a PCI-X device. - -For correct operation, you must interrogate the PCI layer in your -device probe routine to see if the PCI controller on the machine can -properly support the DMA addressing limitation your device has. It is -good style to do this even if your device holds the default setting, +32-bits. For a 64-bit capable device, this needs to be increased. +And for a device with limitations, as discussed in the previous +paragraph, it needs to be decreased. + +Special note about PCI: PCI-X specification requires PCI-X devices to +support 64-bit addressing (DAC) for all transactions. And at least +one platform (SGI SN2) requires 64-bit consistent allocations to +operate correctly when the IO bus is in PCI-X mode. + +For correct operation, you must interrogate the kernel in your device +probe routine to see if the DMA controller on the machine can properly +support the DMA addressing limitation your device has. It is good +style to do this even if your device holds the default setting, because this shows that you did think about these issues wrt. your device. -The query is performed via a call to pci_set_dma_mask(): +The query is performed via a call to dma_set_mask(): - int pci_set_dma_mask(struct pci_dev *pdev, u64 device_mask); + int dma_set_mask(struct device *dev, u64 mask); The query for consistent allocations is performed via a call to -pci_set_consistent_dma_mask(): +dma_set_coherent_mask(): - int pci_set_consistent_dma_mask(struct pci_dev *pdev, u64 device_mask); + int dma_set_coherent_mask(struct device *dev, u64 mask); -Here, pdev is a pointer to the PCI device struct of your device, and -device_mask is a bit mask describing which bits of a PCI address your -device supports. It returns zero if your card can perform DMA -properly on the machine given the address mask you provided. +Here, dev is a pointer to the device struct of your device, and mask +is a bit mask describing which bits of an address your device +supports. It returns zero if your card can perform DMA properly on +the machine given the address mask you provided. In general, the +device struct of your device is embedded in the bus specific device +struct of your device. For example, a pointer to the device struct of +your PCI device is pdev->dev (pdev is a pointer to the PCI device +struct of your device). If it returns non-zero, your device cannot perform DMA properly on this platform, and attempting to do so will result in undefined @@ -133,31 +135,30 @@ of your driver reports that performance is bad or that the device is not even detected, you can ask them for the kernel messages to find out exactly why. -The standard 32-bit addressing PCI device would do something like -this: +The standard 32-bit addressing device would do something like this: - if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) { + if (dma_set_mask(dev, DMA_BIT_MASK(32))) { printk(KERN_WARNING "mydev: No suitable DMA available.\n"); goto ignore_this_device; } -Another common scenario is a 64-bit capable device. The approach -here is to try for 64-bit DAC addressing, but back down to a -32-bit mask should that fail. The PCI platform code may fail the -64-bit mask not because the platform is not capable of 64-bit -addressing. Rather, it may fail in this case simply because -32-bit SAC addressing is done more efficiently than DAC addressing. -Sparc64 is one platform which behaves in this way. +Another common scenario is a 64-bit capable device. The approach here +is to try for 64-bit addressing, but back down to a 32-bit mask that +should not fail. The kernel may fail the 64-bit mask not because the +platform is not capable of 64-bit addressing. Rather, it may fail in +this case simply because 32-bit addressing is done more efficiently +than 64-bit addressing. For example, Sparc64 PCI SAC addressing is +more efficient than DAC addressing. Here is how you would handle a 64-bit capable device which can drive all 64-bits when accessing streaming DMA: int using_dac; - if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) { + if (!dma_set_mask(dev, DMA_BIT_MASK(64))) { using_dac = 1; - } else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) { + } else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) { using_dac = 0; } else { printk(KERN_WARNING @@ -170,36 +171,36 @@ the case would look like this: int using_dac, consistent_using_dac; - if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) { + if (!dma_set_mask(dev, DMA_BIT_MASK(64))) { using_dac = 1; consistent_using_dac = 1; - pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); - } else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) { + dma_set_coherent_mask(dev, DMA_BIT_MASK(64)); + } else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) { using_dac = 0; consistent_using_dac = 0; - pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); } else { printk(KERN_WARNING "mydev: No suitable DMA available.\n"); goto ignore_this_device; } -pci_set_consistent_dma_mask() will always be able to set the same or a -smaller mask as pci_set_dma_mask(). However for the rare case that a +dma_set_coherent_mask() will always be able to set the same or a +smaller mask as dma_set_mask(). However for the rare case that a device driver only uses consistent allocations, one would have to -check the return value from pci_set_consistent_dma_mask(). +check the return value from dma_set_coherent_mask(). Finally, if your device can only drive the low 24-bits of -address during PCI bus mastering you might do something like: +address you might do something like: - if (pci_set_dma_mask(pdev, DMA_BIT_MASK(24))) { + if (dma_set_mask(dev, DMA_BIT_MASK(24))) { printk(KERN_WARNING "mydev: 24-bit DMA addressing not available.\n"); goto ignore_this_device; } -When pci_set_dma_mask() is successful, and returns zero, the PCI layer -saves away this mask you have provided. The PCI layer will use this +When dma_set_mask() is successful, and returns zero, the kernel saves +away this mask you have provided. The kernel will use this information later when you make DMA mappings. There is a case which we are aware of at this time, which is worth @@ -208,7 +209,7 @@ functions (for example a sound card provides playback and record functions) and the various different functions have _different_ DMA addressing limitations, you may wish to probe each mask and only provide the functionality which the machine can handle. It -is important that the last call to pci_set_dma_mask() be for the +is important that the last call to dma_set_mask() be for the most specific mask. Here is pseudo-code showing how this might be done: @@ -217,17 +218,17 @@ Here is pseudo-code showing how this might be done: #define RECORD_ADDRESS_BITS DMA_BIT_MASK(24) struct my_sound_card *card; - struct pci_dev *pdev; + struct device *dev; ... - if (!pci_set_dma_mask(pdev, PLAYBACK_ADDRESS_BITS)) { + if (!dma_set_mask(dev, PLAYBACK_ADDRESS_BITS)) { card->playback_enabled = 1; } else { card->playback_enabled = 0; printk(KERN_WARNING "%s: Playback disabled due to DMA limitations.\n", card->name); } - if (!pci_set_dma_mask(pdev, RECORD_ADDRESS_BITS)) { + if (!dma_set_mask(dev, RECORD_ADDRESS_BITS)) { card->record_enabled = 1; } else { card->record_enabled = 0; @@ -252,8 +253,8 @@ There are two types of DMA mappings: Think of "consistent" as "synchronous" or "coherent". The current default is to return consistent memory in the low 32 - bits of the PCI bus space. However, for future compatibility you - should set the consistent mask even if this default is fine for your + bits of the bus space. However, for future compatibility you should + set the consistent mask even if this default is fine for your driver. Good examples of what to use consistent mappings for are: @@ -285,9 +286,9 @@ There are two types of DMA mappings: found in PCI bridges (such as by reading a register's value after writing it). -- Streaming DMA mappings which are usually mapped for one DMA transfer, - unmapped right after it (unless you use pci_dma_sync_* below) and for which - hardware can optimize for sequential accesses. +- Streaming DMA mappings which are usually mapped for one DMA + transfer, unmapped right after it (unless you use dma_sync_* below) + and for which hardware can optimize for sequential accesses. This of "streaming" as "asynchronous" or "outside the coherency domain". @@ -302,8 +303,8 @@ There are two types of DMA mappings: optimizations the hardware allows. To this end, when using such mappings you must be explicit about what you want to happen. -Neither type of DMA mapping has alignment restrictions that come -from PCI, although some devices may have such restrictions. +Neither type of DMA mapping has alignment restrictions that come from +the underlying bus, although some devices may have such restrictions. Also, systems with caches that aren't DMA-coherent will work better when the underlying buffers don't share cache lines with other data. @@ -315,33 +316,27 @@ you should do: dma_addr_t dma_handle; - cpu_addr = pci_alloc_consistent(pdev, size, &dma_handle); - -where pdev is a struct pci_dev *. This may be called in interrupt context. -You should use dma_alloc_coherent (see DMA-API.txt) for buses -where devices don't have struct pci_dev (like ISA, EISA). + cpu_addr = dma_alloc_coherent(dev, size, &dma_handle, gfp); -This argument is needed because the DMA translations may be bus -specific (and often is private to the bus which the device is attached -to). +where device is a struct device *. This may be called in interrupt +context with the GFP_ATOMIC flag. Size is the length of the region you want to allocate, in bytes. This routine will allocate RAM for that region, so it acts similarly to __get_free_pages (but takes size instead of a page order). If your driver needs regions sized smaller than a page, you may prefer using -the pci_pool interface, described below. - -The consistent DMA mapping interfaces, for non-NULL pdev, will by -default return a DMA address which is SAC (Single Address Cycle) -addressable. Even if the device indicates (via PCI dma mask) that it -may address the upper 32-bits and thus perform DAC cycles, consistent -allocation will only return > 32-bit PCI addresses for DMA if the -consistent dma mask has been explicitly changed via -pci_set_consistent_dma_mask(). This is true of the pci_pool interface -as well. - -pci_alloc_consistent returns two values: the virtual address which you +the dma_pool interface, described below. + +The consistent DMA mapping interfaces, for non-NULL dev, will by +default return a DMA address which is 32-bit addressable. Even if the +device indicates (via DMA mask) that it may address the upper 32-bits, +consistent allocation will only return > 32-bit addresses for DMA if +the consistent DMA mask has been explicitly changed via +dma_set_coherent_mask(). This is true of the dma_pool interface as +well. + +dma_alloc_coherent returns two values: the virtual address which you can use to access it from the CPU and dma_handle which you pass to the card. @@ -354,54 +349,54 @@ buffer you receive will not cross a 64K boundary. To unmap and free such a DMA region, you call: - pci_free_consistent(pdev, size, cpu_addr, dma_handle); + dma_free_coherent(dev, size, cpu_addr, dma_handle); -where pdev, size are the same as in the above call and cpu_addr and -dma_handle are the values pci_alloc_consistent returned to you. +where dev, size are the same as in the above call and cpu_addr and +dma_handle are the values dma_alloc_coherent returned to you. This function may not be called in interrupt context. If your driver needs lots of smaller memory regions, you can write -custom code to subdivide pages returned by pci_alloc_consistent, -or you can use the pci_pool API to do that. A pci_pool is like -a kmem_cache, but it uses pci_alloc_consistent not __get_free_pages. +custom code to subdivide pages returned by dma_alloc_coherent, +or you can use the dma_pool API to do that. A dma_pool is like +a kmem_cache, but it uses dma_alloc_coherent not __get_free_pages. Also, it understands common hardware constraints for alignment, like queue heads needing to be aligned on N byte boundaries. -Create a pci_pool like this: +Create a dma_pool like this: - struct pci_pool *pool; + struct dma_pool *pool; - pool = pci_pool_create(name, pdev, size, align, alloc); + pool = dma_pool_create(name, dev, size, align, alloc); -The "name" is for diagnostics (like a kmem_cache name); pdev and size +The "name" is for diagnostics (like a kmem_cache name); dev and size are as above. The device's hardware alignment requirement for this type of data is "align" (which is expressed in bytes, and must be a power of two). If your device has no boundary crossing restrictions, pass 0 for alloc; passing 4096 says memory allocated from this pool must not cross 4KByte boundaries (but at that time it may be better to -go for pci_alloc_consistent directly instead). +go for dma_alloc_coherent directly instead). -Allocate memory from a pci pool like this: +Allocate memory from a dma pool like this: - cpu_addr = pci_pool_alloc(pool, flags, &dma_handle); + cpu_addr = dma_pool_alloc(pool, flags, &dma_handle); flags are SLAB_KERNEL if blocking is permitted (not in_interrupt nor -holding SMP locks), SLAB_ATOMIC otherwise. Like pci_alloc_consistent, +holding SMP locks), SLAB_ATOMIC otherwise. Like dma_alloc_coherent, this returns two values, cpu_addr and dma_handle. -Free memory that was allocated from a pci_pool like this: +Free memory that was allocated from a dma_pool like this: - pci_pool_free(pool, cpu_addr, dma_handle); + dma_pool_free(pool, cpu_addr, dma_handle); -where pool is what you passed to pci_pool_alloc, and cpu_addr and -dma_handle are the values pci_pool_alloc returned. This function +where pool is what you passed to dma_pool_alloc, and cpu_addr and +dma_handle are the values dma_pool_alloc returned. This function may be called in interrupt context. -Destroy a pci_pool by calling: +Destroy a dma_pool by calling: - pci_pool_destroy(pool); + dma_pool_destroy(pool); -Make sure you've called pci_pool_free for all memory allocated +Make sure you've called dma_pool_free for all memory allocated from a pool before you destroy the pool. This function may not be called in interrupt context. @@ -411,15 +406,15 @@ The interfaces described in subsequent portions of this document take a DMA direction argument, which is an integer and takes on one of the following values: - PCI_DMA_BIDIRECTIONAL - PCI_DMA_TODEVICE - PCI_DMA_FROMDEVICE - PCI_DMA_NONE + DMA_BIDIRECTIONAL + DMA_TO_DEVICE + DMA_FROM_DEVICE + DMA_NONE One should provide the exact DMA direction if you know it. -PCI_DMA_TODEVICE means "from main memory to the PCI device" -PCI_DMA_FROMDEVICE means "from the PCI device to main memory" +DMA_TO_DEVICE means "from main memory to the device" +DMA_FROM_DEVICE means "from the device to main memory" It is the direction in which the data moves during the DMA transfer. @@ -427,12 +422,12 @@ You are _strongly_ encouraged to specify this as precisely as you possibly can. If you absolutely cannot know the direction of the DMA transfer, -specify PCI_DMA_BIDIRECTIONAL. It means that the DMA can go in +specify DMA_BIDIRECTIONAL. It means that the DMA can go in either direction. The platform guarantees that you may legally specify this, and that it will work, but this may be at the cost of performance for example. -The value PCI_DMA_NONE is to be used for debugging. One can +The value DMA_NONE is to be used for debugging. One can hold this in a data structure before you come to know the precise direction, and this will help catch cases where your direction tracking logic has failed to set things up properly. @@ -442,21 +437,21 @@ potential platform-specific optimizations of such) is for debugging. Some platforms actually have a write permission boolean which DMA mappings can be marked with, much like page protections in the user program address space. Such platforms can and do report errors in the -kernel logs when the PCI controller hardware detects violation of the +kernel logs when the DMA controller hardware detects violation of the permission setting. Only streaming mappings specify a direction, consistent mappings implicitly have a direction attribute setting of -PCI_DMA_BIDIRECTIONAL. +DMA_BIDIRECTIONAL. The SCSI subsystem tells you the direction to use in the 'sc_data_direction' member of the SCSI command your driver is working on. For Networking drivers, it's a rather simple affair. For transmit -packets, map/unmap them with the PCI_DMA_TODEVICE direction +packets, map/unmap them with the DMA_TO_DEVICE direction specifier. For receive packets, just the opposite, map/unmap them -with the PCI_DMA_FROMDEVICE direction specifier. +with the DMA_FROM_DEVICE direction specifier. Using Streaming DMA mappings @@ -467,43 +462,43 @@ scatterlist. To map a single region, you do: - struct pci_dev *pdev = mydev->pdev; + struct device *dev = &my_dev->dev; dma_addr_t dma_handle; void *addr = buffer->ptr; size_t size = buffer->len; - dma_handle = pci_map_single(pdev, addr, size, direction); + dma_handle = dma_map_single(dev, addr, size, direction); and to unmap it: - pci_unmap_single(pdev, dma_handle, size, direction); + dma_unmap_single(dev, dma_handle, size, direction); -You should call pci_unmap_single when the DMA activity is finished, e.g. +You should call dma_unmap_single when the DMA activity is finished, e.g. from the interrupt which told you that the DMA transfer is done. Using cpu pointers like this for single mappings has a disadvantage, you cannot reference HIGHMEM memory in this way. Thus, there is a -map/unmap interface pair akin to pci_{map,unmap}_single. These +map/unmap interface pair akin to dma_{map,unmap}_single. These interfaces deal with page/offset pairs instead of cpu pointers. Specifically: - struct pci_dev *pdev = mydev->pdev; + struct device *dev = &my_dev->dev; dma_addr_t dma_handle; struct page *page = buffer->page; unsigned long offset = buffer->offset; size_t size = buffer->len; - dma_handle = pci_map_page(pdev, page, offset, size, direction); + dma_handle = dma_map_page(dev, page, offset, size, direction); ... - pci_unmap_page(pdev, dma_handle, size, direction); + dma_unmap_page(dev, dma_handle, size, direction); Here, "offset" means byte offset within the given page. With scatterlists, you map a region gathered from several regions by: - int i, count = pci_map_sg(pdev, sglist, nents, direction); + int i, count = dma_map_sg(dev, sglist, nents, direction); struct scatterlist *sg; for_each_sg(sglist, sg, count, i) { @@ -527,16 +522,16 @@ accessed sg->address and sg->length as shown above. To unmap a scatterlist, just call: - pci_unmap_sg(pdev, sglist, nents, direction); + dma_unmap_sg(dev, sglist, nents, direction); Again, make sure DMA activity has already finished. -PLEASE NOTE: The 'nents' argument to the pci_unmap_sg call must be - the _same_ one you passed into the pci_map_sg call, +PLEASE NOTE: The 'nents' argument to the dma_unmap_sg call must be + the _same_ one you passed into the dma_map_sg call, it should _NOT_ be the 'count' value _returned_ from the - pci_map_sg call. + dma_map_sg call. -Every pci_map_{single,sg} call should have its pci_unmap_{single,sg} +Every dma_map_{single,sg} call should have its dma_unmap_{single,sg} counterpart, because the bus address space is a shared resource (although in some ports the mapping is per each BUS so less devices contend for the same bus address space) and you could render the machine unusable by eating @@ -547,14 +542,14 @@ the data in between the DMA transfers, the buffer needs to be synced properly in order for the cpu and device to see the most uptodate and correct copy of the DMA buffer. -So, firstly, just map it with pci_map_{single,sg}, and after each DMA +So, firstly, just map it with dma_map_{single,sg}, and after each DMA transfer call either: - pci_dma_sync_single_for_cpu(pdev, dma_handle, size, direction); + dma_sync_single_for_cpu(dev, dma_handle, size, direction); or: - pci_dma_sync_sg_for_cpu(pdev, sglist, nents, direction); + dma_sync_sg_for_cpu(dev, sglist, nents, direction); as appropriate. @@ -562,27 +557,27 @@ Then, if you wish to let the device get at the DMA area again, finish accessing the data with the cpu, and then before actually giving the buffer to the hardware call either: - pci_dma_sync_single_for_device(pdev, dma_handle, size, direction); + dma_sync_single_for_device(dev, dma_handle, size, direction); or: - pci_dma_sync_sg_for_device(dev, sglist, nents, direction); + dma_sync_sg_for_device(dev, sglist, nents, direction); as appropriate. After the last DMA transfer call one of the DMA unmap routines -pci_unmap_{single,sg}. If you don't touch the data from the first pci_map_* -call till pci_unmap_*, then you don't have to call the pci_dma_sync_* +dma_unmap_{single,sg}. If you don't touch the data from the first dma_map_* +call till dma_unmap_*, then you don't have to call the dma_sync_* routines at all. Here is pseudo code which shows a situation in which you would need -to use the pci_dma_sync_*() interfaces. +to use the dma_sync_*() interfaces. my_card_setup_receive_buffer(struct my_card *cp, char *buffer, int len) { dma_addr_t mapping; - mapping = pci_map_single(cp->pdev, buffer, len, PCI_DMA_FROMDEVICE); + mapping = dma_map_single(cp->dev, buffer, len, DMA_FROM_DEVICE); cp->rx_buf = buffer; cp->rx_len = len; @@ -606,25 +601,25 @@ to use the pci_dma_sync_*() interfaces. * the DMA transfer with the CPU first * so that we see updated contents. */ - pci_dma_sync_single_for_cpu(cp->pdev, cp->rx_dma, - cp->rx_len, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&cp->dev, cp->rx_dma, + cp->rx_len, + DMA_FROM_DEVICE); /* Now it is safe to examine the buffer. */ hp = (struct my_card_header *) cp->rx_buf; if (header_is_ok(hp)) { - pci_unmap_single(cp->pdev, cp->rx_dma, cp->rx_len, - PCI_DMA_FROMDEVICE); + dma_unmap_single(&cp->dev, cp->rx_dma, cp->rx_len, + DMA_FROM_DEVICE); pass_to_upper_layers(cp->rx_buf); make_and_setup_new_rx_buf(cp); } else { /* Just sync the buffer and give it back * to the card. */ - pci_dma_sync_single_for_device(cp->pdev, - cp->rx_dma, - cp->rx_len, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&cp->dev, + cp->rx_dma, + cp->rx_len, + DMA_FROM_DEVICE); give_rx_buf_to_card(cp); } } @@ -634,19 +629,19 @@ Drivers converted fully to this interface should not use virt_to_bus any longer, nor should they use bus_to_virt. Some drivers have to be changed a little bit, because there is no longer an equivalent to bus_to_virt in the dynamic DMA mapping scheme - you have to always store the DMA addresses -returned by the pci_alloc_consistent, pci_pool_alloc, and pci_map_single -calls (pci_map_sg stores them in the scatterlist itself if the platform +returned by the dma_alloc_coherent, dma_pool_alloc, and dma_map_single +calls (dma_map_sg stores them in the scatterlist itself if the platform supports dynamic DMA mapping in hardware) in your driver structures and/or in the card registers. -All PCI drivers should be using these interfaces with no exceptions. -It is planned to completely remove virt_to_bus() and bus_to_virt() as +All drivers should be using these interfaces with no exceptions. It +is planned to completely remove virt_to_bus() and bus_to_virt() as they are entirely deprecated. Some ports already do not provide these as it is impossible to correctly support them. Optimizing Unmap State Space Consumption -On many platforms, pci_unmap_{single,page}() is simply a nop. +On many platforms, dma_unmap_{single,page}() is simply a nop. Therefore, keeping track of the mapping address and length is a waste of space. Instead of filling your drivers up with ifdefs and the like to "work around" this (which would defeat the whole purpose of a @@ -655,7 +650,7 @@ portable API) the following facilities are provided. Actually, instead of describing the macros one by one, we'll transform some example code. -1) Use DECLARE_PCI_UNMAP_{ADDR,LEN} in state saving structures. +1) Use DEFINE_DMA_UNMAP_{ADDR,LEN} in state saving structures. Example, before: struct ring_state { @@ -668,14 +663,11 @@ transform some example code. struct ring_state { struct sk_buff *skb; - DECLARE_PCI_UNMAP_ADDR(mapping) - DECLARE_PCI_UNMAP_LEN(len) + DEFINE_DMA_UNMAP_ADDR(mapping); + DEFINE_DMA_UNMAP_LEN(len); }; - NOTE: DO NOT put a semicolon at the end of the DECLARE_*() - macro. - -2) Use pci_unmap_{addr,len}_set to set these values. +2) Use dma_unmap_{addr,len}_set to set these values. Example, before: ringp->mapping = FOO; @@ -683,21 +675,21 @@ transform some example code. after: - pci_unmap_addr_set(ringp, mapping, FOO); - pci_unmap_len_set(ringp, len, BAR); + dma_unmap_addr_set(ringp, mapping, FOO); + dma_unmap_len_set(ringp, len, BAR); -3) Use pci_unmap_{addr,len} to access these values. +3) Use dma_unmap_{addr,len} to access these values. Example, before: - pci_unmap_single(pdev, ringp->mapping, ringp->len, - PCI_DMA_FROMDEVICE); + dma_unmap_single(dev, ringp->mapping, ringp->len, + DMA_FROM_DEVICE); after: - pci_unmap_single(pdev, - pci_unmap_addr(ringp, mapping), - pci_unmap_len(ringp, len), - PCI_DMA_FROMDEVICE); + dma_unmap_single(dev, + dma_unmap_addr(ringp, mapping), + dma_unmap_len(ringp, len), + DMA_FROM_DEVICE); It really should be self-explanatory. We treat the ADDR and LEN separately, because it is possible for an implementation to only @@ -732,15 +724,15 @@ to "Closing". DMA address space is limited on some architectures and an allocation failure can be determined by: -- checking if pci_alloc_consistent returns NULL or pci_map_sg returns 0 +- checking if dma_alloc_coherent returns NULL or dma_map_sg returns 0 -- checking the returned dma_addr_t of pci_map_single and pci_map_page - by using pci_dma_mapping_error(): +- checking the returned dma_addr_t of dma_map_single and dma_map_page + by using dma_mapping_error(): dma_addr_t dma_handle; - dma_handle = pci_map_single(pdev, addr, size, direction); - if (pci_dma_mapping_error(pdev, dma_handle)) { + dma_handle = dma_map_single(dev, addr, size, direction); + if (dma_mapping_error(dev, dma_handle)) { /* * reduce current DMA mapping usage, * delay and try again later or @@ -750,7 +742,7 @@ failure can be determined by: Closing -This document, and the API itself, would not be in it's current +This document, and the API itself, would not be in its current form without the feedback and suggestions from numerous individuals. We would like to specifically mention, in no particular order, the following people: diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 5aceb88b3f8b..05e2ae236865 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -4,20 +4,18 @@ James E.J. Bottomley <James.Bottomley@HansenPartnership.com> This document describes the DMA API. For a more gentle introduction -phrased in terms of the pci_ equivalents (and actual examples) see -Documentation/PCI/PCI-DMA-mapping.txt. +of the API (and actual examples) see +Documentation/DMA-API-HOWTO.txt. -This API is split into two pieces. Part I describes the API and the -corresponding pci_ API. Part II describes the extensions to the API -for supporting non-consistent memory machines. Unless you know that -your driver absolutely has to support non-consistent platforms (this -is usually only legacy platforms) you should only use the API -described in part I. +This API is split into two pieces. Part I describes the API. Part II +describes the extensions to the API for supporting non-consistent +memory machines. Unless you know that your driver absolutely has to +support non-consistent platforms (this is usually only legacy +platforms) you should only use the API described in part I. -Part I - pci_ and dma_ Equivalent API +Part I - dma_ API ------------------------------------- -To get the pci_ API, you must #include <linux/pci.h> To get the dma_ API, you must #include <linux/dma-mapping.h> @@ -27,9 +25,6 @@ Part Ia - Using large dma-coherent buffers void * dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag) -void * -pci_alloc_consistent(struct pci_dev *dev, size_t size, - dma_addr_t *dma_handle) Consistent memory is memory for which a write by either the device or the processor can immediately be read by the processor or device @@ -53,15 +48,11 @@ The simplest way to do that is to use the dma_pool calls (see below). The flag parameter (dma_alloc_coherent only) allows the caller to specify the GFP_ flags (see kmalloc) for the allocation (the implementation may choose to ignore flags that affect the location of -the returned memory, like GFP_DMA). For pci_alloc_consistent, you -must assume GFP_ATOMIC behaviour. +the returned memory, like GFP_DMA). void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle) -void -pci_free_consistent(struct pci_dev *dev, size_t size, void *cpu_addr, - dma_addr_t dma_handle) Free the region of consistent memory you previously allocated. dev, size and dma_handle must all be the same as those passed into the @@ -89,10 +80,6 @@ for alignment, like queue heads needing to be aligned on N-byte boundaries. dma_pool_create(const char *name, struct device *dev, size_t size, size_t align, size_t alloc); - struct pci_pool * - pci_pool_create(const char *name, struct pci_device *dev, - size_t size, size_t align, size_t alloc); - The pool create() routines initialize a pool of dma-coherent buffers for use with a given device. It must be called in a context which can sleep. @@ -108,9 +95,6 @@ from this pool must not cross 4KByte boundaries. void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags, dma_addr_t *dma_handle); - void *pci_pool_alloc(struct pci_pool *pool, gfp_t gfp_flags, - dma_addr_t *dma_handle); - This allocates memory from the pool; the returned memory will meet the size and alignment requirements specified at creation time. Pass GFP_ATOMIC to prevent blocking, or if it's permitted (not in_interrupt, not holding SMP locks), @@ -122,9 +106,6 @@ pool's device. void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t addr); - void pci_pool_free(struct pci_pool *pool, void *vaddr, - dma_addr_t addr); - This puts memory back into the pool. The pool is what was passed to the pool allocation routine; the cpu (vaddr) and dma addresses are what were returned when that routine allocated the memory being freed. @@ -132,8 +113,6 @@ were returned when that routine allocated the memory being freed. void dma_pool_destroy(struct dma_pool *pool); - void pci_pool_destroy(struct pci_pool *pool); - The pool destroy() routines free the resources of the pool. They must be called in a context which can sleep. Make sure you've freed all allocated memory back to the pool before you destroy it. @@ -144,8 +123,6 @@ Part Ic - DMA addressing limitations int dma_supported(struct device *dev, u64 mask) -int -pci_dma_supported(struct pci_dev *hwdev, u64 mask) Checks to see if the device can support DMA to the memory described by mask. @@ -159,8 +136,14 @@ driver writers. int dma_set_mask(struct device *dev, u64 mask) + +Checks to see if the mask is possible and updates the device +parameters if it is. + +Returns: 0 if successful and a negative error if not. + int -pci_set_dma_mask(struct pci_device *dev, u64 mask) +dma_set_coherent_mask(struct device *dev, u64 mask) Checks to see if the mask is possible and updates the device parameters if it is. @@ -187,9 +170,6 @@ Part Id - Streaming DMA mappings dma_addr_t dma_map_single(struct device *dev, void *cpu_addr, size_t size, enum dma_data_direction direction) -dma_addr_t -pci_map_single(struct pci_dev *hwdev, void *cpu_addr, size_t size, - int direction) Maps a piece of processor virtual memory so it can be accessed by the device and returns the physical handle of the memory. @@ -198,14 +178,10 @@ The direction for both api's may be converted freely by casting. However the dma_ API uses a strongly typed enumerator for its direction: -DMA_NONE = PCI_DMA_NONE no direction (used for - debugging) -DMA_TO_DEVICE = PCI_DMA_TODEVICE data is going from the - memory to the device -DMA_FROM_DEVICE = PCI_DMA_FROMDEVICE data is coming from - the device to the - memory -DMA_BIDIRECTIONAL = PCI_DMA_BIDIRECTIONAL direction isn't known +DMA_NONE no direction (used for debugging) +DMA_TO_DEVICE data is going from the memory to the device +DMA_FROM_DEVICE data is coming from the device to the memory +DMA_BIDIRECTIONAL direction isn't known Notes: Not all memory regions in a machine can be mapped by this API. Further, regions that appear to be physically contiguous in @@ -268,9 +244,6 @@ cache lines are updated with data that the device may have changed). void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction direction) -void -pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr, - size_t size, int direction) Unmaps the region previously mapped. All the parameters passed in must be identical to those passed in (and returned) by the mapping @@ -280,15 +253,9 @@ dma_addr_t dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction) -dma_addr_t -pci_map_page(struct pci_dev *hwdev, struct page *page, - unsigned long offset, size_t size, int direction) void dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, enum dma_data_direction direction) -void -pci_unmap_page(struct pci_dev *hwdev, dma_addr_t dma_address, - size_t size, int direction) API for mapping and unmapping for pages. All the notes and warnings for the other mapping APIs apply here. Also, although the <offset> @@ -299,9 +266,6 @@ cache width is. int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -int -pci_dma_mapping_error(struct pci_dev *hwdev, dma_addr_t dma_addr) - In some circumstances dma_map_single and dma_map_page will fail to create a mapping. A driver can check for these errors by testing the returned dma address with dma_mapping_error(). A non-zero return value means the mapping @@ -311,9 +275,6 @@ reduce current DMA mapping usage or delay and try again later). int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) - int - pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, - int nents, int direction) Returns: the number of physical segments mapped (this may be shorter than <nents> passed in if some elements of the scatter/gather list are @@ -353,9 +314,6 @@ accessed sg->address and sg->length as shown above. void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries, enum dma_data_direction direction) - void - pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg, - int nents, int direction) Unmap the previously mapped scatter/gather list. All the parameters must be the same as those and passed in to the scatter/gather mapping @@ -365,21 +323,23 @@ Note: <nents> must be the number you passed in, *not* the number of physical entries returned. void -dma_sync_single(struct device *dev, dma_addr_t dma_handle, size_t size, - enum dma_data_direction direction) +dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, + enum dma_data_direction direction) void -pci_dma_sync_single(struct pci_dev *hwdev, dma_addr_t dma_handle, - size_t size, int direction) +dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size, + enum dma_data_direction direction) void -dma_sync_sg(struct device *dev, struct scatterlist *sg, int nelems, - enum dma_data_direction direction) +dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, + enum dma_data_direction direction) void -pci_dma_sync_sg(struct pci_dev *hwdev, struct scatterlist *sg, - int nelems, int direction) +dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, + enum dma_data_direction direction) -Synchronise a single contiguous or scatter/gather mapping. All the -parameters must be the same as those passed into the single mapping -API. +Synchronise a single contiguous or scatter/gather mapping for the cpu +and device. With the sync_sg API, all the parameters must be the same +as those passed into the single mapping API. With the sync_single API, +you can use dma_handle and size parameters that aren't identical to +those passed into the single mapping API to do a partial sync. Notes: You must do this: @@ -461,9 +421,9 @@ void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr, Part II - Advanced dma_ usage ----------------------------- -Warning: These pieces of the DMA API have no PCI equivalent. They -should also not be used in the majority of cases, since they cater for -unlikely corner cases that don't belong in usual drivers. +Warning: These pieces of the DMA API should not be used in the +majority of cases, since they cater for unlikely corner cases that +don't belong in usual drivers. If you don't understand how cache line coherency works between a processor and an I/O device, you should not be using this part of the @@ -514,16 +474,6 @@ into the width returned by this call. It will also always be a power of two for easy alignment. void -dma_sync_single_range(struct device *dev, dma_addr_t dma_handle, - unsigned long offset, size_t size, - enum dma_data_direction direction) - -Does a partial sync, starting at offset and continuing for size. You -must be careful to observe the cache alignment and width when doing -anything like this. You must also be extra careful about accessing -memory you intend to sync partially. - -void dma_cache_sync(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction) diff --git a/Documentation/DocBook/libata.tmpl b/Documentation/DocBook/libata.tmpl index ba9975771503..8c5411cfeaf0 100644 --- a/Documentation/DocBook/libata.tmpl +++ b/Documentation/DocBook/libata.tmpl @@ -81,16 +81,14 @@ void (*port_disable) (struct ata_port *); </programlisting> <para> - Called from ata_bus_probe() and ata_bus_reset() error paths, - as well as when unregistering from the SCSI module (rmmod, hot - unplug). + Called from ata_bus_probe() error path, as well as when + unregistering from the SCSI module (rmmod, hot unplug). This function should do whatever needs to be done to take the port out of use. In most cases, ata_port_disable() can be used as this hook. </para> <para> Called from ata_bus_probe() on a failed probe. - Called from ata_bus_reset() on a failed bus reset. Called from ata_scsi_release(). </para> @@ -107,10 +105,6 @@ void (*dev_config) (struct ata_port *, struct ata_device *); issue of SET FEATURES - XFER MODE, and prior to operation. </para> <para> - Called by ata_device_add() after ata_dev_identify() determines - a device is present. - </para> - <para> This entry may be specified as NULL in ata_port_operations. </para> @@ -154,8 +148,8 @@ unsigned int (*mode_filter) (struct ata_port *, struct ata_device *, unsigned in <sect2><title>Taskfile read/write</title> <programlisting> -void (*tf_load) (struct ata_port *ap, struct ata_taskfile *tf); -void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf); +void (*sff_tf_load) (struct ata_port *ap, struct ata_taskfile *tf); +void (*sff_tf_read) (struct ata_port *ap, struct ata_taskfile *tf); </programlisting> <para> @@ -164,36 +158,35 @@ void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf); hardware registers / DMA buffers, to obtain the current set of taskfile register values. Most drivers for taskfile-based hardware (PIO or MMIO) use - ata_tf_load() and ata_tf_read() for these hooks. + ata_sff_tf_load() and ata_sff_tf_read() for these hooks. </para> </sect2> <sect2><title>PIO data read/write</title> <programlisting> -void (*data_xfer) (struct ata_device *, unsigned char *, unsigned int, int); +void (*sff_data_xfer) (struct ata_device *, unsigned char *, unsigned int, int); </programlisting> <para> All bmdma-style drivers must implement this hook. This is the low-level operation that actually copies the data bytes during a PIO data transfer. -Typically the driver -will choose one of ata_pio_data_xfer_noirq(), ata_pio_data_xfer(), or -ata_mmio_data_xfer(). +Typically the driver will choose one of ata_sff_data_xfer_noirq(), +ata_sff_data_xfer(), or ata_sff_data_xfer32(). </para> </sect2> <sect2><title>ATA command execute</title> <programlisting> -void (*exec_command)(struct ata_port *ap, struct ata_taskfile *tf); +void (*sff_exec_command)(struct ata_port *ap, struct ata_taskfile *tf); </programlisting> <para> causes an ATA command, previously loaded with ->tf_load(), to be initiated in hardware. - Most drivers for taskfile-based hardware use ata_exec_command() + Most drivers for taskfile-based hardware use ata_sff_exec_command() for this hook. </para> @@ -218,8 +211,8 @@ command. <sect2><title>Read specific ATA shadow registers</title> <programlisting> -u8 (*check_status)(struct ata_port *ap); -u8 (*check_altstatus)(struct ata_port *ap); +u8 (*sff_check_status)(struct ata_port *ap); +u8 (*sff_check_altstatus)(struct ata_port *ap); </programlisting> <para> @@ -227,20 +220,26 @@ u8 (*check_altstatus)(struct ata_port *ap); hardware. On some hardware, reading the Status register has the side effect of clearing the interrupt condition. Most drivers for taskfile-based hardware use - ata_check_status() for this hook. + ata_sff_check_status() for this hook. </para> + + </sect2> + + <sect2><title>Write specific ATA shadow register</title> + <programlisting> +void (*sff_set_devctl)(struct ata_port *ap, u8 ctl); + </programlisting> + <para> - Note that because this is called from ata_device_add(), at - least a dummy function that clears device interrupts must be - provided for all drivers, even if the controller doesn't - actually have a taskfile status register. + Write the device control ATA shadow register to the hardware. + Most drivers don't need to define this. </para> </sect2> <sect2><title>Select ATA device on bus</title> <programlisting> -void (*dev_select)(struct ata_port *ap, unsigned int device); +void (*sff_dev_select)(struct ata_port *ap, unsigned int device); </programlisting> <para> @@ -251,9 +250,7 @@ void (*dev_select)(struct ata_port *ap, unsigned int device); </para> <para> Most drivers for taskfile-based hardware use - ata_std_dev_select() for this hook. Controllers which do not - support second drives on a port (such as SATA contollers) will - use ata_noop_dev_select(). + ata_sff_dev_select() for this hook. </para> </sect2> @@ -441,13 +438,13 @@ void (*irq_clear) (struct ata_port *); to struct ata_host_set. </para> <para> - Most legacy IDE drivers use ata_interrupt() for the + Most legacy IDE drivers use ata_sff_interrupt() for the irq_handler hook, which scans all ports in the host_set, determines which queued command was active (if any), and calls - ata_host_intr(ap,qc). + ata_sff_host_intr(ap,qc). </para> <para> - Most legacy IDE drivers use ata_bmdma_irq_clear() for the + Most legacy IDE drivers use ata_sff_irq_clear() for the irq_clear() hook, which simply clears the interrupt and error flags in the DMA status register. </para> @@ -490,16 +487,12 @@ void (*host_stop) (struct ata_host_set *host_set); allocates space for a legacy IDE PRD table and returns. </para> <para> - ->port_stop() is called after ->host_stop(). It's sole function + ->port_stop() is called after ->host_stop(). Its sole function is to release DMA/memory resources, now that they are no longer actively being used. Many drivers also free driver-private data from port at this time. </para> <para> - Many drivers use ata_port_stop() as this hook, which frees the - PRD table. - </para> - <para> ->host_stop() is called after all ->port_stop() calls have completed. The hook must finalize hardware shutdown, release DMA and other resources, etc. diff --git a/Documentation/DocBook/media-entities.tmpl b/Documentation/DocBook/media-entities.tmpl index c725cb852c54..5d4d40f429a5 100644 --- a/Documentation/DocBook/media-entities.tmpl +++ b/Documentation/DocBook/media-entities.tmpl @@ -17,6 +17,7 @@ <!ENTITY VIDIOC-DBG-G-REGISTER "<link linkend='vidioc-dbg-g-register'><constant>VIDIOC_DBG_G_REGISTER</constant></link>"> <!ENTITY VIDIOC-DBG-S-REGISTER "<link linkend='vidioc-dbg-g-register'><constant>VIDIOC_DBG_S_REGISTER</constant></link>"> <!ENTITY VIDIOC-DQBUF "<link linkend='vidioc-qbuf'><constant>VIDIOC_DQBUF</constant></link>"> +<!ENTITY VIDIOC-DQEVENT "<link linkend='vidioc-dqevent'><constant>VIDIOC_DQEVENT</constant></link>"> <!ENTITY VIDIOC-ENCODER-CMD "<link linkend='vidioc-encoder-cmd'><constant>VIDIOC_ENCODER_CMD</constant></link>"> <!ENTITY VIDIOC-ENUMAUDIO "<link linkend='vidioc-enumaudio'><constant>VIDIOC_ENUMAUDIO</constant></link>"> <!ENTITY VIDIOC-ENUMAUDOUT "<link linkend='vidioc-enumaudioout'><constant>VIDIOC_ENUMAUDOUT</constant></link>"> @@ -60,6 +61,7 @@ <!ENTITY VIDIOC-REQBUFS "<link linkend='vidioc-reqbufs'><constant>VIDIOC_REQBUFS</constant></link>"> <!ENTITY VIDIOC-STREAMOFF "<link linkend='vidioc-streamon'><constant>VIDIOC_STREAMOFF</constant></link>"> <!ENTITY VIDIOC-STREAMON "<link linkend='vidioc-streamon'><constant>VIDIOC_STREAMON</constant></link>"> +<!ENTITY VIDIOC-SUBSCRIBE-EVENT "<link linkend='vidioc-subscribe-event'><constant>VIDIOC_SUBSCRIBE_EVENT</constant></link>"> <!ENTITY VIDIOC-S-AUDIO "<link linkend='vidioc-g-audio'><constant>VIDIOC_S_AUDIO</constant></link>"> <!ENTITY VIDIOC-S-AUDOUT "<link linkend='vidioc-g-audioout'><constant>VIDIOC_S_AUDOUT</constant></link>"> <!ENTITY VIDIOC-S-CROP "<link linkend='vidioc-g-crop'><constant>VIDIOC_S_CROP</constant></link>"> @@ -83,6 +85,7 @@ <!ENTITY VIDIOC-TRY-ENCODER-CMD "<link linkend='vidioc-encoder-cmd'><constant>VIDIOC_TRY_ENCODER_CMD</constant></link>"> <!ENTITY VIDIOC-TRY-EXT-CTRLS "<link linkend='vidioc-g-ext-ctrls'><constant>VIDIOC_TRY_EXT_CTRLS</constant></link>"> <!ENTITY VIDIOC-TRY-FMT "<link linkend='vidioc-g-fmt'><constant>VIDIOC_TRY_FMT</constant></link>"> +<!ENTITY VIDIOC-UNSUBSCRIBE-EVENT "<link linkend='vidioc-subscribe-event'><constant>VIDIOC_UNSUBSCRIBE_EVENT</constant></link>"> <!-- Types --> <!ENTITY v4l2-std-id "<link linkend='v4l2-std-id'>v4l2_std_id</link>"> @@ -141,6 +144,9 @@ <!ENTITY v4l2-enc-idx "struct <link linkend='v4l2-enc-idx'>v4l2_enc_idx</link>"> <!ENTITY v4l2-enc-idx-entry "struct <link linkend='v4l2-enc-idx-entry'>v4l2_enc_idx_entry</link>"> <!ENTITY v4l2-encoder-cmd "struct <link linkend='v4l2-encoder-cmd'>v4l2_encoder_cmd</link>"> +<!ENTITY v4l2-event "struct <link linkend='v4l2-event'>v4l2_event</link>"> +<!ENTITY v4l2-event-subscription "struct <link linkend='v4l2-event-subscription'>v4l2_event_subscription</link>"> +<!ENTITY v4l2-event-vsync "struct <link linkend='v4l2-event-vsync'>v4l2_event_vsync</link>"> <!ENTITY v4l2-ext-control "struct <link linkend='v4l2-ext-control'>v4l2_ext_control</link>"> <!ENTITY v4l2-ext-controls "struct <link linkend='v4l2-ext-controls'>v4l2_ext_controls</link>"> <!ENTITY v4l2-fmtdesc "struct <link linkend='v4l2-fmtdesc'>v4l2_fmtdesc</link>"> @@ -200,6 +206,7 @@ <!ENTITY sub-controls SYSTEM "v4l/controls.xml"> <!ENTITY sub-dev-capture SYSTEM "v4l/dev-capture.xml"> <!ENTITY sub-dev-codec SYSTEM "v4l/dev-codec.xml"> +<!ENTITY sub-dev-event SYSTEM "v4l/dev-event.xml"> <!ENTITY sub-dev-effect SYSTEM "v4l/dev-effect.xml"> <!ENTITY sub-dev-osd SYSTEM "v4l/dev-osd.xml"> <!ENTITY sub-dev-output SYSTEM "v4l/dev-output.xml"> @@ -292,6 +299,8 @@ <!ENTITY sub-v4l2grab-c SYSTEM "v4l/v4l2grab.c.xml"> <!ENTITY sub-videodev2-h SYSTEM "v4l/videodev2.h.xml"> <!ENTITY sub-v4l2 SYSTEM "v4l/v4l2.xml"> +<!ENTITY sub-dqevent SYSTEM "v4l/vidioc-dqevent.xml"> +<!ENTITY sub-subscribe-event SYSTEM "v4l/vidioc-subscribe-event.xml"> <!ENTITY sub-intro SYSTEM "dvb/intro.xml"> <!ENTITY sub-frontend SYSTEM "dvb/frontend.xml"> <!ENTITY sub-dvbproperty SYSTEM "dvb/dvbproperty.xml"> @@ -381,3 +390,5 @@ <!ENTITY reqbufs SYSTEM "v4l/vidioc-reqbufs.xml"> <!ENTITY s-hw-freq-seek SYSTEM "v4l/vidioc-s-hw-freq-seek.xml"> <!ENTITY streamon SYSTEM "v4l/vidioc-streamon.xml"> +<!ENTITY dqevent SYSTEM "v4l/vidioc-dqevent.xml"> +<!ENTITY subscribe_event SYSTEM "v4l/vidioc-subscribe-event.xml"> diff --git a/Documentation/DocBook/mtdnand.tmpl b/Documentation/DocBook/mtdnand.tmpl index 5e7d84b48505..133cd6c3f3c1 100644 --- a/Documentation/DocBook/mtdnand.tmpl +++ b/Documentation/DocBook/mtdnand.tmpl @@ -488,7 +488,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip) The ECC bytes must be placed immidiately after the data bytes in order to make the syndrome generator work. This is contrary to the usual layout used by software ECC. The - seperation of data and out of band area is not longer + separation of data and out of band area is not longer possible. The nand driver code handles this layout and the remaining free bytes in the oob area are managed by the autoplacement code. Provide a matching oob-layout @@ -560,7 +560,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip) bad blocks. They have factory marked good blocks. The marker pattern is erased when the block is erased to be reused. So in case of powerloss before writing the pattern back to the chip this block - would be lost and added to the bad blocks. Therefor we scan the + would be lost and added to the bad blocks. Therefore we scan the chip(s) when we detect them the first time for good blocks and store this information in a bad block table before erasing any of the blocks. @@ -1094,7 +1094,7 @@ in this page</entry> manufacturers specifications. This applies similar to the spare area. </para> <para> - Therefor NAND aware filesystems must either write in page size chunks + Therefore NAND aware filesystems must either write in page size chunks or hold a writebuffer to collect smaller writes until they sum up to pagesize. Available NAND aware filesystems: JFFS2, YAFFS. </para> diff --git a/Documentation/DocBook/sh.tmpl b/Documentation/DocBook/sh.tmpl index 0c3dc4c69dd1..d858d92cf6d9 100644 --- a/Documentation/DocBook/sh.tmpl +++ b/Documentation/DocBook/sh.tmpl @@ -19,13 +19,17 @@ </authorgroup> <copyright> - <year>2008</year> + <year>2008-2010</year> <holder>Paul Mundt</holder> </copyright> <copyright> - <year>2008</year> + <year>2008-2010</year> <holder>Renesas Technology Corp.</holder> </copyright> + <copyright> + <year>2010</year> + <holder>Renesas Electronics Corp.</holder> + </copyright> <legalnotice> <para> @@ -77,7 +81,7 @@ </chapter> <chapter id="clk"> <title>Clock Framework Extensions</title> -!Iarch/sh/include/asm/clock.h +!Iinclude/linux/sh_clk.h </chapter> <chapter id="mach"> <title>Machine Specific Interfaces</title> diff --git a/Documentation/DocBook/tracepoint.tmpl b/Documentation/DocBook/tracepoint.tmpl index 8bca1d5cec09..e8473eae2a20 100644 --- a/Documentation/DocBook/tracepoint.tmpl +++ b/Documentation/DocBook/tracepoint.tmpl @@ -16,6 +16,15 @@ </address> </affiliation> </author> + <author> + <firstname>William</firstname> + <surname>Cohen</surname> + <affiliation> + <address> + <email>wcohen@redhat.com</email> + </address> + </affiliation> + </author> </authorgroup> <legalnotice> @@ -91,4 +100,8 @@ !Iinclude/trace/events/signal.h </chapter> + <chapter id="block"> + <title>Block IO</title> +!Iinclude/trace/events/block.h + </chapter> </book> diff --git a/Documentation/DocBook/v4l/common.xml b/Documentation/DocBook/v4l/common.xml index c65f0ac9b6ee..cea23e1c4fc6 100644 --- a/Documentation/DocBook/v4l/common.xml +++ b/Documentation/DocBook/v4l/common.xml @@ -1170,7 +1170,7 @@ frames per second. If less than this number of frames is to be captured or output, applications can request frame skipping or duplicating on the driver side. This is especially useful when using the &func-read; or &func-write;, which are not augmented by timestamps -or sequence counters, and to avoid unneccessary data copying.</para> +or sequence counters, and to avoid unnecessary data copying.</para> <para>Finally these ioctls can be used to determine the number of buffers used internally by a driver in read/write mode. For diff --git a/Documentation/DocBook/v4l/compat.xml b/Documentation/DocBook/v4l/compat.xml index b9dbdf9e6d29..b42b935913cd 100644 --- a/Documentation/DocBook/v4l/compat.xml +++ b/Documentation/DocBook/v4l/compat.xml @@ -2332,15 +2332,26 @@ more information.</para> </listitem> </orderedlist> </section> - </section> + <section> + <title>V4L2 in Linux 2.6.34</title> + <orderedlist> + <listitem> + <para>Added +<constant>V4L2_CID_IRIS_ABSOLUTE</constant> and +<constant>V4L2_CID_IRIS_RELATIVE</constant> controls to the + <link linkend="camera-controls">Camera controls class</link>. + </para> + </listitem> + </orderedlist> + </section> - <section id="other"> - <title>Relation of V4L2 to other Linux multimedia APIs</title> + <section id="other"> + <title>Relation of V4L2 to other Linux multimedia APIs</title> - <section id="xvideo"> - <title>X Video Extension</title> + <section id="xvideo"> + <title>X Video Extension</title> - <para>The X Video Extension (abbreviated XVideo or just Xv) is + <para>The X Video Extension (abbreviated XVideo or just Xv) is an extension of the X Window system, implemented for example by the XFree86 project. Its scope is similar to V4L2, an API to video capture and output devices for X clients. Xv allows applications to display @@ -2351,7 +2362,7 @@ capture or output still images in XPixmaps<footnote> extension available across many operating systems and architectures.</para> - <para>Because the driver is embedded into the X server Xv has a + <para>Because the driver is embedded into the X server Xv has a number of advantages over the V4L2 <link linkend="overlay">video overlay interface</link>. The driver can easily determine the overlay target, &ie; visible graphics memory or off-screen buffers for a @@ -2360,16 +2371,16 @@ overlay, scaling or color-keying, or the clipping functions of the video capture hardware, always in sync with drawing operations or windows moving or changing their stacking order.</para> - <para>To combine the advantages of Xv and V4L a special Xv + <para>To combine the advantages of Xv and V4L a special Xv driver exists in XFree86 and XOrg, just programming any overlay capable Video4Linux device it finds. To enable it <filename>/etc/X11/XF86Config</filename> must contain these lines:</para> - <para><screen> + <para><screen> Section "Module" Load "v4l" EndSection</screen></para> - <para>As of XFree86 4.2 this driver still supports only V4L + <para>As of XFree86 4.2 this driver still supports only V4L ioctls, however it should work just fine with all V4L2 devices through the V4L2 backward-compatibility layer. Since V4L2 permits multiple opens it is possible (if supported by the V4L2 driver) to capture @@ -2377,83 +2388,84 @@ video while an X client requested video overlay. Restrictions of simultaneous capturing and overlay are discussed in <xref linkend="overlay" /> apply.</para> - <para>Only marginally related to V4L2, XFree86 extended Xv to + <para>Only marginally related to V4L2, XFree86 extended Xv to support hardware YUV to RGB conversion and scaling for faster video playback, and added an interface to MPEG-2 decoding hardware. This API is useful to display images captured with V4L2 devices.</para> - </section> + </section> - <section> - <title>Digital Video</title> + <section> + <title>Digital Video</title> - <para>V4L2 does not support digital terrestrial, cable or + <para>V4L2 does not support digital terrestrial, cable or satellite broadcast. A separate project aiming at digital receivers exists. You can find its homepage at <ulink url="http://linuxtv.org">http://linuxtv.org</ulink>. The Linux DVB API has no connection to the V4L2 API except that drivers for hybrid hardware may support both.</para> - </section> + </section> - <section> - <title>Audio Interfaces</title> + <section> + <title>Audio Interfaces</title> - <para>[to do - OSS/ALSA]</para> + <para>[to do - OSS/ALSA]</para> + </section> </section> - </section> - <section id="experimental"> - <title>Experimental API Elements</title> + <section id="experimental"> + <title>Experimental API Elements</title> - <para>The following V4L2 API elements are currently experimental + <para>The following V4L2 API elements are currently experimental and may change in the future.</para> - <itemizedlist> - <listitem> - <para>Video Output Overlay (OSD) Interface, <xref + <itemizedlist> + <listitem> + <para>Video Output Overlay (OSD) Interface, <xref linkend="osd" />.</para> - </listitem> + </listitem> <listitem> - <para><constant>V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY</constant>, + <para><constant>V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY</constant>, &v4l2-buf-type;, <xref linkend="v4l2-buf-type" />.</para> - </listitem> - <listitem> - <para><constant>V4L2_CAP_VIDEO_OUTPUT_OVERLAY</constant>, + </listitem> + <listitem> + <para><constant>V4L2_CAP_VIDEO_OUTPUT_OVERLAY</constant>, &VIDIOC-QUERYCAP; ioctl, <xref linkend="device-capabilities" />.</para> - </listitem> - <listitem> - <para>&VIDIOC-ENUM-FRAMESIZES; and + </listitem> + <listitem> + <para>&VIDIOC-ENUM-FRAMESIZES; and &VIDIOC-ENUM-FRAMEINTERVALS; ioctls.</para> - </listitem> - <listitem> - <para>&VIDIOC-G-ENC-INDEX; ioctl.</para> - </listitem> - <listitem> - <para>&VIDIOC-ENCODER-CMD; and &VIDIOC-TRY-ENCODER-CMD; + </listitem> + <listitem> + <para>&VIDIOC-G-ENC-INDEX; ioctl.</para> + </listitem> + <listitem> + <para>&VIDIOC-ENCODER-CMD; and &VIDIOC-TRY-ENCODER-CMD; ioctls.</para> - </listitem> - <listitem> - <para>&VIDIOC-DBG-G-REGISTER; and &VIDIOC-DBG-S-REGISTER; + </listitem> + <listitem> + <para>&VIDIOC-DBG-G-REGISTER; and &VIDIOC-DBG-S-REGISTER; ioctls.</para> - </listitem> - <listitem> - <para>&VIDIOC-DBG-G-CHIP-IDENT; ioctl.</para> - </listitem> - </itemizedlist> - </section> + </listitem> + <listitem> + <para>&VIDIOC-DBG-G-CHIP-IDENT; ioctl.</para> + </listitem> + </itemizedlist> + </section> - <section id="obsolete"> - <title>Obsolete API Elements</title> + <section id="obsolete"> + <title>Obsolete API Elements</title> - <para>The following V4L2 API elements were superseded by new + <para>The following V4L2 API elements were superseded by new interfaces and should not be implemented in new drivers.</para> - <itemizedlist> - <listitem> - <para><constant>VIDIOC_G_MPEGCOMP</constant> and + <itemizedlist> + <listitem> + <para><constant>VIDIOC_G_MPEGCOMP</constant> and <constant>VIDIOC_S_MPEGCOMP</constant> ioctls. Use Extended Controls, <xref linkend="extended-controls" />.</para> - </listitem> - </itemizedlist> + </listitem> + </itemizedlist> + </section> </section> <!-- diff --git a/Documentation/DocBook/v4l/controls.xml b/Documentation/DocBook/v4l/controls.xml index f46450610412..8408caaee276 100644 --- a/Documentation/DocBook/v4l/controls.xml +++ b/Documentation/DocBook/v4l/controls.xml @@ -267,6 +267,12 @@ minimum value disables backlight compensation.</entry> <entry>Chroma automatic gain control.</entry> </row> <row> + <entry><constant>V4L2_CID_CHROMA_GAIN</constant></entry> + <entry>integer</entry> + <entry>Adjusts the Chroma gain control (for use when chroma AGC + is disabled).</entry> + </row> + <row> <entry><constant>V4L2_CID_COLOR_KILLER</constant></entry> <entry>boolean</entry> <entry>Enable the color killer (&ie; force a black & white image in case of a weak video signal).</entry> @@ -277,8 +283,15 @@ minimum value disables backlight compensation.</entry> <entry>Selects a color effect. Possible values for <constant>enum v4l2_colorfx</constant> are: <constant>V4L2_COLORFX_NONE</constant> (0), -<constant>V4L2_COLORFX_BW</constant> (1) and -<constant>V4L2_COLORFX_SEPIA</constant> (2).</entry> +<constant>V4L2_COLORFX_BW</constant> (1), +<constant>V4L2_COLORFX_SEPIA</constant> (2), +<constant>V4L2_COLORFX_NEGATIVE</constant> (3), +<constant>V4L2_COLORFX_EMBOSS</constant> (4), +<constant>V4L2_COLORFX_SKETCH</constant> (5), +<constant>V4L2_COLORFX_SKY_BLUE</constant> (6), +<constant>V4L2_COLORFX_GRASS_GREEN</constant> (7), +<constant>V4L2_COLORFX_SKIN_WHITEN</constant> (8) and +<constant>V4L2_COLORFX_VIVID</constant> (9).</entry> </row> <row> <entry><constant>V4L2_CID_ROTATE</constant></entry> @@ -1825,6 +1838,25 @@ wide-angle direction. The zoom speed unit is driver-specific.</entry> <row><entry></entry></row> <row> + <entry spanname="id"><constant>V4L2_CID_IRIS_ABSOLUTE</constant> </entry> + <entry>integer</entry> + </row><row><entry spanname="descr">This control sets the +camera's aperture to the specified value. The unit is undefined. +Larger values open the iris wider, smaller values close it.</entry> + </row> + <row><entry></entry></row> + + <row> + <entry spanname="id"><constant>V4L2_CID_IRIS_RELATIVE</constant> </entry> + <entry>integer</entry> + </row><row><entry spanname="descr">This control modifies the +camera's aperture by the specified amount. The unit is undefined. +Positive values open the iris one step further, negative values close +it one step further. This is a write-only control.</entry> + </row> + <row><entry></entry></row> + + <row> <entry spanname="id"><constant>V4L2_CID_PRIVACY</constant> </entry> <entry>boolean</entry> </row><row><entry spanname="descr">Prevent video from being acquired diff --git a/Documentation/DocBook/v4l/dev-event.xml b/Documentation/DocBook/v4l/dev-event.xml new file mode 100644 index 000000000000..be5a98fb4fab --- /dev/null +++ b/Documentation/DocBook/v4l/dev-event.xml @@ -0,0 +1,31 @@ + <title>Event Interface</title> + + <para>The V4L2 event interface provides means for user to get + immediately notified on certain conditions taking place on a device. + This might include start of frame or loss of signal events, for + example. + </para> + + <para>To receive events, the events the user is interested in first must + be subscribed using the &VIDIOC-SUBSCRIBE-EVENT; ioctl. Once an event is + subscribed, the events of subscribed types are dequeueable using the + &VIDIOC-DQEVENT; ioctl. Events may be unsubscribed using + VIDIOC_UNSUBSCRIBE_EVENT ioctl. The special event type V4L2_EVENT_ALL may + be used to unsubscribe all the events the driver supports.</para> + + <para>The event subscriptions and event queues are specific to file + handles. Subscribing an event on one file handle does not affect + other file handles. + </para> + + <para>The information on dequeueable events is obtained by using select or + poll system calls on video devices. The V4L2 events use POLLPRI events on + poll system call and exceptions on select system call. </para> + + <!-- +Local Variables: +mode: sgml +sgml-parent-document: "v4l2.sgml" +indent-tabs-mode: nil +End: + --> diff --git a/Documentation/DocBook/v4l/io.xml b/Documentation/DocBook/v4l/io.xml index e870330cbf77..d424886beda0 100644 --- a/Documentation/DocBook/v4l/io.xml +++ b/Documentation/DocBook/v4l/io.xml @@ -702,6 +702,16 @@ They can be both cleared however, then the buffer is in "dequeued" state, in the application domain to say so.</entry> </row> <row> + <entry><constant>V4L2_BUF_FLAG_ERROR</constant></entry> + <entry>0x0040</entry> + <entry>When this flag is set, the buffer has been dequeued + successfully, although the data might have been corrupted. + This is recoverable, streaming may continue as normal and + the buffer may be reused normally. + Drivers set this flag when the <constant>VIDIOC_DQBUF</constant> + ioctl is called.</entry> + </row> + <row> <entry><constant>V4L2_BUF_FLAG_KEYFRAME</constant></entry> <entry>0x0008</entry> <entry>Drivers set or clear this flag when calling the @@ -918,8 +928,8 @@ order</emphasis>.</para> <para>When the driver provides or accepts images field by field rather than interleaved, it is also important applications understand -how the fields combine to frames. We distinguish between top and -bottom fields, the <emphasis>spatial order</emphasis>: The first line +how the fields combine to frames. We distinguish between top (aka odd) and +bottom (aka even) fields, the <emphasis>spatial order</emphasis>: The first line of the top field is the first line of an interlaced frame, the first line of the bottom field is the second line of that frame.</para> @@ -972,12 +982,12 @@ between <constant>V4L2_FIELD_TOP</constant> and <row> <entry><constant>V4L2_FIELD_TOP</constant></entry> <entry>2</entry> - <entry>Images consist of the top field only.</entry> + <entry>Images consist of the top (aka odd) field only.</entry> </row> <row> <entry><constant>V4L2_FIELD_BOTTOM</constant></entry> <entry>3</entry> - <entry>Images consist of the bottom field only. + <entry>Images consist of the bottom (aka even) field only. Applications may wish to prevent a device from capturing interlaced images because they will have "comb" or "feathering" artefacts around moving objects.</entry> diff --git a/Documentation/DocBook/v4l/pixfmt.xml b/Documentation/DocBook/v4l/pixfmt.xml index 885968d6a2fc..c4ad0a8e42dc 100644 --- a/Documentation/DocBook/v4l/pixfmt.xml +++ b/Documentation/DocBook/v4l/pixfmt.xml @@ -792,6 +792,18 @@ http://www.thedirks.org/winnov/</ulink></para></entry> <entry>'YYUV'</entry> <entry>unknown</entry> </row> + <row id="V4L2-PIX-FMT-Y4"> + <entry><constant>V4L2_PIX_FMT_Y4</constant></entry> + <entry>'Y04 '</entry> + <entry>Old 4-bit greyscale format. Only the least significant 4 bits of each byte are used, +the other bits are set to 0.</entry> + </row> + <row id="V4L2-PIX-FMT-Y6"> + <entry><constant>V4L2_PIX_FMT_Y6</constant></entry> + <entry>'Y06 '</entry> + <entry>Old 6-bit greyscale format. Only the least significant 6 bits of each byte are used, +the other bits are set to 0.</entry> + </row> </tbody> </tgroup> </table> diff --git a/Documentation/DocBook/v4l/v4l2.xml b/Documentation/DocBook/v4l/v4l2.xml index 060105af49e5..9737243377a3 100644 --- a/Documentation/DocBook/v4l/v4l2.xml +++ b/Documentation/DocBook/v4l/v4l2.xml @@ -401,6 +401,7 @@ and discussions on the V4L mailing list.</revremark> <section id="ttx"> &sub-dev-teletext; </section> <section id="radio"> &sub-dev-radio; </section> <section id="rds"> &sub-dev-rds; </section> + <section id="event"> &sub-dev-event; </section> </chapter> <chapter id="driver"> @@ -426,6 +427,7 @@ and discussions on the V4L mailing list.</revremark> &sub-cropcap; &sub-dbg-g-chip-ident; &sub-dbg-g-register; + &sub-dqevent; &sub-encoder-cmd; &sub-enumaudio; &sub-enumaudioout; @@ -467,6 +469,7 @@ and discussions on the V4L mailing list.</revremark> &sub-reqbufs; &sub-s-hw-freq-seek; &sub-streamon; + &sub-subscribe-event; <!-- End of ioctls. --> &sub-mmap; &sub-munmap; diff --git a/Documentation/DocBook/v4l/videodev2.h.xml b/Documentation/DocBook/v4l/videodev2.h.xml index 068325940658..865b06d9e679 100644 --- a/Documentation/DocBook/v4l/videodev2.h.xml +++ b/Documentation/DocBook/v4l/videodev2.h.xml @@ -1018,6 +1018,13 @@ enum <link linkend="v4l2-colorfx">v4l2_colorfx</link> { V4L2_COLORFX_NONE = 0, V4L2_COLORFX_BW = 1, V4L2_COLORFX_SEPIA = 2, + V4L2_COLORFX_NEGATIVE = 3, + V4L2_COLORFX_EMBOSS = 4, + V4L2_COLORFX_SKETCH = 5, + V4L2_COLORFX_SKY_BLUE = 6, + V4L2_COLORFX_GRASS_GREEN = 7, + V4L2_COLORFX_SKIN_WHITEN = 8, + V4L2_COLORFX_VIVID = 9. }; #define V4L2_CID_AUTOBRIGHTNESS (V4L2_CID_BASE+32) #define V4L2_CID_BAND_STOP_FILTER (V4L2_CID_BASE+33) @@ -1271,6 +1278,9 @@ enum <link linkend="v4l2-exposure-auto-type">v4l2_exposure_auto_type</link> { #define V4L2_CID_PRIVACY (V4L2_CID_CAMERA_CLASS_BASE+16) +#define V4L2_CID_IRIS_ABSOLUTE (V4L2_CID_CAMERA_CLASS_BASE+17) +#define V4L2_CID_IRIS_RELATIVE (V4L2_CID_CAMERA_CLASS_BASE+18) + /* FM Modulator class control IDs */ #define V4L2_CID_FM_TX_CLASS_BASE (V4L2_CTRL_CLASS_FM_TX | 0x900) #define V4L2_CID_FM_TX_CLASS (V4L2_CTRL_CLASS_FM_TX | 1) diff --git a/Documentation/DocBook/v4l/vidioc-dqevent.xml b/Documentation/DocBook/v4l/vidioc-dqevent.xml new file mode 100644 index 000000000000..4e0a7cc30812 --- /dev/null +++ b/Documentation/DocBook/v4l/vidioc-dqevent.xml @@ -0,0 +1,131 @@ +<refentry id="vidioc-dqevent"> + <refmeta> + <refentrytitle>ioctl VIDIOC_DQEVENT</refentrytitle> + &manvol; + </refmeta> + + <refnamediv> + <refname>VIDIOC_DQEVENT</refname> + <refpurpose>Dequeue event</refpurpose> + </refnamediv> + + <refsynopsisdiv> + <funcsynopsis> + <funcprototype> + <funcdef>int <function>ioctl</function></funcdef> + <paramdef>int <parameter>fd</parameter></paramdef> + <paramdef>int <parameter>request</parameter></paramdef> + <paramdef>struct v4l2_event +*<parameter>argp</parameter></paramdef> + </funcprototype> + </funcsynopsis> + </refsynopsisdiv> + + <refsect1> + <title>Arguments</title> + + <variablelist> + <varlistentry> + <term><parameter>fd</parameter></term> + <listitem> + <para>&fd;</para> + </listitem> + </varlistentry> + <varlistentry> + <term><parameter>request</parameter></term> + <listitem> + <para>VIDIOC_DQEVENT</para> + </listitem> + </varlistentry> + <varlistentry> + <term><parameter>argp</parameter></term> + <listitem> + <para></para> + </listitem> + </varlistentry> + </variablelist> + </refsect1> + + <refsect1> + <title>Description</title> + + <para>Dequeue an event from a video device. No input is required + for this ioctl. All the fields of the &v4l2-event; structure are + filled by the driver. The file handle will also receive exceptions + which the application may get by e.g. using the select system + call.</para> + + <table frame="none" pgwide="1" id="v4l2-event"> + <title>struct <structname>v4l2_event</structname></title> + <tgroup cols="4"> + &cs-str; + <tbody valign="top"> + <row> + <entry>__u32</entry> + <entry><structfield>type</structfield></entry> + <entry></entry> + <entry>Type of the event.</entry> + </row> + <row> + <entry>union</entry> + <entry><structfield>u</structfield></entry> + <entry></entry> + <entry></entry> + </row> + <row> + <entry></entry> + <entry>&v4l2-event-vsync;</entry> + <entry><structfield>vsync</structfield></entry> + <entry>Event data for event V4L2_EVENT_VSYNC. + </entry> + </row> + <row> + <entry></entry> + <entry>__u8</entry> + <entry><structfield>data</structfield>[64]</entry> + <entry>Event data. Defined by the event type. The union + should be used to define easily accessible type for + events.</entry> + </row> + <row> + <entry>__u32</entry> + <entry><structfield>pending</structfield></entry> + <entry></entry> + <entry>Number of pending events excluding this one.</entry> + </row> + <row> + <entry>__u32</entry> + <entry><structfield>sequence</structfield></entry> + <entry></entry> + <entry>Event sequence number. The sequence number is + incremented for every subscribed event that takes place. + If sequence numbers are not contiguous it means that + events have been lost. + </entry> + </row> + <row> + <entry>struct timespec</entry> + <entry><structfield>timestamp</structfield></entry> + <entry></entry> + <entry>Event timestamp.</entry> + </row> + <row> + <entry>__u32</entry> + <entry><structfield>reserved</structfield>[9]</entry> + <entry></entry> + <entry>Reserved for future extensions. Drivers must set + the array to zero.</entry> + </row> + </tbody> + </tgroup> + </table> + + </refsect1> +</refentry> +<!-- +Local Variables: +mode: sgml +sgml-parent-document: "v4l2.sgml" +indent-tabs-mode: nil +End: +--> diff --git a/Documentation/DocBook/v4l/vidioc-enuminput.xml b/Documentation/DocBook/v4l/vidioc-enuminput.xml index 71b868e2fb8f..476fe1d2bba0 100644 --- a/Documentation/DocBook/v4l/vidioc-enuminput.xml +++ b/Documentation/DocBook/v4l/vidioc-enuminput.xml @@ -283,7 +283,7 @@ input/output interface to linux-media@vger.kernel.org on 19 Oct 2009. <entry>This input supports setting DV presets by using VIDIOC_S_DV_PRESET.</entry> </row> <row> - <entry><constant>V4L2_OUT_CAP_CUSTOM_TIMINGS</constant></entry> + <entry><constant>V4L2_IN_CAP_CUSTOM_TIMINGS</constant></entry> <entry>0x00000002</entry> <entry>This input supports setting custom video timings by using VIDIOC_S_DV_TIMINGS.</entry> </row> diff --git a/Documentation/DocBook/v4l/vidioc-g-parm.xml b/Documentation/DocBook/v4l/vidioc-g-parm.xml index 78332d365ce9..392aa9e5571e 100644 --- a/Documentation/DocBook/v4l/vidioc-g-parm.xml +++ b/Documentation/DocBook/v4l/vidioc-g-parm.xml @@ -55,7 +55,7 @@ captured or output, applications can request frame skipping or duplicating on the driver side. This is especially useful when using the <function>read()</function> or <function>write()</function>, which are not augmented by timestamps or sequence counters, and to avoid -unneccessary data copying.</para> +unnecessary data copying.</para> <para>Further these ioctls can be used to determine the number of buffers used internally by a driver in read/write mode. For diff --git a/Documentation/DocBook/v4l/vidioc-qbuf.xml b/Documentation/DocBook/v4l/vidioc-qbuf.xml index b843bd7b3897..ab691ebf3b93 100644 --- a/Documentation/DocBook/v4l/vidioc-qbuf.xml +++ b/Documentation/DocBook/v4l/vidioc-qbuf.xml @@ -111,7 +111,11 @@ from the driver's outgoing queue. They just set the and <structfield>reserved</structfield> fields of a &v4l2-buffer; as above, when <constant>VIDIOC_DQBUF</constant> is called with a pointer to this structure the driver fills the -remaining fields or returns an error code.</para> +remaining fields or returns an error code. The driver may also set +<constant>V4L2_BUF_FLAG_ERROR</constant> in the <structfield>flags</structfield> +field. It indicates a non-critical (recoverable) streaming error. In such case +the application may continue as normal, but should be aware that data in the +dequeued buffer might be corrupted.</para> <para>By default <constant>VIDIOC_DQBUF</constant> blocks when no buffer is in the outgoing queue. When the @@ -158,7 +162,13 @@ enqueue a user pointer buffer.</para> <para><constant>VIDIOC_DQBUF</constant> failed due to an internal error. Can also indicate temporary problems like signal loss. Note the driver might dequeue an (empty) buffer despite -returning an error, or even stop capturing.</para> +returning an error, or even stop capturing. Reusing such buffer may be unsafe +though and its details (e.g. <structfield>index</structfield>) may not be +returned either. It is recommended that drivers indicate recoverable errors +by setting the <constant>V4L2_BUF_FLAG_ERROR</constant> and returning 0 instead. +In that case the application should be able to safely reuse the buffer and +continue streaming. + </para> </listitem> </varlistentry> </variablelist> diff --git a/Documentation/DocBook/v4l/vidioc-queryctrl.xml b/Documentation/DocBook/v4l/vidioc-queryctrl.xml index 4876ff1a1a04..8e0e055ac934 100644 --- a/Documentation/DocBook/v4l/vidioc-queryctrl.xml +++ b/Documentation/DocBook/v4l/vidioc-queryctrl.xml @@ -325,7 +325,7 @@ should be part of the control documentation.</entry> <entry>n/a</entry> <entry>This is not a control. When <constant>VIDIOC_QUERYCTRL</constant> is called with a control ID -equal to a control class code (see <xref linkend="ctrl-class" />), the +equal to a control class code (see <xref linkend="ctrl-class" />) + 1, the ioctl returns the name of the control class and this control type. Older drivers which do not support this feature return an &EINVAL;.</entry> diff --git a/Documentation/DocBook/v4l/vidioc-reqbufs.xml b/Documentation/DocBook/v4l/vidioc-reqbufs.xml index 1c0816372074..69800ae23348 100644 --- a/Documentation/DocBook/v4l/vidioc-reqbufs.xml +++ b/Documentation/DocBook/v4l/vidioc-reqbufs.xml @@ -61,7 +61,7 @@ fields of the <structname>v4l2_requestbuffers</structname> structure. They set the <structfield>type</structfield> field to the respective stream or buffer type, the <structfield>count</structfield> field to the desired number of buffers, <structfield>memory</structfield> -must be set to the requested I/O method and the reserved array +must be set to the requested I/O method and the <structfield>reserved</structfield> array must be zeroed. When the ioctl is called with a pointer to this structure the driver will attempt to allocate the requested number of buffers and it stores the actual number diff --git a/Documentation/DocBook/v4l/vidioc-subscribe-event.xml b/Documentation/DocBook/v4l/vidioc-subscribe-event.xml new file mode 100644 index 000000000000..8b501791aa68 --- /dev/null +++ b/Documentation/DocBook/v4l/vidioc-subscribe-event.xml @@ -0,0 +1,133 @@ +<refentry id="vidioc-subscribe-event"> + <refmeta> + <refentrytitle>ioctl VIDIOC_SUBSCRIBE_EVENT, VIDIOC_UNSUBSCRIBE_EVENT</refentrytitle> + &manvol; + </refmeta> + + <refnamediv> + <refname>VIDIOC_SUBSCRIBE_EVENT, VIDIOC_UNSUBSCRIBE_EVENT</refname> + <refpurpose>Subscribe or unsubscribe event</refpurpose> + </refnamediv> + + <refsynopsisdiv> + <funcsynopsis> + <funcprototype> + <funcdef>int <function>ioctl</function></funcdef> + <paramdef>int <parameter>fd</parameter></paramdef> + <paramdef>int <parameter>request</parameter></paramdef> + <paramdef>struct v4l2_event_subscription +*<parameter>argp</parameter></paramdef> + </funcprototype> + </funcsynopsis> + </refsynopsisdiv> + + <refsect1> + <title>Arguments</title> + + <variablelist> + <varlistentry> + <term><parameter>fd</parameter></term> + <listitem> + <para>&fd;</para> + </listitem> + </varlistentry> + <varlistentry> + <term><parameter>request</parameter></term> + <listitem> + <para>VIDIOC_SUBSCRIBE_EVENT, VIDIOC_UNSUBSCRIBE_EVENT</para> + </listitem> + </varlistentry> + <varlistentry> + <term><parameter>argp</parameter></term> + <listitem> + <para></para> + </listitem> + </varlistentry> + </variablelist> + </refsect1> + + <refsect1> + <title>Description</title> + + <para>Subscribe or unsubscribe V4L2 event. Subscribed events are + dequeued by using the &VIDIOC-DQEVENT; ioctl.</para> + + <table frame="none" pgwide="1" id="v4l2-event-subscription"> + <title>struct <structname>v4l2_event_subscription</structname></title> + <tgroup cols="3"> + &cs-str; + <tbody valign="top"> + <row> + <entry>__u32</entry> + <entry><structfield>type</structfield></entry> + <entry>Type of the event.</entry> + </row> + <row> + <entry>__u32</entry> + <entry><structfield>reserved</structfield>[7]</entry> + <entry>Reserved for future extensions. Drivers and applications + must set the array to zero.</entry> + </row> + </tbody> + </tgroup> + </table> + + <table frame="none" pgwide="1" id="event-type"> + <title>Event Types</title> + <tgroup cols="3"> + &cs-def; + <tbody valign="top"> + <row> + <entry><constant>V4L2_EVENT_ALL</constant></entry> + <entry>0</entry> + <entry>All events. V4L2_EVENT_ALL is valid only for + VIDIOC_UNSUBSCRIBE_EVENT for unsubscribing all events at once. + </entry> + </row> + <row> + <entry><constant>V4L2_EVENT_VSYNC</constant></entry> + <entry>1</entry> + <entry>This event is triggered on the vertical sync. + This event has &v4l2-event-vsync; associated with it. + </entry> + </row> + <row> + <entry><constant>V4L2_EVENT_EOS</constant></entry> + <entry>2</entry> + <entry>This event is triggered when the end of a stream is reached. + This is typically used with MPEG decoders to report to the application + when the last of the MPEG stream has been decoded. + </entry> + </row> + <row> + <entry><constant>V4L2_EVENT_PRIVATE_START</constant></entry> + <entry>0x08000000</entry> + <entry>Base event number for driver-private events.</entry> + </row> + </tbody> + </tgroup> + </table> + + <table frame="none" pgwide="1" id="v4l2-event-vsync"> + <title>struct <structname>v4l2_event_vsync</structname></title> + <tgroup cols="3"> + &cs-str; + <tbody valign="top"> + <row> + <entry>__u8</entry> + <entry><structfield>field</structfield></entry> + <entry>The upcoming field. See &v4l2-field;.</entry> + </row> + </tbody> + </tgroup> + </table> + + </refsect1> +</refentry> +<!-- +Local Variables: +mode: sgml +sgml-parent-document: "v4l2.sgml" +indent-tabs-mode: nil +End: +--> diff --git a/Documentation/DocBook/writing-an-alsa-driver.tmpl b/Documentation/DocBook/writing-an-alsa-driver.tmpl index 0d0f7b4d4b1a..0ba149de2608 100644 --- a/Documentation/DocBook/writing-an-alsa-driver.tmpl +++ b/Documentation/DocBook/writing-an-alsa-driver.tmpl @@ -5518,34 +5518,41 @@ struct _snd_pcm_runtime { ]]> </programlisting> </informalexample> + + For the raw data, <structfield>size</structfield> field must be + set properly. This specifies the maximum size of the proc file access. </para> <para> - The callback is much more complicated than the text-file - version. You need to use a low-level I/O functions such as + The read/write callbacks of raw mode are more direct than the text mode. + You need to use a low-level I/O functions such as <function>copy_from/to_user()</function> to transfer the data. <informalexample> <programlisting> <![CDATA[ - static long my_file_io_read(struct snd_info_entry *entry, + static ssize_t my_file_io_read(struct snd_info_entry *entry, void *file_private_data, struct file *file, char *buf, - unsigned long count, - unsigned long pos) + size_t count, + loff_t pos) { - long size = count; - if (pos + size > local_max_size) - size = local_max_size - pos; - if (copy_to_user(buf, local_data + pos, size)) + if (copy_to_user(buf, local_data + pos, count)) return -EFAULT; - return size; + return count; } ]]> </programlisting> </informalexample> + + If the size of the info entry has been set up properly, + <structfield>count</structfield> and <structfield>pos</structfield> are + guaranteed to fit within 0 and the given size. + You don't have to check the range in the callbacks unless any + other condition is required. + </para> </chapter> diff --git a/Documentation/DocBook/writing_usb_driver.tmpl b/Documentation/DocBook/writing_usb_driver.tmpl index eeff19ca831b..bd97a13fa5ae 100644 --- a/Documentation/DocBook/writing_usb_driver.tmpl +++ b/Documentation/DocBook/writing_usb_driver.tmpl @@ -342,7 +342,7 @@ static inline void skel_delete (struct usb_skel *dev) { kfree (dev->bulk_in_buffer); if (dev->bulk_out_buffer != NULL) - usb_buffer_free (dev->udev, dev->bulk_out_size, + usb_free_coherent (dev->udev, dev->bulk_out_size, dev->bulk_out_buffer, dev->write_urb->transfer_dma); usb_free_urb (dev->write_urb); diff --git a/Documentation/HOWTO b/Documentation/HOWTO index 8495fc970391..40ada93b820a 100644 --- a/Documentation/HOWTO +++ b/Documentation/HOWTO @@ -221,8 +221,8 @@ branches. These different branches are: - main 2.6.x kernel tree - 2.6.x.y -stable kernel tree - 2.6.x -git kernel patches - - 2.6.x -mm kernel patches - subsystem specific kernel trees and patches + - the 2.6.x -next kernel tree for integration tests 2.6.x kernel tree ----------------- @@ -232,9 +232,9 @@ process is as follows: - As soon as a new kernel is released a two weeks window is open, during this period of time maintainers can submit big diffs to Linus, usually the patches that have already been included in the - -mm kernel for a few weeks. The preferred way to submit big changes + -next kernel for a few weeks. The preferred way to submit big changes is using git (the kernel's source management tool, more information - can be found at http://git.or.cz/) but plain patches are also just + can be found at http://git-scm.com/) but plain patches are also just fine. - After two weeks a -rc1 kernel is released it is now possible to push only patches that do not include new features that could affect the @@ -293,84 +293,43 @@ daily and represent the current state of Linus' tree. They are more experimental than -rc kernels since they are generated automatically without even a cursory glance to see if they are sane. -2.6.x -mm kernel patches ------------------------- -These are experimental kernel patches released by Andrew Morton. Andrew -takes all of the different subsystem kernel trees and patches and mushes -them together, along with a lot of patches that have been plucked from -the linux-kernel mailing list. This tree serves as a proving ground for -new features and patches. Once a patch has proved its worth in -mm for -a while Andrew or the subsystem maintainer pushes it on to Linus for -inclusion in mainline. - -It is heavily encouraged that all new patches get tested in the -mm tree -before they are sent to Linus for inclusion in the main kernel tree. Code -which does not make an appearance in -mm before the opening of the merge -window will prove hard to merge into the mainline. - -These kernels are not appropriate for use on systems that are supposed -to be stable and they are more risky to run than any of the other -branches. - -If you wish to help out with the kernel development process, please test -and use these kernel releases and provide feedback to the linux-kernel -mailing list if you have any problems, and if everything works properly. - -In addition to all the other experimental patches, these kernels usually -also contain any changes in the mainline -git kernels available at the -time of release. - -The -mm kernels are not released on a fixed schedule, but usually a few --mm kernels are released in between each -rc kernel (1 to 3 is common). - Subsystem Specific kernel trees and patches ------------------------------------------- -A number of the different kernel subsystem developers expose their -development trees so that others can see what is happening in the -different areas of the kernel. These trees are pulled into the -mm -kernel releases as described above. - -Here is a list of some of the different kernel trees available: - git trees: - - Kbuild development tree, Sam Ravnborg <sam@ravnborg.org> - git.kernel.org:/pub/scm/linux/kernel/git/sam/kbuild.git - - - ACPI development tree, Len Brown <len.brown@intel.com> - git.kernel.org:/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git - - - Block development tree, Jens Axboe <jens.axboe@oracle.com> - git.kernel.org:/pub/scm/linux/kernel/git/axboe/linux-2.6-block.git - - - DRM development tree, Dave Airlie <airlied@linux.ie> - git.kernel.org:/pub/scm/linux/kernel/git/airlied/drm-2.6.git - - - ia64 development tree, Tony Luck <tony.luck@intel.com> - git.kernel.org:/pub/scm/linux/kernel/git/aegl/linux-2.6.git - - - infiniband, Roland Dreier <rolandd@cisco.com> - git.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git - - - libata, Jeff Garzik <jgarzik@pobox.com> - git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/libata-dev.git - - - network drivers, Jeff Garzik <jgarzik@pobox.com> - git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6.git - - - pcmcia, Dominik Brodowski <linux@dominikbrodowski.net> - git.kernel.org:/pub/scm/linux/kernel/git/brodo/pcmcia-2.6.git - - - SCSI, James Bottomley <James.Bottomley@hansenpartnership.com> - git.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git - - - x86, Ingo Molnar <mingo@elte.hu> - git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git - - quilt trees: - - USB, Driver Core, and I2C, Greg Kroah-Hartman <gregkh@suse.de> - kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/ +The maintainers of the various kernel subsystems --- and also many +kernel subsystem developers --- expose their current state of +development in source repositories. That way, others can see what is +happening in the different areas of the kernel. In areas where +development is rapid, a developer may be asked to base his submissions +onto such a subsystem kernel tree so that conflicts between the +submission and other already ongoing work are avoided. + +Most of these repositories are git trees, but there are also other SCMs +in use, or patch queues being published as quilt series. Addresses of +these subsystem repositories are listed in the MAINTAINERS file. Many +of them can be browsed at http://git.kernel.org/. + +Before a proposed patch is committed to such a subsystem tree, it is +subject to review which primarily happens on mailing lists (see the +respective section below). For several kernel subsystems, this review +process is tracked with the tool patchwork. Patchwork offers a web +interface which shows patch postings, any comments on a patch or +revisions to it, and maintainers can mark patches as under review, +accepted, or rejected. Most of these patchwork sites are listed at +http://patchwork.kernel.org/ or http://patchwork.ozlabs.org/. + +2.6.x -next kernel tree for integration tests +--------------------------------------------- +Before updates from subsystem trees are merged into the mainline 2.6.x +tree, they need to be integration-tested. For this purpose, a special +testing repository exists into which virtually all subsystem trees are +pulled on an almost daily basis: + http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git + http://linux.f-seidel.de/linux-next/pmwiki/ + +This way, the -next kernel gives a summary outlook onto what will be +expected to go into the mainline kernel at the next merge period. +Adventurous testers are very welcome to runtime-test the -next kernel. - Other kernel trees can be found listed at http://git.kernel.org/ and in - the MAINTAINERS file. Bug Reporting ------------- diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt index bc38283379f0..69dd29ed824e 100644 --- a/Documentation/IPMI.txt +++ b/Documentation/IPMI.txt @@ -365,6 +365,7 @@ You can change this at module load time (for a module) with: regshifts=<shift1>,<shift2>,... slave_addrs=<addr1>,<addr2>,... force_kipmid=<enable1>,<enable2>,... + kipmid_max_busy_us=<ustime1>,<ustime2>,... unload_when_empty=[0|1] Each of these except si_trydefaults is a list, the first item for the @@ -433,6 +434,7 @@ kernel command line as: ipmi_si.regshifts=<shift1>,<shift2>,... ipmi_si.slave_addrs=<addr1>,<addr2>,... ipmi_si.force_kipmid=<enable1>,<enable2>,... + ipmi_si.kipmid_max_busy_us=<ustime1>,<ustime2>,... It works the same as the module parameters of the same names. @@ -450,6 +452,16 @@ force this thread on or off. If you force it off and don't have interrupts, the driver will run VERY slowly. Don't blame me, these interfaces suck. +Unfortunately, this thread can use a lot of CPU depending on the +interface's performance. This can waste a lot of CPU and cause +various issues with detecting idle CPU and using extra power. To +avoid this, the kipmid_max_busy_us sets the maximum amount of time, in +microseconds, that kipmid will spin before sleeping for a tick. This +value sets a balance between performance and CPU waste and needs to be +tuned to your needs. Maybe, someday, auto-tuning will be added, but +that's not a simple thing and even the auto-tuning would need to be +tuned to the user's desired performance. + The driver supports a hot add and remove of interfaces. This way, interfaces can be added or removed after the kernel is up and running. This is done using /sys/modules/ipmi_si/parameters/hotmod, which is a diff --git a/Documentation/Makefile b/Documentation/Makefile index 94b945733534..6fc7ea1d1f9d 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -1,3 +1,3 @@ obj-m := DocBook/ accounting/ auxdisplay/ connector/ \ - filesystems/configfs/ ia64/ networking/ \ - pcmcia/ spi/ video4linux/ vm/ watchdog/src/ + filesystems/ filesystems/configfs/ ia64/ laptops/ networking/ \ + pcmcia/ spi/ timers/ video4linux/ vm/ watchdog/src/ diff --git a/Documentation/PCI/pci-error-recovery.txt b/Documentation/PCI/pci-error-recovery.txt index e83f2ea76415..898ded24510d 100644 --- a/Documentation/PCI/pci-error-recovery.txt +++ b/Documentation/PCI/pci-error-recovery.txt @@ -216,7 +216,7 @@ The driver should return one of the following result codes: - PCI_ERS_RESULT_NEED_RESET Driver returns this if it thinks the device is not - recoverable in it's current state and it needs a slot + recoverable in its current state and it needs a slot reset to proceed. - PCI_ERS_RESULT_DISCONNECT @@ -241,7 +241,7 @@ in working condition. The driver is not supposed to restart normal driver I/O operations at this point. It should limit itself to "probing" the device to -check it's recoverability status. If all is right, then the platform +check its recoverability status. If all is right, then the platform will call resume() once all drivers have ack'd link_reset(). Result codes: diff --git a/Documentation/RCU/NMI-RCU.txt b/Documentation/RCU/NMI-RCU.txt index a6d32e65d222..a8536cb88091 100644 --- a/Documentation/RCU/NMI-RCU.txt +++ b/Documentation/RCU/NMI-RCU.txt @@ -34,7 +34,7 @@ NMI handler. cpu = smp_processor_id(); ++nmi_count(cpu); - if (!rcu_dereference(nmi_callback)(regs, cpu)) + if (!rcu_dereference_sched(nmi_callback)(regs, cpu)) default_do_nmi(regs); nmi_exit(); @@ -47,12 +47,13 @@ function pointer. If this handler returns zero, do_nmi() invokes the default_do_nmi() function to handle a machine-specific NMI. Finally, preemption is restored. -Strictly speaking, rcu_dereference() is not needed, since this code runs -only on i386, which does not need rcu_dereference() anyway. However, -it is a good documentation aid, particularly for anyone attempting to -do something similar on Alpha. +In theory, rcu_dereference_sched() is not needed, since this code runs +only on i386, which in theory does not need rcu_dereference_sched() +anyway. However, in practice it is a good documentation aid, particularly +for anyone attempting to do something similar on Alpha or on systems +with aggressive optimizing compilers. -Quick Quiz: Why might the rcu_dereference() be necessary on Alpha, +Quick Quiz: Why might the rcu_dereference_sched() be necessary on Alpha, given that the code referenced by the pointer is read-only? @@ -99,17 +100,21 @@ invoke irq_enter() and irq_exit() on NMI entry and exit, respectively. Answer to Quick Quiz - Why might the rcu_dereference() be necessary on Alpha, given + Why might the rcu_dereference_sched() be necessary on Alpha, given that the code referenced by the pointer is read-only? Answer: The caller to set_nmi_callback() might well have - initialized some data that is to be used by the - new NMI handler. In this case, the rcu_dereference() - would be needed, because otherwise a CPU that received - an NMI just after the new handler was set might see - the pointer to the new NMI handler, but the old - pre-initialized version of the handler's data. - - More important, the rcu_dereference() makes it clear - to someone reading the code that the pointer is being - protected by RCU. + initialized some data that is to be used by the new NMI + handler. In this case, the rcu_dereference_sched() would + be needed, because otherwise a CPU that received an NMI + just after the new handler was set might see the pointer + to the new NMI handler, but the old pre-initialized + version of the handler's data. + + This same sad story can happen on other CPUs when using + a compiler with aggressive pointer-value speculation + optimizations. + + More important, the rcu_dereference_sched() makes it + clear to someone reading the code that the pointer is + being protected by RCU-sched. diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index cbc180f90194..790d1a812376 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -260,7 +260,8 @@ over a rather long period of time, but improvements are always welcome! The reason that it is permissible to use RCU list-traversal primitives when the update-side lock is held is that doing so can be quite helpful in reducing code bloat when common code is - shared between readers and updaters. + shared between readers and updaters. Additional primitives + are provided for this case, as discussed in lockdep.txt. 10. Conversely, if you are in an RCU read-side critical section, and you don't hold the appropriate update-side lock, you -must- @@ -344,8 +345,8 @@ over a rather long period of time, but improvements are always welcome! requiring SRCU's read-side deadlock immunity or low read-side realtime latency. - Note that, rcu_assign_pointer() and rcu_dereference() relate to - SRCU just as they do to other forms of RCU. + Note that, rcu_assign_pointer() relates to SRCU just as they do + to other forms of RCU. 15. The whole point of call_rcu(), synchronize_rcu(), and friends is to wait until all pre-existing readers have finished before diff --git a/Documentation/RCU/lockdep.txt b/Documentation/RCU/lockdep.txt index fe24b58627bd..d7a49b2f6994 100644 --- a/Documentation/RCU/lockdep.txt +++ b/Documentation/RCU/lockdep.txt @@ -32,9 +32,20 @@ checking of rcu_dereference() primitives: srcu_dereference(p, sp): Check for SRCU read-side critical section. rcu_dereference_check(p, c): - Use explicit check expression "c". + Use explicit check expression "c". This is useful in + code that is invoked by both readers and updaters. rcu_dereference_raw(p) Don't check. (Use sparingly, if at all.) + rcu_dereference_protected(p, c): + Use explicit check expression "c", and omit all barriers + and compiler constraints. This is useful when the data + structure cannot change, for example, in code that is + invoked only by updaters. + rcu_access_pointer(p): + Return the value of the pointer and omit all barriers, + but retain the compiler constraints that prevent duplicating + or coalescsing. This is useful when when testing the + value of the pointer itself, for example, against NULL. The rcu_dereference_check() check expression can be any boolean expression, but would normally include one of the rcu_read_lock_held() @@ -59,7 +70,20 @@ In case (1), the pointer is picked up in an RCU-safe manner for vanilla RCU read-side critical sections, in case (2) the ->file_lock prevents any change from taking place, and finally, in case (3) the current task is the only task accessing the file_struct, again preventing any change -from taking place. +from taking place. If the above statement was invoked only from updater +code, it could instead be written as follows: + + file = rcu_dereference_protected(fdt->fd[fd], + lockdep_is_held(&files->file_lock) || + atomic_read(&files->count) == 1); + +This would verify cases #2 and #3 above, and furthermore lockdep would +complain if this was used in an RCU read-side critical section unless one +of these two cases held. Because rcu_dereference_protected() omits all +barriers and compiler constraints, it generates better code than do the +other flavors of rcu_dereference(). On the other hand, it is illegal +to use rcu_dereference_protected() if either the RCU-protected pointer +or the RCU-protected data that it points to can change concurrently. There are currently only "universal" versions of the rcu_assign_pointer() and RCU list-/tree-traversal primitives, which do not (yet) check for diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index 1423d2570d78..44c6dcc93d6d 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -3,35 +3,79 @@ Using RCU's CPU Stall Detector The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables RCU's CPU stall detector, which detects conditions that unduly delay RCU grace periods. The stall detector's idea of what constitutes -"unduly delayed" is controlled by a pair of C preprocessor macros: +"unduly delayed" is controlled by a set of C preprocessor macros: RCU_SECONDS_TILL_STALL_CHECK This macro defines the period of time that RCU will wait from the beginning of a grace period until it issues an RCU CPU - stall warning. It is normally ten seconds. + stall warning. This time period is normally ten seconds. RCU_SECONDS_TILL_STALL_RECHECK This macro defines the period of time that RCU will wait after - issuing a stall warning until it issues another stall warning. - It is normally set to thirty seconds. + issuing a stall warning until it issues another stall warning + for the same stall. This time period is normally set to thirty + seconds. RCU_STALL_RAT_DELAY - The CPU stall detector tries to make the offending CPU rat on itself, - as this often gives better-quality stack traces. However, if - the offending CPU does not detect its own stall in the number - of jiffies specified by RCU_STALL_RAT_DELAY, then other CPUs will - complain. This is normally set to two jiffies. + The CPU stall detector tries to make the offending CPU print its + own warnings, as this often gives better-quality stack traces. + However, if the offending CPU does not detect its own stall in + the number of jiffies specified by RCU_STALL_RAT_DELAY, then + some other CPU will complain. This delay is normally set to + two jiffies. -The following problems can result in an RCU CPU stall warning: +When a CPU detects that it is stalling, it will print a message similar +to the following: + +INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies) + +This message indicates that CPU 5 detected that it was causing a stall, +and that the stall was affecting RCU-sched. This message will normally be +followed by a stack dump of the offending CPU. On TREE_RCU kernel builds, +RCU and RCU-sched are implemented by the same underlying mechanism, +while on TREE_PREEMPT_RCU kernel builds, RCU is instead implemented +by rcu_preempt_state. + +On the other hand, if the offending CPU fails to print out a stall-warning +message quickly enough, some other CPU will print a message similar to +the following: + +INFO: rcu_bh_state detected stalls on CPUs/tasks: { 3 5 } (detected by 2, 2502 jiffies) + +This message indicates that CPU 2 detected that CPUs 3 and 5 were both +causing stalls, and that the stall was affecting RCU-bh. This message +will normally be followed by stack dumps for each CPU. Please note that +TREE_PREEMPT_RCU builds can be stalled by tasks as well as by CPUs, +and that the tasks will be indicated by PID, for example, "P3421". +It is even possible for a rcu_preempt_state stall to be caused by both +CPUs -and- tasks, in which case the offending CPUs and tasks will all +be called out in the list. + +Finally, if the grace period ends just as the stall warning starts +printing, there will be a spurious stall-warning message: + +INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffies) + +This is rare, but does happen from time to time in real life. + +So your kernel printed an RCU CPU stall warning. The next question is +"What caused it?" The following problems can result in RCU CPU stall +warnings: o A CPU looping in an RCU read-side critical section. -o A CPU looping with interrupts disabled. +o A CPU looping with interrupts disabled. This condition can + result in RCU-sched and RCU-bh stalls. -o A CPU looping with preemption disabled. +o A CPU looping with preemption disabled. This condition can + result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh + stalls. + +o A CPU looping with bottom halves disabled. This condition can + result in RCU-sched and RCU-bh stalls. o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel without invoking schedule(). @@ -39,20 +83,24 @@ o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel o A bug in the RCU implementation. o A hardware failure. This is quite unlikely, but has occurred - at least once in a former life. A CPU failed in a running system, + at least once in real life. A CPU failed in a running system, becoming unresponsive, but not causing an immediate crash. This resulted in a series of RCU CPU stall warnings, eventually leading the realization that the CPU had failed. -The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning. -SRCU does not do so directly, but its calls to synchronize_sched() will -result in RCU-sched detecting any CPU stalls that might be occurring. - -To diagnose the cause of the stall, inspect the stack traces. The offending -function will usually be near the top of the stack. If you have a series -of stall warnings from a single extended stall, comparing the stack traces -can often help determine where the stall is occurring, which will usually -be in the function nearest the top of the stack that stays the same from -trace to trace. +The RCU, RCU-sched, and RCU-bh implementations have CPU stall +warning. SRCU does not have its own CPU stall warnings, but its +calls to synchronize_sched() will result in RCU-sched detecting +RCU-sched-related CPU stalls. Please note that RCU only detects +CPU stalls when there is a grace period in progress. No grace period, +no CPU stall warnings. + +To diagnose the cause of the stall, inspect the stack traces. +The offending function will usually be near the top of the stack. +If you have a series of stall warnings from a single extended stall, +comparing the stack traces can often help determine where the stall +is occurring, which will usually be in the function nearest the top of +that portion of the stack which remains the same from trace to trace. +If you can reliably trigger the stall, ftrace can be quite helpful. RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE. diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index 0e50bc2aa1e2..5d9016795fd8 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt @@ -182,16 +182,6 @@ Similarly, sched_expedited RCU provides the following: sched_expedited-torture: Reader Pipe: 12660320201 95875 0 0 0 0 0 0 0 0 0 sched_expedited-torture: Reader Batch: 12660424885 0 0 0 0 0 0 0 0 0 0 sched_expedited-torture: Free-Block Circulation: 1090795 1090795 1090794 1090793 1090792 1090791 1090790 1090789 1090788 1090787 0 - state: -1 / 0:0 3:0 4:0 - -As before, the first four lines are similar to those for RCU. -The last line shows the task-migration state. The first number is --1 if synchronize_sched_expedited() is idle, -2 if in the process of -posting wakeups to the migration kthreads, and N when waiting on CPU N. -Each of the colon-separated fields following the "/" is a CPU:state pair. -Valid states are "0" for idle, "1" for waiting for quiescent state, -"2" for passed through quiescent state, and "3" when a race with a -CPU-hotplug event forces use of the synchronize_sched() primitive. USAGE diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index 8608fd85e921..efd8cc95c06b 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -256,23 +256,23 @@ o Each element of the form "1/1 0:127 ^0" represents one struct The output of "cat rcu/rcu_pending" looks as follows: rcu_sched: - 0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741 - 1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792 - 2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629 - 3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723 - 4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110 - 5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456 - 6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834 - 7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888 + 0 np=255892 qsp=53936 rpq=85 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741 + 1 np=261224 qsp=54638 rpq=33 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792 + 2 np=237496 qsp=49664 rpq=23 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629 + 3 np=236249 qsp=48766 rpq=98 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723 + 4 np=221310 qsp=46850 rpq=7 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110 + 5 np=237332 qsp=48449 rpq=9 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456 + 6 np=219995 qsp=46718 rpq=12 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834 + 7 np=249893 qsp=49390 rpq=42 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888 rcu_bh: - 0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314 - 1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180 - 2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936 - 3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863 - 4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671 - 5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235 - 6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921 - 7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542 + 0 np=146741 qsp=1419 rpq=6 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314 + 1 np=155792 qsp=12597 rpq=3 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180 + 2 np=136629 qsp=18680 rpq=1 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936 + 3 np=137723 qsp=2843 rpq=0 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863 + 4 np=123110 qsp=12433 rpq=0 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671 + 5 np=137456 qsp=4210 rpq=1 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235 + 6 np=120834 qsp=9902 rpq=2 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921 + 7 np=144888 qsp=26336 rpq=0 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542 As always, this is once again split into "rcu_sched" and "rcu_bh" portions, with CONFIG_TREE_PREEMPT_RCU kernels having an additional @@ -284,6 +284,9 @@ o "np" is the number of times that __rcu_pending() has been invoked o "qsp" is the number of times that the RCU was waiting for a quiescent state from this CPU. +o "rpq" is the number of times that the CPU had passed through + a quiescent state, but not yet reported it to RCU. + o "cbr" is the number of times that this CPU had RCU callbacks that had passed through a grace period, and were thus ready to be invoked. diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 1dc00ee97163..cfaac34c4557 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -840,6 +840,12 @@ SRCU: Initialization/cleanup init_srcu_struct cleanup_srcu_struct +All: lockdep-checked RCU-protected pointer access + + rcu_dereference_check + rcu_dereference_protected + rcu_access_pointer + See the comment headers in the source code (or the docbook generated from them) for more information. diff --git a/Documentation/Smack.txt b/Documentation/Smack.txt index 34614b4c708e..e9dab41c0fe0 100644 --- a/Documentation/Smack.txt +++ b/Documentation/Smack.txt @@ -73,7 +73,7 @@ NOTE: Smack labels are limited to 23 characters. The attr command If you don't do anything special all users will get the floor ("_") label when they log in. If you do want to log in via the hacked ssh at other labels use the attr command to set the smack value on the -home directory and it's contents. +home directory and its contents. You can add access rules in /etc/smack/accesses. They take the form: diff --git a/Documentation/SubmitChecklist b/Documentation/SubmitChecklist index 1053a56be3b1..8916ca48bc95 100644 --- a/Documentation/SubmitChecklist +++ b/Documentation/SubmitChecklist @@ -9,10 +9,14 @@ Documentation/SubmittingPatches and elsewhere regarding submitting Linux kernel patches. -1: Builds cleanly with applicable or modified CONFIG options =y, =m, and +1: If you use a facility then #include the file that defines/declares + that facility. Don't depend on other header files pulling in ones + that you use. + +2: Builds cleanly with applicable or modified CONFIG options =y, =m, and =n. No gcc warnings/errors, no linker warnings/errors. -2: Passes allnoconfig, allmodconfig +2b: Passes allnoconfig, allmodconfig 3: Builds on multiple CPU architectures by using local cross-compile tools or some other build farm. diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX index 82e418d648d0..7f5fc3ba9c91 100644 --- a/Documentation/arm/00-INDEX +++ b/Documentation/arm/00-INDEX @@ -20,6 +20,8 @@ Samsung-S3C24XX - S3C24XX ARM Linux Overview Sharp-LH - Linux on Sharp LH79524 and LH7A40X System On a Chip (SOC) +SPEAr + - ST SPEAr platform Linux Overview VFP/ - Release notes for Linux Kernel Vector Floating Point support code empeg/ diff --git a/Documentation/arm/SA1100/ADSBitsy b/Documentation/arm/SA1100/ADSBitsy index 7197a9e958ee..f9f62e8c0719 100644 --- a/Documentation/arm/SA1100/ADSBitsy +++ b/Documentation/arm/SA1100/ADSBitsy @@ -32,7 +32,7 @@ Notes: - The flash on board is divided into 3 partitions. You should be careful to use flash on board. - It's partition is different from GraphicsClient Plus and GraphicsMaster + Its partition is different from GraphicsClient Plus and GraphicsMaster - 16bpp mode requires a different cable than what ships with the board. Contact ADS or look through the manual to wire your own. Currently, diff --git a/Documentation/arm/SPEAr/overview.txt b/Documentation/arm/SPEAr/overview.txt new file mode 100644 index 000000000000..253a35c6f782 --- /dev/null +++ b/Documentation/arm/SPEAr/overview.txt @@ -0,0 +1,60 @@ + SPEAr ARM Linux Overview + ========================== + +Introduction +------------ + + SPEAr (Structured Processor Enhanced Architecture). + weblink : http://www.st.com/spear + + The ST Microelectronics SPEAr range of ARM9/CortexA9 System-on-Chip CPUs are + supported by the 'spear' platform of ARM Linux. Currently SPEAr300, + SPEAr310, SPEAr320 and SPEAr600 SOCs are supported. Support for the SPEAr13XX + series is in progress. + + Hierarchy in SPEAr is as follows: + + SPEAr (Platform) + - SPEAr3XX (3XX SOC series, based on ARM9) + - SPEAr300 (SOC) + - SPEAr300_EVB (Evaluation Board) + - SPEAr310 (SOC) + - SPEAr310_EVB (Evaluation Board) + - SPEAr320 (SOC) + - SPEAr320_EVB (Evaluation Board) + - SPEAr6XX (6XX SOC series, based on ARM9) + - SPEAr600 (SOC) + - SPEAr600_EVB (Evaluation Board) + - SPEAr13XX (13XX SOC series, based on ARM CORTEXA9) + - SPEAr1300 (SOC) + + Configuration + ------------- + + A generic configuration is provided for each machine, and can be used as the + default by + make spear600_defconfig + make spear300_defconfig + make spear310_defconfig + make spear320_defconfig + + Layout + ------ + + The common files for multiple machine families (SPEAr3XX, SPEAr6XX and + SPEAr13XX) are located in the platform code contained in arch/arm/plat-spear + with headers in plat/. + + Each machine series have a directory with name arch/arm/mach-spear followed by + series name. Like mach-spear3xx, mach-spear6xx and mach-spear13xx. + + Common file for machines of spear3xx family is mach-spear3xx/spear3xx.c and for + spear6xx is mach-spear6xx/spear6xx.c. mach-spear* also contain soc/machine + specific files, like spear300.c, spear310.c, spear320.c and spear600.c. + mach-spear* also contains board specific files for each machine type. + + + Document Author + --------------- + + Viresh Kumar, (c) 2010 ST Microelectronics diff --git a/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt b/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt index 76b3a11e90be..fa968aa99d67 100644 --- a/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt +++ b/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt @@ -14,8 +14,8 @@ Introduction how the clocks are arranged. The first implementation used as single PLL to feed the ARM, memory and peripherals via a series of dividers and muxes and this is the implementation that is documented here. A - newer version where there is a seperate PLL and clock divider for the - ARM core is available as a seperate driver. + newer version where there is a separate PLL and clock divider for the + ARM core is available as a separate driver. Layout diff --git a/Documentation/arm/Samsung/Overview.txt b/Documentation/arm/Samsung/Overview.txt new file mode 100644 index 000000000000..7cced1fea9c3 --- /dev/null +++ b/Documentation/arm/Samsung/Overview.txt @@ -0,0 +1,86 @@ + Samsung ARM Linux Overview + ========================== + +Introduction +------------ + + The Samsung range of ARM SoCs spans many similar devices, from the initial + ARM9 through to the newest ARM cores. This document shows an overview of + the current kernel support, how to use it and where to find the code + that supports this. + + The currently supported SoCs are: + + - S3C24XX: See Documentation/arm/Samsung-S3C24XX/Overview.txt for full list + - S3C64XX: S3C6400 and S3C6410 + - S5PC6440 + + S5PC100 and S5PC110 support is currently being merged + + +S3C24XX Systems +--------------- + + There is still documentation in Documnetation/arm/Samsung-S3C24XX/ which + deals with the architecture and drivers specific to these devices. + + See Documentation/arm/Samsung-S3C24XX/Overview.txt for more information + on the implementation details and specific support. + + +Configuration +------------- + + A number of configurations are supplied, as there is no current way of + unifying all the SoCs into one kernel. + + s5p6440_defconfig - S5P6440 specific default configuration + s5pc100_defconfig - S5PC100 specific default configuration + + +Layout +------ + + The directory layout is currently being restructured, and consists of + several platform directories and then the machine specific directories + of the CPUs being built for. + + plat-samsung provides the base for all the implementations, and is the + last in the line of include directories that are processed for the build + specific information. It contains the base clock, GPIO and device definitions + to get the system running. + + plat-s3c is the s3c24xx/s3c64xx platform directory, although it is currently + involved in other builds this will be phased out once the relevant code is + moved elsewhere. + + plat-s3c24xx is for s3c24xx specific builds, see the S3C24XX docs. + + plat-s3c64xx is for the s3c64xx specific bits, see the S3C24XX docs. + + plat-s5p is for s5p specific builds, more to be added. + + + [ to finish ] + + +Port Contributors +----------------- + + Ben Dooks (BJD) + Vincent Sanders + Herbert Potzl + Arnaud Patard (RTP) + Roc Wu + Klaus Fetscher + Dimitry Andric + Shannon Holland + Guillaume Gourat (NexVision) + Christer Weinigel (wingel) (Acer N30) + Lucas Correia Villa Real (S3C2400 port) + + +Document Author +--------------- + +Copyright 2009-2010 Ben Dooks <ben-linux@fluff.org> diff --git a/Documentation/arm/Samsung/clksrc-change-registers.awk b/Documentation/arm/Samsung/clksrc-change-registers.awk new file mode 100755 index 000000000000..0c50220851fb --- /dev/null +++ b/Documentation/arm/Samsung/clksrc-change-registers.awk @@ -0,0 +1,167 @@ +#!/usr/bin/awk -f +# +# Copyright 2010 Ben Dooks <ben-linux@fluff.org> +# +# Released under GPLv2 + +# example usage +# ./clksrc-change-registers.awk arch/arm/plat-s5pc1xx/include/plat/regs-clock.h < src > dst + +function extract_value(s) +{ + eqat = index(s, "=") + comat = index(s, ",") + return substr(s, eqat+2, (comat-eqat)-2) +} + +function remove_brackets(b) +{ + return substr(b, 2, length(b)-2) +} + +function splitdefine(l, p) +{ + r = split(l, tp) + + p[0] = tp[2] + p[1] = remove_brackets(tp[3]) +} + +function find_length(f) +{ + if (0) + printf "find_length " f "\n" > "/dev/stderr" + + if (f ~ /0x1/) + return 1 + else if (f ~ /0x3/) + return 2 + else if (f ~ /0x7/) + return 3 + else if (f ~ /0xf/) + return 4 + + printf "unknown legnth " f "\n" > "/dev/stderr" + exit +} + +function find_shift(s) +{ + id = index(s, "<") + if (id <= 0) { + printf "cannot find shift " s "\n" > "/dev/stderr" + exit + } + + return substr(s, id+2) +} + + +BEGIN { + if (ARGC < 2) { + print "too few arguments" > "/dev/stderr" + exit + } + +# read the header file and find the mask values that we will need +# to replace and create an associative array of values + + while (getline line < ARGV[1] > 0) { + if (line ~ /\#define.*_MASK/ && + !(line ~ /S5PC100_EPLL_MASK/) && + !(line ~ /USB_SIG_MASK/)) { + splitdefine(line, fields) + name = fields[0] + if (0) + printf "MASK " line "\n" > "/dev/stderr" + dmask[name,0] = find_length(fields[1]) + dmask[name,1] = find_shift(fields[1]) + if (0) + printf "=> '" name "' LENGTH=" dmask[name,0] " SHIFT=" dmask[name,1] "\n" > "/dev/stderr" + } else { + } + } + + delete ARGV[1] +} + +/clksrc_clk.*=.*{/ { + shift="" + mask="" + divshift="" + reg_div="" + reg_src="" + indent=1 + + print $0 + + for(; indent >= 1;) { + if ((getline line) <= 0) { + printf "unexpected end of file" > "/dev/stderr" + exit 1; + } + + if (line ~ /\.shift/) { + shift = extract_value(line) + } else if (line ~ /\.mask/) { + mask = extract_value(line) + } else if (line ~ /\.reg_divider/) { + reg_div = extract_value(line) + } else if (line ~ /\.reg_source/) { + reg_src = extract_value(line) + } else if (line ~ /\.divider_shift/) { + divshift = extract_value(line) + } else if (line ~ /{/) { + indent++ + print line + } else if (line ~ /}/) { + indent-- + + if (indent == 0) { + if (0) { + printf "shift '" shift "' ='" dmask[shift,0] "'\n" > "/dev/stderr" + printf "mask '" mask "'\n" > "/dev/stderr" + printf "dshft '" divshift "'\n" > "/dev/stderr" + printf "rdiv '" reg_div "'\n" > "/dev/stderr" + printf "rsrc '" reg_src "'\n" > "/dev/stderr" + } + + generated = mask + sub(reg_src, reg_div, generated) + + if (0) { + printf "/* rsrc " reg_src " */\n" + printf "/* rdiv " reg_div " */\n" + printf "/* shift " shift " */\n" + printf "/* mask " mask " */\n" + printf "/* generated " generated " */\n" + } + + if (reg_div != "") { + printf "\t.reg_div = { " + printf ".reg = " reg_div ", " + printf ".shift = " dmask[generated,1] ", " + printf ".size = " dmask[generated,0] ", " + printf "},\n" + } + + printf "\t.reg_src = { " + printf ".reg = " reg_src ", " + printf ".shift = " dmask[mask,1] ", " + printf ".size = " dmask[mask,0] ", " + + printf "},\n" + + } + + print line + } else { + print line + } + + if (0) + printf indent ":" line "\n" > "/dev/stderr" + } +} + +// && ! /clksrc_clk.*=.*{/ { print $0 } diff --git a/Documentation/arm/Sharp-LH/ADC-LH7-Touchscreen b/Documentation/arm/Sharp-LH/ADC-LH7-Touchscreen index 1e6a23fdf2fc..dc460f055647 100644 --- a/Documentation/arm/Sharp-LH/ADC-LH7-Touchscreen +++ b/Documentation/arm/Sharp-LH/ADC-LH7-Touchscreen @@ -7,7 +7,7 @@ The driver only implements a four-wire touch panel protocol. The touchscreen driver is maintenance free except for the pen-down or touch threshold. Some resistive displays and board combinations may -require tuning of this threshold. The driver exposes some of it's +require tuning of this threshold. The driver exposes some of its internal state in the sys filesystem. If the kernel is configured with it, CONFIG_SYSFS, and sysfs is mounted at /sys, there will be a directory diff --git a/Documentation/atomic_ops.txt b/Documentation/atomic_ops.txt index 396bec3b74ed..ac4d47187122 100644 --- a/Documentation/atomic_ops.txt +++ b/Documentation/atomic_ops.txt @@ -320,7 +320,7 @@ counter decrement would not become globally visible until the obj->active update does. As a historical note, 32-bit Sparc used to only allow usage of -24-bits of it's atomic_t type. This was because it used 8 bits +24-bits of its atomic_t type. This was because it used 8 bits as a spinlock for SMP safety. Sparc32 lacked a "compare and swap" type instruction. However, 32-bit Sparc has since been moved over to a "hash table of spinlocks" scheme, that allows the full 32-bit diff --git a/Documentation/blackfin/bfin-gpio-notes.txt b/Documentation/blackfin/bfin-gpio-notes.txt index 9898c7ded7d3..f731c1e56475 100644 --- a/Documentation/blackfin/bfin-gpio-notes.txt +++ b/Documentation/blackfin/bfin-gpio-notes.txt @@ -43,7 +43,7 @@ void bfin_gpio_irq_free(unsigned gpio); The request functions will record the function state for a certain pin, - the free functions will clear it's function state. + the free functions will clear its function state. Once a pin is requested, it can't be requested again before it is freed by previous caller, otherwise kernel will dump stacks, and the request function fail. diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index 6fab97ea7e6b..508b5b2b0289 100644 --- a/Documentation/block/biodoc.txt +++ b/Documentation/block/biodoc.txt @@ -1162,8 +1162,8 @@ where a driver received a request ala this before: As mentioned, there is no virtual mapping of a bio. For DMA, this is not a problem as the driver probably never will need a virtual mapping. -Instead it needs a bus mapping (pci_map_page for a single segment or -use blk_rq_map_sg for scatter gather) to be able to ship it to the driver. For +Instead it needs a bus mapping (dma_map_page for a single segment or +use dma_map_sg for scatter gather) to be able to ship it to the driver. For PIO drivers (or drivers that need to revert to PIO transfer once in a while (IDE for example)), where the CPU is doing the actual data transfer a virtual mapping is needed. If the driver supports highmem I/O, diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt index 2b5f823abd03..9164ae3b83bc 100644 --- a/Documentation/cachetlb.txt +++ b/Documentation/cachetlb.txt @@ -5,7 +5,7 @@ This document describes the cache/tlb flushing interfaces called by the Linux VM subsystem. It enumerates over each interface, -describes it's intended purpose, and what side effect is expected +describes its intended purpose, and what side effect is expected after the interface is invoked. The side effects described below are stated for a uniprocessor @@ -231,7 +231,7 @@ require a whole different set of interfaces to handle properly. The biggest problem is that of virtual aliasing in the data cache of a processor. -Is your port susceptible to virtual aliasing in it's D-cache? +Is your port susceptible to virtual aliasing in its D-cache? Well, if your D-cache is virtually indexed, is larger in size than PAGE_SIZE, and does not prevent multiple cache lines for the same physical address from existing at once, you have this problem. @@ -249,7 +249,7 @@ one way to solve this (in particular SPARC_FLAG_MMAPSHARED). Next, you have to solve the D-cache aliasing issue for all other cases. Please keep in mind that fact that, for a given page mapped into some user address space, there is always at least one more -mapping, that of the kernel in it's linear mapping starting at +mapping, that of the kernel in its linear mapping starting at PAGE_OFFSET. So immediately, once the first user maps a given physical page into its address space, by implication the D-cache aliasing problem has the potential to exist since the kernel already diff --git a/Documentation/cgroups/cgroup_event_listener.c b/Documentation/cgroups/cgroup_event_listener.c new file mode 100644 index 000000000000..8c2bfc4a6358 --- /dev/null +++ b/Documentation/cgroups/cgroup_event_listener.c @@ -0,0 +1,110 @@ +/* + * cgroup_event_listener.c - Simple listener of cgroup events + * + * Copyright (C) Kirill A. Shutemov <kirill@shutemov.name> + */ + +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <libgen.h> +#include <limits.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> + +#include <sys/eventfd.h> + +#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>\n" + +int main(int argc, char **argv) +{ + int efd = -1; + int cfd = -1; + int event_control = -1; + char event_control_path[PATH_MAX]; + char line[LINE_MAX]; + int ret; + + if (argc != 3) { + fputs(USAGE_STR, stderr); + return 1; + } + + cfd = open(argv[1], O_RDONLY); + if (cfd == -1) { + fprintf(stderr, "Cannot open %s: %s\n", argv[1], + strerror(errno)); + goto out; + } + + ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control", + dirname(argv[1])); + if (ret >= PATH_MAX) { + fputs("Path to cgroup.event_control is too long\n", stderr); + goto out; + } + + event_control = open(event_control_path, O_WRONLY); + if (event_control == -1) { + fprintf(stderr, "Cannot open %s: %s\n", event_control_path, + strerror(errno)); + goto out; + } + + efd = eventfd(0, 0); + if (efd == -1) { + perror("eventfd() failed"); + goto out; + } + + ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]); + if (ret >= LINE_MAX) { + fputs("Arguments string is too long\n", stderr); + goto out; + } + + ret = write(event_control, line, strlen(line) + 1); + if (ret == -1) { + perror("Cannot write to cgroup.event_control"); + goto out; + } + + while (1) { + uint64_t result; + + ret = read(efd, &result, sizeof(result)); + if (ret == -1) { + if (errno == EINTR) + continue; + perror("Cannot read from eventfd"); + break; + } + assert(ret == sizeof(result)); + + ret = access(event_control_path, W_OK); + if ((ret == -1) && (errno == ENOENT)) { + puts("The cgroup seems to have removed."); + ret = 0; + break; + } + + if (ret == -1) { + perror("cgroup.event_control " + "is not accessable any more"); + break; + } + + printf("%s %s: crossed\n", argv[1], argv[2]); + } + +out: + if (efd >= 0) + close(efd); + if (event_control >= 0) + close(event_control); + if (cfd >= 0) + close(cfd); + + return (ret != 0); +} diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 0b33bfe7dde9..57444c2609fc 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -22,6 +22,8 @@ CONTENTS: 2. Usage Examples and Syntax 2.1 Basic Usage 2.2 Attaching processes + 2.3 Mounting hierarchies by name + 2.4 Notification API 3. Kernel API 3.1 Overview 3.2 Synchronization @@ -233,8 +235,7 @@ containing the following files describing that cgroup: - cgroup.procs: list of tgids in the cgroup. This list is not guaranteed to be sorted or free of duplicate tgids, and userspace should sort/uniquify the list if this property is required. - Writing a tgid into this file moves all threads with that tgid into - this cgroup. + This is a read-only file, for now. - notify_on_release flag: run the release agent on exit? - release_agent: the path to use for release notifications (this file exists in the top cgroup only) @@ -434,6 +435,25 @@ you give a subsystem a name. The name of the subsystem appears as part of the hierarchy description in /proc/mounts and /proc/<pid>/cgroups. +2.4 Notification API +-------------------- + +There is mechanism which allows to get notifications about changing +status of a cgroup. + +To register new notification handler you need: + - create a file descriptor for event notification using eventfd(2); + - open a control file to be monitored (e.g. memory.usage_in_bytes); + - write "<event_fd> <control_fd> <args>" to cgroup.event_control. + Interpretation of args is defined by control file implementation; + +eventfd will be woken up by control file implementation or when the +cgroup is removed. + +To unregister notification handler just close eventfd. + +NOTE: Support of notifications should be implemented for the control +file. See documentation for the subsystem. 3. Kernel API ============= @@ -488,6 +508,11 @@ Each subsystem should: - add an entry in linux/cgroup_subsys.h - define a cgroup_subsys object called <name>_subsys +If a subsystem can be compiled as a module, it should also have in its +module initcall a call to cgroup_load_subsys(), and in its exitcall a +call to cgroup_unload_subsys(). It should also set its_subsys.module = +THIS_MODULE in its .c file. + Each subsystem may export the following methods. The only mandatory methods are create/destroy. Any others that are null are presumed to be successful no-ops. @@ -536,10 +561,21 @@ returns an error, this will abort the attach operation. If a NULL task is passed, then a successful result indicates that *any* unspecified task can be moved into the cgroup. Note that this isn't called on a fork. If this method returns 0 (success) then this should -remain valid while the caller holds cgroup_mutex. If threadgroup is +remain valid while the caller holds cgroup_mutex and it is ensured that either +attach() or cancel_attach() will be called in future. If threadgroup is true, then a successful result indicates that all threads in the given thread's threadgroup can be moved together. +void cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *task, bool threadgroup) +(cgroup_mutex held by caller) + +Called when a task attach operation has failed after can_attach() has succeeded. +A subsystem whose can_attach() has some side-effects should provide this +function, so that the subsystem can implement a rollback. If not, not necessary. +This will be called only about subsystems whose can_attach() operation have +succeeded. + void attach(struct cgroup_subsys *ss, struct cgroup *cgrp, struct cgroup *old_cgrp, struct task_struct *task, bool threadgroup) diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index 1d7e9784439a..51682ab2dd1a 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -42,7 +42,7 @@ Nodes to a set of tasks. In this document "Memory Node" refers to an on-line node that contains memory. Cpusets constrain the CPU and Memory placement of tasks to only -the resources within a tasks current cpuset. They form a nested +the resources within a task's current cpuset. They form a nested hierarchy visible in a virtual file system. These are the essential hooks, beyond what is already present, required to manage dynamic job placement on large systems. @@ -53,11 +53,11 @@ Documentation/cgroups/cgroups.txt. Requests by a task, using the sched_setaffinity(2) system call to include CPUs in its CPU affinity mask, and using the mbind(2) and set_mempolicy(2) system calls to include Memory Nodes in its memory -policy, are both filtered through that tasks cpuset, filtering out any +policy, are both filtered through that task's cpuset, filtering out any CPUs or Memory Nodes not in that cpuset. The scheduler will not schedule a task on a CPU that is not allowed in its cpus_allowed vector, and the kernel page allocator will not allocate a page on a -node that is not allowed in the requesting tasks mems_allowed vector. +node that is not allowed in the requesting task's mems_allowed vector. User level code may create and destroy cpusets by name in the cgroup virtual file system, manage the attributes and permissions of these @@ -121,9 +121,9 @@ Cpusets extends these two mechanisms as follows: - Each task in the system is attached to a cpuset, via a pointer in the task structure to a reference counted cgroup structure. - Calls to sched_setaffinity are filtered to just those CPUs - allowed in that tasks cpuset. + allowed in that task's cpuset. - Calls to mbind and set_mempolicy are filtered to just - those Memory Nodes allowed in that tasks cpuset. + those Memory Nodes allowed in that task's cpuset. - The root cpuset contains all the systems CPUs and Memory Nodes. - For any cpuset, one can define child cpusets containing a subset @@ -141,11 +141,11 @@ into the rest of the kernel, none in performance critical paths: - in init/main.c, to initialize the root cpuset at system boot. - in fork and exit, to attach and detach a task from its cpuset. - in sched_setaffinity, to mask the requested CPUs by what's - allowed in that tasks cpuset. + allowed in that task's cpuset. - in sched.c migrate_live_tasks(), to keep migrating tasks within the CPUs allowed by their cpuset, if possible. - in the mbind and set_mempolicy system calls, to mask the requested - Memory Nodes by what's allowed in that tasks cpuset. + Memory Nodes by what's allowed in that task's cpuset. - in page_alloc.c, to restrict memory to allowed nodes. - in vmscan.c, to restrict page recovery to the current cpuset. @@ -155,7 +155,7 @@ new system calls are added for cpusets - all support for querying and modifying cpusets is via this cpuset file system. The /proc/<pid>/status file for each task has four added lines, -displaying the tasks cpus_allowed (on which CPUs it may be scheduled) +displaying the task's cpus_allowed (on which CPUs it may be scheduled) and mems_allowed (on which Memory Nodes it may obtain memory), in the two formats seen in the following example: @@ -168,20 +168,20 @@ Each cpuset is represented by a directory in the cgroup file system containing (on top of the standard cgroup files) the following files describing that cpuset: - - cpus: list of CPUs in that cpuset - - mems: list of Memory Nodes in that cpuset - - memory_migrate flag: if set, move pages to cpusets nodes - - cpu_exclusive flag: is cpu placement exclusive? - - mem_exclusive flag: is memory placement exclusive? - - mem_hardwall flag: is memory allocation hardwalled - - memory_pressure: measure of how much paging pressure in cpuset - - memory_spread_page flag: if set, spread page cache evenly on allowed nodes - - memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes - - sched_load_balance flag: if set, load balance within CPUs on that cpuset - - sched_relax_domain_level: the searching range when migrating tasks + - cpuset.cpus: list of CPUs in that cpuset + - cpuset.mems: list of Memory Nodes in that cpuset + - cpuset.memory_migrate flag: if set, move pages to cpusets nodes + - cpuset.cpu_exclusive flag: is cpu placement exclusive? + - cpuset.mem_exclusive flag: is memory placement exclusive? + - cpuset.mem_hardwall flag: is memory allocation hardwalled + - cpuset.memory_pressure: measure of how much paging pressure in cpuset + - cpuset.memory_spread_page flag: if set, spread page cache evenly on allowed nodes + - cpuset.memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes + - cpuset.sched_load_balance flag: if set, load balance within CPUs on that cpuset + - cpuset.sched_relax_domain_level: the searching range when migrating tasks In addition, the root cpuset only has the following file: - - memory_pressure_enabled flag: compute memory_pressure? + - cpuset.memory_pressure_enabled flag: compute memory_pressure? New cpusets are created using the mkdir system call or shell command. The properties of a cpuset, such as its flags, allowed @@ -229,7 +229,7 @@ If a cpuset is cpu or mem exclusive, no other cpuset, other than a direct ancestor or descendant, may share any of the same CPUs or Memory Nodes. -A cpuset that is mem_exclusive *or* mem_hardwall is "hardwalled", +A cpuset that is cpuset.mem_exclusive *or* cpuset.mem_hardwall is "hardwalled", i.e. it restricts kernel allocations for page, buffer and other data commonly shared by the kernel across multiple users. All cpusets, whether hardwalled or not, restrict allocations of memory for user @@ -304,15 +304,15 @@ times 1000. --------------------------- There are two boolean flag files per cpuset that control where the kernel allocates pages for the file system buffers and related in -kernel data structures. They are called 'memory_spread_page' and -'memory_spread_slab'. +kernel data structures. They are called 'cpuset.memory_spread_page' and +'cpuset.memory_spread_slab'. -If the per-cpuset boolean flag file 'memory_spread_page' is set, then +If the per-cpuset boolean flag file 'cpuset.memory_spread_page' is set, then the kernel will spread the file system buffers (page cache) evenly over all the nodes that the faulting task is allowed to use, instead of preferring to put those pages on the node where the task is running. -If the per-cpuset boolean flag file 'memory_spread_slab' is set, +If the per-cpuset boolean flag file 'cpuset.memory_spread_slab' is set, then the kernel will spread some file system related slab caches, such as for inodes and dentries evenly over all the nodes that the faulting task is allowed to use, instead of preferring to put those @@ -323,41 +323,41 @@ stack segment pages of a task. By default, both kinds of memory spreading are off, and memory pages are allocated on the node local to where the task is running, -except perhaps as modified by the tasks NUMA mempolicy or cpuset +except perhaps as modified by the task's NUMA mempolicy or cpuset configuration, so long as sufficient free memory pages are available. When new cpusets are created, they inherit the memory spread settings of their parent. Setting memory spreading causes allocations for the affected page -or slab caches to ignore the tasks NUMA mempolicy and be spread +or slab caches to ignore the task's NUMA mempolicy and be spread instead. Tasks using mbind() or set_mempolicy() calls to set NUMA mempolicies will not notice any change in these calls as a result of -their containing tasks memory spread settings. If memory spreading +their containing task's memory spread settings. If memory spreading is turned off, then the currently specified NUMA mempolicy once again applies to memory page allocations. -Both 'memory_spread_page' and 'memory_spread_slab' are boolean flag +Both 'cpuset.memory_spread_page' and 'cpuset.memory_spread_slab' are boolean flag files. By default they contain "0", meaning that the feature is off for that cpuset. If a "1" is written to that file, then that turns the named feature on. The implementation is simple. -Setting the flag 'memory_spread_page' turns on a per-process flag +Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag PF_SPREAD_PAGE for each task that is in that cpuset or subsequently joins that cpuset. The page allocation calls for the page cache is modified to perform an inline check for this PF_SPREAD_PAGE task flag, and if set, a call to a new routine cpuset_mem_spread_node() returns the node to prefer for the allocation. -Similarly, setting 'memory_spread_slab' turns on the flag +Similarly, setting 'cpuset.memory_spread_slab' turns on the flag PF_SPREAD_SLAB, and appropriately marked slab caches will allocate pages from the node returned by cpuset_mem_spread_node(). The cpuset_mem_spread_node() routine is also simple. It uses the value of a per-task rotor cpuset_mem_spread_rotor to select the next -node in the current tasks mems_allowed to prefer for the allocation. +node in the current task's mems_allowed to prefer for the allocation. This memory placement policy is also known (in other contexts) as round-robin or interleave. @@ -404,24 +404,24 @@ the following two situations: system overhead on those CPUs, including avoiding task load balancing if that is not needed. -When the per-cpuset flag "sched_load_balance" is enabled (the default -setting), it requests that all the CPUs in that cpusets allowed 'cpus' +When the per-cpuset flag "cpuset.sched_load_balance" is enabled (the default +setting), it requests that all the CPUs in that cpusets allowed 'cpuset.cpus' be contained in a single sched domain, ensuring that load balancing can move a task (not otherwised pinned, as by sched_setaffinity) from any CPU in that cpuset to any other. -When the per-cpuset flag "sched_load_balance" is disabled, then the +When the per-cpuset flag "cpuset.sched_load_balance" is disabled, then the scheduler will avoid load balancing across the CPUs in that cpuset, --except-- in so far as is necessary because some overlapping cpuset has "sched_load_balance" enabled. -So, for example, if the top cpuset has the flag "sched_load_balance" +So, for example, if the top cpuset has the flag "cpuset.sched_load_balance" enabled, then the scheduler will have one sched domain covering all -CPUs, and the setting of the "sched_load_balance" flag in any other +CPUs, and the setting of the "cpuset.sched_load_balance" flag in any other cpusets won't matter, as we're already fully load balancing. Therefore in the above two situations, the top cpuset flag -"sched_load_balance" should be disabled, and only some of the smaller, +"cpuset.sched_load_balance" should be disabled, and only some of the smaller, child cpusets have this flag enabled. When doing this, you don't usually want to leave any unpinned tasks in @@ -433,7 +433,7 @@ scheduler might not consider the possibility of load balancing that task to that underused CPU. Of course, tasks pinned to a particular CPU can be left in a cpuset -that disables "sched_load_balance" as those tasks aren't going anywhere +that disables "cpuset.sched_load_balance" as those tasks aren't going anywhere else anyway. There is an impedance mismatch here, between cpusets and sched domains. @@ -443,19 +443,19 @@ overlap and each CPU is in at most one sched domain. It is necessary for sched domains to be flat because load balancing across partially overlapping sets of CPUs would risk unstable dynamics that would be beyond our understanding. So if each of two partially -overlapping cpusets enables the flag 'sched_load_balance', then we +overlapping cpusets enables the flag 'cpuset.sched_load_balance', then we form a single sched domain that is a superset of both. We won't move a task to a CPU outside it cpuset, but the scheduler load balancing code might waste some compute cycles considering that possibility. This mismatch is why there is not a simple one-to-one relation -between which cpusets have the flag "sched_load_balance" enabled, +between which cpusets have the flag "cpuset.sched_load_balance" enabled, and the sched domain configuration. If a cpuset enables the flag, it will get balancing across all its CPUs, but if it disables the flag, it will only be assured of no load balancing if no other overlapping cpuset enables the flag. -If two cpusets have partially overlapping 'cpus' allowed, and only +If two cpusets have partially overlapping 'cpuset.cpus' allowed, and only one of them has this flag enabled, then the other may find its tasks only partially load balanced, just on the overlapping CPUs. This is just the general case of the top_cpuset example given a few @@ -468,23 +468,23 @@ load balancing to the other CPUs. 1.7.1 sched_load_balance implementation details. ------------------------------------------------ -The per-cpuset flag 'sched_load_balance' defaults to enabled (contrary +The per-cpuset flag 'cpuset.sched_load_balance' defaults to enabled (contrary to most cpuset flags.) When enabled for a cpuset, the kernel will ensure that it can load balance across all the CPUs in that cpuset (makes sure that all the CPUs in the cpus_allowed of that cpuset are in the same sched domain.) -If two overlapping cpusets both have 'sched_load_balance' enabled, +If two overlapping cpusets both have 'cpuset.sched_load_balance' enabled, then they will be (must be) both in the same sched domain. -If, as is the default, the top cpuset has 'sched_load_balance' enabled, +If, as is the default, the top cpuset has 'cpuset.sched_load_balance' enabled, then by the above that means there is a single sched domain covering the whole system, regardless of any other cpuset settings. The kernel commits to user space that it will avoid load balancing where it can. It will pick as fine a granularity partition of sched domains as it can while still providing load balancing for any set -of CPUs allowed to a cpuset having 'sched_load_balance' enabled. +of CPUs allowed to a cpuset having 'cpuset.sched_load_balance' enabled. The internal kernel cpuset to scheduler interface passes from the cpuset code to the scheduler code a partition of the load balanced @@ -495,9 +495,9 @@ all the CPUs that must be load balanced. The cpuset code builds a new such partition and passes it to the scheduler sched domain setup code, to have the sched domains rebuilt as necessary, whenever: - - the 'sched_load_balance' flag of a cpuset with non-empty CPUs changes, + - the 'cpuset.sched_load_balance' flag of a cpuset with non-empty CPUs changes, - or CPUs come or go from a cpuset with this flag enabled, - - or 'sched_relax_domain_level' value of a cpuset with non-empty CPUs + - or 'cpuset.sched_relax_domain_level' value of a cpuset with non-empty CPUs and with this flag enabled changes, - or a cpuset with non-empty CPUs and with this flag enabled is removed, - or a cpu is offlined/onlined. @@ -542,7 +542,7 @@ As the result, task B on CPU X need to wait task A or wait load balance on the next tick. For some applications in special situation, waiting 1 tick may be too long. -The 'sched_relax_domain_level' file allows you to request changing +The 'cpuset.sched_relax_domain_level' file allows you to request changing this searching range as you like. This file takes int value which indicates size of searching range in levels ideally as follows, otherwise initial value -1 that indicates the cpuset has no request. @@ -559,8 +559,8 @@ The system default is architecture dependent. The system default can be changed using the relax_domain_level= boot parameter. This file is per-cpuset and affect the sched domain where the cpuset -belongs to. Therefore if the flag 'sched_load_balance' of a cpuset -is disabled, then 'sched_relax_domain_level' have no effect since +belongs to. Therefore if the flag 'cpuset.sched_load_balance' of a cpuset +is disabled, then 'cpuset.sched_relax_domain_level' have no effect since there is no sched domain belonging the cpuset. If multiple cpusets are overlapping and hence they form a single sched @@ -594,7 +594,7 @@ is attached, is subtle. If a cpuset has its Memory Nodes modified, then for each task attached to that cpuset, the next time that the kernel attempts to allocate a page of memory for that task, the kernel will notice the change -in the tasks cpuset, and update its per-task memory placement to +in the task's cpuset, and update its per-task memory placement to remain within the new cpusets memory placement. If the task was using mempolicy MPOL_BIND, and the nodes to which it was bound overlap with its new cpuset, then the task will continue to use whatever subset @@ -603,13 +603,13 @@ was using MPOL_BIND and now none of its MPOL_BIND nodes are allowed in the new cpuset, then the task will be essentially treated as if it was MPOL_BIND bound to the new cpuset (even though its NUMA placement, as queried by get_mempolicy(), doesn't change). If a task is moved -from one cpuset to another, then the kernel will adjust the tasks +from one cpuset to another, then the kernel will adjust the task's memory placement, as above, the next time that the kernel attempts to allocate a page of memory for that task. -If a cpuset has its 'cpus' modified, then each task in that cpuset +If a cpuset has its 'cpuset.cpus' modified, then each task in that cpuset will have its allowed CPU placement changed immediately. Similarly, -if a tasks pid is written to another cpusets 'tasks' file, then its +if a task's pid is written to another cpusets 'cpuset.tasks' file, then its allowed CPU placement is changed immediately. If such a task had been bound to some subset of its cpuset using the sched_setaffinity() call, the task will be allowed to run on any CPU allowed in its new cpuset, @@ -622,21 +622,21 @@ and the processor placement is updated immediately. Normally, once a page is allocated (given a physical page of main memory) then that page stays on whatever node it was allocated, so long as it remains allocated, even if the -cpusets memory placement policy 'mems' subsequently changes. -If the cpuset flag file 'memory_migrate' is set true, then when +cpusets memory placement policy 'cpuset.mems' subsequently changes. +If the cpuset flag file 'cpuset.memory_migrate' is set true, then when tasks are attached to that cpuset, any pages that task had allocated to it on nodes in its previous cpuset are migrated -to the tasks new cpuset. The relative placement of the page within +to the task's new cpuset. The relative placement of the page within the cpuset is preserved during these migration operations if possible. For example if the page was on the second valid node of the prior cpuset then the page will be placed on the second valid node of the new cpuset. -Also if 'memory_migrate' is set true, then if that cpusets -'mems' file is modified, pages allocated to tasks in that -cpuset, that were on nodes in the previous setting of 'mems', +Also if 'cpuset.memory_migrate' is set true, then if that cpuset's +'cpuset.mems' file is modified, pages allocated to tasks in that +cpuset, that were on nodes in the previous setting of 'cpuset.mems', will be moved to nodes in the new setting of 'mems.' -Pages that were not in the tasks prior cpuset, or in the cpusets -prior 'mems' setting, will not be moved. +Pages that were not in the task's prior cpuset, or in the cpuset's +prior 'cpuset.mems' setting, will not be moved. There is an exception to the above. If hotplug functionality is used to remove all the CPUs that are currently assigned to a cpuset, @@ -655,7 +655,7 @@ There is a second exception to the above. GFP_ATOMIC requests are kernel internal allocations that must be satisfied, immediately. The kernel may drop some request, in rare cases even panic, if a GFP_ATOMIC alloc fails. If the request cannot be satisfied within -the current tasks cpuset, then we relax the cpuset, and look for +the current task's cpuset, then we relax the cpuset, and look for memory anywhere we can find it. It's better to violate the cpuset than stress the kernel. @@ -678,8 +678,8 @@ and then start a subshell 'sh' in that cpuset: cd /dev/cpuset mkdir Charlie cd Charlie - /bin/echo 2-3 > cpus - /bin/echo 1 > mems + /bin/echo 2-3 > cpuset.cpus + /bin/echo 1 > cpuset.mems /bin/echo $$ > tasks sh # The subshell 'sh' is now running in cpuset Charlie @@ -725,10 +725,13 @@ Now you want to do something with this cpuset. In this directory you can find several files: # ls -cpu_exclusive memory_migrate mems tasks -cpus memory_pressure notify_on_release -mem_exclusive memory_spread_page sched_load_balance -mem_hardwall memory_spread_slab sched_relax_domain_level +cpuset.cpu_exclusive cpuset.memory_spread_slab +cpuset.cpus cpuset.mems +cpuset.mem_exclusive cpuset.sched_load_balance +cpuset.mem_hardwall cpuset.sched_relax_domain_level +cpuset.memory_migrate notify_on_release +cpuset.memory_pressure tasks +cpuset.memory_spread_page Reading them will give you information about the state of this cpuset: the CPUs and Memory Nodes it can use, the processes that are using @@ -736,13 +739,13 @@ it, its properties. By writing to these files you can manipulate the cpuset. Set some flags: -# /bin/echo 1 > cpu_exclusive +# /bin/echo 1 > cpuset.cpu_exclusive Add some cpus: -# /bin/echo 0-7 > cpus +# /bin/echo 0-7 > cpuset.cpus Add some mems: -# /bin/echo 0-7 > mems +# /bin/echo 0-7 > cpuset.mems Now attach your shell to this cpuset: # /bin/echo $$ > tasks @@ -774,28 +777,28 @@ echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent This is the syntax to use when writing in the cpus or mems files in cpuset directories: -# /bin/echo 1-4 > cpus -> set cpus list to cpus 1,2,3,4 -# /bin/echo 1,2,3,4 > cpus -> set cpus list to cpus 1,2,3,4 +# /bin/echo 1-4 > cpuset.cpus -> set cpus list to cpus 1,2,3,4 +# /bin/echo 1,2,3,4 > cpuset.cpus -> set cpus list to cpus 1,2,3,4 To add a CPU to a cpuset, write the new list of CPUs including the CPU to be added. To add 6 to the above cpuset: -# /bin/echo 1-4,6 > cpus -> set cpus list to cpus 1,2,3,4,6 +# /bin/echo 1-4,6 > cpuset.cpus -> set cpus list to cpus 1,2,3,4,6 Similarly to remove a CPU from a cpuset, write the new list of CPUs without the CPU to be removed. To remove all the CPUs: -# /bin/echo "" > cpus -> clear cpus list +# /bin/echo "" > cpuset.cpus -> clear cpus list 2.3 Setting flags ----------------- The syntax is very simple: -# /bin/echo 1 > cpu_exclusive -> set flag 'cpu_exclusive' -# /bin/echo 0 > cpu_exclusive -> unset flag 'cpu_exclusive' +# /bin/echo 1 > cpuset.cpu_exclusive -> set flag 'cpuset.cpu_exclusive' +# /bin/echo 0 > cpuset.cpu_exclusive -> unset flag 'cpuset.cpu_exclusive' 2.4 Attaching processes ----------------------- diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt index 72db89ed0609..b7eececfb195 100644 --- a/Documentation/cgroups/memcg_test.txt +++ b/Documentation/cgroups/memcg_test.txt @@ -1,6 +1,6 @@ Memory Resource Controller(Memcg) Implementation Memo. -Last Updated: 2009/1/20 -Base Kernel Version: based on 2.6.29-rc2. +Last Updated: 2010/2 +Base Kernel Version: based on 2.6.33-rc7-mm(candidate for 34). Because VM is getting complex (one of reasons is memcg...), memcg's behavior is complex. This is a document for memcg's internal behavior. @@ -244,7 +244,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. we have to check if OLDPAGE/NEWPAGE is a valid page after commit(). 8. LRU - Each memcg has its own private LRU. Now, it's handling is under global + Each memcg has its own private LRU. Now, its handling is under global VM's control (means that it's handled under global zone->lru_lock). Almost all routines around memcg's LRU is called by global LRU's list management functions under zone->lru_lock(). @@ -337,7 +337,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. race and lock dependency with other cgroup subsystems. example) - # mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices + # mount -t cgroup none /cgroup -o cpuset,memory,cpu,devices and do task move, mkdir, rmdir etc...under this. @@ -348,7 +348,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. For example, test like following is good. (Shell-A) - # mount -t cgroup none /cgroup -t memory + # mount -t cgroup none /cgroup -o memory # mkdir /cgroup/test # echo 40M > /cgroup/test/memory.limit_in_bytes # echo 0 > /cgroup/test/tasks @@ -378,3 +378,42 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. #echo 50M > memory.limit_in_bytes #echo 50M > memory.memsw.limit_in_bytes run 51M of malloc + + 9.9 Move charges at task migration + Charges associated with a task can be moved along with task migration. + + (Shell-A) + #mkdir /cgroup/A + #echo $$ >/cgroup/A/tasks + run some programs which uses some amount of memory in /cgroup/A. + + (Shell-B) + #mkdir /cgroup/B + #echo 1 >/cgroup/B/memory.move_charge_at_immigrate + #echo "pid of the program running in group A" >/cgroup/B/tasks + + You can see charges have been moved by reading *.usage_in_bytes or + memory.stat of both A and B. + See 8.2 of Documentation/cgroups/memory.txt to see what value should be + written to move_charge_at_immigrate. + + 9.10 Memory thresholds + Memory controler implements memory thresholds using cgroups notification + API. You can use Documentation/cgroups/cgroup_event_listener.c to test + it. + + (Shell-A) Create cgroup and run event listener + # mkdir /cgroup/A + # ./cgroup_event_listener /cgroup/A/memory.usage_in_bytes 5M + + (Shell-B) Add task to cgroup and try to allocate and free memory + # echo $$ >/cgroup/A/tasks + # a="$(dd if=/dev/zero bs=1M count=10)" + # a= + + You will see message from cgroup_event_listener every time you cross + the thresholds. + + Use /cgroup/A/memory.memsw.usage_in_bytes to test memsw thresholds. + + It's good idea to test root cgroup as well. diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index b871f2552b45..6cab1f29da4c 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -182,6 +182,8 @@ list. NOTE: Reclaim does not work for the root cgroup, since we cannot set any limits on the root cgroup. +Note2: When panic_on_oom is set to "2", the whole system will panic. + 2. Locking The memory controller uses the following hierarchy @@ -261,11 +263,13 @@ some of the pages cached in the cgroup (page cache pages). 4.2 Task migration -When a task migrates from one cgroup to another, it's charge is not -carried forward. The pages allocated from the original cgroup still +When a task migrates from one cgroup to another, its charge is not +carried forward by default. The pages allocated from the original cgroup still remain charged to it, the charge is dropped when the page is freed or reclaimed. +Note: You can move charges of a task along with task migration. See 8. + 4.3 Removing a cgroup A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a @@ -336,7 +340,7 @@ Note: 5.3 swappiness Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only. - Following cgroups' swapiness can't be changed. + Following cgroups' swappiness can't be changed. - root cgroup (uses /proc/sys/vm/swappiness). - a cgroup which uses hierarchy and it has child cgroup. - a cgroup which uses hierarchy and not the root of hierarchy. @@ -377,7 +381,8 @@ The feature can be disabled by NOTE1: Enabling/disabling will fail if the cgroup already has other cgroups created below it. -NOTE2: This feature can be enabled/disabled per subtree. +NOTE2: When panic_on_oom is set to "2", the whole system will panic in +case of an oom event in any cgroup. 7. Soft limits @@ -414,7 +419,76 @@ NOTE1: Soft limits take effect over a long period of time, since they involve NOTE2: It is recommended to set the soft limit always below the hard limit, otherwise the hard limit will take precedence. -8. TODO +8. Move charges at task migration + +Users can move charges associated with a task along with task migration, that +is, uncharge task's pages from the old cgroup and charge them to the new cgroup. +This feature is not supported in !CONFIG_MMU environments because of lack of +page tables. + +8.1 Interface + +This feature is disabled by default. It can be enabled(and disabled again) by +writing to memory.move_charge_at_immigrate of the destination cgroup. + +If you want to enable it: + +# echo (some positive value) > memory.move_charge_at_immigrate + +Note: Each bits of move_charge_at_immigrate has its own meaning about what type + of charges should be moved. See 8.2 for details. +Note: Charges are moved only when you move mm->owner, IOW, a leader of a thread + group. +Note: If we cannot find enough space for the task in the destination cgroup, we + try to make space by reclaiming memory. Task migration may fail if we + cannot make enough space. +Note: It can take several seconds if you move charges in giga bytes order. + +And if you want disable it again: + +# echo 0 > memory.move_charge_at_immigrate + +8.2 Type of charges which can be move + +Each bits of move_charge_at_immigrate has its own meaning about what type of +charges should be moved. + + bit | what type of charges would be moved ? + -----+------------------------------------------------------------------------ + 0 | A charge of an anonymous page(or swap of it) used by the target task. + | Those pages and swaps must be used only by the target task. You must + | enable Swap Extension(see 2.4) to enable move of swap charges. + +Note: Those pages and swaps must be charged to the old cgroup. +Note: More type of pages(e.g. file cache, shmem,) will be supported by other + bits in future. + +8.3 TODO + +- Add support for other types of pages(e.g. file cache, shmem, etc.). +- Implement madvise(2) to let users decide the vma to be moved or not to be + moved. +- All of moving charge operations are done under cgroup_mutex. It's not good + behavior to hold the mutex too long, so we may need some trick. + +9. Memory thresholds + +Memory controler implements memory thresholds using cgroups notification +API (see cgroups.txt). It allows to register multiple memory and memsw +thresholds and gets notifications when it crosses. + +To register a threshold application need: + - create an eventfd using eventfd(2); + - open memory.usage_in_bytes or memory.memsw.usage_in_bytes; + - write string like "<event_fd> <memory.usage_in_bytes> <threshold>" to + cgroup.event_control. + +Application will be notified through eventfd when memory usage crosses +threshold in any direction. + +It's applicable for root and non-root cgroup. + +10. TODO 1. Add support for accounting huge pages (as a separate controller) 2. Make per-cgroup scanner reclaim not-shared pages first diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt new file mode 100644 index 000000000000..8117e5bf6065 --- /dev/null +++ b/Documentation/circular-buffers.txt @@ -0,0 +1,234 @@ + ================ + CIRCULAR BUFFERS + ================ + +By: David Howells <dhowells@redhat.com> + Paul E. McKenney <paulmck@linux.vnet.ibm.com> + + +Linux provides a number of features that can be used to implement circular +buffering. There are two sets of such features: + + (1) Convenience functions for determining information about power-of-2 sized + buffers. + + (2) Memory barriers for when the producer and the consumer of objects in the + buffer don't want to share a lock. + +To use these facilities, as discussed below, there needs to be just one +producer and just one consumer. It is possible to handle multiple producers by +serialising them, and to handle multiple consumers by serialising them. + + +Contents: + + (*) What is a circular buffer? + + (*) Measuring power-of-2 buffers. + + (*) Using memory barriers with circular buffers. + - The producer. + - The consumer. + + +========================== +WHAT IS A CIRCULAR BUFFER? +========================== + +First of all, what is a circular buffer? A circular buffer is a buffer of +fixed, finite size into which there are two indices: + + (1) A 'head' index - the point at which the producer inserts items into the + buffer. + + (2) A 'tail' index - the point at which the consumer finds the next item in + the buffer. + +Typically when the tail pointer is equal to the head pointer, the buffer is +empty; and the buffer is full when the head pointer is one less than the tail +pointer. + +The head index is incremented when items are added, and the tail index when +items are removed. The tail index should never jump the head index, and both +indices should be wrapped to 0 when they reach the end of the buffer, thus +allowing an infinite amount of data to flow through the buffer. + +Typically, items will all be of the same unit size, but this isn't strictly +required to use the techniques below. The indices can be increased by more +than 1 if multiple items or variable-sized items are to be included in the +buffer, provided that neither index overtakes the other. The implementer must +be careful, however, as a region more than one unit in size may wrap the end of +the buffer and be broken into two segments. + + +============================ +MEASURING POWER-OF-2 BUFFERS +============================ + +Calculation of the occupancy or the remaining capacity of an arbitrarily sized +circular buffer would normally be a slow operation, requiring the use of a +modulus (divide) instruction. However, if the buffer is of a power-of-2 size, +then a much quicker bitwise-AND instruction can be used instead. + +Linux provides a set of macros for handling power-of-2 circular buffers. These +can be made use of by: + + #include <linux/circ_buf.h> + +The macros are: + + (*) Measure the remaining capacity of a buffer: + + CIRC_SPACE(head_index, tail_index, buffer_size); + + This returns the amount of space left in the buffer[1] into which items + can be inserted. + + + (*) Measure the maximum consecutive immediate space in a buffer: + + CIRC_SPACE_TO_END(head_index, tail_index, buffer_size); + + This returns the amount of consecutive space left in the buffer[1] into + which items can be immediately inserted without having to wrap back to the + beginning of the buffer. + + + (*) Measure the occupancy of a buffer: + + CIRC_CNT(head_index, tail_index, buffer_size); + + This returns the number of items currently occupying a buffer[2]. + + + (*) Measure the non-wrapping occupancy of a buffer: + + CIRC_CNT_TO_END(head_index, tail_index, buffer_size); + + This returns the number of consecutive items[2] that can be extracted from + the buffer without having to wrap back to the beginning of the buffer. + + +Each of these macros will nominally return a value between 0 and buffer_size-1, +however: + + [1] CIRC_SPACE*() are intended to be used in the producer. To the producer + they will return a lower bound as the producer controls the head index, + but the consumer may still be depleting the buffer on another CPU and + moving the tail index. + + To the consumer it will show an upper bound as the producer may be busy + depleting the space. + + [2] CIRC_CNT*() are intended to be used in the consumer. To the consumer they + will return a lower bound as the consumer controls the tail index, but the + producer may still be filling the buffer on another CPU and moving the + head index. + + To the producer it will show an upper bound as the consumer may be busy + emptying the buffer. + + [3] To a third party, the order in which the writes to the indices by the + producer and consumer become visible cannot be guaranteed as they are + independent and may be made on different CPUs - so the result in such a + situation will merely be a guess, and may even be negative. + + +=========================================== +USING MEMORY BARRIERS WITH CIRCULAR BUFFERS +=========================================== + +By using memory barriers in conjunction with circular buffers, you can avoid +the need to: + + (1) use a single lock to govern access to both ends of the buffer, thus + allowing the buffer to be filled and emptied at the same time; and + + (2) use atomic counter operations. + +There are two sides to this: the producer that fills the buffer, and the +consumer that empties it. Only one thing should be filling a buffer at any one +time, and only one thing should be emptying a buffer at any one time, but the +two sides can operate simultaneously. + + +THE PRODUCER +------------ + +The producer will look something like this: + + spin_lock(&producer_lock); + + unsigned long head = buffer->head; + unsigned long tail = ACCESS_ONCE(buffer->tail); + + if (CIRC_SPACE(head, tail, buffer->size) >= 1) { + /* insert one item into the buffer */ + struct item *item = buffer[head]; + + produce_item(item); + + smp_wmb(); /* commit the item before incrementing the head */ + + buffer->head = (head + 1) & (buffer->size - 1); + + /* wake_up() will make sure that the head is committed before + * waking anyone up */ + wake_up(consumer); + } + + spin_unlock(&producer_lock); + +This will instruct the CPU that the contents of the new item must be written +before the head index makes it available to the consumer and then instructs the +CPU that the revised head index must be written before the consumer is woken. + +Note that wake_up() doesn't have to be the exact mechanism used, but whatever +is used must guarantee a (write) memory barrier between the update of the head +index and the change of state of the consumer, if a change of state occurs. + + +THE CONSUMER +------------ + +The consumer will look something like this: + + spin_lock(&consumer_lock); + + unsigned long head = ACCESS_ONCE(buffer->head); + unsigned long tail = buffer->tail; + + if (CIRC_CNT(head, tail, buffer->size) >= 1) { + /* read index before reading contents at that index */ + smp_read_barrier_depends(); + + /* extract one item from the buffer */ + struct item *item = buffer[tail]; + + consume_item(item); + + smp_mb(); /* finish reading descriptor before incrementing tail */ + + buffer->tail = (tail + 1) & (buffer->size - 1); + } + + spin_unlock(&consumer_lock); + +This will instruct the CPU to make sure the index is up to date before reading +the new item, and then it shall make sure the CPU has finished reading the item +before it writes the new tail pointer, which will erase the item. + + +Note the use of ACCESS_ONCE() in both algorithms to read the opposition index. +This prevents the compiler from discarding and reloading its cached value - +which some compilers will do across smp_read_barrier_depends(). This isn't +strictly needed if you can be sure that the opposition index will _only_ be +used the once. + + +=============== +FURTHER READING +=============== + +See also Documentation/memory-barriers.txt for a description of Linux's memory +barrier facilities. diff --git a/Documentation/connector/cn_test.c b/Documentation/connector/cn_test.c index b07add3467f1..7764594778d4 100644 --- a/Documentation/connector/cn_test.c +++ b/Documentation/connector/cn_test.c @@ -25,6 +25,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <linux/timer.h> #include <linux/connector.h> diff --git a/Documentation/connector/connector.txt b/Documentation/connector/connector.txt index 78c9466a9aa8..e5c5f5e6ab70 100644 --- a/Documentation/connector/connector.txt +++ b/Documentation/connector/connector.txt @@ -88,7 +88,7 @@ int cn_netlink_send(struct cn_msg *msg, u32 __groups, int gfp_mask); int gfp_mask - GFP mask. Note: When registering new callback user, connector core assigns - netlink group to the user which is equal to it's id.idx. + netlink group to the user which is equal to its id.idx. /*****************************************/ Protocol description. diff --git a/Documentation/console/console.txt b/Documentation/console/console.txt index 877a1b26cc3d..926cf1b5e63e 100644 --- a/Documentation/console/console.txt +++ b/Documentation/console/console.txt @@ -74,7 +74,7 @@ driver takes over the consoles vacated by the driver. Binding, on the other hand, will bind the driver to the consoles that are currently occupied by a system driver. -NOTE1: Binding and binding must be selected in Kconfig. It's under: +NOTE1: Binding and unbinding must be selected in Kconfig. It's under: Device Drivers -> Character devices -> Support for binding and unbinding console drivers diff --git a/Documentation/credentials.txt b/Documentation/credentials.txt index df03169782ea..a2db35287003 100644 --- a/Documentation/credentials.txt +++ b/Documentation/credentials.txt @@ -408,9 +408,6 @@ This should be used inside the RCU read lock, as in the following example: ... } -A function need not get RCU read lock to use __task_cred() if it is holding a -spinlock at the time as this implicitly holds the RCU read lock. - Should it be necessary to hold another task's credentials for a long period of time, and possibly to sleep whilst doing so, then the caller should get a reference on them using: @@ -426,17 +423,16 @@ credentials, hiding the RCU magic from the caller: uid_t task_uid(task) Task's real UID uid_t task_euid(task) Task's effective UID -If the caller is holding a spinlock or the RCU read lock at the time anyway, -then: +If the caller is holding the RCU read lock at the time anyway, then: __task_cred(task)->uid __task_cred(task)->euid should be used instead. Similarly, if multiple aspects of a task's credentials -need to be accessed, RCU read lock or a spinlock should be used, __task_cred() -called, the result stored in a temporary pointer and then the credential -aspects called from that before dropping the lock. This prevents the -potentially expensive RCU magic from being invoked multiple times. +need to be accessed, RCU read lock should be used, __task_cred() called, the +result stored in a temporary pointer and then the credential aspects called +from that before dropping the lock. This prevents the potentially expensive +RCU magic from being invoked multiple times. Should some other single aspect of another task's credentials need to be accessed, then this can be used: diff --git a/Documentation/driver-model/platform.txt b/Documentation/driver-model/platform.txt index 2e2c2ea90ceb..41f41632ee55 100644 --- a/Documentation/driver-model/platform.txt +++ b/Documentation/driver-model/platform.txt @@ -192,7 +192,7 @@ command line. This will execute all matching early_param() callbacks. User specified early platform devices will be registered at this point. For the early serial console case the user can specify port on the kernel command line as "earlyprintk=serial.0" where "earlyprintk" is -the class string, "serial" is the name of the platfrom driver and +the class string, "serial" is the name of the platform driver and 0 is the platform device id. If the id is -1 then the dot and the id can be omitted. diff --git a/Documentation/dvb/ci.txt b/Documentation/dvb/ci.txt index 2ecd834585e6..4a0c2b56e690 100644 --- a/Documentation/dvb/ci.txt +++ b/Documentation/dvb/ci.txt @@ -41,7 +41,7 @@ This application requires the following to function properly as of now. * Cards that fall in this category ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -At present the cards that fall in this category are the Twinhan and it's +At present the cards that fall in this category are the Twinhan and its clones, these cards are available as VVMER, Tomato, Hercules, Orange and so on. diff --git a/Documentation/dvb/contributors.txt b/Documentation/dvb/contributors.txt index 4865addebe1c..47c30098dab6 100644 --- a/Documentation/dvb/contributors.txt +++ b/Documentation/dvb/contributors.txt @@ -1,7 +1,7 @@ Thanks go to the following people for patches and contributions: Michael Hunold <m.hunold@gmx.de> - for the initial saa7146 driver and it's recent overhaul + for the initial saa7146 driver and its recent overhaul Christian Theiss for his work on the initial Linux DVB driver diff --git a/Documentation/eisa.txt b/Documentation/eisa.txt index 60e361ba08c0..f297fc1202ae 100644 --- a/Documentation/eisa.txt +++ b/Documentation/eisa.txt @@ -171,7 +171,7 @@ device. virtual_root.force_probe : Force the probing code to probe EISA slots even when it cannot find an -EISA compliant mainboard (nothing appears on slot 0). Defaultd to 0 +EISA compliant mainboard (nothing appears on slot 0). Defaults to 0 (don't force), and set to 1 (force probing) when either CONFIG_ALPHA_JENSEN or CONFIG_EISA_VLB_PRIMING are set. diff --git a/Documentation/email-clients.txt b/Documentation/email-clients.txt index a618efab7b15..945ff3fda433 100644 --- a/Documentation/email-clients.txt +++ b/Documentation/email-clients.txt @@ -216,26 +216,14 @@ Works. Use "Insert file..." or external editor. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Gmail (Web GUI) -If you just have to use Gmail to send patches, it CAN be made to work. It -requires a bit of external help, though. - -The first problem is that Gmail converts tabs to spaces. This will -totally break your patches. To prevent this, you have to use a different -editor. There is a firefox extension called "ViewSourceWith" -(https://addons.mozilla.org/en-US/firefox/addon/394) which allows you to -edit any text box in the editor of your choice. Configure it to launch -your favorite editor. When you want to send a patch, use this technique. -Once you have crafted your messsage + patch, save and exit the editor, -which should reload the Gmail edit box. GMAIL WILL PRESERVE THE TABS. -Hoorah. Apparently you can cut-n-paste literal tabs, but Gmail will -convert those to spaces upon sending! - -The second problem is that Gmail converts tabs to spaces on replies. If -you reply to a patch, don't expect to be able to apply it as a patch. - -The last problem is that Gmail will base64-encode any message that has a -non-ASCII character. That includes things like European names. Be aware. - -Gmail is not convenient for lkml patches, but CAN be made to work. +Does not work for sending patches. + +Gmail web client converts tabs to spaces automatically. + +At the same time it wraps lines every 78 chars with CRLF style line breaks +although tab2space problem can be solved with external editor. + +Another problem is that Gmail will base64-encode any message that has a +non-ASCII character. That includes things like European names. ### diff --git a/Documentation/fb/imacfb.txt b/Documentation/fb/efifb.txt index 316ec9bb7deb..a59916c29b33 100644 --- a/Documentation/fb/imacfb.txt +++ b/Documentation/fb/efifb.txt @@ -1,9 +1,9 @@ -What is imacfb? +What is efifb? =============== This is a generic EFI platform driver for Intel based Apple computers. -Imacfb is only for EFI booted Intel Macs. +efifb is only for EFI booted Intel Macs. Supported Hardware ================== @@ -16,16 +16,16 @@ MacMini How to use it? ============== -Imacfb does not have any kind of autodetection of your machine. +efifb does not have any kind of autodetection of your machine. You have to add the following kernel parameters in your elilo.conf: Macbook : - video=imacfb:macbook + video=efifb:macbook MacMini : - video=imacfb:mini + video=efifb:mini Macbook Pro 15", iMac 17" : - video=imacfb:i17 + video=efifb:i17 Macbook Pro 17", iMac 20" : - video=imacfb:i20 + video=efifb:i20 -- Edgar Hucek <gimli@dark-green.com> diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index a5cc0db63d7a..a86152ae2f6f 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -241,16 +241,6 @@ Who: Thomas Gleixner <tglx@linutronix.de> --------------------------- -What (Why): - - xt_recent: the old ipt_recent proc dir - (superseded by /proc/net/xt_recent) - -When: January 2009 or Linux 2.7.0, whichever comes first -Why: Superseded by newer revisions or modules -Who: Jan Engelhardt <jengelh@computergmbh.de> - ---------------------------- - What: GPIO autorequest on gpio_direction_{input,output}() in gpiolib When: February 2010 Why: All callers should use explicit gpio_request()/gpio_free(). @@ -520,26 +510,21 @@ Who: Hans de Goede <hdegoede@redhat.com> ---------------------------- -What: corgikbd, spitzkbd, tosakbd driver -When: 2.6.35 -Files: drivers/input/keyboard/{corgi,spitz,tosa}kbd.c -Why: We now have a generic GPIO based matrix keyboard driver that - are fully capable of handling all the keys on these devices. - The original drivers manipulate the GPIO registers directly - and so are difficult to maintain. -Who: Eric Miao <eric.y.miao@gmail.com> +What: sysfs-class-rfkill state file +When: Feb 2014 +Files: net/rfkill/core.c +Why: Documented as obsolete since Feb 2010. This file is limited to 3 + states while the rfkill drivers can have 4 states. +Who: anybody or Florian Mickler <florian@mickler.org> ---------------------------- -What: corgi_ssp and corgi_ts driver -When: 2.6.35 -Files: arch/arm/mach-pxa/corgi_ssp.c, drivers/input/touchscreen/corgi_ts.c -Why: The corgi touchscreen is now deprecated in favour of the generic - ads7846.c driver. The noise reduction technique used in corgi_ts.c, - that's to wait till vsync before ADC sampling, is also integrated into - ads7846 driver now. Provided that the original driver is not generic - and is difficult to maintain, it will be removed later. -Who: Eric Miao <eric.y.miao@gmail.com> +What: sysfs-class-rfkill claim file +When: Feb 2012 +Files: net/rfkill/core.c +Why: It is not possible to claim an rfkill driver since 2007. This is + Documented as obsolete since Feb 2010. +Who: anybody or Florian Mickler <florian@mickler.org> ---------------------------- @@ -564,6 +549,16 @@ Who: Avi Kivity <avi@redhat.com> ---------------------------- +What: xtime, wall_to_monotonic +When: 2.6.36+ +Files: kernel/time/timekeeping.c include/linux/time.h +Why: Cleaning up timekeeping internal values. Please use + existing timekeeping accessor functions to access + the equivalent functionality. +Who: John Stultz <johnstul@us.ibm.com> + +---------------------------- + What: KVM kernel-allocated memory slots When: July 2010 Why: Since 2.6.25, kvm supports user-allocated memory slots, which are @@ -582,3 +577,72 @@ Why: The paravirt mmu host support is slower than non-paravirt mmu, both Who: Avi Kivity <avi@redhat.com> ---------------------------- + +What: "acpi=ht" boot option +When: 2.6.35 +Why: Useful in 2003, implementation is a hack. + Generally invoked by accident today. + Seen as doing more harm than good. +Who: Len Brown <len.brown@intel.com> + +---------------------------- + +What: iwlwifi 50XX module parameters +When: 2.6.40 +Why: The "..50" modules parameters were used to configure 5000 series and + up devices; different set of module parameters also available for 4965 + with same functionalities. Consolidate both set into single place + in drivers/net/wireless/iwlwifi/iwl-agn.c + +Who: Wey-Yi Guy <wey-yi.w.guy@intel.com> + +---------------------------- + +What: iwl4965 alias support +When: 2.6.40 +Why: Internal alias support has been present in module-init-tools for some + time, the MODULE_ALIAS("iwl4965") boilerplate aliases can be removed + with no impact. + +Who: Wey-Yi Guy <wey-yi.w.guy@intel.com> + +--------------------------- + +What: xt_NOTRACK +Files: net/netfilter/xt_NOTRACK.c +When: April 2011 +Why: Superseded by xt_CT +Who: Netfilter developer team <netfilter-devel@vger.kernel.org> + +--------------------------- + +What: video4linux /dev/vtx teletext API support +When: 2.6.35 +Files: drivers/media/video/saa5246a.c drivers/media/video/saa5249.c + include/linux/videotext.h +Why: The vtx device nodes have been superseded by vbi device nodes + for many years. No applications exist that use the vtx support. + Of the two i2c drivers that actually support this API the saa5249 + has been impossible to use for a year now and no known hardware + that supports this device exists. The saa5246a is theoretically + supported by the old mxb boards, but it never actually worked. + + In summary: there is no hardware that can use this API and there + are no applications actually implementing this API. + + The vtx support still reserves minors 192-223 and we would really + like to reuse those for upcoming new functionality. In the unlikely + event that new hardware appears that wants to use the functionality + provided by the vtx API, then that functionality should be build + around the sliced VBI API instead. +Who: Hans Verkuil <hverkuil@xs4all.nl> + +---------------------------- + +What: IRQF_DISABLED +When: 2.6.36 +Why: The flag is a NOOP as we run interrupt handlers with interrupts disabled +Who: Thomas Gleixner <tglx@linutronix.de> + +---------------------------- + diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index 5139b8c9d5af..4303614b5add 100644 --- a/Documentation/filesystems/00-INDEX +++ b/Documentation/filesystems/00-INDEX @@ -16,6 +16,8 @@ befs.txt - information about the BeOS filesystem for Linux. bfs.txt - info for the SCO UnixWare Boot Filesystem (BFS). +ceph.txt + - info for the Ceph Distributed File System cifs.txt - description of the CIFS filesystem. coda.txt @@ -32,6 +34,8 @@ dlmfs.txt - info on the userspace interface to the OCFS2 DLM. dnotify.txt - info about directory notification in Linux. +dnotify_test.c + - example program for dnotify ecryptfs.txt - docs on eCryptfs: stacked cryptographic filesystem for Linux. exofs.txt diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt index 57e0b80a5274..c0236e753bc8 100644 --- a/Documentation/filesystems/9p.txt +++ b/Documentation/filesystems/9p.txt @@ -37,6 +37,15 @@ For Plan 9 From User Space applications (http://swtch.com/plan9) mount -t 9p `namespace`/acme /mnt/9 -o trans=unix,uname=$USER +For server running on QEMU host with virtio transport: + + mount -t 9p -o trans=virtio <mount_tag> /mnt/9 + +where mount_tag is the tag associated by the server to each of the exported +mount points. Each 9P export is seen by the client as a virtio device with an +associated "mount_tag" property. Available mount tags can be +seen by reading /sys/bus/virtio/drivers/9pnet_virtio/virtio<n>/mount_tag files. + OPTIONS ======= @@ -47,7 +56,7 @@ OPTIONS fd - used passed file descriptors for connection (see rfdno and wfdno) virtio - connect to the next virtio channel available - (from lguest or KVM with trans_virtio module) + (from QEMU with trans_virtio module) rdma - connect to a specified RDMA channel uname=name user name to attempt mount as on the remote server. The @@ -85,7 +94,12 @@ OPTIONS port=n port to connect to on the remote server - noextend force legacy mode (no 9p2000.u semantics) + noextend force legacy mode (no 9p2000.u or 9p2000.L semantics) + + version=name Select 9P protocol version. Valid options are: + 9p2000 - Legacy mode (same as noextend) + 9p2000.u - Use 9P2000.u protocol + 9p2000.L - Use 9P2000.L protocol dfltuid attempt to mount as a particular uid diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 06bbbed71206..af1608070cd5 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -178,7 +178,7 @@ prototypes: locking rules: All except set_page_dirty may block - BKL PageLocked(page) i_sem + BKL PageLocked(page) i_mutex writepage: no yes, unlocks (see below) readpage: no yes, unlocks sync_page: no maybe @@ -429,7 +429,7 @@ check_flags: no implementations. If your fs is not using generic_file_llseek, you need to acquire and release the appropriate locks in your ->llseek(). For many filesystems, it is probably safe to acquire the inode -semaphore. Note some filesystems (i.e. remote ones) provide no +mutex. Note some filesystems (i.e. remote ones) provide no protection for i_size so you will need to use the BKL. Note: ext2_release() was *the* source of contention on fs-intensive diff --git a/Documentation/filesystems/Makefile b/Documentation/filesystems/Makefile new file mode 100644 index 000000000000..a5dd114da14f --- /dev/null +++ b/Documentation/filesystems/Makefile @@ -0,0 +1,8 @@ +# kbuild trick to avoid linker error. Can be omitted if a module is built. +obj- := dummy.o + +# List of programs to build +hostprogs-y := dnotify_test + +# Tell kbuild to always build the programs +always := $(hostprogs-y) diff --git a/Documentation/filesystems/autofs4-mount-control.txt b/Documentation/filesystems/autofs4-mount-control.txt index 8f78ded4b648..51986bf08a4d 100644 --- a/Documentation/filesystems/autofs4-mount-control.txt +++ b/Documentation/filesystems/autofs4-mount-control.txt @@ -146,7 +146,7 @@ found to be inadequate, in this case. The Generic Netlink system was used for this as raw Netlink would lead to a significant increase in complexity. There's no question that the Generic Netlink system is an elegant solution for common case ioctl functions but it's not a complete -replacement probably because it's primary purpose in life is to be a +replacement probably because its primary purpose in life is to be a message bus implementation rather than specifically an ioctl replacement. While it would be possible to work around this there is one concern that lead to the decision to not use it. This is that the autofs diff --git a/Documentation/filesystems/ceph.txt b/Documentation/filesystems/ceph.txt new file mode 100644 index 000000000000..763d8ebbbebd --- /dev/null +++ b/Documentation/filesystems/ceph.txt @@ -0,0 +1,140 @@ +Ceph Distributed File System +============================ + +Ceph is a distributed network file system designed to provide good +performance, reliability, and scalability. + +Basic features include: + + * POSIX semantics + * Seamless scaling from 1 to many thousands of nodes + * High availability and reliability. No single point of failure. + * N-way replication of data across storage nodes + * Fast recovery from node failures + * Automatic rebalancing of data on node addition/removal + * Easy deployment: most FS components are userspace daemons + +Also, + * Flexible snapshots (on any directory) + * Recursive accounting (nested files, directories, bytes) + +In contrast to cluster filesystems like GFS, OCFS2, and GPFS that rely +on symmetric access by all clients to shared block devices, Ceph +separates data and metadata management into independent server +clusters, similar to Lustre. Unlike Lustre, however, metadata and +storage nodes run entirely as user space daemons. Storage nodes +utilize btrfs to store data objects, leveraging its advanced features +(checksumming, metadata replication, etc.). File data is striped +across storage nodes in large chunks to distribute workload and +facilitate high throughputs. When storage nodes fail, data is +re-replicated in a distributed fashion by the storage nodes themselves +(with some minimal coordination from a cluster monitor), making the +system extremely efficient and scalable. + +Metadata servers effectively form a large, consistent, distributed +in-memory cache above the file namespace that is extremely scalable, +dynamically redistributes metadata in response to workload changes, +and can tolerate arbitrary (well, non-Byzantine) node failures. The +metadata server takes a somewhat unconventional approach to metadata +storage to significantly improve performance for common workloads. In +particular, inodes with only a single link are embedded in +directories, allowing entire directories of dentries and inodes to be +loaded into its cache with a single I/O operation. The contents of +extremely large directories can be fragmented and managed by +independent metadata servers, allowing scalable concurrent access. + +The system offers automatic data rebalancing/migration when scaling +from a small cluster of just a few nodes to many hundreds, without +requiring an administrator carve the data set into static volumes or +go through the tedious process of migrating data between servers. +When the file system approaches full, new nodes can be easily added +and things will "just work." + +Ceph includes flexible snapshot mechanism that allows a user to create +a snapshot on any subdirectory (and its nested contents) in the +system. Snapshot creation and deletion are as simple as 'mkdir +.snap/foo' and 'rmdir .snap/foo'. + +Ceph also provides some recursive accounting on directories for nested +files and bytes. That is, a 'getfattr -d foo' on any directory in the +system will reveal the total number of nested regular files and +subdirectories, and a summation of all nested file sizes. This makes +the identification of large disk space consumers relatively quick, as +no 'du' or similar recursive scan of the file system is required. + + +Mount Syntax +============ + +The basic mount syntax is: + + # mount -t ceph monip[:port][,monip2[:port]...]:/[subdir] mnt + +You only need to specify a single monitor, as the client will get the +full list when it connects. (However, if the monitor you specify +happens to be down, the mount won't succeed.) The port can be left +off if the monitor is using the default. So if the monitor is at +1.2.3.4, + + # mount -t ceph 1.2.3.4:/ /mnt/ceph + +is sufficient. If /sbin/mount.ceph is installed, a hostname can be +used instead of an IP address. + + + +Mount Options +============= + + ip=A.B.C.D[:N] + Specify the IP and/or port the client should bind to locally. + There is normally not much reason to do this. If the IP is not + specified, the client's IP address is determined by looking at the + address its connection to the monitor originates from. + + wsize=X + Specify the maximum write size in bytes. By default there is no + maximum. Ceph will normally size writes based on the file stripe + size. + + rsize=X + Specify the maximum readahead. + + mount_timeout=X + Specify the timeout value for mount (in seconds), in the case + of a non-responsive Ceph file system. The default is 30 + seconds. + + rbytes + When stat() is called on a directory, set st_size to 'rbytes', + the summation of file sizes over all files nested beneath that + directory. This is the default. + + norbytes + When stat() is called on a directory, set st_size to the + number of entries in that directory. + + nocrc + Disable CRC32C calculation for data writes. If set, the storage node + must rely on TCP's error correction to detect data corruption + in the data payload. + + noasyncreaddir + Disable client's use its local cache to satisfy readdir + requests. (This does not change correctness; the client uses + cached metadata only when a lease or capability ensures it is + valid.) + + +More Information +================ + +For more information on Ceph, see the home page at + http://ceph.newdream.net/ + +The Linux kernel client source tree is available at + git://ceph.newdream.net/git/ceph-client.git + git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git + +and the source for the full system is at + git://ceph.newdream.net/git/ceph.git diff --git a/Documentation/filesystems/dlmfs.txt b/Documentation/filesystems/dlmfs.txt index c50bbb2d52b4..1b528b2ad809 100644 --- a/Documentation/filesystems/dlmfs.txt +++ b/Documentation/filesystems/dlmfs.txt @@ -47,7 +47,7 @@ You'll want to start heartbeating on a volume which all the nodes in your lockspace can access. The easiest way to do this is via ocfs2_hb_ctl (distributed with ocfs2-tools). Right now it requires that an OCFS2 file system be in place so that it can automatically -find it's heartbeat area, though it will eventually support heartbeat +find its heartbeat area, though it will eventually support heartbeat against raw disks. Please see the ocfs2_hb_ctl and mkfs.ocfs2 manual pages distributed diff --git a/Documentation/filesystems/dnotify.txt b/Documentation/filesystems/dnotify.txt index 9f5d338ddbb8..6baf88f46859 100644 --- a/Documentation/filesystems/dnotify.txt +++ b/Documentation/filesystems/dnotify.txt @@ -62,38 +62,9 @@ disabled, fcntl(fd, F_NOTIFY, ...) will return -EINVAL. Example ------- +See Documentation/filesystems/dnotify_test.c for an example. - #define _GNU_SOURCE /* needed to get the defines */ - #include <fcntl.h> /* in glibc 2.2 this has the needed - values defined */ - #include <signal.h> - #include <stdio.h> - #include <unistd.h> - - static volatile int event_fd; - - static void handler(int sig, siginfo_t *si, void *data) - { - event_fd = si->si_fd; - } - - int main(void) - { - struct sigaction act; - int fd; - - act.sa_sigaction = handler; - sigemptyset(&act.sa_mask); - act.sa_flags = SA_SIGINFO; - sigaction(SIGRTMIN + 1, &act, NULL); - - fd = open(".", O_RDONLY); - fcntl(fd, F_SETSIG, SIGRTMIN + 1); - fcntl(fd, F_NOTIFY, DN_MODIFY|DN_CREATE|DN_MULTISHOT); - /* we will now be notified if any of the files - in "." is modified or new files are created */ - while (1) { - pause(); - printf("Got event on fd=%d\n", event_fd); - } - } +NOTE +---- +Beginning with Linux 2.6.13, dnotify has been replaced by inotify. +See Documentation/filesystems/inotify.txt for more information on it. diff --git a/Documentation/filesystems/dnotify_test.c b/Documentation/filesystems/dnotify_test.c new file mode 100644 index 000000000000..8b37b4a1e18d --- /dev/null +++ b/Documentation/filesystems/dnotify_test.c @@ -0,0 +1,34 @@ +#define _GNU_SOURCE /* needed to get the defines */ +#include <fcntl.h> /* in glibc 2.2 this has the needed + values defined */ +#include <signal.h> +#include <stdio.h> +#include <unistd.h> + +static volatile int event_fd; + +static void handler(int sig, siginfo_t *si, void *data) +{ + event_fd = si->si_fd; +} + +int main(void) +{ + struct sigaction act; + int fd; + + act.sa_sigaction = handler; + sigemptyset(&act.sa_mask); + act.sa_flags = SA_SIGINFO; + sigaction(SIGRTMIN + 1, &act, NULL); + + fd = open(".", O_RDONLY); + fcntl(fd, F_SETSIG, SIGRTMIN + 1); + fcntl(fd, F_NOTIFY, DN_MODIFY|DN_CREATE|DN_MULTISHOT); + /* we will now be notified if any of the files + in "." is modified or new files are created */ + while (1) { + pause(); + printf("Got event on fd=%d\n", event_fd); + } +} diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt index 606233cd4618..1b805a0efbb0 100644 --- a/Documentation/filesystems/fiemap.txt +++ b/Documentation/filesystems/fiemap.txt @@ -38,7 +38,7 @@ flags, it will return EBADR and the contents of fm_flags will contain the set of flags which caused the error. If the kernel is compatible with all flags passed, the contents of fm_flags will be unmodified. It is up to userspace to determine whether rejection of a particular -flag is fatal to it's operation. This scheme is intended to allow the +flag is fatal to its operation. This scheme is intended to allow the fiemap interface to grow in the future but without losing compatibility with old software. @@ -56,7 +56,7 @@ If this flag is set, the kernel will sync the file before mapping extents. * FIEMAP_FLAG_XATTR If this flag is set, the extents returned will describe the inodes -extended attribute lookup tree, instead of it's data tree. +extended attribute lookup tree, instead of its data tree. Extent Mapping @@ -89,7 +89,7 @@ struct fiemap_extent { }; All offsets and lengths are in bytes and mirror those on disk. It is valid -for an extents logical offset to start before the request or it's logical +for an extents logical offset to start before the request or its logical length to extend past the request. Unless FIEMAP_EXTENT_NOT_ALIGNED is returned, fe_logical, fe_physical, and fe_length will be aligned to the block size of the file system. With the exception of extents flagged as @@ -125,7 +125,7 @@ been allocated for the file yet. * FIEMAP_EXTENT_DELALLOC - This will also set FIEMAP_EXTENT_UNKNOWN. -Delayed allocation - while there is data for this extent, it's +Delayed allocation - while there is data for this extent, its physical location has not been allocated yet. * FIEMAP_EXTENT_ENCODED @@ -159,7 +159,7 @@ Data is located within a meta data block. Data is packed into a block with data from other files. * FIEMAP_EXTENT_UNWRITTEN -Unwritten extent - the extent is allocated but it's data has not been +Unwritten extent - the extent is allocated but its data has not been initialized. This indicates the extent's data will be all zero if read through the filesystem but the contents are undefined if read directly from the device. @@ -176,7 +176,7 @@ VFS -> File System Implementation File systems wishing to support fiemap must implement a ->fiemap callback on their inode_operations structure. The fs ->fiemap call is responsible for -defining it's set of supported fiemap flags, and calling a helper function on +defining its set of supported fiemap flags, and calling a helper function on each discovered extent: struct inode_operations { diff --git a/Documentation/filesystems/fuse.txt b/Documentation/filesystems/fuse.txt index 397a41adb4c3..13af4a49e7db 100644 --- a/Documentation/filesystems/fuse.txt +++ b/Documentation/filesystems/fuse.txt @@ -91,7 +91,7 @@ Mount options 'default_permissions' By default FUSE doesn't check file access permissions, the - filesystem is free to implement it's access policy or leave it to + filesystem is free to implement its access policy or leave it to the underlying file access mechanism (e.g. in case of network filesystems). This option enables permission checking, restricting access based on file mode. It is usually useful together with the @@ -171,7 +171,7 @@ or may honor them by sending a reply to the _original_ request, with the error set to EINTR. It is also possible that there's a race between processing the -original request and it's INTERRUPT request. There are two possibilities: +original request and its INTERRUPT request. There are two possibilities: 1) The INTERRUPT request is processed before the original request is processed diff --git a/Documentation/filesystems/gfs2.txt b/Documentation/filesystems/gfs2.txt index 5e3ab8f3beff..0b59c0200912 100644 --- a/Documentation/filesystems/gfs2.txt +++ b/Documentation/filesystems/gfs2.txt @@ -1,7 +1,7 @@ Global File System ------------------ -http://sources.redhat.com/cluster/ +http://sources.redhat.com/cluster/wiki/ GFS is a cluster file system. It allows a cluster of computers to simultaneously use a block device that is shared between them (with FC, @@ -36,11 +36,11 @@ GFS2 is not on-disk compatible with previous versions of GFS, but it is pretty close. The following man pages can be found at the URL above: - fsck.gfs2 to repair a filesystem - gfs2_grow to expand a filesystem online - gfs2_jadd to add journals to a filesystem online - gfs2_tool to manipulate, examine and tune a filesystem + fsck.gfs2 to repair a filesystem + gfs2_grow to expand a filesystem online + gfs2_jadd to add journals to a filesystem online + gfs2_tool to manipulate, examine and tune a filesystem gfs2_quota to examine and change quota values in a filesystem gfs2_convert to convert a gfs filesystem to gfs2 in-place mount.gfs2 to help mount(8) mount a filesystem - mkfs.gfs2 to make a filesystem + mkfs.gfs2 to make a filesystem diff --git a/Documentation/filesystems/hpfs.txt b/Documentation/filesystems/hpfs.txt index fa45c3baed98..74630bd504fb 100644 --- a/Documentation/filesystems/hpfs.txt +++ b/Documentation/filesystems/hpfs.txt @@ -103,7 +103,7 @@ to analyze or change OS2SYS.INI. Codepages HPFS can contain several uppercasing tables for several codepages and each -file has a pointer to codepage it's name is in. However OS/2 was created in +file has a pointer to codepage its name is in. However OS/2 was created in America where people don't care much about codepages and so multiple codepages support is quite buggy. I have Czech OS/2 working in codepage 852 on my disk. Once I booted English OS/2 working in cp 850 and I created a file on my 852 diff --git a/Documentation/filesystems/logfs.txt b/Documentation/filesystems/logfs.txt index e64c94ba401a..bca42c22a143 100644 --- a/Documentation/filesystems/logfs.txt +++ b/Documentation/filesystems/logfs.txt @@ -59,7 +59,7 @@ Levels ------ Garbage collection (GC) may fail if all data is written -indiscriminately. One requirement of GC is that data is seperated +indiscriminately. One requirement of GC is that data is separated roughly according to the distance between the tree root and the data. Effectively that means all file data is on level 0, indirect blocks are on levels 1, 2, 3 4 or 5 for 1x, 2x, 3x, 4x or 5x indirect blocks, @@ -67,7 +67,7 @@ respectively. Inode file data is on level 6 for the inodes and 7-11 for indirect blocks. Each segment contains objects of a single level only. As a result, -each level requires its own seperate segment to be open for writing. +each level requires its own separate segment to be open for writing. Inode File ---------- @@ -106,9 +106,9 @@ Vim --- By cleverly predicting the life time of data, it is possible to -seperate long-living data from short-living data and thereby reduce +separate long-living data from short-living data and thereby reduce the GC overhead later. Each type of distinc life expectency (vim) can -have a seperate segment open for writing. Each (level, vim) tupel can +have a separate segment open for writing. Each (level, vim) tupel can be open just once. If an open segment with unknown vim is encountered at mount time, it is closed and ignored henceforth. diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt index 6a53a84afc72..04884914a1c8 100644 --- a/Documentation/filesystems/nfs/nfs41-server.txt +++ b/Documentation/filesystems/nfs/nfs41-server.txt @@ -137,7 +137,7 @@ NS*| OPENATTR | OPT | | Section 18.17 | | READ | REQ | | Section 18.22 | | READDIR | REQ | | Section 18.23 | | READLINK | OPT | | Section 18.24 | -NS | RECLAIM_COMPLETE | REQ | | Section 18.51 | + | RECLAIM_COMPLETE | REQ | | Section 18.51 | | RELEASE_LOCKOWNER | MNI | | N/A | | REMOVE | REQ | | Section 18.25 | | RENAME | REQ | | Section 18.26 | diff --git a/Documentation/filesystems/nfs/rpc-cache.txt b/Documentation/filesystems/nfs/rpc-cache.txt index 8a382bea6808..ebcaaee21616 100644 --- a/Documentation/filesystems/nfs/rpc-cache.txt +++ b/Documentation/filesystems/nfs/rpc-cache.txt @@ -185,7 +185,7 @@ failed lookup meant a definite 'no'. request/response format ----------------------- -While each cache is free to use it's own format for requests +While each cache is free to use its own format for requests and responses over channel, the following is recommended as appropriate and support routines are available to help: Each request or response record should be printable ASCII diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt index cf6d0d85ca82..d3e7673995eb 100644 --- a/Documentation/filesystems/nilfs2.txt +++ b/Documentation/filesystems/nilfs2.txt @@ -50,8 +50,8 @@ NILFS2 supports the following mount options: (*) == default nobarrier Disables barriers. -errors=continue(*) Keep going on a filesystem error. -errors=remount-ro Remount the filesystem read-only on an error. +errors=continue Keep going on a filesystem error. +errors=remount-ro(*) Remount the filesystem read-only on an error. errors=panic Panic and halt the machine if an error occurs. cp=n Specify the checkpoint-number of the snapshot to be mounted. Checkpoints and snapshots are listed by lscp diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt index c58b9f5ba002..1f7ae144f6d8 100644 --- a/Documentation/filesystems/ocfs2.txt +++ b/Documentation/filesystems/ocfs2.txt @@ -80,3 +80,10 @@ user_xattr (*) Enables Extended User Attributes. nouser_xattr Disables Extended User Attributes. acl Enables POSIX Access Control Lists support. noacl (*) Disables POSIX Access Control Lists support. +resv_level=2 (*) Set how agressive allocation reservations will be. + Valid values are between 0 (reservations off) to 8 + (maximum space for reservations). +dir_resv_level= (*) By default, directory reservations will scale with file + reservations - users should rarely need to change this + value. If allocation reservations are turned off, this + option will have no effect. diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 96a44dd95e03..9fb6cbe70bde 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -195,7 +195,7 @@ asynchronous manner and the vaule may not be very precise. To see a precise snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table. It's slow but very precise. -Table 1-2: Contents of the statm files (as of 2.6.30-rc7) +Table 1-2: Contents of the status files (as of 2.6.30-rc7) .............................................................................. Field Content Name filename of the executable @@ -305,7 +305,7 @@ Table 1-4: Contents of the stat files (as of 2.6.30-rc7) cgtime guest time of the task children in jiffies .............................................................................. -The /proc/PID/map file containing the currently mapped memory regions and +The /proc/PID/maps file containing the currently mapped memory regions and their access permissions. The format is: @@ -316,7 +316,7 @@ address perms offset dev inode pathname 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test 0804a000-0806b000 rw-p 00000000 00:00 0 [heap] a7cb1000-a7cb2000 ---p 00000000 00:00 0 -a7cb2000-a7eb2000 rw-p 00000000 00:00 0 [threadstack:001ff4b4] +a7cb2000-a7eb2000 rw-p 00000000 00:00 0 a7eb2000-a7eb3000 ---p 00000000 00:00 0 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 @@ -352,7 +352,6 @@ is not associated with a file: [stack] = the stack of the main process [vdso] = the "virtual dynamic shared object", the kernel system call handler - [threadstack:xxxxxxxx] = the stack of the thread, xxxxxxxx is the stack size or if empty, the mapping is anonymous. @@ -566,6 +565,10 @@ The default_smp_affinity mask applies to all non-active IRQs, which are the IRQs which have not yet been allocated/activated, and hence which lack a /proc/irq/[0-9]* directory. +The node file on an SMP system shows the node to which the device using the IRQ +reports itself as being attached. This hardware locality information does not +include information about any possible driver locality preference. + prof_cpu_mask specifies which CPUs are to be profiled by the system wide profiler. Default value is ffffffff (all cpus). @@ -965,7 +968,7 @@ your system and how much traffic was routed over those devices: ...] 1375103 17405 0 0 0 0 0 0 ...] 1703981 5535 0 0 0 3 0 0 -In addition, each Channel Bond interface has it's own directory. For +In addition, each Channel Bond interface has its own directory. For example, the bond0 device will have a directory called /proc/net/bond0/. It will contain information that is specific to that bond, such as the current slaves of the bond, the link status of the slaves, and how @@ -1362,7 +1365,7 @@ been accounted as having caused 1MB of write. In other words: The number of bytes which this process caused to not happen, by truncating pagecache. A task can cause "negative" IO too. If this task truncates some dirty pagecache, some IO which another task has been accounted -for (in it's write_bytes) will not be happening. We _could_ just subtract that +for (in its write_bytes) will not be happening. We _could_ just subtract that from the truncating task's write_bytes, but there is information loss in doing that. diff --git a/Documentation/filesystems/smbfs.txt b/Documentation/filesystems/smbfs.txt index f673ef0de0f7..194fb0decd2c 100644 --- a/Documentation/filesystems/smbfs.txt +++ b/Documentation/filesystems/smbfs.txt @@ -3,6 +3,6 @@ protocol used by Windows for Workgroups, Windows 95 and Windows NT. Smbfs was inspired by Samba, the program written by Andrew Tridgell that turns any Unix host into a file server for DOS or Windows clients. -Smbfs is a SMB client, but uses parts of samba for it's operation. For +Smbfs is a SMB client, but uses parts of samba for its operation. For more info on samba, including documentation, please go to http://www.samba.org/ and then on to your nearest mirror. diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt index 3015da0c6b2a..fe09a2cb1858 100644 --- a/Documentation/filesystems/tmpfs.txt +++ b/Documentation/filesystems/tmpfs.txt @@ -82,11 +82,13 @@ tmpfs has a mount option to set the NUMA memory allocation policy for all files in that instance (if CONFIG_NUMA is enabled) - which can be adjusted on the fly via 'mount -o remount ...' -mpol=default prefers to allocate memory from the local node +mpol=default use the process allocation policy + (see set_mempolicy(2)) mpol=prefer:Node prefers to allocate memory from the given Node mpol=bind:NodeList allocates memory only from nodes in NodeList mpol=interleave prefers to allocate from each node in turn mpol=interleave:NodeList allocates from each node of NodeList in turn +mpol=local prefers to allocate memory from the local node NodeList format is a comma-separated list of decimal numbers and ranges, a range being two hyphen-separated decimal numbers, the smallest and @@ -134,3 +136,5 @@ Author: Christoph Rohland <cr@sap.com>, 1.12.01 Updated: Hugh Dickins, 4 June 2007 +Updated: + KOSAKI Motohiro, 16 Mar 2010 diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 3de2f32edd90..b66858538df5 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -72,7 +72,7 @@ structure (this is the kernel-side implementation of file descriptors). The freshly allocated file structure is initialized with a pointer to the dentry and a set of file operation member functions. These are taken from the inode data. The open() file method is then -called so the specific filesystem implementation can do it's work. You +called so the specific filesystem implementation can do its work. You can see that this is another switch performed by the VFS. The file structure is placed into the file descriptor table for the process. diff --git a/Documentation/hwmon/abituguru b/Documentation/hwmon/abituguru index 87ffa0f5ec70..5eb3b9d5f0d5 100644 --- a/Documentation/hwmon/abituguru +++ b/Documentation/hwmon/abituguru @@ -30,7 +30,7 @@ Supported chips: bank1_types=1,1,0,0,0,0,0,2,0,0,0,0,2,0,0,1 You may also need to specify the fan_sensors option for these boards fan_sensors=5 - 2) There is a seperate abituguru3 driver for these motherboards, + 2) There is a separate abituguru3 driver for these motherboards, the abituguru (without the 3 !) driver will not work on these motherboards (and visa versa)! diff --git a/Documentation/hwmon/lm85 b/Documentation/hwmon/lm85 index a13680871bc7..a76aefeeb68a 100644 --- a/Documentation/hwmon/lm85 +++ b/Documentation/hwmon/lm85 @@ -157,7 +157,7 @@ temperature configuration points: There are three PWM outputs. The LM85 datasheet suggests that the pwm3 output control both fan3 and fan4. Each PWM can be individually -configured and assigned to a zone for it's control value. Each PWM can be +configured and assigned to a zone for its control value. Each PWM can be configured individually according to the following options. * pwm#_auto_pwm_min - this specifies the PWM value for temp#_auto_temp_off diff --git a/Documentation/i2c/writing-clients b/Documentation/i2c/writing-clients index 3219ee0dbfef..5ebf5af1d716 100644 --- a/Documentation/i2c/writing-clients +++ b/Documentation/i2c/writing-clients @@ -74,6 +74,11 @@ structure at all. You should use this to keep device-specific data. /* retrieve the value */ void *i2c_get_clientdata(const struct i2c_client *client); +Note that starting with kernel 2.6.34, you don't have to set the `data' field +to NULL in remove() or if probe() failed anymore. The i2c-core does this +automatically on these occasions. Those are also the only times the core will +touch this field. + Accessing the client ==================== diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt index a10c3b6ba7c4..56941ae1f5db 100644 --- a/Documentation/input/elantech.txt +++ b/Documentation/input/elantech.txt @@ -333,14 +333,14 @@ byte 0: byte 1: bit 7 6 5 4 3 2 1 0 - x15 x14 x13 x12 x11 x10 x9 x8 + . . . . . x10 x9 x8 byte 2: bit 7 6 5 4 3 2 1 0 x7 x6 x5 x4 x4 x2 x1 x0 - x15..x0 = absolute x value (horizontal) + x10..x0 = absolute x value (horizontal) byte 3: @@ -350,14 +350,14 @@ byte 3: byte 4: bit 7 6 5 4 3 2 1 0 - y15 y14 y13 y12 y11 y10 y8 y8 + . . . . . . y9 y8 byte 5: bit 7 6 5 4 3 2 1 0 y7 y6 y5 y4 y3 y2 y1 y0 - y15..y0 = absolute y value (vertical) + y9..y0 = absolute y value (vertical) 4.2.2 Two finger touch diff --git a/Documentation/input/joystick.txt b/Documentation/input/joystick.txt index 154d767b2acb..8007b7ca87bf 100644 --- a/Documentation/input/joystick.txt +++ b/Documentation/input/joystick.txt @@ -402,7 +402,7 @@ for the port of the SoundFusion is supported by the cs461x.c module. ~~~~~~~~~~~~~~~~~~~~~~~~ The Live! has a special PCI gameport, which, although it doesn't provide any "Enhanced" stuff like 4DWave and friends, is quite a bit faster than -it's ISA counterparts. It also requires special support, hence the +its ISA counterparts. It also requires special support, hence the emu10k1-gp.c module for it instead of the normal ns558.c one. 3.15 SoundBlaster 64 and 128 - ES1370 and ES1371, ESS Solo1 and S3 SonicVibes diff --git a/Documentation/input/multi-touch-protocol.txt b/Documentation/input/multi-touch-protocol.txt index 8490480ce432..c0fc1c75fd88 100644 --- a/Documentation/input/multi-touch-protocol.txt +++ b/Documentation/input/multi-touch-protocol.txt @@ -68,6 +68,22 @@ like: SYN_MT_REPORT SYN_REPORT +Here is the sequence after lifting one of the fingers: + + ABS_MT_POSITION_X + ABS_MT_POSITION_Y + SYN_MT_REPORT + SYN_REPORT + +And here is the sequence after lifting the remaining finger: + + SYN_MT_REPORT + SYN_REPORT + +If the driver reports one of BTN_TOUCH or ABS_PRESSURE in addition to the +ABS_MT events, the last SYN_MT_REPORT event may be omitted. Otherwise, the +last SYN_REPORT will be dropped by the input core, resulting in no +zero-finger event reaching userland. Event Semantics --------------- @@ -217,11 +233,6 @@ where examples can be found. 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] The multi-touch X driver is currently in the prototyping stage. At the -time of writing (April 2009), the MT protocol is not yet merged, and the -prototype implements finger matching, basic mouse support and two-finger -scrolling. The project aims at improving the quality of current multi-touch -functionality available in the Synaptics X driver, and in addition -implement more advanced gestures. +[3] Multitouch X driver project: http://bitmath.org/code/multitouch/. [4] See the section on event computation. [5] See the section on finger tracking. diff --git a/Documentation/input/rotary-encoder.txt b/Documentation/input/rotary-encoder.txt index 3a6aec40c0b0..8b4129de1d2d 100644 --- a/Documentation/input/rotary-encoder.txt +++ b/Documentation/input/rotary-encoder.txt @@ -75,7 +75,7 @@ and the number of steps or will clamp at the maximum and zero depending on the configuration. Because GPIO to IRQ mapping is platform specific, this information must -be given in seperately to the driver. See the example below. +be given in separately to the driver. See the example below. ---------<snip>--------- diff --git a/Documentation/intel_txt.txt b/Documentation/intel_txt.txt index f40a1f030019..5dc59b04a71f 100644 --- a/Documentation/intel_txt.txt +++ b/Documentation/intel_txt.txt @@ -126,7 +126,7 @@ o Tboot then applies an (optional) user-defined launch policy to o Tboot adjusts the e820 table provided by the bootloader to reserve its own location in memory as well as to reserve certain other TXT-related regions. -o As part of it's launch, tboot DMA protects all of RAM (using the +o As part of its launch, tboot DMA protects all of RAM (using the VT-d PMRs). Thus, the kernel must be booted with 'intel_iommu=on' in order to remove this blanket protection and use VT-d's page-level protection. @@ -161,13 +161,15 @@ o In order to put a system into any of the sleep states after a TXT has been restored, it will restore the TPM PCRs and then transfer control back to the kernel's S3 resume vector. In order to preserve system integrity across S3, the kernel - provides tboot with a set of memory ranges (kernel - code/data/bss, S3 resume code, and AP trampoline) that tboot - will calculate a MAC (message authentication code) over and then - seal with the TPM. On resume and once the measured environment - has been re-established, tboot will re-calculate the MAC and - verify it against the sealed value. Tboot's policy determines - what happens if the verification fails. + provides tboot with a set of memory ranges (RAM and RESERVED_KERN + in the e820 table, but not any memory that BIOS might alter over + the S3 transition) that tboot will calculate a MAC (message + authentication code) over and then seal with the TPM. On resume + and once the measured environment has been re-established, tboot + will re-calculate the MAC and verify it against the sealed value. + Tboot's policy determines what happens if the verification fails. + Note that the c/s 194 of tboot which has the new MAC code supports + this. That's pretty much it for TXT support. diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 35c9b51d20ea..dd5806f4fcc4 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -291,6 +291,7 @@ Code Seq#(hex) Include File Comments 0x92 00-0F drivers/usb/mon/mon_bin.c 0x93 60-7F linux/auto_fs.h 0x94 all fs/btrfs/ioctl.h +0x97 00-7F fs/ceph/ioctl.h Ceph file system 0x99 00-0F 537-Addinboard driver <mailto:buk@buks.ipn.de> 0xA0 all linux/sdp/sdp.h Industrial Device Project diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt index c412c245848f..b472e4e0ba67 100644 --- a/Documentation/kbuild/kconfig-language.txt +++ b/Documentation/kbuild/kconfig-language.txt @@ -181,7 +181,7 @@ Expressions are listed in decreasing order of precedence. (7) Returns the result of max(/expr/, /expr/). An expression can have a value of 'n', 'm' or 'y' (or 0, 1, 2 -respectively for calculations). A menu entry becomes visible when it's +respectively for calculations). A menu entry becomes visible when its expression evaluates to 'm' or 'y'. There are two types of symbols: constant and non-constant symbols. diff --git a/Documentation/kbuild/kconfig.txt b/Documentation/kbuild/kconfig.txt index 49efae703979..b2cb16ebcb16 100644 --- a/Documentation/kbuild/kconfig.txt +++ b/Documentation/kbuild/kconfig.txt @@ -96,7 +96,7 @@ Environment variables for 'silentoldconfig' KCONFIG_NOSILENTUPDATE -------------------------------------------------- If this variable has a non-blank value, it prevents silent kernel -config udpates (requires explicit updates). +config updates (requires explicit updates). KCONFIG_AUTOCONFIG -------------------------------------------------- diff --git a/Documentation/kernel-docs.txt b/Documentation/kernel-docs.txt index 28cdc2af2131..ec8d31ee12e0 100644 --- a/Documentation/kernel-docs.txt +++ b/Documentation/kernel-docs.txt @@ -116,7 +116,7 @@ Author: Ingo Molnar, Gadi Oxman and Miguel de Icaza. URL: http://www.linuxjournal.com/article.php?sid=2391 Keywords: RAID, MD driver. - Description: Linux Journal Kernel Korner article. Here is it's + Description: Linux Journal Kernel Korner article. Here is its abstract: "A description of the implementation of the RAID-1, RAID-4 and RAID-5 personalities of the MD device driver in the Linux kernel, providing users with high performance and reliable, @@ -127,7 +127,7 @@ URL: http://www.linuxjournal.com/article.php?sid=1219 Keywords: device driver, module, loading/unloading modules, allocating resources. - Description: Linux Journal Kernel Korner article. Here is it's + Description: Linux Journal Kernel Korner article. Here is its abstract: "This is the first of a series of four articles co-authored by Alessandro Rubini and Georg Zezchwitz which present a practical approach to writing Linux device drivers as kernel @@ -141,7 +141,7 @@ Keywords: character driver, init_module, clean_up module, autodetection, mayor number, minor number, file operations, open(), close(). - Description: Linux Journal Kernel Korner article. Here is it's + Description: Linux Journal Kernel Korner article. Here is its abstract: "This article, the second of four, introduces part of the actual code to create custom module implementing a character device driver. It describes the code for module initialization and @@ -152,7 +152,7 @@ URL: http://www.linuxjournal.com/article.php?sid=1221 Keywords: read(), write(), select(), ioctl(), blocking/non blocking mode, interrupt handler. - Description: Linux Journal Kernel Korner article. Here is it's + Description: Linux Journal Kernel Korner article. Here is its abstract: "This article, the third of four on writing character device drivers, introduces concepts of reading, writing, and using ioctl-calls". @@ -161,7 +161,7 @@ Author: Alessandro Rubini and Georg v. Zezschwitz. URL: http://www.linuxjournal.com/article.php?sid=1222 Keywords: interrupts, irqs, DMA, bottom halves, task queues. - Description: Linux Journal Kernel Korner article. Here is it's + Description: Linux Journal Kernel Korner article. Here is its abstract: "This is the fourth in a series of articles about writing character device drivers as loadable kernel modules. This month, we further investigate the field of interrupt handling. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 3bc48b0bd3a9..b12bacd252fc 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -99,6 +99,7 @@ parameter is applicable: SWSUSP Software suspend (hibernation) is enabled. SUSPEND System suspend states are enabled. FTRACE Function tracing enabled. + TPM TPM drivers are enabled. TS Appropriate touchscreen support is enabled. UMS USB Mass Storage support is enabled. USB USB support is enabled. @@ -151,6 +152,7 @@ and is between 256 and 4096 characters. It is defined in the file strict -- Be less tolerant of platforms that are not strictly ACPI specification compliant. rsdt -- prefer RSDT over (default) XSDT + copy_dsdt -- copy DSDT to memory See also Documentation/power/pm.txt, pci=noacpi @@ -200,10 +202,6 @@ and is between 256 and 4096 characters. It is defined in the file acpi_display_output=video See above. - acpi_early_pdc_eval [HW,ACPI] Evaluate processor _PDC methods - early. Needed on some platforms to properly - initialize the EC. - acpi_irq_balance [HW,ACPI] ACPI will balance active IRQs default in APIC mode @@ -324,15 +322,12 @@ and is between 256 and 4096 characters. It is defined in the file amd_iommu= [HW,X86-84] Pass parameters to the AMD IOMMU driver in the system. Possible values are: - isolate - enable device isolation (each device, as far - as possible, will get its own protection - domain) [default] - share - put every device behind one IOMMU into the - same protection domain fullflush - enable flushing of IO/TLB entries when they are unmapped. Otherwise they are flushed before they will be reused, which is a lot of faster + off - do not initialize any AMD IOMMU found in + the system amijoy.map= [HW,JOY] Amiga joystick support Map of devices attached to JOY0DAT and JOY1DAT @@ -793,8 +788,12 @@ and is between 256 and 4096 characters. It is defined in the file as early as possible in order to facilitate early boot debugging. - ftrace_dump_on_oops + ftrace_dump_on_oops[=orig_cpu] [FTRACE] will dump the trace buffers on oops. + If no parameter is passed, ftrace will dump + buffers of all CPUs, but if you pass orig_cpu, it will + dump only the buffer of the CPU that triggered the + oops. ftrace_filter=[function-list] [FTRACE] Limit the functions traced by the function @@ -1203,7 +1202,7 @@ and is between 256 and 4096 characters. It is defined in the file libata.force= [LIBATA] Force configurations. The format is comma separated list of "[ID:]VAL" where ID is - PORT[:DEVICE]. PORT and DEVICE are decimal numbers + PORT[.DEVICE]. PORT and DEVICE are decimal numbers matching port, link or device. Basically, it matches the ATA ID string printed on console by libata. If the whole ID part is omitted, the last PORT and DEVICE @@ -2619,6 +2618,15 @@ and is between 256 and 4096 characters. It is defined in the file tp720= [HW,PS2] + tpm_suspend_pcr=[HW,TPM] + Format: integer pcr id + Specify that at suspend time, the tpm driver + should extend the specified pcr with zeros, + as a workaround for some chips which fail to + flush the last written pcr on TPM_SaveState. + This will guarantee that all the other pcrs + are saved. + trace_buf_size=nn[KMG] [FTRACE] will set tracing buffer size. diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt index c79ab996dada..3ab2472509cb 100644 --- a/Documentation/kobject.txt +++ b/Documentation/kobject.txt @@ -59,37 +59,56 @@ nice to have in other objects. The C language does not allow for the direct expression of inheritance, so other techniques - such as structure embedding - must be used. -So, for example, the UIO code has a structure that defines the memory -region associated with a uio device: +(As an aside, for those familiar with the kernel linked list implementation, +this is analogous as to how "list_head" structs are rarely useful on +their own, but are invariably found embedded in the larger objects of +interest.) -struct uio_mem { +So, for example, the UIO code in drivers/uio/uio.c has a structure that +defines the memory region associated with a uio device: + + struct uio_map { struct kobject kobj; - unsigned long addr; - unsigned long size; - int memtype; - void __iomem *internal_addr; -}; + struct uio_mem *mem; + }; -If you have a struct uio_mem structure, finding its embedded kobject is +If you have a struct uio_map structure, finding its embedded kobject is just a matter of using the kobj member. Code that works with kobjects will often have the opposite problem, however: given a struct kobject pointer, what is the pointer to the containing structure? You must avoid tricks (such as assuming that the kobject is at the beginning of the structure) and, instead, use the container_of() macro, found in <linux/kernel.h>: - container_of(pointer, type, member) + container_of(pointer, type, member) + +where: + + * "pointer" is the pointer to the embedded kobject, + * "type" is the type of the containing structure, and + * "member" is the name of the structure field to which "pointer" points. + +The return value from container_of() is a pointer to the corresponding +container type. So, for example, a pointer "kp" to a struct kobject +embedded *within* a struct uio_map could be converted to a pointer to the +*containing* uio_map structure with: + + struct uio_map *u_map = container_of(kp, struct uio_map, kobj); + +For convenience, programmers often define a simple macro for "back-casting" +kobject pointers to the containing type. Exactly this happens in the +earlier drivers/uio/uio.c, as you can see here: + + struct uio_map { + struct kobject kobj; + struct uio_mem *mem; + }; -where pointer is the pointer to the embedded kobject, type is the type of -the containing structure, and member is the name of the structure field to -which pointer points. The return value from container_of() is a pointer to -the given type. So, for example, a pointer "kp" to a struct kobject -embedded within a struct uio_mem could be converted to a pointer to the -containing uio_mem structure with: + #define to_map(map) container_of(map, struct uio_map, kobj) - struct uio_mem *u_mem = container_of(kp, struct uio_mem, kobj); +where the macro argument "map" is a pointer to the struct kobject in +question. That macro is subsequently invoked with: -Programmers often define a simple macro for "back-casting" kobject pointers -to the containing type. + struct uio_map *map = to_map(kobj); Initialization of kobjects @@ -266,7 +285,7 @@ kobj_type: struct kobj_type { void (*release)(struct kobject *); - struct sysfs_ops *sysfs_ops; + const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; }; @@ -387,4 +406,5 @@ called, and the objects in the former circle release each other. Example code to copy from For a more complete example of using ksets and kobjects properly, see the -sample/kobject/kset-example.c code. +example programs samples/kobject/{kobject-example.c,kset-example.c}, +which will be built as loadable modules if you select CONFIG_SAMPLE_KOBJECT. diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt index 2f9115c0ae62..6653017680dd 100644 --- a/Documentation/kprobes.txt +++ b/Documentation/kprobes.txt @@ -165,8 +165,8 @@ the user entry_handler invocation is also skipped. 1.4 How Does Jump Optimization Work? -If you configured your kernel with CONFIG_OPTPROBES=y (currently -this option is supported on x86/x86-64, non-preemptive kernel) and +If your kernel is built with CONFIG_OPTPROBES=y (currently this flag +is automatically set 'y' on x86/x86-64, non-preemptive kernel) and the "debug.kprobes_optimization" kernel parameter is set to 1 (see sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump instruction instead of a breakpoint instruction at each probepoint. @@ -271,8 +271,6 @@ tweak the kernel's execution path, you need to suppress optimization, using one of the following techniques: - Specify an empty function for the kprobe's post_handler or break_handler. or -- Config CONFIG_OPTPROBES=n. - or - Execute 'sysctl -w debug.kprobes_optimization=n' 2. Architectures Supported @@ -307,10 +305,6 @@ it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO), so you can use "objdump -d -l vmlinux" to see the source-to-object code mapping. -If you want to reduce probing overhead, set "Kprobes jump optimization -support" (CONFIG_OPTPROBES) to "y". You can find this option under the -"Kprobes" line. - 4. API Reference The Kprobes API includes a "register" function and an "unregister" @@ -332,7 +326,7 @@ occurs during execution of kp->pre_handler or kp->post_handler, or during single-stepping of the probed instruction, Kprobes calls kp->fault_handler. Any or all handlers can be NULL. If kp->flags is set KPROBE_FLAG_DISABLED, that kp will be registered but disabled, -so, it's handlers aren't hit until calling enable_kprobe(kp). +so, its handlers aren't hit until calling enable_kprobe(kp). NOTE: 1. With the introduction of the "symbol_name" field to struct kprobe, diff --git a/Documentation/laptops/00-INDEX b/Documentation/laptops/00-INDEX index ee5692b26dd4..fa688538e757 100644 --- a/Documentation/laptops/00-INDEX +++ b/Documentation/laptops/00-INDEX @@ -2,6 +2,12 @@ - This file acer-wmi.txt - information on the Acer Laptop WMI Extras driver. +asus-laptop.txt + - information on the Asus Laptop Extras driver. +disk-shock-protection.txt + - information on hard disk shock protection. +dslm.c + - Simple Disk Sleep Monitor program laptop-mode.txt - how to conserve battery power using laptop-mode. sony-laptop.txt diff --git a/Documentation/laptops/Makefile b/Documentation/laptops/Makefile new file mode 100644 index 000000000000..5cb144af3c09 --- /dev/null +++ b/Documentation/laptops/Makefile @@ -0,0 +1,8 @@ +# kbuild trick to avoid linker error. Can be omitted if a module is built. +obj- := dummy.o + +# List of programs to build +hostprogs-y := dslm + +# Tell kbuild to always build the programs +always := $(hostprogs-y) diff --git a/Documentation/laptops/dslm.c b/Documentation/laptops/dslm.c new file mode 100644 index 000000000000..72ff290c5fc6 --- /dev/null +++ b/Documentation/laptops/dslm.c @@ -0,0 +1,166 @@ +/* + * dslm.c + * Simple Disk Sleep Monitor + * by Bartek Kania + * Licenced under the GPL + */ +#include <unistd.h> +#include <stdlib.h> +#include <stdio.h> +#include <fcntl.h> +#include <errno.h> +#include <time.h> +#include <string.h> +#include <signal.h> +#include <sys/ioctl.h> +#include <linux/hdreg.h> + +#ifdef DEBUG +#define D(x) x +#else +#define D(x) +#endif + +int endit = 0; + +/* Check if the disk is in powersave-mode + * Most of the code is stolen from hdparm. + * 1 = active, 0 = standby/sleep, -1 = unknown */ +static int check_powermode(int fd) +{ + unsigned char args[4] = {WIN_CHECKPOWERMODE1,0,0,0}; + int state; + + if (ioctl(fd, HDIO_DRIVE_CMD, &args) + && (args[0] = WIN_CHECKPOWERMODE2) /* try again with 0x98 */ + && ioctl(fd, HDIO_DRIVE_CMD, &args)) { + if (errno != EIO || args[0] != 0 || args[1] != 0) { + state = -1; /* "unknown"; */ + } else + state = 0; /* "sleeping"; */ + } else { + state = (args[2] == 255) ? 1 : 0; + } + D(printf(" drive state is: %d\n", state)); + + return state; +} + +static char *state_name(int i) +{ + if (i == -1) return "unknown"; + if (i == 0) return "sleeping"; + if (i == 1) return "active"; + + return "internal error"; +} + +static char *myctime(time_t time) +{ + char *ts = ctime(&time); + ts[strlen(ts) - 1] = 0; + + return ts; +} + +static void measure(int fd) +{ + time_t start_time; + int last_state; + time_t last_time; + int curr_state; + time_t curr_time = 0; + time_t time_diff; + time_t active_time = 0; + time_t sleep_time = 0; + time_t unknown_time = 0; + time_t total_time = 0; + int changes = 0; + float tmp; + + printf("Starting measurements\n"); + + last_state = check_powermode(fd); + start_time = last_time = time(0); + printf(" System is in state %s\n\n", state_name(last_state)); + + while(!endit) { + sleep(1); + curr_state = check_powermode(fd); + + if (curr_state != last_state || endit) { + changes++; + curr_time = time(0); + time_diff = curr_time - last_time; + + if (last_state == 1) active_time += time_diff; + else if (last_state == 0) sleep_time += time_diff; + else unknown_time += time_diff; + + last_state = curr_state; + last_time = curr_time; + + printf("%s: State-change to %s\n", myctime(curr_time), + state_name(curr_state)); + } + } + changes--; /* Compensate for SIGINT */ + + total_time = time(0) - start_time; + printf("\nTotal running time: %lus\n", curr_time - start_time); + printf(" State changed %d times\n", changes); + + tmp = (float)sleep_time / (float)total_time * 100; + printf(" Time in sleep state: %lus (%.2f%%)\n", sleep_time, tmp); + tmp = (float)active_time / (float)total_time * 100; + printf(" Time in active state: %lus (%.2f%%)\n", active_time, tmp); + tmp = (float)unknown_time / (float)total_time * 100; + printf(" Time in unknown state: %lus (%.2f%%)\n", unknown_time, tmp); +} + +static void ender(int s) +{ + endit = 1; +} + +static void usage(void) +{ + puts("usage: dslm [-w <time>] <disk>"); + exit(0); +} + +int main(int argc, char **argv) +{ + int fd; + char *disk = 0; + int settle_time = 60; + + /* Parse the simple command-line */ + if (argc == 2) + disk = argv[1]; + else if (argc == 4) { + settle_time = atoi(argv[2]); + disk = argv[3]; + } else + usage(); + + if (!(fd = open(disk, O_RDONLY|O_NONBLOCK))) { + printf("Can't open %s, because: %s\n", disk, strerror(errno)); + exit(-1); + } + + if (settle_time) { + printf("Waiting %d seconds for the system to settle down to " + "'normal'\n", settle_time); + sleep(settle_time); + } else + puts("Not waiting for system to settle down"); + + signal(SIGINT, ender); + + measure(fd); + + close(fd); + + return 0; +} diff --git a/Documentation/laptops/laptop-mode.txt b/Documentation/laptops/laptop-mode.txt index eeedee11c8c2..0bf25eebce94 100644 --- a/Documentation/laptops/laptop-mode.txt +++ b/Documentation/laptops/laptop-mode.txt @@ -207,7 +207,7 @@ Tips & Tricks * Drew Scott Daniels observed: "I don't know why, but when I decrease the number of colours that my display uses it consumes less battery power. I've seen this on powerbooks too. I hope that this is a piece of information that - might be useful to the Laptop Mode patch or it's users." + might be useful to the Laptop Mode patch or its users." * In syslog.conf, you can prefix entries with a dash ``-'' to omit syncing the file after every logging. When you're using laptop-mode and your disk doesn't @@ -779,172 +779,4 @@ Monitoring tool --------------- Bartek Kania submitted this, it can be used to measure how much time your disk -spends spun up/down. - ----------------------------dslm.c BEGIN----------------------------------------- -/* - * Simple Disk Sleep Monitor - * by Bartek Kania - * Licenced under the GPL - */ -#include <unistd.h> -#include <stdlib.h> -#include <stdio.h> -#include <fcntl.h> -#include <errno.h> -#include <time.h> -#include <string.h> -#include <signal.h> -#include <sys/ioctl.h> -#include <linux/hdreg.h> - -#ifdef DEBUG -#define D(x) x -#else -#define D(x) -#endif - -int endit = 0; - -/* Check if the disk is in powersave-mode - * Most of the code is stolen from hdparm. - * 1 = active, 0 = standby/sleep, -1 = unknown */ -int check_powermode(int fd) -{ - unsigned char args[4] = {WIN_CHECKPOWERMODE1,0,0,0}; - int state; - - if (ioctl(fd, HDIO_DRIVE_CMD, &args) - && (args[0] = WIN_CHECKPOWERMODE2) /* try again with 0x98 */ - && ioctl(fd, HDIO_DRIVE_CMD, &args)) { - if (errno != EIO || args[0] != 0 || args[1] != 0) { - state = -1; /* "unknown"; */ - } else - state = 0; /* "sleeping"; */ - } else { - state = (args[2] == 255) ? 1 : 0; - } - D(printf(" drive state is: %d\n", state)); - - return state; -} - -char *state_name(int i) -{ - if (i == -1) return "unknown"; - if (i == 0) return "sleeping"; - if (i == 1) return "active"; - - return "internal error"; -} - -char *myctime(time_t time) -{ - char *ts = ctime(&time); - ts[strlen(ts) - 1] = 0; - - return ts; -} - -void measure(int fd) -{ - time_t start_time; - int last_state; - time_t last_time; - int curr_state; - time_t curr_time = 0; - time_t time_diff; - time_t active_time = 0; - time_t sleep_time = 0; - time_t unknown_time = 0; - time_t total_time = 0; - int changes = 0; - float tmp; - - printf("Starting measurements\n"); - - last_state = check_powermode(fd); - start_time = last_time = time(0); - printf(" System is in state %s\n\n", state_name(last_state)); - - while(!endit) { - sleep(1); - curr_state = check_powermode(fd); - - if (curr_state != last_state || endit) { - changes++; - curr_time = time(0); - time_diff = curr_time - last_time; - - if (last_state == 1) active_time += time_diff; - else if (last_state == 0) sleep_time += time_diff; - else unknown_time += time_diff; - - last_state = curr_state; - last_time = curr_time; - - printf("%s: State-change to %s\n", myctime(curr_time), - state_name(curr_state)); - } - } - changes--; /* Compensate for SIGINT */ - - total_time = time(0) - start_time; - printf("\nTotal running time: %lus\n", curr_time - start_time); - printf(" State changed %d times\n", changes); - - tmp = (float)sleep_time / (float)total_time * 100; - printf(" Time in sleep state: %lus (%.2f%%)\n", sleep_time, tmp); - tmp = (float)active_time / (float)total_time * 100; - printf(" Time in active state: %lus (%.2f%%)\n", active_time, tmp); - tmp = (float)unknown_time / (float)total_time * 100; - printf(" Time in unknown state: %lus (%.2f%%)\n", unknown_time, tmp); -} - -void ender(int s) -{ - endit = 1; -} - -void usage() -{ - puts("usage: dslm [-w <time>] <disk>"); - exit(0); -} - -int main(int argc, char **argv) -{ - int fd; - char *disk = 0; - int settle_time = 60; - - /* Parse the simple command-line */ - if (argc == 2) - disk = argv[1]; - else if (argc == 4) { - settle_time = atoi(argv[2]); - disk = argv[3]; - } else - usage(); - - if (!(fd = open(disk, O_RDONLY|O_NONBLOCK))) { - printf("Can't open %s, because: %s\n", disk, strerror(errno)); - exit(-1); - } - - if (settle_time) { - printf("Waiting %d seconds for the system to settle down to " - "'normal'\n", settle_time); - sleep(settle_time); - } else - puts("Not waiting for system to settle down"); - - signal(SIGINT, ender); - - measure(fd); - - close(fd); - - return 0; -} ----------------------------dslm.c END------------------------------------------- +spends spun up/down. See Documentation/laptops/dslm.c diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c index 3119f5db75bd..e9ce3c554514 100644 --- a/Documentation/lguest/lguest.c +++ b/Documentation/lguest/lguest.c @@ -263,7 +263,7 @@ static u8 *get_feature_bits(struct device *dev) * Launcher virtual with an offset. * * This can be tough to get your head around, but usually it just means that we - * use these trivial conversion functions when the Guest gives us it's + * use these trivial conversion functions when the Guest gives us its * "physical" addresses: */ static void *from_guest_phys(unsigned long addr) diff --git a/Documentation/md.txt b/Documentation/md.txt index 188f4768f1d5..e4e893ef3e01 100644 --- a/Documentation/md.txt +++ b/Documentation/md.txt @@ -136,7 +136,7 @@ raid_disks != 0. Then uninitialized devices can be added with ADD_NEW_DISK. The structure passed to ADD_NEW_DISK must specify the state of the device -and it's role in the array. +and its role in the array. Once started with RUN_ARRAY, uninitialized spares can be added with HOT_ADD_DISK. diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 7f5809eddee6..631ad2f1b229 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -3,6 +3,7 @@ ============================ By: David Howells <dhowells@redhat.com> + Paul E. McKenney <paulmck@linux.vnet.ibm.com> Contents: @@ -60,6 +61,10 @@ Contents: - And then there's the Alpha. + (*) Example uses. + + - Circular buffers. + (*) References. @@ -2226,6 +2231,21 @@ The Alpha defines the Linux kernel's memory barrier model. See the subsection on "Cache Coherency" above. +============ +EXAMPLE USES +============ + +CIRCULAR BUFFERS +---------------- + +Memory barriers can be used to implement circular buffering without the need +of a lock to serialise the producer with the consumer. See: + + Documentation/circular-buffers.txt + +for details. + + ========== REFERENCES ========== diff --git a/Documentation/netlabel/lsm_interface.txt b/Documentation/netlabel/lsm_interface.txt index 98dd9f7430f2..638c74f7de7f 100644 --- a/Documentation/netlabel/lsm_interface.txt +++ b/Documentation/netlabel/lsm_interface.txt @@ -38,7 +38,7 @@ Depending on the exact configuration, translation between the network packet label and the internal LSM security identifier can be time consuming. The NetLabel label mapping cache is a caching mechanism which can be used to sidestep much of this overhead once a mapping has been established. Once the -LSM has received a packet, used NetLabel to decode it's security attributes, +LSM has received a packet, used NetLabel to decode its security attributes, and translated the security attributes into a LSM internal identifier the LSM can use the NetLabel caching functions to associate the LSM internal identifier with the network packet's label. This means that in the future diff --git a/Documentation/networking/Makefile b/Documentation/networking/Makefile index 6d8af1ac56c4..5aba7a33aeeb 100644 --- a/Documentation/networking/Makefile +++ b/Documentation/networking/Makefile @@ -6,3 +6,5 @@ hostprogs-y := ifenslave # Tell kbuild to always build the programs always := $(hostprogs-y) + +obj-m := timestamping/ diff --git a/Documentation/networking/caif/Linux-CAIF.txt b/Documentation/networking/caif/Linux-CAIF.txt new file mode 100644 index 000000000000..7fe7a9a33a4f --- /dev/null +++ b/Documentation/networking/caif/Linux-CAIF.txt @@ -0,0 +1,212 @@ +Linux CAIF +=========== +copyright (C) ST-Ericsson AB 2010 +Author: Sjur Brendeland/ sjur.brandeland@stericsson.com +License terms: GNU General Public License (GPL) version 2 + + +Introduction +------------ +CAIF is a MUX protocol used by ST-Ericsson cellular modems for +communication between Modem and host. The host processes can open virtual AT +channels, initiate GPRS Data connections, Video channels and Utility Channels. +The Utility Channels are general purpose pipes between modem and host. + +ST-Ericsson modems support a number of transports between modem +and host. Currently, UART and Loopback are available for Linux. + + +Architecture: +------------ +The implementation of CAIF is divided into: +* CAIF Socket Layer, Kernel API, and Net Device. +* CAIF Core Protocol Implementation +* CAIF Link Layer, implemented as NET devices. + + + RTNL + ! + ! +------+ +------+ +------+ + ! +------+! +------+! +------+! + ! ! Sock !! !Kernel!! ! Net !! + ! ! API !+ ! API !+ ! Dev !+ <- CAIF Client APIs + ! +------+ +------! +------+ + ! ! ! ! + ! +----------!----------+ + ! +------+ <- CAIF Protocol Implementation + +-------> ! CAIF ! + ! Core ! + +------+ + +--------!--------+ + ! ! + +------+ +-----+ + ! ! ! TTY ! <- Link Layer (Net Devices) + +------+ +-----+ + + +Using the Kernel API +---------------------- +The Kernel API is used for accessing CAIF channels from the +kernel. +The user of the API has to implement two callbacks for receive +and control. +The receive callback gives a CAIF packet as a SKB. The control +callback will +notify of channel initialization complete, and flow-on/flow- +off. + + + struct caif_device caif_dev = { + .caif_config = { + .name = "MYDEV" + .type = CAIF_CHTY_AT + } + .receive_cb = my_receive, + .control_cb = my_control, + }; + caif_add_device(&caif_dev); + caif_transmit(&caif_dev, skb); + +See the caif_kernel.h for details about the CAIF kernel API. + + +I M P L E M E N T A T I O N +=========================== +=========================== + +CAIF Core Protocol Layer +========================================= + +CAIF Core layer implements the CAIF protocol as defined by ST-Ericsson. +It implements the CAIF protocol stack in a layered approach, where +each layer described in the specification is implemented as a separate layer. +The architecture is inspired by the design patterns "Protocol Layer" and +"Protocol Packet". + +== CAIF structure == +The Core CAIF implementation contains: + - Simple implementation of CAIF. + - Layered architecture (a la Streams), each layer in the CAIF + specification is implemented in a separate c-file. + - Clients must implement PHY layer to access physical HW + with receive and transmit functions. + - Clients must call configuration function to add PHY layer. + - Clients must implement CAIF layer to consume/produce + CAIF payload with receive and transmit functions. + - Clients must call configuration function to add and connect the + Client layer. + - When receiving / transmitting CAIF Packets (cfpkt), ownership is passed + to the called function (except for framing layers' receive functions + or if a transmit function returns an error, in which case the caller + must free the packet). + +Layered Architecture +-------------------- +The CAIF protocol can be divided into two parts: Support functions and Protocol +Implementation. The support functions include: + + - CFPKT CAIF Packet. Implementation of CAIF Protocol Packet. The + CAIF Packet has functions for creating, destroying and adding content + and for adding/extracting header and trailers to protocol packets. + + - CFLST CAIF list implementation. + + - CFGLUE CAIF Glue. Contains OS Specifics, such as memory + allocation, endianness, etc. + +The CAIF Protocol implementation contains: + + - CFCNFG CAIF Configuration layer. Configures the CAIF Protocol + Stack and provides a Client interface for adding Link-Layer and + Driver interfaces on top of the CAIF Stack. + + - CFCTRL CAIF Control layer. Encodes and Decodes control messages + such as enumeration and channel setup. Also matches request and + response messages. + + - CFSERVL General CAIF Service Layer functionality; handles flow + control and remote shutdown requests. + + - CFVEI CAIF VEI layer. Handles CAIF AT Channels on VEI (Virtual + External Interface). This layer encodes/decodes VEI frames. + + - CFDGML CAIF Datagram layer. Handles CAIF Datagram layer (IP + traffic), encodes/decodes Datagram frames. + + - CFMUX CAIF Mux layer. Handles multiplexing between multiple + physical bearers and multiple channels such as VEI, Datagram, etc. + The MUX keeps track of the existing CAIF Channels and + Physical Instances and selects the apropriate instance based + on Channel-Id and Physical-ID. + + - CFFRML CAIF Framing layer. Handles Framing i.e. Frame length + and frame checksum. + + - CFSERL CAIF Serial layer. Handles concatenation/split of frames + into CAIF Frames with correct length. + + + + +---------+ + | Config | + | CFCNFG | + +---------+ + ! + +---------+ +---------+ +---------+ + | AT | | Control | | Datagram| + | CFVEIL | | CFCTRL | | CFDGML | + +---------+ +---------+ +---------+ + \_____________!______________/ + ! + +---------+ + | MUX | + | | + +---------+ + _____!_____ + / \ + +---------+ +---------+ + | CFFRML | | CFFRML | + | Framing | | Framing | + +---------+ +---------+ + ! ! + +---------+ +---------+ + | | | Serial | + | | | CFSERL | + +---------+ +---------+ + + +In this layered approach the following "rules" apply. + - All layers embed the same structure "struct cflayer" + - A layer does not depend on any other layer's private data. + - Layers are stacked by setting the pointers + layer->up , layer->dn + - In order to send data upwards, each layer should do + layer->up->receive(layer->up, packet); + - In order to send data downwards, each layer should do + layer->dn->transmit(layer->dn, packet); + + +Linux Driver Implementation +=========================== + +Linux GPRS Net Device and CAIF socket are implemented on top of the +CAIF Core protocol. The Net device and CAIF socket have an instance of +'struct cflayer', just like the CAIF Core protocol stack. +Net device and Socket implement the 'receive()' function defined by +'struct cflayer', just like the rest of the CAIF stack. In this way, transmit and +receive of packets is handled as by the rest of the layers: the 'dn->transmit()' +function is called in order to transmit data. + +The layer on top of the CAIF Core implementation is +sometimes referred to as the "Client layer". + + +Configuration of Link Layer +--------------------------- +The Link Layer is implemented as Linux net devices (struct net_device). +Payload handling and registration is done using standard Linux mechanisms. + +The CAIF Protocol relies on a loss-less link layer without implementing +retransmission. This implies that packet drops must not happen. +Therefore a flow-control mechanism is implemented where the physical +interface can initiate flow stop for all CAIF Channels. diff --git a/Documentation/networking/caif/README b/Documentation/networking/caif/README new file mode 100644 index 000000000000..757ccfaa1385 --- /dev/null +++ b/Documentation/networking/caif/README @@ -0,0 +1,109 @@ +Copyright (C) ST-Ericsson AB 2010 +Author: Sjur Brendeland/ sjur.brandeland@stericsson.com +License terms: GNU General Public License (GPL) version 2 +--------------------------------------------------------- + +=== Start === +If you have compiled CAIF for modules do: + +$modprobe crc_ccitt +$modprobe caif +$modprobe caif_socket +$modprobe chnl_net + + +=== Preparing the setup with a STE modem === + +If you are working on integration of CAIF you should make sure +that the kernel is built with module support. + +There are some things that need to be tweaked to get the host TTY correctly +set up to talk to the modem. +Since the CAIF stack is running in the kernel and we want to use the existing +TTY, we are installing our physical serial driver as a line discipline above +the TTY device. + +To achieve this we need to install the N_CAIF ldisc from user space. +The benefit is that we can hook up to any TTY. + +The use of Start-of-frame-extension (STX) must also be set as +module parameter "ser_use_stx". + +Normally Frame Checksum is always used on UART, but this is also provided as a +module parameter "ser_use_fcs". + +$ modprobe caif_serial ser_ttyname=/dev/ttyS0 ser_use_stx=yes +$ ifconfig caif_ttyS0 up + +PLEASE NOTE: There is a limitation in Android shell. + It only accepts one argument to insmod/modprobe! + +=== Trouble shooting === + +There are debugfs parameters provided for serial communication. +/sys/kernel/debug/caif_serial/<tty-name>/ + +* ser_state: Prints the bit-mask status where + - 0x02 means SENDING, this is a transient state. + - 0x10 means FLOW_OFF_SENT, i.e. the previous frame has not been sent + and is blocking further send operation. Flow OFF has been propagated + to all CAIF Channels using this TTY. + +* tty_status: Prints the bit-mask tty status information + - 0x01 - tty->warned is on. + - 0x02 - tty->low_latency is on. + - 0x04 - tty->packed is on. + - 0x08 - tty->flow_stopped is on. + - 0x10 - tty->hw_stopped is on. + - 0x20 - tty->stopped is on. + +* last_tx_msg: Binary blob Prints the last transmitted frame. + This can be printed with + $od --format=x1 /sys/kernel/debug/caif_serial/<tty>/last_rx_msg. + The first two tx messages sent look like this. Note: The initial + byte 02 is start of frame extension (STX) used for re-syncing + upon errors. + + - Enumeration: + 0000000 02 05 00 00 03 01 d2 02 + | | | | | | + STX(1) | | | | + Length(2)| | | + Control Channel(1) + Command:Enumeration(1) + Link-ID(1) + Checksum(2) + - Channel Setup: + 0000000 02 07 00 00 00 21 a1 00 48 df + | | | | | | | | + STX(1) | | | | | | + Length(2)| | | | | + Control Channel(1) + Command:Channel Setup(1) + Channel Type(1) + Priority and Link-ID(1) + Endpoint(1) + Checksum(2) + +* last_rx_msg: Prints the last transmitted frame. + The RX messages for LinkSetup look almost identical but they have the + bit 0x20 set in the command bit, and Channel Setup has added one byte + before Checksum containing Channel ID. + NOTE: Several CAIF Messages might be concatenated. The maximum debug + buffer size is 128 bytes. + +== Error Scenarios: +- last_tx_msg contains channel setup message and last_rx_msg is empty -> + The host seems to be able to send over the UART, at least the CAIF ldisc get + notified that sending is completed. + +- last_tx_msg contains enumeration message and last_rx_msg is empty -> + The host is not able to send the message from UART, the tty has not been + able to complete the transmit operation. + +- if /sys/kernel/debug/caif_serial/<tty>/tty_status is non-zero there + might be problems transmitting over UART. + E.g. host and modem wiring is not correct you will typically see + tty_status = 0x10 (hw_stopped) and ser_state = 0x10 (FLOW_OFF_SENT). + You will probably see the enumeration message in last_tx_message + and empty last_rx_message. diff --git a/Documentation/networking/ifenslave.c b/Documentation/networking/ifenslave.c index 1b96ccda3836..2bac9618c345 100644 --- a/Documentation/networking/ifenslave.c +++ b/Documentation/networking/ifenslave.c @@ -756,7 +756,7 @@ static int enslave(char *master_ifname, char *slave_ifname) */ if (abi_ver < 1) { /* For old ABI, the master needs to be - * down before setting it's hwaddr + * down before setting its hwaddr */ res = set_if_down(master_ifname, master_flags.ifr_flags); if (res) { diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 8b72c88ba213..d0536b5a4e01 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -588,6 +588,37 @@ ip_local_port_range - 2 INTEGERS (i.e. by default) range 1024-4999 is enough to issue up to 2000 connections per second to systems supporting timestamps. +ip_local_reserved_ports - list of comma separated ranges + Specify the ports which are reserved for known third-party + applications. These ports will not be used by automatic port + assignments (e.g. when calling connect() or bind() with port + number 0). Explicit port allocation behavior is unchanged. + + The format used for both input and output is a comma separated + list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and + 10). Writing to the file will clear all previously reserved + ports and update the current list with the one given in the + input. + + Note that ip_local_port_range and ip_local_reserved_ports + settings are independent and both are considered by the kernel + when determining which ports are available for automatic port + assignments. + + You can reserve ports which are not in the current + ip_local_port_range, e.g.: + + $ cat /proc/sys/net/ipv4/ip_local_port_range + 32000 61000 + $ cat /proc/sys/net/ipv4/ip_local_reserved_ports + 8080,9148 + + although this is redundant. However such a setting is useful + if later the port range is changed to a value that will + include the reserved ports. + + Default: Empty + ip_nonlocal_bind - BOOLEAN If set, allows processes to bind() to non-local IP addresses, which can be quite useful - but may break some applications. diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt index 63214b280e00..e7bf3979facb 100644 --- a/Documentation/networking/l2tp.txt +++ b/Documentation/networking/l2tp.txt @@ -1,44 +1,95 @@ -This brief document describes how to use the kernel's PPPoL2TP driver -to provide L2TP functionality. L2TP is a protocol that tunnels one or -more PPP sessions over a UDP tunnel. It is commonly used for VPNs +This document describes how to use the kernel's L2TP drivers to +provide L2TP functionality. L2TP is a protocol that tunnels one or +more sessions over an IP tunnel. It is commonly used for VPNs (L2TP/IPSec) and by ISPs to tunnel subscriber PPP sessions over an IP -network infrastructure. +network infrastructure. With L2TPv3, it is also useful as a Layer-2 +tunneling infrastructure. + +Features +======== + +L2TPv2 (PPP over L2TP (UDP tunnels)). +L2TPv3 ethernet pseudowires. +L2TPv3 PPP pseudowires. +L2TPv3 IP encapsulation. +Netlink sockets for L2TPv3 configuration management. + +History +======= + +The original pppol2tp driver was introduced in 2.6.23 and provided +L2TPv2 functionality (rfc2661). L2TPv2 is used to tunnel one or more PPP +sessions over a UDP tunnel. + +L2TPv3 (rfc3931) changes the protocol to allow different frame types +to be passed over an L2TP tunnel by moving the PPP-specific parts of +the protocol out of the core L2TP packet headers. Each frame type is +known as a pseudowire type. Ethernet, PPP, HDLC, Frame Relay and ATM +pseudowires for L2TP are defined in separate RFC standards. Another +change for L2TPv3 is that it can be carried directly over IP with no +UDP header (UDP is optional). It is also possible to create static +unmanaged L2TPv3 tunnels manually without a control protocol +(userspace daemon) to manage them. + +To support L2TPv3, the original pppol2tp driver was split up to +separate the L2TP and PPP functionality. Existing L2TPv2 userspace +apps should be unaffected as the original pppol2tp sockets API is +retained. L2TPv3, however, uses netlink to manage L2TPv3 tunnels and +sessions. Design ====== -The PPPoL2TP driver, drivers/net/pppol2tp.c, provides a mechanism by -which PPP frames carried through an L2TP session are passed through -the kernel's PPP subsystem. The standard PPP daemon, pppd, handles all -PPP interaction with the peer. PPP network interfaces are created for -each local PPP endpoint. - -The L2TP protocol http://www.faqs.org/rfcs/rfc2661.html defines L2TP -control and data frames. L2TP control frames carry messages between -L2TP clients/servers and are used to setup / teardown tunnels and -sessions. An L2TP client or server is implemented in userspace and -will use a regular UDP socket per tunnel. L2TP data frames carry PPP -frames, which may be PPP control or PPP data. The kernel's PPP +The L2TP protocol separates control and data frames. The L2TP kernel +drivers handle only L2TP data frames; control frames are always +handled by userspace. L2TP control frames carry messages between L2TP +clients/servers and are used to setup / teardown tunnels and +sessions. An L2TP client or server is implemented in userspace. + +Each L2TP tunnel is implemented using a UDP or L2TPIP socket; L2TPIP +provides L2TPv3 IP encapsulation (no UDP) and is implemented using a +new l2tpip socket family. The tunnel socket is typically created by +userspace, though for unmanaged L2TPv3 tunnels, the socket can also be +created by the kernel. Each L2TP session (pseudowire) gets a network +interface instance. In the case of PPP, these interfaces are created +indirectly by pppd using a pppol2tp socket. In the case of ethernet, +the netdevice is created upon a netlink request to create an L2TPv3 +ethernet pseudowire. + +For PPP, the PPPoL2TP driver, net/l2tp/l2tp_ppp.c, provides a +mechanism by which PPP frames carried through an L2TP session are +passed through the kernel's PPP subsystem. The standard PPP daemon, +pppd, handles all PPP interaction with the peer. PPP network +interfaces are created for each local PPP endpoint. The kernel's PPP subsystem arranges for PPP control frames to be delivered to pppd, while data frames are forwarded as usual. +For ethernet, the L2TPETH driver, net/l2tp/l2tp_eth.c, implements a +netdevice driver, managing virtual ethernet devices, one per +pseudowire. These interfaces can be managed using standard Linux tools +such as "ip" and "ifconfig". If only IP frames are passed over the +tunnel, the interface can be given an IP addresses of itself and its +peer. If non-IP frames are to be passed over the tunnel, the interface +can be added to a bridge using brctl. All L2TP datapath protocol +functions are handled by the L2TP core driver. + Each tunnel and session within a tunnel is assigned a unique tunnel_id and session_id. These ids are carried in the L2TP header of every -control and data packet. The pppol2tp driver uses them to lookup -internal tunnel and/or session contexts. Zero tunnel / session ids are -treated specially - zero ids are never assigned to tunnels or sessions -in the network. In the driver, the tunnel context keeps a pointer to -the tunnel UDP socket. The session context keeps a pointer to the -PPPoL2TP socket, as well as other data that lets the driver interface -to the kernel PPP subsystem. - -Note that the pppol2tp kernel driver handles only L2TP data frames; -L2TP control frames are simply passed up to userspace in the UDP -tunnel socket. The kernel handles all datapath aspects of the -protocol, including data packet resequencing (if enabled). - -There are a number of requirements on the userspace L2TP daemon in -order to use the pppol2tp driver. +control and data packet. (Actually, in L2TPv3, the tunnel_id isn't +present in data frames - it is inferred from the IP connection on +which the packet was received.) The L2TP driver uses the ids to lookup +internal tunnel and/or session contexts to determine how to handle the +packet. Zero tunnel / session ids are treated specially - zero ids are +never assigned to tunnels or sessions in the network. In the driver, +the tunnel context keeps a reference to the tunnel UDP or L2TPIP +socket. The session context holds data that lets the driver interface +to the kernel's network frame type subsystems, i.e. PPP, ethernet. + +Userspace Programming +===================== + +For L2TPv2, there are a number of requirements on the userspace L2TP +daemon in order to use the pppol2tp driver. 1. Use a UDP socket per tunnel. @@ -86,6 +137,35 @@ In addition to the standard PPP ioctls, a PPPIOCGL2TPSTATS is provided to retrieve tunnel and session statistics from the kernel using the PPPoX socket of the appropriate tunnel or session. +For L2TPv3, userspace must use the netlink API defined in +include/linux/l2tp.h to manage tunnel and session contexts. The +general procedure to create a new L2TP tunnel with one session is:- + +1. Open a GENL socket using L2TP_GENL_NAME for configuring the kernel + using netlink. + +2. Create a UDP or L2TPIP socket for the tunnel. + +3. Create a new L2TP tunnel using a L2TP_CMD_TUNNEL_CREATE + request. Set attributes according to desired tunnel parameters, + referencing the UDP or L2TPIP socket created in the previous step. + +4. Create a new L2TP session in the tunnel using a + L2TP_CMD_SESSION_CREATE request. + +The tunnel and all of its sessions are closed when the tunnel socket +is closed. The netlink API may also be used to delete sessions and +tunnels. Configuration and status info may be set or read using netlink. + +The L2TP driver also supports static (unmanaged) L2TPv3 tunnels. These +are where there is no L2TP control message exchange with the peer to +setup the tunnel; the tunnel is configured manually at each end of the +tunnel. There is no need for an L2TP userspace application in this +case -- the tunnel socket is created by the kernel and configured +using parameters sent in the L2TP_CMD_TUNNEL_CREATE netlink +request. The "ip" utility of iproute2 has commands for managing static +L2TPv3 tunnels; do "ip l2tp help" for more information. + Debugging ========= @@ -102,6 +182,69 @@ PPPOL2TP_MSG_CONTROL userspace - kernel interface PPPOL2TP_MSG_SEQ sequence numbers handling PPPOL2TP_MSG_DATA data packets +If enabled, files under a l2tp debugfs directory can be used to dump +kernel state about L2TP tunnels and sessions. To access it, the +debugfs filesystem must first be mounted. + +# mount -t debugfs debugfs /debug + +Files under the l2tp directory can then be accessed. + +# cat /debug/l2tp/tunnels + +The debugfs files should not be used by applications to obtain L2TP +state information because the file format is subject to change. It is +implemented to provide extra debug information to help diagnose +problems.) Users should use the netlink API. + +/proc/net/pppol2tp is also provided for backwards compaibility with +the original pppol2tp driver. It lists information about L2TPv2 +tunnels and sessions only. Its use is discouraged. + +Unmanaged L2TPv3 Tunnels +======================== + +Some commercial L2TP products support unmanaged L2TPv3 ethernet +tunnels, where there is no L2TP control protocol; tunnels are +configured at each side manually. New commands are available in +iproute2's ip utility to support this. + +To create an L2TPv3 ethernet pseudowire between local host 192.168.1.1 +and peer 192.168.1.2, using IP addresses 10.5.1.1 and 10.5.1.2 for the +tunnel endpoints:- + +# modprobe l2tp_eth +# modprobe l2tp_netlink + +# ip l2tp add tunnel tunnel_id 1 peer_tunnel_id 1 udp_sport 5000 \ + udp_dport 5000 encap udp local 192.168.1.1 remote 192.168.1.2 +# ip l2tp add session tunnel_id 1 session_id 1 peer_session_id 1 +# ifconfig -a +# ip addr add 10.5.1.2/32 peer 10.5.1.1/32 dev l2tpeth0 +# ifconfig l2tpeth0 up + +Choose IP addresses to be the address of a local IP interface and that +of the remote system. The IP addresses of the l2tpeth0 interface can be +anything suitable. + +Repeat the above at the peer, with ports, tunnel/session ids and IP +addresses reversed. The tunnel and session IDs can be any non-zero +32-bit number, but the values must be reversed at the peer. + +Host 1 Host2 +udp_sport=5000 udp_sport=5001 +udp_dport=5001 udp_dport=5000 +tunnel_id=42 tunnel_id=45 +peer_tunnel_id=45 peer_tunnel_id=42 +session_id=128 session_id=5196755 +peer_session_id=5196755 peer_session_id=128 + +When done at both ends of the tunnel, it should be possible to send +data over the network. e.g. + +# ping 10.5.1.1 + + Sample Userspace Code ===================== @@ -158,12 +301,48 @@ Sample Userspace Code } return 0; +Internal Implementation +======================= + +The driver keeps a struct l2tp_tunnel context per L2TP tunnel and a +struct l2tp_session context for each session. The l2tp_tunnel is +always associated with a UDP or L2TP/IP socket and keeps a list of +sessions in the tunnel. The l2tp_session context keeps kernel state +about the session. It has private data which is used for data specific +to the session type. With L2TPv2, the session always carried PPP +traffic. With L2TPv3, the session can also carry ethernet frames +(ethernet pseudowire) or other data types such as ATM, HDLC or Frame +Relay. + +When a tunnel is first opened, the reference count on the socket is +increased using sock_hold(). This ensures that the kernel socket +cannot be removed while L2TP's data structures reference it. + +Some L2TP sessions also have a socket (PPP pseudowires) while others +do not (ethernet pseudowires). We can't use the socket reference count +as the reference count for session contexts. The L2TP implementation +therefore has its own internal reference counts on the session +contexts. + +To Do +===== + +Add L2TP tunnel switching support. This would route tunneled traffic +from one L2TP tunnel into another. Specified in +http://tools.ietf.org/html/draft-ietf-l2tpext-tunnel-switching-08 + +Add L2TPv3 VLAN pseudowire support. + +Add L2TPv3 IP pseudowire support. + +Add L2TPv3 ATM pseudowire support. + Miscellaneous -============ +============= -The PPPoL2TP driver was developed as part of the OpenL2TP project by +The L2TP drivers were developed as part of the OpenL2TP project by Katalix Systems Ltd. OpenL2TP is a full-featured L2TP client / server, designed from the ground up to have the L2TP datapath in the kernel. The project also implemented the pppol2tp plugin for pppd which allows pppd to use the kernel driver. Details can be found at -http://openl2tp.sourceforge.net. +http://www.openl2tp.org. diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index 09ab0d290326..98f71a5cef00 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -100,7 +100,7 @@ by the kernel. The destruction of the socket and all associated resources is done by a simple call to close(fd). -Next I will describe PACKET_MMAP settings and it's constraints, +Next I will describe PACKET_MMAP settings and its constraints, also the mapping of the circular buffer in the user process and the use of this buffer. @@ -432,7 +432,7 @@ TP_STATUS_LOSING : indicates there were packet drops from last time the PACKET_STATISTICS option. TP_STATUS_CSUMNOTREADY: currently it's used for outgoing IP packets which - it's checksum will be done in hardware. So while + its checksum will be done in hardware. So while reading the packet we should not try to check the checksum. diff --git a/Documentation/networking/skfp.txt b/Documentation/networking/skfp.txt index abfddf81e34a..203ec66c9fb4 100644 --- a/Documentation/networking/skfp.txt +++ b/Documentation/networking/skfp.txt @@ -68,7 +68,7 @@ Compaq adapters (not tested): ======================= From v2.01 on, the driver is integrated in the linux kernel sources. -Therefor, the installation is the same as for any other adapter +Therefore, the installation is the same as for any other adapter supported by the kernel. Refer to the manual of your distribution about the installation of network adapters. diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt new file mode 100644 index 000000000000..7ee770b5ef5f --- /dev/null +++ b/Documentation/networking/stmmac.txt @@ -0,0 +1,143 @@ + STMicroelectronics 10/100/1000 Synopsys Ethernet driver + +Copyright (C) 2007-2010 STMicroelectronics Ltd +Author: Giuseppe Cavallaro <peppe.cavallaro@st.com> + +This is the driver for the MAC 10/100/1000 on-chip Ethernet controllers +(Synopsys IP blocks); it has been fully tested on STLinux platforms. + +Currently this network device driver is for all STM embedded MAC/GMAC +(7xxx SoCs). + +DWC Ether MAC 10/100/1000 Universal version 3.41a and DWC Ether MAC 10/100 +Universal version 4.0 have been used for developing the first code +implementation. + +Please, for more information also visit: www.stlinux.com + +1) Kernel Configuration +The kernel configuration option is STMMAC_ETH: + Device Drivers ---> Network device support ---> Ethernet (1000 Mbit) ---> + STMicroelectronics 10/100/1000 Ethernet driver (STMMAC_ETH) + +2) Driver parameters list: + debug: message level (0: no output, 16: all); + phyaddr: to manually provide the physical address to the PHY device; + dma_rxsize: DMA rx ring size; + dma_txsize: DMA tx ring size; + buf_sz: DMA buffer size; + tc: control the HW FIFO threshold; + tx_coe: Enable/Disable Tx Checksum Offload engine; + watchdog: transmit timeout (in milliseconds); + flow_ctrl: Flow control ability [on/off]; + pause: Flow Control Pause Time; + tmrate: timer period (only if timer optimisation is configured). + +3) Command line options +Driver parameters can be also passed in command line by using: + stmmaceth=dma_rxsize:128,dma_txsize:512 + +4) Driver information and notes + +4.1) Transmit process +The xmit method is invoked when the kernel needs to transmit a packet; it sets +the descriptors in the ring and informs the DMA engine that there is a packet +ready to be transmitted. +Once the controller has finished transmitting the packet, an interrupt is +triggered; So the driver will be able to release the socket buffers. +By default, the driver sets the NETIF_F_SG bit in the features field of the +net_device structure enabling the scatter/gather feature. + +4.2) Receive process +When one or more packets are received, an interrupt happens. The interrupts +are not queued so the driver has to scan all the descriptors in the ring during +the receive process. +This is based on NAPI so the interrupt handler signals only if there is work to be +done, and it exits. +Then the poll method will be scheduled at some future point. +The incoming packets are stored, by the DMA, in a list of pre-allocated socket +buffers in order to avoid the memcpy (Zero-copy). + +4.3) Timer-Driver Interrupt +Instead of having the device that asynchronously notifies the frame receptions, the +driver configures a timer to generate an interrupt at regular intervals. +Based on the granularity of the timer, the frames that are received by the device +will experience different levels of latency. Some NICs have dedicated timer +device to perform this task. STMMAC can use either the RTC device or the TMU +channel 2 on STLinux platforms. +The timers frequency can be passed to the driver as parameter; when change it, +take care of both hardware capability and network stability/performance impact. +Several performance tests on STM platforms showed this optimisation allows to spare +the CPU while having the maximum throughput. + +4.4) WOL +Wake up on Lan feature through Magic Frame is only supported for the GMAC +core. + +4.5) DMA descriptors +Driver handles both normal and enhanced descriptors. The latter has been only +tested on DWC Ether MAC 10/100/1000 Universal version 3.41a. + +4.6) Ethtool support +Ethtool is supported. Driver statistics and internal errors can be taken using: +ethtool -S ethX command. It is possible to dump registers etc. + +4.7) Jumbo and Segmentation Offloading +Jumbo frames are supported and tested for the GMAC. +The GSO has been also added but it's performed in software. +LRO is not supported. + +4.8) Physical +The driver is compatible with PAL to work with PHY and GPHY devices. + +4.9) Platform information +Several information came from the platform; please refer to the +driver's Header file in include/linux directory. + +struct plat_stmmacenet_data { + int bus_id; + int pbl; + int has_gmac; + void (*fix_mac_speed)(void *priv, unsigned int speed); + void (*bus_setup)(unsigned long ioaddr); +#ifdef CONFIG_STM_DRIVERS + struct stm_pad_config *pad_config; +#endif + void *bsp_priv; +}; + +Where: +- pbl (Programmable Burst Length) is maximum number of + beats to be transferred in one DMA transaction. + GMAC also enables the 4xPBL by default. +- fix_mac_speed and bus_setup are used to configure internal target + registers (on STM platforms); +- has_gmac: GMAC core is on board (get it at run-time in the next step); +- bus_id: bus identifier. + +struct plat_stmmacphy_data { + int bus_id; + int phy_addr; + unsigned int phy_mask; + int interface; + int (*phy_reset)(void *priv); + void *priv; +}; + +Where: +- bus_id: bus identifier; +- phy_addr: physical address used for the attached phy device; + set it to -1 to get it at run-time; +- interface: physical MII interface mode; +- phy_reset: hook to reset HW function. + +TODO: +- Continue to make the driver more generic and suitable for other Synopsys + Ethernet controllers used on other architectures (i.e. ARM). +- 10G controllers are not supported. +- MAC uses Normal descriptors and GMAC uses enhanced ones. + This is a limit that should be reviewed. MAC could want to + use the enhanced structure. +- Checksumming: Rx/Tx csum is done in HW in case of GMAC only. +- Review the timer optimisation code to use an embedded device that seems to be + available in new chip generations. diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 0e58b4539176..e8c8f4f06c67 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -41,11 +41,12 @@ SOF_TIMESTAMPING_SOFTWARE: return system time stamp generated in SOF_TIMESTAMPING_TX/RX determine how time stamps are generated. SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the following control message: - struct scm_timestamping { - struct timespec systime; - struct timespec hwtimetrans; - struct timespec hwtimeraw; - }; + +struct scm_timestamping { + struct timespec systime; + struct timespec hwtimetrans; + struct timespec hwtimeraw; +}; recvmsg() can be used to get this control message for regular incoming packets. For send time stamps the outgoing packet is looped back to @@ -87,12 +88,13 @@ by the network device and will be empty without that support. SIOCSHWTSTAMP: Hardware time stamping must also be initialized for each device driver -that is expected to do hardware time stamping. The parameter is: +that is expected to do hardware time stamping. The parameter is defined in +/include/linux/net_tstamp.h as: struct hwtstamp_config { - int flags; /* no flags defined right now, must be zero */ - int tx_type; /* HWTSTAMP_TX_* */ - int rx_filter; /* HWTSTAMP_FILTER_* */ + int flags; /* no flags defined right now, must be zero */ + int tx_type; /* HWTSTAMP_TX_* */ + int rx_filter; /* HWTSTAMP_FILTER_* */ }; Desired behavior is passed into the kernel and to a specific device by @@ -139,42 +141,56 @@ enum { /* time stamp any incoming packet */ HWTSTAMP_FILTER_ALL, - /* return value: time stamp all packets requested plus some others */ - HWTSTAMP_FILTER_SOME, + /* return value: time stamp all packets requested plus some others */ + HWTSTAMP_FILTER_SOME, /* PTP v1, UDP, any kind of event packet */ HWTSTAMP_FILTER_PTP_V1_L4_EVENT, - ... + /* for the complete list of values, please check + * the include file /include/linux/net_tstamp.h + */ }; DEVICE IMPLEMENTATION A driver which supports hardware time stamping must support the -SIOCSHWTSTAMP ioctl. Time stamps for received packets must be stored -in the skb with skb_hwtstamp_set(). +SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with +the actual values as described in the section on SIOCSHWTSTAMP. + +Time stamps for received packets must be stored in the skb. To get a pointer +to the shared time stamp structure of the skb call skb_hwtstamps(). Then +set the time stamps in the structure: + +struct skb_shared_hwtstamps { + /* hardware time stamp transformed into duration + * since arbitrary point in time + */ + ktime_t hwtstamp; + ktime_t syststamp; /* hwtstamp transformed to system time base */ +}; Time stamps for outgoing packets are to be generated as follows: -- In hard_start_xmit(), check if skb_hwtstamp_check_tx_hardware() - returns non-zero. If yes, then the driver is expected - to do hardware time stamping. +- In hard_start_xmit(), check if skb_tx(skb)->hardware is set no-zero. + If yes, then the driver is expected to do hardware time stamping. - If this is possible for the skb and requested, then declare - that the driver is doing the time stamping by calling - skb_hwtstamp_tx_in_progress(). A driver not supporting - hardware time stamping doesn't do that. A driver must never - touch sk_buff::tstamp! It is used to store how time stamping - for an outgoing packets is to be done. + that the driver is doing the time stamping by setting the field + skb_tx(skb)->in_progress non-zero. You might want to keep a pointer + to the associated skb for the next step and not free the skb. A driver + not supporting hardware time stamping doesn't do that. A driver must + never touch sk_buff::tstamp! It is used to store software generated + time stamps by the network subsystem. - As soon as the driver has sent the packet and/or obtained a hardware time stamp for it, it passes the time stamp back by calling skb_hwtstamp_tx() with the original skb, the raw - hardware time stamp and a handle to the device (necessary - to convert the hardware time stamp to system time). If obtaining - the hardware time stamp somehow fails, then the driver should - not fall back to software time stamping. The rationale is that - this would occur at a later time in the processing pipeline - than other software time stamping and therefore could lead - to unexpected deltas between time stamps. -- If the driver did not call skb_hwtstamp_tx_in_progress(), then + hardware time stamp. skb_hwtstamp_tx() clones the original skb and + adds the timestamps, therefore the original skb has to be freed now. + If obtaining the hardware time stamp somehow fails, then the driver + should not fall back to software time stamping. The rationale is that + this would occur at a later time in the processing pipeline than other + software time stamping and therefore could lead to unexpected deltas + between time stamps. +- If the driver did not call set skb_tx(skb)->in_progress, then dev_hard_start_xmit() checks whether software time stamping is wanted as fallback and potentially generates the time stamp. diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile index 2a1489fdc036..e79973443e9f 100644 --- a/Documentation/networking/timestamping/Makefile +++ b/Documentation/networking/timestamping/Makefile @@ -1,6 +1,13 @@ -CPPFLAGS = -I../../../include +# kbuild trick to avoid linker error. Can be omitted if a module is built. +obj- := dummy.o -timestamping: timestamping.c +# List of programs to build +hostprogs-y := timestamping + +# Tell kbuild to always build the programs +always := $(hostprogs-y) + +HOSTCFLAGS_timestamping.o += -I$(objtree)/usr/include clean: rm -f timestamping diff --git a/Documentation/networking/timestamping/timestamping.c b/Documentation/networking/timestamping/timestamping.c index a7936fe8444a..8ba82bfe6a33 100644 --- a/Documentation/networking/timestamping/timestamping.c +++ b/Documentation/networking/timestamping/timestamping.c @@ -41,9 +41,9 @@ #include <arpa/inet.h> #include <net/if.h> -#include "asm/types.h" -#include "linux/net_tstamp.h" -#include "linux/errqueue.h" +#include <asm/types.h> +#include <linux/net_tstamp.h> +#include <linux/errqueue.h> #ifndef SO_TIMESTAMPING # define SO_TIMESTAMPING 37 @@ -164,7 +164,7 @@ static void printpacket(struct msghdr *msg, int res, gettimeofday(&now, 0); - printf("%ld.%06ld: received %s data, %d bytes from %s, %d bytes control messages\n", + printf("%ld.%06ld: received %s data, %d bytes from %s, %zu bytes control messages\n", (long)now.tv_sec, (long)now.tv_usec, (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular", res, @@ -173,7 +173,7 @@ static void printpacket(struct msghdr *msg, int res, for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { - printf(" cmsg len %d: ", cmsg->cmsg_len); + printf(" cmsg len %zu: ", cmsg->cmsg_len); switch (cmsg->cmsg_level) { case SOL_SOCKET: printf("SOL_SOCKET "); @@ -370,7 +370,7 @@ int main(int argc, char **argv) } sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_UDP); - if (socket < 0) + if (sock < 0) bail("socket"); memset(&device, 0, sizeof(device)); diff --git a/Documentation/networking/x25-iface.txt b/Documentation/networking/x25-iface.txt index 975cc87ebdd1..78f662ee0622 100644 --- a/Documentation/networking/x25-iface.txt +++ b/Documentation/networking/x25-iface.txt @@ -20,23 +20,23 @@ the rest of the skbuff, if any more information does exist. Packet Layer to Device Driver ----------------------------- -First Byte = 0x00 +First Byte = 0x00 (X25_IFACE_DATA) This indicates that the rest of the skbuff contains data to be transmitted over the LAPB link. The LAPB link should already exist before any data is passed down. -First Byte = 0x01 +First Byte = 0x01 (X25_IFACE_CONNECT) Establish the LAPB link. If the link is already established then the connect confirmation message should be returned as soon as possible. -First Byte = 0x02 +First Byte = 0x02 (X25_IFACE_DISCONNECT) Terminate the LAPB link. If it is already disconnected then the disconnect confirmation message should be returned as soon as possible. -First Byte = 0x03 +First Byte = 0x03 (X25_IFACE_PARAMS) LAPB parameters. To be defined. @@ -44,22 +44,22 @@ LAPB parameters. To be defined. Device Driver to Packet Layer ----------------------------- -First Byte = 0x00 +First Byte = 0x00 (X25_IFACE_DATA) This indicates that the rest of the skbuff contains data that has been received over the LAPB link. -First Byte = 0x01 +First Byte = 0x01 (X25_IFACE_CONNECT) LAPB link has been established. The same message is used for both a LAPB link connect_confirmation and a connect_indication. -First Byte = 0x02 +First Byte = 0x02 (X25_IFACE_DISCONNECT) LAPB link has been terminated. This same message is used for both a LAPB link disconnect_confirmation and a disconnect_indication. -First Byte = 0x03 +First Byte = 0x03 (X25_IFACE_PARAMS) LAPB parameters. To be defined. diff --git a/Documentation/padata.txt b/Documentation/padata.txt new file mode 100644 index 000000000000..269d7d0d8335 --- /dev/null +++ b/Documentation/padata.txt @@ -0,0 +1,107 @@ +The padata parallel execution mechanism +Last updated for 2.6.34 + +Padata is a mechanism by which the kernel can farm work out to be done in +parallel on multiple CPUs while retaining the ordering of tasks. It was +developed for use with the IPsec code, which needs to be able to perform +encryption and decryption on large numbers of packets without reordering +those packets. The crypto developers made a point of writing padata in a +sufficiently general fashion that it could be put to other uses as well. + +The first step in using padata is to set up a padata_instance structure for +overall control of how tasks are to be run: + + #include <linux/padata.h> + + struct padata_instance *padata_alloc(const struct cpumask *cpumask, + struct workqueue_struct *wq); + +The cpumask describes which processors will be used to execute work +submitted to this instance. The workqueue wq is where the work will +actually be done; it should be a multithreaded queue, naturally. + +There are functions for enabling and disabling the instance: + + void padata_start(struct padata_instance *pinst); + void padata_stop(struct padata_instance *pinst); + +These functions literally do nothing beyond setting or clearing the +"padata_start() was called" flag; if that flag is not set, other functions +will refuse to work. + +The list of CPUs to be used can be adjusted with these functions: + + int padata_set_cpumask(struct padata_instance *pinst, + cpumask_var_t cpumask); + int padata_add_cpu(struct padata_instance *pinst, int cpu); + int padata_remove_cpu(struct padata_instance *pinst, int cpu); + +Changing the CPU mask has the look of an expensive operation, though, so it +probably should not be done with great frequency. + +Actually submitting work to the padata instance requires the creation of a +padata_priv structure: + + struct padata_priv { + /* Other stuff here... */ + void (*parallel)(struct padata_priv *padata); + void (*serial)(struct padata_priv *padata); + }; + +This structure will almost certainly be embedded within some larger +structure specific to the work to be done. Most its fields are private to +padata, but the structure should be zeroed at initialization time, and the +parallel() and serial() functions should be provided. Those functions will +be called in the process of getting the work done as we will see +momentarily. + +The submission of work is done with: + + int padata_do_parallel(struct padata_instance *pinst, + struct padata_priv *padata, int cb_cpu); + +The pinst and padata structures must be set up as described above; cb_cpu +specifies which CPU will be used for the final callback when the work is +done; it must be in the current instance's CPU mask. The return value from +padata_do_parallel() is a little strange; zero is an error return +indicating that the caller forgot the padata_start() formalities. -EBUSY +means that somebody, somewhere else is messing with the instance's CPU +mask, while -EINVAL is a complaint about cb_cpu not being in that CPU mask. +If all goes well, this function will return -EINPROGRESS, indicating that +the work is in progress. + +Each task submitted to padata_do_parallel() will, in turn, be passed to +exactly one call to the above-mentioned parallel() function, on one CPU, so +true parallelism is achieved by submitting multiple tasks. Despite the +fact that the workqueue is used to make these calls, parallel() is run with +software interrupts disabled and thus cannot sleep. The parallel() +function gets the padata_priv structure pointer as its lone parameter; +information about the actual work to be done is probably obtained by using +container_of() to find the enclosing structure. + +Note that parallel() has no return value; the padata subsystem assumes that +parallel() will take responsibility for the task from this point. The work +need not be completed during this call, but, if parallel() leaves work +outstanding, it should be prepared to be called again with a new job before +the previous one completes. When a task does complete, parallel() (or +whatever function actually finishes the job) should inform padata of the +fact with a call to: + + void padata_do_serial(struct padata_priv *padata); + +At some point in the future, padata_do_serial() will trigger a call to the +serial() function in the padata_priv structure. That call will happen on +the CPU requested in the initial call to padata_do_parallel(); it, too, is +done through the workqueue, but with local software interrupts disabled. +Note that this call may be deferred for a while since the padata code takes +pains to ensure that tasks are completed in the order in which they were +submitted. + +The one remaining function in the padata API should be called to clean up +when a padata instance is no longer needed: + + void padata_free(struct padata_instance *pinst); + +This function will busy-wait while any remaining tasks are completed, so it +might be best not to call it while there is work outstanding. Shutting +down the workqueue, if necessary, should be done separately. diff --git a/Documentation/pcmcia/driver-changes.txt b/Documentation/pcmcia/driver-changes.txt index 446f43b309df..61bc4e943116 100644 --- a/Documentation/pcmcia/driver-changes.txt +++ b/Documentation/pcmcia/driver-changes.txt @@ -1,4 +1,17 @@ This file details changes in 2.6 which affect PCMCIA card driver authors: +* No dev_node_t (as of 2.6.35) + There is no more need to fill out a "dev_node_t" structure. + +* New IRQ request rules (as of 2.6.35) + Instead of the old pcmcia_request_irq() interface, drivers may now + choose between: + - calling request_irq/free_irq directly. Use the IRQ from *p_dev->irq. + - use pcmcia_request_irq(p_dev, handler_t); the PCMCIA core will + clean up automatically on calls to pcmcia_disable_device() or + device ejection. + - drivers still not capable of IRQF_SHARED (or not telling us so) may + use the deprecated pcmcia_request_exclusive_irq() for the time + being; they might receive a shared IRQ nonetheless. * no cs_error / CS_CHECK / CONFIG_PCMCIA_DEBUG (as of 2.6.33) Instead of the cs_error() callback or the CS_CHECK() macro, please use diff --git a/Documentation/pnp.txt b/Documentation/pnp.txt index a327db67782a..763e4659bf18 100644 --- a/Documentation/pnp.txt +++ b/Documentation/pnp.txt @@ -57,7 +57,7 @@ PC standard floppy disk controller # cat resources DISABLED -- Notice the string "DISABLED". THis means the device is not active. +- Notice the string "DISABLED". This means the device is not active. 3.) check the device's possible configurations (optional) # cat options @@ -139,7 +139,7 @@ Plug and Play but it is planned to be in the near future. Requirements for a Linux PnP protocol: 1.) the protocol must use EISA IDs -2.) the protocol must inform the PnP Layer of a devices current configuration +2.) the protocol must inform the PnP Layer of a device's current configuration - the ability to set resources is optional but preferred. The following are PnP protocol related functions: @@ -158,7 +158,7 @@ pnp_remove_device - automatically will free mem used by the device and related structures pnp_add_id -- adds a EISA ID to the list of supported IDs for the specified device +- adds an EISA ID to the list of supported IDs for the specified device For more information consult the source of a protocol such as /drivers/pnp/pnpbios/core.c. @@ -167,7 +167,7 @@ For more information consult the source of a protocol such as Linux Plug and Play Drivers --------------------------- - This section contains information for linux PnP driver developers. + This section contains information for Linux PnP driver developers. The New Way ........... @@ -235,11 +235,10 @@ static int __init serial8250_pnp_init(void) The Old Way ........... -a series of compatibility functions have been created to make it easy to convert - +A series of compatibility functions have been created to make it easy to convert ISAPNP drivers. They should serve as a temporary solution only. -they are as follows: +They are as follows: struct pnp_card *pnp_find_card(unsigned short vendor, unsigned short device, diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt index c9abbd86bc18..57080cd74575 100644 --- a/Documentation/power/devices.txt +++ b/Documentation/power/devices.txt @@ -1,7 +1,13 @@ +Device Power Management + +Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. +Copyright (c) 2010 Alan Stern <stern@rowland.harvard.edu> + + Most of the code in Linux is device drivers, so most of the Linux power -management code is also driver-specific. Most drivers will do very little; -others, especially for platforms with small batteries (like cell phones), -will do a lot. +management (PM) code is also driver-specific. Most drivers will do very +little; others, especially for platforms with small batteries (like cell +phones), will do a lot. This writeup gives an overview of how drivers interact with system-wide power management goals, emphasizing the models and interfaces that are @@ -15,9 +21,10 @@ Drivers will use one or both of these models to put devices into low-power states: System Sleep model: - Drivers can enter low power states as part of entering system-wide - low-power states like "suspend-to-ram", or (mostly for systems with - disks) "hibernate" (suspend-to-disk). + Drivers can enter low-power states as part of entering system-wide + low-power states like "suspend" (also known as "suspend-to-RAM"), or + (mostly for systems with disks) "hibernation" (also known as + "suspend-to-disk"). This is something that device, bus, and class drivers collaborate on by implementing various role-specific suspend and resume methods to @@ -25,33 +32,41 @@ states: them without loss of data. Some drivers can manage hardware wakeup events, which make the system - leave that low-power state. This feature may be disabled using the - relevant /sys/devices/.../power/wakeup file; enabling it may cost some - power usage, but let the whole system enter low power states more often. + leave the low-power state. This feature may be enabled or disabled + using the relevant /sys/devices/.../power/wakeup file (for Ethernet + drivers the ioctl interface used by ethtool may also be used for this + purpose); enabling it may cost some power usage, but let the whole + system enter low-power states more often. Runtime Power Management model: - Drivers may also enter low power states while the system is running, - independently of other power management activity. Upstream drivers - will normally not know (or care) if the device is in some low power - state when issuing requests; the driver will auto-resume anything - that's needed when it gets a request. - - This doesn't have, or need much infrastructure; it's just something you - should do when writing your drivers. For example, clk_disable() unused - clocks as part of minimizing power drain for currently-unused hardware. - Of course, sometimes clusters of drivers will collaborate with each - other, which could involve task-specific power management. - -There's not a lot to be said about those low power states except that they -are very system-specific, and often device-specific. Also, that if enough -drivers put themselves into low power states (at "runtime"), the effect may be -the same as entering some system-wide low-power state (system sleep) ... and -that synergies exist, so that several drivers using runtime pm might put the -system into a state where even deeper power saving options are available. - -Most suspended devices will have quiesced all I/O: no more DMA or irqs, no -more data read or written, and requests from upstream drivers are no longer -accepted. A given bus or platform may have different requirements though. + Devices may also be put into low-power states while the system is + running, independently of other power management activity in principle. + However, devices are not generally independent of each other (for + example, a parent device cannot be suspended unless all of its child + devices have been suspended). Moreover, depending on the bus type the + device is on, it may be necessary to carry out some bus-specific + operations on the device for this purpose. Devices put into low power + states at run time may require special handling during system-wide power + transitions (suspend or hibernation). + + For these reasons not only the device driver itself, but also the + appropriate subsystem (bus type, device type or device class) driver and + the PM core are involved in runtime power management. As in the system + sleep power management case, they need to collaborate by implementing + various role-specific suspend and resume methods, so that the hardware + is cleanly powered down and reactivated without data or service loss. + +There's not a lot to be said about those low-power states except that they are +very system-specific, and often device-specific. Also, that if enough devices +have been put into low-power states (at runtime), the effect may be very similar +to entering some system-wide low-power state (system sleep) ... and that +synergies exist, so that several drivers using runtime PM might put the system +into a state where even deeper power saving options are available. + +Most suspended devices will have quiesced all I/O: no more DMA or IRQs (except +for wakeup events), no more data read or written, and requests from upstream +drivers are no longer accepted. A given bus or platform may have different +requirements though. Examples of hardware wakeup events include an alarm from a real time clock, network wake-on-LAN packets, keyboard or mouse activity, and media insertion @@ -60,129 +75,152 @@ or removal (for PCMCIA, MMC/SD, USB, and so on). Interfaces for Entering System Sleep States =========================================== -Most of the programming interfaces a device driver needs to know about -relate to that first model: entering a system-wide low power state, -rather than just minimizing power consumption by one device. - - -Bus Driver Methods ------------------- -The core methods to suspend and resume devices reside in struct bus_type. -These are mostly of interest to people writing infrastructure for busses -like PCI or USB, or because they define the primitives that device drivers -may need to apply in domain-specific ways to their devices: - -struct bus_type { - ... - int (*suspend)(struct device *dev, pm_message_t state); - int (*resume)(struct device *dev); +There are programming interfaces provided for subsystems (bus type, device type, +device class) and device drivers to allow them to participate in the power +management of devices they are concerned with. These interfaces cover both +system sleep and runtime power management. + + +Device Power Management Operations +---------------------------------- +Device power management operations, at the subsystem level as well as at the +device driver level, are implemented by defining and populating objects of type +struct dev_pm_ops: + +struct dev_pm_ops { + int (*prepare)(struct device *dev); + void (*complete)(struct device *dev); + int (*suspend)(struct device *dev); + int (*resume)(struct device *dev); + int (*freeze)(struct device *dev); + int (*thaw)(struct device *dev); + int (*poweroff)(struct device *dev); + int (*restore)(struct device *dev); + int (*suspend_noirq)(struct device *dev); + int (*resume_noirq)(struct device *dev); + int (*freeze_noirq)(struct device *dev); + int (*thaw_noirq)(struct device *dev); + int (*poweroff_noirq)(struct device *dev); + int (*restore_noirq)(struct device *dev); + int (*runtime_suspend)(struct device *dev); + int (*runtime_resume)(struct device *dev); + int (*runtime_idle)(struct device *dev); }; -Bus drivers implement those methods as appropriate for the hardware and -the drivers using it; PCI works differently from USB, and so on. Not many -people write bus drivers; most driver code is a "device driver" that -builds on top of bus-specific framework code. +This structure is defined in include/linux/pm.h and the methods included in it +are also described in that file. Their roles will be explained in what follows. +For now, it should be sufficient to remember that the last three methods are +specific to runtime power management while the remaining ones are used during +system-wide power transitions. -For more information on these driver calls, see the description later; -they are called in phases for every device, respecting the parent-child -sequencing in the driver model tree. Note that as this is being written, -only the suspend() and resume() are widely available; not many bus drivers -leverage all of those phases, or pass them down to lower driver levels. +There also is a deprecated "old" or "legacy" interface for power management +operations available at least for some subsystems. This approach does not use +struct dev_pm_ops objects and it is suitable only for implementing system sleep +power management methods. Therefore it is not described in this document, so +please refer directly to the source code for more information about it. -/sys/devices/.../power/wakeup files ------------------------------------ -All devices in the driver model have two flags to control handling of -wakeup events, which are hardware signals that can force the device and/or -system out of a low power state. These are initialized by bus or device -driver code using device_init_wakeup(dev,can_wakeup). +Subsystem-Level Methods +----------------------- +The core methods to suspend and resume devices reside in struct dev_pm_ops +pointed to by the pm member of struct bus_type, struct device_type and +struct class. They are mostly of interest to the people writing infrastructure +for buses, like PCI or USB, or device type and device class drivers. -The "can_wakeup" flag just records whether the device (and its driver) can -physically support wakeup events. When that flag is clear, the sysfs -"wakeup" file is empty, and device_may_wakeup() returns false. +Bus drivers implement these methods as appropriate for the hardware and the +drivers using it; PCI works differently from USB, and so on. Not many people +write subsystem-level drivers; most driver code is a "device driver" that builds +on top of bus-specific framework code. -For devices that can issue wakeup events, a separate flag controls whether -that device should try to use its wakeup mechanism. The initial value of -device_may_wakeup() will be true, so that the device's "wakeup" file holds -the value "enabled". Userspace can change that to "disabled" so that -device_may_wakeup() returns false; or change it back to "enabled" (so that -it returns true again). +For more information on these driver calls, see the description later; +they are called in phases for every device, respecting the parent-child +sequencing in the driver model tree. -EXAMPLE: PCI Device Driver Methods +/sys/devices/.../power/wakeup files ----------------------------------- -PCI framework software calls these methods when the PCI device driver bound -to a device device has provided them: - -struct pci_driver { - ... - int (*suspend)(struct pci_device *pdev, pm_message_t state); - int (*suspend_late)(struct pci_device *pdev, pm_message_t state); +All devices in the driver model have two flags to control handling of wakeup +events (hardware signals that can force the device and/or system out of a low +power state). These flags are initialized by bus or device driver code using +device_set_wakeup_capable() and device_set_wakeup_enable(), defined in +include/linux/pm_wakeup.h. - int (*resume_early)(struct pci_device *pdev); - int (*resume)(struct pci_device *pdev); -}; - -Drivers will implement those methods, and call PCI-specific procedures -like pci_set_power_state(), pci_enable_wake(), pci_save_state(), and -pci_restore_state() to manage PCI-specific mechanisms. (PCI config space -could be saved during driver probe, if it weren't for the fact that some -systems rely on userspace tweaking using setpci.) Devices are suspended -before their bridges enter low power states, and likewise bridges resume -before their devices. - - -Upper Layers of Driver Stacks ------------------------------ -Device drivers generally have at least two interfaces, and the methods -sketched above are the ones which apply to the lower level (nearer PCI, USB, -or other bus hardware). The network and block layers are examples of upper -level interfaces, as is a character device talking to userspace. - -Power management requests normally need to flow through those upper levels, -which often use domain-oriented requests like "blank that screen". In -some cases those upper levels will have power management intelligence that -relates to end-user activity, or other devices that work in cooperation. - -When those interfaces are structured using class interfaces, there is a -standard way to have the upper layer stop issuing requests to a given -class device (and restart later): - -struct class { - ... - int (*suspend)(struct device *dev, pm_message_t state); - int (*resume)(struct device *dev); -}; - -Those calls are issued in specific phases of the process by which the -system enters a low power "suspend" state, or resumes from it. - - -Calling Drivers to Enter System Sleep States -============================================ -When the system enters a low power state, each device's driver is asked -to suspend the device by putting it into state compatible with the target +The "can_wakeup" flag just records whether the device (and its driver) can +physically support wakeup events. The device_set_wakeup_capable() routine +affects this flag. The "should_wakeup" flag controls whether the device should +try to use its wakeup mechanism. device_set_wakeup_enable() affects this flag; +for the most part drivers should not change its value. The initial value of +should_wakeup is supposed to be false for the majority of devices; the major +exceptions are power buttons, keyboards, and Ethernet adapters whose WoL +(wake-on-LAN) feature has been set up with ethtool. + +Whether or not a device is capable of issuing wakeup events is a hardware +matter, and the kernel is responsible for keeping track of it. By contrast, +whether or not a wakeup-capable device should issue wakeup events is a policy +decision, and it is managed by user space through a sysfs attribute: the +power/wakeup file. User space can write the strings "enabled" or "disabled" to +set or clear the should_wakeup flag, respectively. Reads from the file will +return the corresponding string if can_wakeup is true, but if can_wakeup is +false then reads will return an empty string, to indicate that the device +doesn't support wakeup events. (But even though the file appears empty, writes +will still affect the should_wakeup flag.) + +The device_may_wakeup() routine returns true only if both flags are set. +Drivers should check this routine when putting devices in a low-power state +during a system sleep transition, to see whether or not to enable the devices' +wakeup mechanisms. However for runtime power management, wakeup events should +be enabled whenever the device and driver both support them, regardless of the +should_wakeup flag. + + +/sys/devices/.../power/control files +------------------------------------ +Each device in the driver model has a flag to control whether it is subject to +runtime power management. This flag, called runtime_auto, is initialized by the +bus type (or generally subsystem) code using pm_runtime_allow() or +pm_runtime_forbid(); the default is to allow runtime power management. + +The setting can be adjusted by user space by writing either "on" or "auto" to +the device's power/control sysfs file. Writing "auto" calls pm_runtime_allow(), +setting the flag and allowing the device to be runtime power-managed by its +driver. Writing "on" calls pm_runtime_forbid(), clearing the flag, returning +the device to full power if it was in a low-power state, and preventing the +device from being runtime power-managed. User space can check the current value +of the runtime_auto flag by reading the file. + +The device's runtime_auto flag has no effect on the handling of system-wide +power transitions. In particular, the device can (and in the majority of cases +should and will) be put into a low-power state during a system-wide transition +to a sleep state even though its runtime_auto flag is clear. + +For more information about the runtime power management framework, refer to +Documentation/power/runtime_pm.txt. + + +Calling Drivers to Enter and Leave System Sleep States +====================================================== +When the system goes into a sleep state, each device's driver is asked to +suspend the device by putting it into a state compatible with the target system state. That's usually some version of "off", but the details are system-specific. Also, wakeup-enabled devices will usually stay partly functional in order to wake the system. -When the system leaves that low power state, the device's driver is asked -to resume it. The suspend and resume operations always go together, and -both are multi-phase operations. +When the system leaves that low-power state, the device's driver is asked to +resume it by returning it to full power. The suspend and resume operations +always go together, and both are multi-phase operations. -For simple drivers, suspend might quiesce the device using the class code -and then turn its hardware as "off" as possible with late_suspend. The +For simple drivers, suspend might quiesce the device using class code +and then turn its hardware as "off" as possible during suspend_noirq. The matching resume calls would then completely reinitialize the hardware before reactivating its class I/O queues. -More power-aware drivers drivers will use more than one device low power -state, either at runtime or during system sleep states, and might trigger -system wakeup events. +More power-aware drivers might prepare the devices for triggering system wakeup +events. Call Sequence Guarantees ------------------------ -To ensure that bridges and similar links needed to talk to a device are +To ensure that bridges and similar links needing to talk to a device are available when the device is suspended or resumed, the device tree is walked in a bottom-up order to suspend devices. A top-down order is used to resume those devices. @@ -194,67 +232,310 @@ its parent; and can't be removed or suspended after that parent. The policy is that the device tree should match hardware bus topology. (Or at least the control bus, for devices which use multiple busses.) In particular, this means that a device registration may fail if the parent of -the device is suspending (ie. has been chosen by the PM core as the next +the device is suspending (i.e. has been chosen by the PM core as the next device to suspend) or has already suspended, as well as after all of the other devices have been suspended. Device drivers must be prepared to cope with such situations. -Suspending Devices ------------------- -Suspending a given device is done in several phases. Suspending the -system always includes every phase, executing calls for every device -before the next phase begins. Not all busses or classes support all -these callbacks; and not all drivers use all the callbacks. +System Power Management Phases +------------------------------ +Suspending or resuming the system is done in several phases. Different phases +are used for standby or memory sleep states ("suspend-to-RAM") and the +hibernation state ("suspend-to-disk"). Each phase involves executing callbacks +for every device before the next phase begins. Not all busses or classes +support all these callbacks and not all drivers use all the callbacks. The +various phases always run after tasks have been frozen and before they are +unfrozen. Furthermore, the *_noirq phases run at a time when IRQ handlers have +been disabled (except for those marked with the IRQ_WAKEUP flag). -The phases are seen by driver notifications issued in this order: +Most phases use bus, type, and class callbacks (that is, methods defined in +dev->bus->pm, dev->type->pm, and dev->class->pm). The prepare and complete +phases are exceptions; they use only bus callbacks. When multiple callbacks +are used in a phase, they are invoked in the order: <class, type, bus> during +power-down transitions and in the opposite order during power-up transitions. +For example, during the suspend phase the PM core invokes - 1 class.suspend(dev, message) is called after tasks are frozen, for - devices associated with a class that has such a method. This - method may sleep. + dev->class->pm.suspend(dev); + dev->type->pm.suspend(dev); + dev->bus->pm.suspend(dev); - Since I/O activity usually comes from such higher layers, this is - a good place to quiesce all drivers of a given type (and keep such - code out of those drivers). +before moving on to the next device, whereas during the resume phase the core +invokes - 2 bus.suspend(dev, message) is called next. This method may sleep, - and is often morphed into a device driver call with bus-specific - parameters and/or rules. + dev->bus->pm.resume(dev); + dev->type->pm.resume(dev); + dev->class->pm.resume(dev); - This call should handle parts of device suspend logic that require - sleeping. It probably does work to quiesce the device which hasn't - been abstracted into class.suspend(). +These callbacks may in turn invoke device- or driver-specific methods stored in +dev->driver->pm, but they don't have to. -The pm_message_t parameter is currently used to refine those semantics -(described later). -At the end of those phases, drivers should normally have stopped all I/O -transactions (DMA, IRQs), saved enough state that they can re-initialize -or restore previous state (as needed by the hardware), and placed the -device into a low-power state. On many platforms they will also use -clk_disable() to gate off one or more clock sources; sometimes they will -also switch off power supplies, or reduce voltages. Drivers which have -runtime PM support may already have performed some or all of the steps -needed to prepare for the upcoming system sleep state. +Entering System Suspend +----------------------- +When the system goes into the standby or memory sleep state, the phases are: + + prepare, suspend, suspend_noirq. + + 1. The prepare phase is meant to prevent races by preventing new devices + from being registered; the PM core would never know that all the + children of a device had been suspended if new children could be + registered at will. (By contrast, devices may be unregistered at any + time.) Unlike the other suspend-related phases, during the prepare + phase the device tree is traversed top-down. + + The prepare phase uses only a bus callback. After the callback method + returns, no new children may be registered below the device. The method + may also prepare the device or driver in some way for the upcoming + system power transition, but it should not put the device into a + low-power state. + + 2. The suspend methods should quiesce the device to stop it from performing + I/O. They also may save the device registers and put it into the + appropriate low-power state, depending on the bus type the device is on, + and they may enable wakeup events. + + 3. The suspend_noirq phase occurs after IRQ handlers have been disabled, + which means that the driver's interrupt handler will not be called while + the callback method is running. The methods should save the values of + the device's registers that weren't saved previously and finally put the + device into the appropriate low-power state. + + The majority of subsystems and device drivers need not implement this + callback. However, bus types allowing devices to share interrupt + vectors, like PCI, generally need it; otherwise a driver might encounter + an error during the suspend phase by fielding a shared interrupt + generated by some other device after its own device had been set to low + power. + +At the end of these phases, drivers should have stopped all I/O transactions +(DMA, IRQs), saved enough state that they can re-initialize or restore previous +state (as needed by the hardware), and placed the device into a low-power state. +On many platforms they will gate off one or more clock sources; sometimes they +will also switch off power supplies or reduce voltages. (Drivers supporting +runtime PM may already have performed some or all of these steps.) + +If device_may_wakeup(dev) returns true, the device should be prepared for +generating hardware wakeup signals to trigger a system wakeup event when the +system is in the sleep state. For example, enable_irq_wake() might identify +GPIO signals hooked up to a switch or other external hardware, and +pci_enable_wake() does something similar for the PCI PME signal. + +If any of these callbacks returns an error, the system won't enter the desired +low-power state. Instead the PM core will unwind its actions by resuming all +the devices that were suspended. + + +Leaving System Suspend +---------------------- +When resuming from standby or memory sleep, the phases are: + + resume_noirq, resume, complete. + + 1. The resume_noirq callback methods should perform any actions needed + before the driver's interrupt handlers are invoked. This generally + means undoing the actions of the suspend_noirq phase. If the bus type + permits devices to share interrupt vectors, like PCI, the method should + bring the device and its driver into a state in which the driver can + recognize if the device is the source of incoming interrupts, if any, + and handle them correctly. + + For example, the PCI bus type's ->pm.resume_noirq() puts the device into + the full-power state (D0 in the PCI terminology) and restores the + standard configuration registers of the device. Then it calls the + device driver's ->pm.resume_noirq() method to perform device-specific + actions. + + 2. The resume methods should bring the the device back to its operating + state, so that it can perform normal I/O. This generally involves + undoing the actions of the suspend phase. + + 3. The complete phase uses only a bus callback. The method should undo the + actions of the prepare phase. Note, however, that new children may be + registered below the device as soon as the resume callbacks occur; it's + not necessary to wait until the complete phase. + +At the end of these phases, drivers should be as functional as they were before +suspending: I/O can be performed using DMA and IRQs, and the relevant clocks are +gated on. Even if the device was in a low-power state before the system sleep +because of runtime power management, afterwards it should be back in its +full-power state. There are multiple reasons why it's best to do this; they are +discussed in more detail in Documentation/power/runtime_pm.txt. -When any driver sees that its device_can_wakeup(dev), it should make sure -to use the relevant hardware signals to trigger a system wakeup event. -For example, enable_irq_wake() might identify GPIO signals hooked up to -a switch or other external hardware, and pci_enable_wake() does something -similar for PCI's PME# signal. +However, the details here may again be platform-specific. For example, +some systems support multiple "run" states, and the mode in effect at +the end of resume might not be the one which preceded suspension. +That means availability of certain clocks or power supplies changed, +which could easily affect how a driver works. + +Drivers need to be able to handle hardware which has been reset since the +suspend methods were called, for example by complete reinitialization. +This may be the hardest part, and the one most protected by NDA'd documents +and chip errata. It's simplest if the hardware state hasn't changed since +the suspend was carried out, but that can't be guaranteed (in fact, it ususally +is not the case). + +Drivers must also be prepared to notice that the device has been removed +while the system was powered down, whenever that's physically possible. +PCMCIA, MMC, USB, Firewire, SCSI, and even IDE are common examples of busses +where common Linux platforms will see such removal. Details of how drivers +will notice and handle such removals are currently bus-specific, and often +involve a separate thread. + +These callbacks may return an error value, but the PM core will ignore such +errors since there's nothing it can do about them other than printing them in +the system log. + + +Entering Hibernation +-------------------- +Hibernating the system is more complicated than putting it into the standby or +memory sleep state, because it involves creating and saving a system image. +Therefore there are more phases for hibernation, with a different set of +callbacks. These phases always run after tasks have been frozen and memory has +been freed. + +The general procedure for hibernation is to quiesce all devices (freeze), create +an image of the system memory while everything is stable, reactivate all +devices (thaw), write the image to permanent storage, and finally shut down the +system (poweroff). The phases used to accomplish this are: + + prepare, freeze, freeze_noirq, thaw_noirq, thaw, complete, + prepare, poweroff, poweroff_noirq + + 1. The prepare phase is discussed in the "Entering System Suspend" section + above. + + 2. The freeze methods should quiesce the device so that it doesn't generate + IRQs or DMA, and they may need to save the values of device registers. + However the device does not have to be put in a low-power state, and to + save time it's best not to do so. Also, the device should not be + prepared to generate wakeup events. + + 3. The freeze_noirq phase is analogous to the suspend_noirq phase discussed + above, except again that the device should not be put in a low-power + state and should not be allowed to generate wakeup events. + +At this point the system image is created. All devices should be inactive and +the contents of memory should remain undisturbed while this happens, so that the +image forms an atomic snapshot of the system state. + + 4. The thaw_noirq phase is analogous to the resume_noirq phase discussed + above. The main difference is that its methods can assume the device is + in the same state as at the end of the freeze_noirq phase. + + 5. The thaw phase is analogous to the resume phase discussed above. Its + methods should bring the device back to an operating state, so that it + can be used for saving the image if necessary. + + 6. The complete phase is discussed in the "Leaving System Suspend" section + above. + +At this point the system image is saved, and the devices then need to be +prepared for the upcoming system shutdown. This is much like suspending them +before putting the system into the standby or memory sleep state, and the phases +are similar. + + 7. The prepare phase is discussed above. + + 8. The poweroff phase is analogous to the suspend phase. + + 9. The poweroff_noirq phase is analogous to the suspend_noirq phase. + +The poweroff and poweroff_noirq callbacks should do essentially the same things +as the suspend and suspend_noirq callbacks. The only notable difference is that +they need not store the device register values, because the registers should +already have been stored during the freeze or freeze_noirq phases. + + +Leaving Hibernation +------------------- +Resuming from hibernation is, again, more complicated than resuming from a sleep +state in which the contents of main memory are preserved, because it requires +a system image to be loaded into memory and the pre-hibernation memory contents +to be restored before control can be passed back to the image kernel. + +Although in principle, the image might be loaded into memory and the +pre-hibernation memory contents restored by the boot loader, in practice this +can't be done because boot loaders aren't smart enough and there is no +established protocol for passing the necessary information. So instead, the +boot loader loads a fresh instance of the kernel, called the boot kernel, into +memory and passes control to it in the usual way. Then the boot kernel reads +the system image, restores the pre-hibernation memory contents, and passes +control to the image kernel. Thus two different kernels are involved in +resuming from hibernation. In fact, the boot kernel may be completely different +from the image kernel: a different configuration and even a different version. +This has important consequences for device drivers and their subsystems. + +To be able to load the system image into memory, the boot kernel needs to +include at least a subset of device drivers allowing it to access the storage +medium containing the image, although it doesn't need to include all of the +drivers present in the image kernel. After the image has been loaded, the +devices managed by the boot kernel need to be prepared for passing control back +to the image kernel. This is very similar to the initial steps involved in +creating a system image, and it is accomplished in the same way, using prepare, +freeze, and freeze_noirq phases. However the devices affected by these phases +are only those having drivers in the boot kernel; other devices will still be in +whatever state the boot loader left them. + +Should the restoration of the pre-hibernation memory contents fail, the boot +kernel would go through the "thawing" procedure described above, using the +thaw_noirq, thaw, and complete phases, and then continue running normally. This +happens only rarely. Most often the pre-hibernation memory contents are +restored successfully and control is passed to the image kernel, which then +becomes responsible for bringing the system back to the working state. + +To achieve this, the image kernel must restore the devices' pre-hibernation +functionality. The operation is much like waking up from the memory sleep +state, although it involves different phases: + + restore_noirq, restore, complete + + 1. The restore_noirq phase is analogous to the resume_noirq phase. + + 2. The restore phase is analogous to the resume phase. + + 3. The complete phase is discussed above. + +The main difference from resume[_noirq] is that restore[_noirq] must assume the +device has been accessed and reconfigured by the boot loader or the boot kernel. +Consequently the state of the device may be different from the state remembered +from the freeze and freeze_noirq phases. The device may even need to be reset +and completely re-initialized. In many cases this difference doesn't matter, so +the resume[_noirq] and restore[_norq] method pointers can be set to the same +routines. Nevertheless, different callback pointers are used in case there is a +situation where it actually matters. -If a driver (or bus, or class) fails it suspend method, the system won't -enter the desired low power state; it will resume all the devices it's -suspended so far. -Note that drivers may need to perform different actions based on the target -system lowpower/sleep state. At this writing, there are only platform -specific APIs through which drivers could determine those target states. +System Devices +-------------- +System devices (sysdevs) follow a slightly different API, which can be found in + + include/linux/sysdev.h + drivers/base/sys.c + +System devices will be suspended with interrupts disabled, and after all other +devices have been suspended. On resume, they will be resumed before any other +devices, and also with interrupts disabled. These things occur in special +"sysdev_driver" phases, which affect only system devices. + +Thus, after the suspend_noirq (or freeze_noirq or poweroff_noirq) phase, when +the non-boot CPUs are all offline and IRQs are disabled on the remaining online +CPU, then a sysdev_driver.suspend phase is carried out, and the system enters a +sleep state (or a system image is created). During resume (or after the image +has been created or loaded) a sysdev_driver.resume phase is carried out, IRQs +are enabled on the only online CPU, the non-boot CPUs are enabled, and the +resume_noirq (or thaw_noirq or restore_noirq) phase begins. + +Code to actually enter and exit the system-wide low power state sometimes +involves hardware details that are only known to the boot firmware, and +may leave a CPU running software (from SRAM or flash memory) that monitors +the system and manages its wakeup sequence. Device Low Power (suspend) States --------------------------------- -Device low-power states aren't very standard. One device might only handle +Device low-power states aren't standard. One device might only handle "on" and "off, while another might support a dozen different versions of "on" (how many engines are active?), plus a state that gets back to "on" faster than from a full "off". @@ -265,7 +546,7 @@ PCI device may not perform DMA or issue IRQs, and any wakeup events it issues would be issued through the PME# bus signal. Plus, there are several PCI-standard device states, some of which are optional. -In contrast, integrated system-on-chip processors often use irqs as the +In contrast, integrated system-on-chip processors often use IRQs as the wakeup event sources (so drivers would call enable_irq_wake) and might be able to treat DMA completion as a wakeup event (sometimes DMA can stay active too, it'd only be the CPU and some peripherals that sleep). @@ -284,120 +565,17 @@ ways; the aforementioned LCD might be active in one product's "standby", but a different product using the same SOC might work differently. -Meaning of pm_message_t.event ------------------------------ -Parameters to suspend calls include the device affected and a message of -type pm_message_t, which has one field: the event. If driver does not -recognize the event code, suspend calls may abort the request and return -a negative errno. However, most drivers will be fine if they implement -PM_EVENT_SUSPEND semantics for all messages. +Power Management Notifiers +-------------------------- +There are some operations that cannot be carried out by the power management +callbacks discussed above, because the callbacks occur too late or too early. +To handle these cases, subsystems and device drivers may register power +management notifiers that are called before tasks are frozen and after they have +been thawed. Generally speaking, the PM notifiers are suitable for performing +actions that either require user space to be available, or at least won't +interfere with user space. -The event codes are used to refine the goal of suspending the device, and -mostly matter when creating or resuming system memory image snapshots, as -used with suspend-to-disk: - - PM_EVENT_SUSPEND -- quiesce the driver and put hardware into a low-power - state. When used with system sleep states like "suspend-to-RAM" or - "standby", the upcoming resume() call will often be able to rely on - state kept in hardware, or issue system wakeup events. - - PM_EVENT_HIBERNATE -- Put hardware into a low-power state and enable wakeup - events as appropriate. It is only used with hibernation - (suspend-to-disk) and few devices are able to wake up the system from - this state; most are completely powered off. - - PM_EVENT_FREEZE -- quiesce the driver, but don't necessarily change into - any low power mode. A system snapshot is about to be taken, often - followed by a call to the driver's resume() method. Neither wakeup - events nor DMA are allowed. - - PM_EVENT_PRETHAW -- quiesce the driver, knowing that the upcoming resume() - will restore a suspend-to-disk snapshot from a different kernel image. - Drivers that are smart enough to look at their hardware state during - resume() processing need that state to be correct ... a PRETHAW could - be used to invalidate that state (by resetting the device), like a - shutdown() invocation would before a kexec() or system halt. Other - drivers might handle this the same way as PM_EVENT_FREEZE. Neither - wakeup events nor DMA are allowed. - -To enter "standby" (ACPI S1) or "Suspend to RAM" (STR, ACPI S3) states, or -the similarly named APM states, only PM_EVENT_SUSPEND is used; the other event -codes are used for hibernation ("Suspend to Disk", STD, ACPI S4). - -There's also PM_EVENT_ON, a value which never appears as a suspend event -but is sometimes used to record the "not suspended" device state. - - -Resuming Devices ----------------- -Resuming is done in multiple phases, much like suspending, with all -devices processing each phase's calls before the next phase begins. - -The phases are seen by driver notifications issued in this order: - - 1 bus.resume(dev) reverses the effects of bus.suspend(). This may - be morphed into a device driver call with bus-specific parameters; - implementations may sleep. - - 2 class.resume(dev) is called for devices associated with a class - that has such a method. Implementations may sleep. - - This reverses the effects of class.suspend(), and would usually - reactivate the device's I/O queue. - -At the end of those phases, drivers should normally be as functional as -they were before suspending: I/O can be performed using DMA and IRQs, and -the relevant clocks are gated on. The device need not be "fully on"; it -might be in a runtime lowpower/suspend state that acts as if it were. - -However, the details here may again be platform-specific. For example, -some systems support multiple "run" states, and the mode in effect at -the end of resume() might not be the one which preceded suspension. -That means availability of certain clocks or power supplies changed, -which could easily affect how a driver works. - - -Drivers need to be able to handle hardware which has been reset since the -suspend methods were called, for example by complete reinitialization. -This may be the hardest part, and the one most protected by NDA'd documents -and chip errata. It's simplest if the hardware state hasn't changed since -the suspend() was called, but that can't always be guaranteed. - -Drivers must also be prepared to notice that the device has been removed -while the system was powered off, whenever that's physically possible. -PCMCIA, MMC, USB, Firewire, SCSI, and even IDE are common examples of busses -where common Linux platforms will see such removal. Details of how drivers -will notice and handle such removals are currently bus-specific, and often -involve a separate thread. - - -Note that the bus-specific runtime PM wakeup mechanism can exist, and might -be defined to share some of the same driver code as for system wakeup. For -example, a bus-specific device driver's resume() method might be used there, -so it wouldn't only be called from bus.resume() during system-wide wakeup. -See bus-specific information about how runtime wakeup events are handled. - - -System Devices --------------- -System devices follow a slightly different API, which can be found in - - include/linux/sysdev.h - drivers/base/sys.c - -System devices will only be suspended with interrupts disabled, and after -all other devices have been suspended. On resume, they will be resumed -before any other devices, and also with interrupts disabled. - -That is, IRQs are disabled, the suspend_late() phase begins, then the -sysdev_driver.suspend() phase, and the system enters a sleep state. Then -the sysdev_driver.resume() phase begins, followed by the resume_early() -phase, after which IRQs are enabled. - -Code to actually enter and exit the system-wide low power state sometimes -involves hardware details that are only known to the boot firmware, and -may leave a CPU running software (from SRAM or flash memory) that monitors -the system and manages its wakeup sequence. +For details refer to Documentation/power/notifiers.txt. Runtime Power Management @@ -407,82 +585,23 @@ running. This feature is useful for devices that are not being used, and can offer significant power savings on a running system. These devices often support a range of runtime power states, which might use names such as "off", "sleep", "idle", "active", and so on. Those states will in some -cases (like PCI) be partially constrained by a bus the device uses, and will +cases (like PCI) be partially constrained by the bus the device uses, and will usually include hardware states that are also used in system sleep states. -However, note that if a driver puts a device into a runtime low power state -and the system then goes into a system-wide sleep state, it normally ought -to resume into that runtime low power state rather than "full on". Such -distinctions would be part of the driver-internal state machine for that -hardware; the whole point of runtime power management is to be sure that -drivers are decoupled in that way from the state machine governing phases -of the system-wide power/sleep state transitions. - - -Power Saving Techniques ------------------------ -Normally runtime power management is handled by the drivers without specific -userspace or kernel intervention, by device-aware use of techniques like: - - Using information provided by other system layers - - stay deeply "off" except between open() and close() - - if transceiver/PHY indicates "nobody connected", stay "off" - - application protocols may include power commands or hints - - Using fewer CPU cycles - - using DMA instead of PIO - - removing timers, or making them lower frequency - - shortening "hot" code paths - - eliminating cache misses - - (sometimes) offloading work to device firmware - - Reducing other resource costs - - gating off unused clocks in software (or hardware) - - switching off unused power supplies - - eliminating (or delaying/merging) IRQs - - tuning DMA to use word and/or burst modes - - Using device-specific low power states - - using lower voltages - - avoiding needless DMA transfers - -Read your hardware documentation carefully to see the opportunities that -may be available. If you can, measure the actual power usage and check -it against the budget established for your project. - - -Examples: USB hosts, system timer, system CPU ----------------------------------------------- -USB host controllers make interesting, if complex, examples. In many cases -these have no work to do: no USB devices are connected, or all of them are -in the USB "suspend" state. Linux host controller drivers can then disable -periodic DMA transfers that would otherwise be a constant power drain on the -memory subsystem, and enter a suspend state. In power-aware controllers, -entering that suspend state may disable the clock used with USB signaling, -saving a certain amount of power. - -The controller will be woken from that state (with an IRQ) by changes to the -signal state on the data lines of a given port, for example by an existing -peripheral requesting "remote wakeup" or by plugging a new peripheral. The -same wakeup mechanism usually works from "standby" sleep states, and on some -systems also from "suspend to RAM" (or even "suspend to disk") states. -(Except that ACPI may be involved instead of normal IRQs, on some hardware.) - -System devices like timers and CPUs may have special roles in the platform -power management scheme. For example, system timers using a "dynamic tick" -approach don't just save CPU cycles (by eliminating needless timer IRQs), -but they may also open the door to using lower power CPU "idle" states that -cost more than a jiffie to enter and exit. On x86 systems these are states -like "C3"; note that periodic DMA transfers from a USB host controller will -also prevent entry to a C3 state, much like a periodic timer IRQ. - -That kind of runtime mechanism interaction is common. "System On Chip" (SOC) -processors often have low power idle modes that can't be entered unless -certain medium-speed clocks (often 12 or 48 MHz) are gated off. When the -drivers gate those clocks effectively, then the system idle task may be able -to use the lower power idle modes and thereby increase battery life. - -If the CPU can have a "cpufreq" driver, there also may be opportunities -to shift to lower voltage settings and reduce the power cost of executing -a given number of instructions. (Without voltage adjustment, it's rare -for cpufreq to save much power; the cost-per-instruction must go down.) +A system-wide power transition can be started while some devices are in low +power states due to runtime power management. The system sleep PM callbacks +should recognize such situations and react to them appropriately, but the +necessary actions are subsystem-specific. + +In some cases the decision may be made at the subsystem level while in other +cases the device driver may be left to decide. In some cases it may be +desirable to leave a suspended device in that state during a system-wide power +transition, but in other cases the device must be put back into the full-power +state temporarily, for example so that its system wakeup capability can be +disabled. This all depends on the hardware and the design of the subsystem and +device driver in question. + +During system-wide resume from a sleep state it's best to put devices into the +full-power state, as explained in Documentation/power/runtime_pm.txt. Refer to +that document for more information regarding this particular issue as well as +for information on the device runtime power management framework in general. diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt index c40866e8b957..bfed898a03fc 100644 --- a/Documentation/power/pm_qos_interface.txt +++ b/Documentation/power/pm_qos_interface.txt @@ -18,44 +18,46 @@ and pm_qos_params.h. This is done because having the available parameters being runtime configurable or changeable from a driver was seen as too easy to abuse. -For each parameter a list of performance requirements is maintained along with +For each parameter a list of performance requests is maintained along with an aggregated target value. The aggregated target value is updated with -changes to the requirement list or elements of the list. Typically the -aggregated target value is simply the max or min of the requirement values held +changes to the request list or elements of the list. Typically the +aggregated target value is simply the max or min of the request values held in the parameter list elements. From kernel mode the use of this interface is simple: -pm_qos_add_requirement(param_id, name, target_value): -Will insert a named element in the list for that identified PM_QOS parameter -with the target value. Upon change to this list the new target is recomputed -and any registered notifiers are called only if the target value is now -different. -pm_qos_update_requirement(param_id, name, new_target_value): -Will search the list identified by the param_id for the named list element and -then update its target value, calling the notification tree if the aggregated -target is changed. with that name is already registered. +handle = pm_qos_add_request(param_class, target_value): +Will insert an element into the list for that identified PM_QOS class with the +target value. Upon change to this list the new target is recomputed and any +registered notifiers are called only if the target value is now different. +Clients of pm_qos need to save the returned handle. -pm_qos_remove_requirement(param_id, name): -Will search the identified list for the named element and remove it, after -removal it will update the aggregate target and call the notification tree if -the target was changed as a result of removing the named requirement. +void pm_qos_update_request(handle, new_target_value): +Will update the list element pointed to by the handle with the new target value +and recompute the new aggregated target, calling the notification tree if the +target is changed. + +void pm_qos_remove_request(handle): +Will remove the element. After removal it will update the aggregate target and +call the notification tree if the target was changed as a result of removing +the request. From user mode: -Only processes can register a pm_qos requirement. To provide for automatic -cleanup for process the interface requires the process to register its -parameter requirements in the following way: +Only processes can register a pm_qos request. To provide for automatic +cleanup of a process, the interface requires the process to register its +parameter requests in the following way: To register the default pm_qos target for the specific parameter, the process must open one of /dev/[cpu_dma_latency, network_latency, network_throughput] As long as the device node is held open that process has a registered -requirement on the parameter. The name of the requirement is "process_<PID>" -derived from the current->pid from within the open system call. +request on the parameter. -To change the requested target value the process needs to write a s32 value to -the open device node. This translates to a pm_qos_update_requirement call. +To change the requested target value the process needs to write an s32 value to +the open device node. Alternatively the user mode program could write a hex +string for the value using 10 char long format e.g. "0x12345678". This +translates to a pm_qos_update_request call. To remove the user mode request for a target value simply close the device node. diff --git a/Documentation/power/regulator/consumer.txt b/Documentation/power/regulator/consumer.txt index cdebb5145c25..55c4175d8099 100644 --- a/Documentation/power/regulator/consumer.txt +++ b/Documentation/power/regulator/consumer.txt @@ -8,11 +8,11 @@ Please see overview.txt for a description of the terms used in this text. 1. Consumer Regulator Access (static & dynamic drivers) ======================================================= -A consumer driver can get access to it's supply regulator by calling :- +A consumer driver can get access to its supply regulator by calling :- regulator = regulator_get(dev, "Vcc"); -The consumer passes in it's struct device pointer and power supply ID. The core +The consumer passes in its struct device pointer and power supply ID. The core then finds the correct regulator by consulting a machine specific lookup table. If the lookup is successful then this call will return a pointer to the struct regulator that supplies this consumer. @@ -34,7 +34,7 @@ usually be called in your device drivers probe() and remove() respectively. 2. Regulator Output Enable & Disable (static & dynamic drivers) ==================================================================== -A consumer can enable it's power supply by calling:- +A consumer can enable its power supply by calling:- int regulator_enable(regulator); @@ -49,7 +49,7 @@ int regulator_is_enabled(regulator); This will return > zero when the regulator is enabled. -A consumer can disable it's supply when no longer needed by calling :- +A consumer can disable its supply when no longer needed by calling :- int regulator_disable(regulator); @@ -140,7 +140,7 @@ by calling :- int regulator_set_optimum_mode(struct regulator *regulator, int load_uA); This will cause the core to recalculate the total load on the regulator (based -on all it's consumers) and change operating mode (if necessary and permitted) +on all its consumers) and change operating mode (if necessary and permitted) to best match the current operating load. The load_uA value can be determined from the consumers datasheet. e.g.most diff --git a/Documentation/power/regulator/machine.txt b/Documentation/power/regulator/machine.txt index 63728fed620b..bdec39b9bd75 100644 --- a/Documentation/power/regulator/machine.txt +++ b/Documentation/power/regulator/machine.txt @@ -52,7 +52,7 @@ static struct regulator_init_data regulator1_data = { }; Regulator-1 supplies power to Regulator-2. This relationship must be registered -with the core so that Regulator-1 is also enabled when Consumer A enables it's +with the core so that Regulator-1 is also enabled when Consumer A enables its supply (Regulator-2). The supply regulator is set by the supply_regulator_dev field below:- diff --git a/Documentation/power/regulator/overview.txt b/Documentation/power/regulator/overview.txt index ffd185bb6054..9363e056188a 100644 --- a/Documentation/power/regulator/overview.txt +++ b/Documentation/power/regulator/overview.txt @@ -35,16 +35,16 @@ Some terms used in this document:- o Consumer - Electronic device that is supplied power by a regulator. Consumers can be classified into two types:- - Static: consumer does not change it's supply voltage or + Static: consumer does not change its supply voltage or current limit. It only needs to enable or disable it's - power supply. It's supply voltage is set by the hardware, + power supply. Its supply voltage is set by the hardware, bootloader, firmware or kernel board initialisation code. Dynamic: consumer needs to change it's supply voltage or current limit to meet operation demands. - o Power Domain - Electronic circuit that is supplied it's input power by the + o Power Domain - Electronic circuit that is supplied its input power by the output power of a regulator, switch or by another power domain. diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt index ab00eeddecaf..55b859b3bc72 100644 --- a/Documentation/power/runtime_pm.txt +++ b/Documentation/power/runtime_pm.txt @@ -256,7 +256,7 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: to suspend the device again in future int pm_runtime_resume(struct device *dev); - - execute the subsystem-leve resume callback for the device; returns 0 on + - execute the subsystem-level resume callback for the device; returns 0 on success, 1 if the device's run-time PM status was already 'active' or error code on failure, where -EAGAIN means it may be safe to attempt to resume the device again in future, but 'power.runtime_error' should be diff --git a/Documentation/power/userland-swsusp.txt b/Documentation/power/userland-swsusp.txt index b967cd9137d6..81680f9f5909 100644 --- a/Documentation/power/userland-swsusp.txt +++ b/Documentation/power/userland-swsusp.txt @@ -24,6 +24,10 @@ assumed to be in the resume mode. The device cannot be open for simultaneous reading and writing. It is also impossible to have the device open more than once at a time. +Even opening the device has side effects. Data structures are +allocated, and PM_HIBERNATION_PREPARE / PM_RESTORE_PREPARE chains are +called. + The ioctl() commands recognized by the device are: SNAPSHOT_FREEZE - freeze user space processes (the current process is diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt index 79f533f38c61..46d22105aa07 100644 --- a/Documentation/powerpc/booting-without-of.txt +++ b/Documentation/powerpc/booting-without-of.txt @@ -1289,7 +1289,7 @@ link between a device node and its interrupt parent in the interrupt tree. The value of interrupt-parent is the phandle of the parent node. -If the interrupt-parent property is not defined for a node, it's +If the interrupt-parent property is not defined for a node, its interrupt parent is assumed to be an ancestor in the node's _device tree_ hierarchy. diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt index 6e37be1eeb2d..4f8930263dd9 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt +++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt @@ -21,6 +21,15 @@ Required properties: - fsl,qe-num-snums: define how many serial number(SNUM) the QE can use for the threads. +Optional properties: +- fsl,firmware-phandle: + Usage: required only if there is no fsl,qe-firmware child node + Value type: <phandle> + Definition: Points to a firmware node (see "QE Firmware Node" below) + that contains the firmware that should be uploaded for this QE. + The compatible property for the firmware node should say, + "fsl,qe-firmware". + Recommended properties - brg-frequency : the internal clock source frequency for baud-rate generators in Hz. @@ -59,3 +68,48 @@ Example: reg = <0 c000>; }; }; + +* QE Firmware Node + +This node defines a firmware binary that is embedded in the device tree, for +the purpose of passing the firmware from bootloader to the kernel, or from +the hypervisor to the guest. + +The firmware node itself contains the firmware binary contents, a compatible +property, and any firmware-specific properties. The node should be placed +inside a QE node that needs it. Doing so eliminates the need for a +fsl,firmware-phandle property. Other QE nodes that need the same firmware +should define an fsl,firmware-phandle property that points to the firmware node +in the first QE node. + +The fsl,firmware property can be specified in the DTS (possibly using incbin) +or can be inserted by the boot loader at boot time. + +Required properties: + - compatible + Usage: required + Value type: <string> + Definition: A standard property. Specify a string that indicates what + kind of firmware it is. For QE, this should be "fsl,qe-firmware". + + - fsl,firmware + Usage: required + Value type: <prop-encoded-array>, encoded as an array of bytes + Definition: A standard property. This property contains the firmware + binary "blob". + +Example: + qe1@e0080000 { + compatible = "fsl,qe"; + qe_firmware:qe-firmware { + compatible = "fsl,qe-firmware"; + fsl,firmware = [0x70 0xcd 0x00 0x00 0x01 0x46 0x45 ...]; + }; + ... + }; + + qe2@e0090000 { + compatible = "fsl,qe"; + fsl,firmware-phandle = <&qe_firmware>; + ... + }; diff --git a/Documentation/powerpc/dts-bindings/xilinx.txt b/Documentation/powerpc/dts-bindings/xilinx.txt index ea68046bb9cb..299d0923537b 100644 --- a/Documentation/powerpc/dts-bindings/xilinx.txt +++ b/Documentation/powerpc/dts-bindings/xilinx.txt @@ -11,7 +11,7 @@ control how the core is synthesized. Historically, the EDK tool would extract the device parameters relevant to device drivers and copy them into an 'xparameters.h' in the form of #define symbols. This tells the - device drivers how the IP cores are configured, but it requres the kernel + device drivers how the IP cores are configured, but it requires the kernel to be recompiled every time the FPGA bitstream is resynthesized. The new approach is to export the parameters into the device tree and diff --git a/Documentation/powerpc/phyp-assisted-dump.txt b/Documentation/powerpc/phyp-assisted-dump.txt index c4682b982a2e..ad340205d96a 100644 --- a/Documentation/powerpc/phyp-assisted-dump.txt +++ b/Documentation/powerpc/phyp-assisted-dump.txt @@ -19,7 +19,7 @@ dump offers several strong, practical advantages: immediately available to the system for normal use. -- After the dump is completed, no further reboots are required; the system will be fully usable, and running - in it's normal, production mode on it normal kernel. + in its normal, production mode on its normal kernel. The above can only be accomplished by coordination with, and assistance from the hypervisor. The procedure is diff --git a/Documentation/rbtree.txt b/Documentation/rbtree.txt index aae8355d3166..221f38be98f4 100644 --- a/Documentation/rbtree.txt +++ b/Documentation/rbtree.txt @@ -190,3 +190,61 @@ Example: for (node = rb_first(&mytree); node; node = rb_next(node)) printk("key=%s\n", rb_entry(node, struct mytype, node)->keystring); +Support for Augmented rbtrees +----------------------------- + +Augmented rbtree is an rbtree with "some" additional data stored in each node. +This data can be used to augment some new functionality to rbtree. +Augmented rbtree is an optional feature built on top of basic rbtree +infrastructure. rbtree user who wants this feature will have an augment +callback function in rb_root initialized. + +This callback function will be called from rbtree core routines whenever +a node has a change in one or both of its children. It is the responsibility +of the callback function to recalculate the additional data that is in the +rb node using new children information. Note that if this new additional +data affects the parent node's additional data, then callback function has +to handle it and do the recursive updates. + + +Interval tree is an example of augmented rb tree. Reference - +"Introduction to Algorithms" by Cormen, Leiserson, Rivest and Stein. +More details about interval trees: + +Classical rbtree has a single key and it cannot be directly used to store +interval ranges like [lo:hi] and do a quick lookup for any overlap with a new +lo:hi or to find whether there is an exact match for a new lo:hi. + +However, rbtree can be augmented to store such interval ranges in a structured +way making it possible to do efficient lookup and exact match. + +This "extra information" stored in each node is the maximum hi +(max_hi) value among all the nodes that are its descendents. This +information can be maintained at each node just be looking at the node +and its immediate children. And this will be used in O(log n) lookup +for lowest match (lowest start address among all possible matches) +with something like: + +find_lowest_match(lo, hi, node) +{ + lowest_match = NULL; + while (node) { + if (max_hi(node->left) > lo) { + // Lowest overlap if any must be on left side + node = node->left; + } else if (overlap(lo, hi, node)) { + lowest_match = node; + break; + } else if (lo > node->lo) { + // Lowest overlap if any must be on right side + node = node->right; + } else { + break; + } + } + return lowest_match; +} + +Finding exact match will be to first find lowest match and then to follow +successor nodes looking for exact match, until the start of a node is beyond +the hi value we are looking for. diff --git a/Documentation/rfkill.txt b/Documentation/rfkill.txt index b4860509c319..83668e5dd17f 100644 --- a/Documentation/rfkill.txt +++ b/Documentation/rfkill.txt @@ -99,37 +99,15 @@ system. Also, it is possible to switch all rfkill drivers (or all drivers of a specified type) into a state which also updates the default state for hotplugged devices. -After an application opens /dev/rfkill, it can read the current state of -all devices, and afterwards can poll the descriptor for hotplug or state -change events. - -Applications must ignore operations (the "op" field) they do not handle, -this allows the API to be extended in the future. - -Additionally, each rfkill device is registered in sysfs and there has the -following attributes: - - name: Name assigned by driver to this key (interface or driver name). - type: Driver type string ("wlan", "bluetooth", etc). - persistent: Whether the soft blocked state is initialised from - non-volatile storage at startup. - state: Current state of the transmitter - 0: RFKILL_STATE_SOFT_BLOCKED - transmitter is turned off by software - 1: RFKILL_STATE_UNBLOCKED - transmitter is (potentially) active - 2: RFKILL_STATE_HARD_BLOCKED - transmitter is forced off by something outside of - the driver's control. - This file is deprecated because it can only properly show - three of the four possible states, soft-and-hard-blocked is - missing. - claim: 0: Kernel handles events - This file is deprecated because there no longer is a way to - claim just control over a single rfkill instance. - -rfkill devices also issue uevents (with an action of "change"), with the -following environment variables set: +After an application opens /dev/rfkill, it can read the current state of all +devices. Changes can be either obtained by either polling the descriptor for +hotplug or state change events or by listening for uevents emitted by the +rfkill core framework. + +Additionally, each rfkill device is registered in sysfs and emits uevents. + +rfkill devices issue uevents (with an action of "change"), with the following +environment variables set: RFKILL_NAME RFKILL_STATE @@ -137,3 +115,7 @@ RFKILL_TYPE The contents of these variables corresponds to the "name", "state" and "type" sysfs files explained above. + + +For further details consult Documentation/ABI/stable/dev-rfkill and +Documentation/ABI/stable/sysfs-class-rfkill. diff --git a/Documentation/rt-mutex-design.txt b/Documentation/rt-mutex-design.txt index 4b736d24da7a..8df0b782c4d7 100644 --- a/Documentation/rt-mutex-design.txt +++ b/Documentation/rt-mutex-design.txt @@ -657,7 +657,7 @@ here. The waiter structure has a "task" field that points to the task that is blocked on the mutex. This field can be NULL the first time it goes through the loop -or if the task is a pending owner and had it's mutex stolen. If the "task" +or if the task is a pending owner and had its mutex stolen. If the "task" field is NULL then we need to set up the accounting for it. Task blocks on mutex diff --git a/Documentation/s390/kvm.txt b/Documentation/s390/kvm.txt index 6f5ceb0f09fc..85f3280d7ef6 100644 --- a/Documentation/s390/kvm.txt +++ b/Documentation/s390/kvm.txt @@ -102,7 +102,7 @@ args: unsigned long see also: include/linux/kvm.h This ioctl stores the state of the cpu at the guest real address given as argument, unless one of the following values defined in include/linux/kvm.h -is given as arguement: +is given as argument: KVM_S390_STORE_STATUS_NOADDR - the CPU stores its status to the save area in absolute lowcore as defined by the principles of operation KVM_S390_STORE_STATUS_PREFIXED - the CPU stores its status to the save area in diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt index 6f33593e59e2..8239ebbcddce 100644 --- a/Documentation/scheduler/sched-design-CFS.txt +++ b/Documentation/scheduler/sched-design-CFS.txt @@ -211,7 +211,7 @@ provide fair CPU time to each such task group. For example, it may be desirable to first provide fair CPU time to each user on the system and then to each task belonging to a user. -CONFIG_GROUP_SCHED strives to achieve exactly that. It lets tasks to be +CONFIG_CGROUP_SCHED strives to achieve exactly that. It lets tasks to be grouped and divides CPU time fairly among such groups. CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and @@ -220,38 +220,11 @@ SCHED_RR) tasks. CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and SCHED_BATCH) tasks. -At present, there are two (mutually exclusive) mechanisms to group tasks for -CPU bandwidth control purposes: - - - Based on user id (CONFIG_USER_SCHED) - - With this option, tasks are grouped according to their user id. - - - Based on "cgroup" pseudo filesystem (CONFIG_CGROUP_SCHED) - - This options needs CONFIG_CGROUPS to be defined, and lets the administrator + These options need CONFIG_CGROUPS to be defined, and let the administrator create arbitrary groups of tasks, using the "cgroup" pseudo filesystem. See Documentation/cgroups/cgroups.txt for more information about this filesystem. -Only one of these options to group tasks can be chosen and not both. - -When CONFIG_USER_SCHED is defined, a directory is created in sysfs for each new -user and a "cpu_share" file is added in that directory. - - # cd /sys/kernel/uids - # cat 512/cpu_share # Display user 512's CPU share - 1024 - # echo 2048 > 512/cpu_share # Modify user 512's CPU share - # cat 512/cpu_share # Display user 512's CPU share - 2048 - # - -CPU bandwidth between two users is divided in the ratio of their CPU shares. -For example: if you would like user "root" to get twice the bandwidth of user -"guest," then set the cpu_share for both the users such that "root"'s cpu_share -is twice "guest"'s cpu_share. - -When CONFIG_CGROUP_SCHED is defined, a "cpu.shares" file is created for each +When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each group created using the pseudo filesystem. See example steps below to create task groups and modify their CPU share using the "cgroups" pseudo filesystem. @@ -273,24 +246,3 @@ task groups and modify their CPU share using the "cgroups" pseudo filesystem. # #Launch gmplayer (or your favourite movie player) # echo <movie_player_pid> > multimedia/tasks - -8. Implementation note: user namespaces - -User namespaces are intended to be hierarchical. But they are currently -only partially implemented. Each of those has ramifications for CFS. - -First, since user namespaces are hierarchical, the /sys/kernel/uids -presentation is inadequate. Eventually we will likely want to use sysfs -tagging to provide private views of /sys/kernel/uids within each user -namespace. - -Second, the hierarchical nature is intended to support completely -unprivileged use of user namespaces. So if using user groups, then -we want the users in a user namespace to be children of the user -who created it. - -That is currently unimplemented. So instead, every user in a new -user namespace will receive 1024 shares just like any user in the -initial user namespace. Note that at the moment creation of a new -user namespace requires each of CAP_SYS_ADMIN, CAP_SETUID, and -CAP_SETGID. diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt index 86eabe6c3419..605b0d40329d 100644 --- a/Documentation/scheduler/sched-rt-group.txt +++ b/Documentation/scheduler/sched-rt-group.txt @@ -126,23 +126,12 @@ priority! 2.3 Basis for grouping tasks ---------------------------- -There are two compile-time settings for allocating CPU bandwidth. These are -configured using the "Basis for grouping tasks" multiple choice menu under -General setup > Group CPU Scheduler: - -a. CONFIG_USER_SCHED (aka "Basis for grouping tasks" = "user id") - -This lets you use the virtual files under -"/sys/kernel/uids/<uid>/cpu_rt_runtime_us" to control he CPU time reserved for -each user . - -The other option is: - -.o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups") +Enabling CONFIG_RT_GROUP_SCHED lets you explicitly allocate real +CPU bandwidth to task groups. This uses the /cgroup virtual file system and "/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each -control group instead. +control group. For more information on working with control groups, you should read Documentation/cgroups/cgroups.txt as well. @@ -161,8 +150,7 @@ For now, this can be simplified to just the following (but see Future plans): =============== There is work in progress to make the scheduling period for each group -("/sys/kernel/uids/<uid>/cpu_rt_period_us" or -"/cgroup/<cgroup>/cpu.rt_period_us" respectively) configurable as well. +("/cgroup/<cgroup>/cpu.rt_period_us") configurable as well. The constraint on the period is that a subgroup must have a smaller or equal period to its parent. But realistically its not very useful _yet_ diff --git a/Documentation/scsi/ChangeLog.lpfc b/Documentation/scsi/ChangeLog.lpfc index ff19a52fe004..e759e92e286d 100644 --- a/Documentation/scsi/ChangeLog.lpfc +++ b/Documentation/scsi/ChangeLog.lpfc @@ -707,7 +707,7 @@ Changes from 20040920 to 20041018 * Integrate patches from Christoph Hellwig: two new helpers common to lpfc_sli_resume_iocb and lpfc_sli_issue_iocb - singificant cleanup of those two functions - the unused SLI_IOCB_USE_TXQ is - gone - lpfc_sli_issue_iocb_wait loses it's flags argument + gone - lpfc_sli_issue_iocb_wait loses its flags argument totally. * Fix in lpfc_sli.c: we can not store a 5 bit value in a 4-bit field. @@ -989,8 +989,8 @@ Changes from 20040709 to 20040716 * Remove redundant port_cmp != 2 check in if (!port_cmp) { .... if (port_cmp != 2).... } * Clock changes: removed struct clk_data and timerList. - * Clock changes: seperate nodev_tmo and els_retry_delay into 2 - seperate timers and convert to 1 argument changed + * Clock changes: separate nodev_tmo and els_retry_delay into 2 + separate timers and convert to 1 argument changed LPFC_NODE_FARP_PEND_t to struct lpfc_node_farp_pend convert ipfarp_tmo to 1 argument convert target struct tmofunc and rtplunfunc to 1 argument * cr_count, cr_delay and @@ -1028,7 +1028,7 @@ Changes from 20040614 to 20040709 * Remove the need for buf_tmo. * Changed ULP_BDE64 to struct ulp_bde64. * Changed ULP_BDE to struct ulp_bde. - * Cleanup lpfc_os_return_scsi_cmd() and it's call path. + * Cleanup lpfc_os_return_scsi_cmd() and its call path. * Removed lpfc_no_device_delay. * Consolidating lpfc_hba_put_event() into lpfc_put_event(). * Removed following attributes and their functionality: @@ -1514,7 +1514,7 @@ Changes from 20040402 to 20040409 * Remove unused elxclock declaration in elx_sli.h. * Since everywhere IOCB_ENTRY is used, the return value is cast, move the cast into the macro. - * Split ioctls out into seperate files + * Split ioctls out into separate files Changes from 20040326 to 20040402 @@ -1534,7 +1534,7 @@ Changes from 20040326 to 20040402 * Unused variable cleanup * Use Linux list macros for DMABUF_t * Break up ioctls into 3 sections, dfc, util, hbaapi - rearranged code so this could be easily seperated into a + rearranged code so this could be easily separated into a differnet module later All 3 are currently turned on by defines in lpfc_ioctl.c LPFC_DFC_IOCTL, LPFC_UTIL_IOCTL, LPFC_HBAAPI_IOCTL @@ -1551,7 +1551,7 @@ Changes from 20040326 to 20040402 started by lpfc_online(). lpfc_offline() only stopped els_timeout routine. It now stops all timeout routines associated with that hba. - * Replace seperate next and prev pointers in struct + * Replace separate next and prev pointers in struct lpfc_bindlist with list_head type. In elxHBA_t, replace fc_nlpbind_start and _end with fc_nlpbind_list and use list_head macros to access it. diff --git a/Documentation/scsi/FlashPoint.txt b/Documentation/scsi/FlashPoint.txt index d5acaa300a46..1540a92f6d2b 100644 --- a/Documentation/scsi/FlashPoint.txt +++ b/Documentation/scsi/FlashPoint.txt @@ -71,7 +71,7 @@ peters@mylex.com Ever since its introduction last October, the BusLogic FlashPoint LT has been problematic for members of the Linux community, in that no Linux -drivers have been available for this new Ultra SCSI product. Despite it's +drivers have been available for this new Ultra SCSI product. Despite its officially being positioned as a desktop workstation product, and not being particularly well suited for a high performance multitasking operating system like Linux, the FlashPoint LT has been touted by computer system diff --git a/Documentation/scsi/dtc3x80.txt b/Documentation/scsi/dtc3x80.txt index e8ae6230ab3e..1d7af9f9a8ed 100644 --- a/Documentation/scsi/dtc3x80.txt +++ b/Documentation/scsi/dtc3x80.txt @@ -12,7 +12,7 @@ The 3180 does not. Otherwise, they are identical. The DTC3x80 does not support DMA but it does have Pseudo-DMA which is supported by the driver. -It's DTC406 scsi chip is supposedly compatible with the NCR 53C400. +Its DTC406 scsi chip is supposedly compatible with the NCR 53C400. It is memory mapped, uses an IRQ, but no dma or io-port. There is internal DMA, between SCSI bus and an on-chip 128-byte buffer. Double buffering is done automagically by the chip. Data is transferred diff --git a/Documentation/scsi/ncr53c8xx.txt b/Documentation/scsi/ncr53c8xx.txt index 08e2b4d04aab..cda5f8fa2c66 100644 --- a/Documentation/scsi/ncr53c8xx.txt +++ b/Documentation/scsi/ncr53c8xx.txt @@ -1479,7 +1479,7 @@ Wide16 SCSI. Enabling serial NVRAM support enables detection of the serial NVRAM included on Symbios and some Symbios compatible host adaptors, and Tekram boards. The serial NVRAM is used by Symbios and Tekram to hold set up parameters for the -host adaptor and it's attached drives. +host adaptor and its attached drives. The Symbios NVRAM also holds data on the boot order of host adaptors in a system with more than one host adaptor. This enables the order of scanning diff --git a/Documentation/scsi/osst.txt b/Documentation/scsi/osst.txt index f536907e241d..2b21890bc983 100644 --- a/Documentation/scsi/osst.txt +++ b/Documentation/scsi/osst.txt @@ -40,7 +40,7 @@ behavior looks very much the same as st to the userspace applications. History ------- -In the first place, osst shared it's identity very much with st. That meant +In the first place, osst shared its identity very much with st. That meant that it used the same kernel structures and the same device node as st. So you could only have either of them being present in the kernel. This has been fixed by registering an own device, now. diff --git a/Documentation/scsi/scsi_fc_transport.txt b/Documentation/scsi/scsi_fc_transport.txt index aec6549ab097..e00192de4d1c 100644 --- a/Documentation/scsi/scsi_fc_transport.txt +++ b/Documentation/scsi/scsi_fc_transport.txt @@ -70,7 +70,7 @@ Overview: up to an administrative entity controlling the vport. For example, if vports are to be associated with virtual machines, a XEN mgmt utility would be responsible for creating wwpn/wwnn's for the vport, - using it's own naming authority and OUI. (Note: it already does this + using its own naming authority and OUI. (Note: it already does this for virtual MAC addresses). @@ -81,7 +81,7 @@ Device Trees and Vport Objects: with rports and scsi target objects underneath it. Currently the FC transport creates the vport object and places it under the scsi_host object corresponding to the physical adapter. The LLDD will allocate - a new scsi_host for the vport and link it's object under the vport. + a new scsi_host for the vport and link its object under the vport. The remainder of the tree under the vports scsi_host is the same as the non-NPIV case. The transport is written currently to easily allow the parent of the vport to be something other than the scsi_host. diff --git a/Documentation/scsi/sym53c8xx_2.txt b/Documentation/scsi/sym53c8xx_2.txt index eb9a7b905b64..6f63b7989679 100644 --- a/Documentation/scsi/sym53c8xx_2.txt +++ b/Documentation/scsi/sym53c8xx_2.txt @@ -687,7 +687,7 @@ maintain the driver code. Enabling serial NVRAM support enables detection of the serial NVRAM included on Symbios and some Symbios compatible host adaptors, and Tekram boards. The serial NVRAM is used by Symbios and Tekram to hold set up parameters for the -host adaptor and it's attached drives. +host adaptor and its attached drives. The Symbios NVRAM also holds data on the boot order of host adaptors in a system with more than one host adaptor. This information is no longer used diff --git a/Documentation/serial/tty.txt b/Documentation/serial/tty.txt index 5e5349a4fcd2..7c900507279f 100644 --- a/Documentation/serial/tty.txt +++ b/Documentation/serial/tty.txt @@ -105,6 +105,10 @@ write_wakeup() - May be called at any point between open and close. is permitted to call the driver write method from this function. In such a situation defer it. +dcd_change() - Report to the tty line the current DCD pin status + changes and the relative timestamp. The timestamp + can be NULL. + Driver Access diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt index 33df82e3a398..2075bbb8b3e2 100644 --- a/Documentation/sound/alsa/ALSA-Configuration.txt +++ b/Documentation/sound/alsa/ALSA-Configuration.txt @@ -227,6 +227,16 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. The power-management is supported. + Module snd-asihpi + ----------------- + + Module for AudioScience ASI soundcards + + enable_hpi_hwdep - enable HPI hwdep for AudioScience soundcard + + This module supports multiple cards. + The driver requires the firmware loader support on kernel. + Module snd-atiixp ----------------- @@ -622,28 +632,23 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. The power-management is supported. - Module snd-es968 - ---------------- - - Module for sound cards based on ESS ES968 chip (PnP only). - - This module supports multiple cards, PnP and autoprobe. - - The power-management is supported. - Module snd-es1688 ----------------- Module for ESS AudioDrive ES-1688 and ES-688 sound cards. - port - port # for ES-1688 chip (0x220,0x240,0x260) - fm_port - port # for OPL3 (option; share the same port as default) + isapnp - ISA PnP detection - 0 = disable, 1 = enable (default) mpu_port - port # for MPU-401 port (0x300,0x310,0x320,0x330), -1 = disable (default) - irq - IRQ # for ES-1688 chip (5,7,9,10) mpu_irq - IRQ # for MPU-401 port (5,7,9,10) + fm_port - port # for OPL3 (option; share the same port as default) + + with isapnp=0, the following additional options are available: + port - port # for ES-1688 chip (0x220,0x240,0x260) + irq - IRQ # for ES-1688 chip (5,7,9,10) dma8 - DMA # for ES-1688 chip (0,1,3) - This module supports multiple cards and autoprobe (without MPU-401 port). + This module supports multiple cards and autoprobe (without MPU-401 port) + and PnP with the ES968 chip. Module snd-es18xx ----------------- @@ -1812,7 +1817,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. Module snd-ua101 ---------------- - Module for the Edirol UA-101 audio/MIDI interface. + Module for the Edirol UA-101/UA-1000 audio/MIDI interfaces. This module supports multiple devices, autoprobe and hotplugging. diff --git a/Documentation/sound/alsa/HD-Audio.txt b/Documentation/sound/alsa/HD-Audio.txt index f4dd3bf99d12..bdafdbd32561 100644 --- a/Documentation/sound/alsa/HD-Audio.txt +++ b/Documentation/sound/alsa/HD-Audio.txt @@ -119,10 +119,18 @@ the codec slots 0 and 1 no matter what the hardware reports. Interrupt Handling ~~~~~~~~~~~~~~~~~~ -In rare but some cases, the interrupt isn't properly handled as -default. You would notice this by the DMA transfer error reported by -ALSA PCM core, for example. Using MSI might help in such a case. -Pass `enable_msi=1` option for enabling MSI. +HD-audio driver uses MSI as default (if available) since 2.6.33 +kernel as MSI works better on some machines, and in general, it's +better for performance. However, Nvidia controllers showed bad +regressions with MSI (especially in a combination with AMD chipset), +thus we disabled MSI for them. + +There seem also still other devices that don't work with MSI. If you +see a regression wrt the sound quality (stuttering, etc) or a lock-up +in the recent kernel, try to pass `enable_msi=0` option to disable +MSI. If it works, you can add the known bad device to the blacklist +defined in hda_intel.c. In such a case, please report and give the +patch back to the upstream developer. HD-AUDIO CODEC @@ -196,7 +204,6 @@ generic parser regardless of the codec. Usually the codec-specific parser is much better than the generic parser (as now). Thus this option is more about the debugging purpose. - Speaker and Headphone Output ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ One of the most frequent (and obvious) bugs with HD-audio is the @@ -592,6 +599,9 @@ probing, the proc file is available, so you can get the raw codec information before modified by the driver. Of course, the driver isn't usable with `probe_only=1`. But you can continue the configuration via hwdep sysfs file if hda-reconfig option is enabled. +Using `probe_only` mask 2 skips the reset of HDA codecs (use +`probe_only=3` as module option). The hwdep interface can be used +to determine the BIOS codec initialization. hda-verb diff --git a/Documentation/sound/alsa/soc/dapm.txt b/Documentation/sound/alsa/soc/dapm.txt index 9ac842be9b4f..05bf5a0eee41 100644 --- a/Documentation/sound/alsa/soc/dapm.txt +++ b/Documentation/sound/alsa/soc/dapm.txt @@ -188,8 +188,8 @@ The WM8731 output mixer has 3 inputs (sources) 3. Mic Sidetone Input Each input in this example has a kcontrol associated with it (defined in example -above) and is connected to the output mixer via it's kcontrol name. We can now -connect the destination widget (wrt audio signal) with it's source widgets. +above) and is connected to the output mixer via its kcontrol name. We can now +connect the destination widget (wrt audio signal) with its source widgets. /* output mixer */ {"Output Mixer", "Line Bypass Switch", "Line Input"}, diff --git a/Documentation/sound/alsa/soc/machine.txt b/Documentation/sound/alsa/soc/machine.txt index bab7711ce963..2524c75557df 100644 --- a/Documentation/sound/alsa/soc/machine.txt +++ b/Documentation/sound/alsa/soc/machine.txt @@ -67,7 +67,7 @@ static struct snd_soc_dai_link corgi_dai = { .ops = &corgi_ops, }; -struct snd_soc_card then sets up the machine with it's DAIs. e.g. +struct snd_soc_card then sets up the machine with its DAIs. e.g. /* corgi audio machine driver */ static struct snd_soc_card snd_soc_corgi = { diff --git a/Documentation/sound/alsa/soc/overview.txt b/Documentation/sound/alsa/soc/overview.txt index 1e4c6d3655f2..138ac88c1461 100644 --- a/Documentation/sound/alsa/soc/overview.txt +++ b/Documentation/sound/alsa/soc/overview.txt @@ -33,7 +33,7 @@ features :- and machines. * Easy I2S/PCM audio interface setup between codec and SoC. Each SoC - interface and codec registers it's audio interface capabilities with the + interface and codec registers its audio interface capabilities with the core and are subsequently matched and configured when the application hardware parameters are known. diff --git a/Documentation/sparse.txt b/Documentation/sparse.txt index 34c76a55bc04..9b659c79a547 100644 --- a/Documentation/sparse.txt +++ b/Documentation/sparse.txt @@ -54,12 +54,12 @@ Getting sparse ~~~~~~~~~~~~~~ You can get latest released versions from the Sparse homepage at -http://www.kernel.org/pub/linux/kernel/people/josh/sparse/ +https://sparse.wiki.kernel.org/index.php/Main_Page Alternatively, you can get snapshots of the latest development version of sparse using git to clone.. - git://git.kernel.org/pub/scm/linux/kernel/git/josh/sparse.git + git://git.kernel.org/pub/scm/devel/sparse/sparse.git DaveJ has hourly generated tarballs of the git tree available at.. diff --git a/Documentation/spi/spidev_test.c b/Documentation/spi/spidev_test.c index 10abd3773e49..16feda901469 100644 --- a/Documentation/spi/spidev_test.c +++ b/Documentation/spi/spidev_test.c @@ -58,7 +58,7 @@ static void transfer(int fd) }; ret = ioctl(fd, SPI_IOC_MESSAGE(1), &tr); - if (ret == 1) + if (ret < 1) pabort("can't send spi message"); for (ret = 0; ret < ARRAY_SIZE(tx); ret++) { diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt index 5effa5bd993b..e213f45cf9d7 100644 --- a/Documentation/stable_kernel_rules.txt +++ b/Documentation/stable_kernel_rules.txt @@ -18,16 +18,15 @@ Rules on what kind of patches are accepted, and which ones are not, into the - It cannot contain any "trivial" fixes in it (spelling changes, whitespace cleanups, etc). - It must follow the Documentation/SubmittingPatches rules. - - It or an equivalent fix must already exist in Linus' tree. Quote the - respective commit ID in Linus' tree in your patch submission to -stable. + - It or an equivalent fix must already exist in Linus' tree (upstream). Procedure for submitting patches to the -stable tree: - Send the patch, after verifying that it follows the above rules, to - stable@kernel.org. - - To have the patch automatically included in the stable tree, add the - the tag + stable@kernel.org. You must note the upstream commit ID in the changelog + of your submission. + - To have the patch automatically included in the stable tree, add the tag Cc: stable@kernel.org in the sign-off area. Once the patch is merged it will be applied to the stable tree without anything else needing to be done by the author diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index df38ef046f8d..cbd05ffc606b 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -84,6 +84,16 @@ netdev_max_backlog Maximum number of packets, queued on the INPUT side, when the interface receives packets faster than kernel can process them. +netdev_tstamp_prequeue +---------------------- + +If set to 0, RX packet timestamps can be sampled after RPS processing, when +the target CPU processes packets. It might give some delay on timestamps, but +permit to distribute the load on several cpus. + +If set to 1 (default), timestamps are sampled as soon as possible, before +queueing. + optmem_max ---------- diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index fc5790d36cd9..6c7d18c53f84 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -573,11 +573,14 @@ Because other nodes' memory may be free. This means system total status may be not fatal yet. If this is set to 2, the kernel panics compulsorily even on the -above-mentioned. +above-mentioned. Even oom happens under memory cgroup, the whole +system panics. The default value is 0. 1 and 2 are for failover of clustering. Please select either according to your policy of failover. +panic_on_oom=2+kdump gives you very strong tool to investigate +why oom happens. You can get snapshot. ============================================================= diff --git a/Documentation/sysfs-rules.txt b/Documentation/sysfs-rules.txt index 5d8bc2cd250c..c1a1fd636bf9 100644 --- a/Documentation/sysfs-rules.txt +++ b/Documentation/sysfs-rules.txt @@ -125,7 +125,7 @@ versions of the sysfs interface. - Block The converted block subsystem at /sys/class/block or /sys/subsystem/block will contain the links for disks and partitions - at the same level, never in a hierarchy. Assuming the block subsytem to + at the same level, never in a hierarchy. Assuming the block subsystem to contain only disks and not partition devices in the same flat list is a bug in the application. diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt index d56a01775423..5c17196c8fe9 100644 --- a/Documentation/sysrq.txt +++ b/Documentation/sysrq.txt @@ -177,13 +177,13 @@ virtual console (ALT+Fn) and then back again should also help. * I hit SysRq, but nothing seems to happen, what's wrong? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -There are some keyboards that send different scancodes for SysRq than the -pre-defined 0x54. So if SysRq doesn't work out of the box for a certain -keyboard, run 'showkey -s' to find out the proper scancode sequence. Then -use 'setkeycodes <sequence> 84' to define this sequence to the usual SysRq -code (84 is decimal for 0x54). It's probably best to put this command in a -boot script. Oh, and by the way, you exit 'showkey' by not typing anything -for ten seconds. +There are some keyboards that produce a different keycode for SysRq than the +pre-defined value of 99 (see KEY_SYSRQ in include/linux/input.h), or which +don't have a SysRq key at all. In these cases, run 'showkey -s' to find an +appropriate scancode sequence, and use 'setkeycodes <sequence> 99' to map +this sequence to the usual SysRq code (e.g., 'setkeycodes e05b 99'). It's +probably best to put this command in a boot script. Oh, and by the way, you +exit 'showkey' by not typing anything for ten seconds. * I want to add SysRQ key events to a module, how does it work? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX index 397dc35e1323..a9248da5cdbc 100644 --- a/Documentation/timers/00-INDEX +++ b/Documentation/timers/00-INDEX @@ -4,6 +4,8 @@ highres.txt - High resolution timers and dynamic ticks design notes hpet.txt - High Precision Event Timer Driver for Linux +hpet_example.c + - sample hpet timer test program hrtimers.txt - subsystem for high-resolution kernel timers timer_stats.txt diff --git a/Documentation/timers/Makefile b/Documentation/timers/Makefile new file mode 100644 index 000000000000..c85625f4ab25 --- /dev/null +++ b/Documentation/timers/Makefile @@ -0,0 +1,8 @@ +# kbuild trick to avoid linker error. Can be omitted if a module is built. +obj- := dummy.o + +# List of programs to build +hostprogs-y := hpet_example + +# Tell kbuild to always build the programs +always := $(hostprogs-y) diff --git a/Documentation/timers/hpet.txt b/Documentation/timers/hpet.txt index 16d25e6b5a00..767392ffd31e 100644 --- a/Documentation/timers/hpet.txt +++ b/Documentation/timers/hpet.txt @@ -26,274 +26,5 @@ initialization. An example of this initialization can be found in arch/x86/kernel/hpet.c. The driver provides a userspace API which resembles the API found in the -RTC driver framework. An example user space program is provided below. - -#include <stdio.h> -#include <stdlib.h> -#include <unistd.h> -#include <fcntl.h> -#include <string.h> -#include <memory.h> -#include <malloc.h> -#include <time.h> -#include <ctype.h> -#include <sys/types.h> -#include <sys/wait.h> -#include <signal.h> -#include <fcntl.h> -#include <errno.h> -#include <sys/time.h> -#include <linux/hpet.h> - - -extern void hpet_open_close(int, const char **); -extern void hpet_info(int, const char **); -extern void hpet_poll(int, const char **); -extern void hpet_fasync(int, const char **); -extern void hpet_read(int, const char **); - -#include <sys/poll.h> -#include <sys/ioctl.h> -#include <signal.h> - -struct hpet_command { - char *command; - void (*func)(int argc, const char ** argv); -} hpet_command[] = { - { - "open-close", - hpet_open_close - }, - { - "info", - hpet_info - }, - { - "poll", - hpet_poll - }, - { - "fasync", - hpet_fasync - }, -}; - -int -main(int argc, const char ** argv) -{ - int i; - - argc--; - argv++; - - if (!argc) { - fprintf(stderr, "-hpet: requires command\n"); - return -1; - } - - - for (i = 0; i < (sizeof (hpet_command) / sizeof (hpet_command[0])); i++) - if (!strcmp(argv[0], hpet_command[i].command)) { - argc--; - argv++; - fprintf(stderr, "-hpet: executing %s\n", - hpet_command[i].command); - hpet_command[i].func(argc, argv); - return 0; - } - - fprintf(stderr, "do_hpet: command %s not implemented\n", argv[0]); - - return -1; -} - -void -hpet_open_close(int argc, const char **argv) -{ - int fd; - - if (argc != 1) { - fprintf(stderr, "hpet_open_close: device-name\n"); - return; - } - - fd = open(argv[0], O_RDONLY); - if (fd < 0) - fprintf(stderr, "hpet_open_close: open failed\n"); - else - close(fd); - - return; -} - -void -hpet_info(int argc, const char **argv) -{ -} - -void -hpet_poll(int argc, const char **argv) -{ - unsigned long freq; - int iterations, i, fd; - struct pollfd pfd; - struct hpet_info info; - struct timeval stv, etv; - struct timezone tz; - long usec; - - if (argc != 3) { - fprintf(stderr, "hpet_poll: device-name freq iterations\n"); - return; - } - - freq = atoi(argv[1]); - iterations = atoi(argv[2]); - - fd = open(argv[0], O_RDONLY); - - if (fd < 0) { - fprintf(stderr, "hpet_poll: open of %s failed\n", argv[0]); - return; - } - - if (ioctl(fd, HPET_IRQFREQ, freq) < 0) { - fprintf(stderr, "hpet_poll: HPET_IRQFREQ failed\n"); - goto out; - } - - if (ioctl(fd, HPET_INFO, &info) < 0) { - fprintf(stderr, "hpet_poll: failed to get info\n"); - goto out; - } - - fprintf(stderr, "hpet_poll: info.hi_flags 0x%lx\n", info.hi_flags); - - if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) { - fprintf(stderr, "hpet_poll: HPET_EPI failed\n"); - goto out; - } - - if (ioctl(fd, HPET_IE_ON, 0) < 0) { - fprintf(stderr, "hpet_poll, HPET_IE_ON failed\n"); - goto out; - } - - pfd.fd = fd; - pfd.events = POLLIN; - - for (i = 0; i < iterations; i++) { - pfd.revents = 0; - gettimeofday(&stv, &tz); - if (poll(&pfd, 1, -1) < 0) - fprintf(stderr, "hpet_poll: poll failed\n"); - else { - long data; - - gettimeofday(&etv, &tz); - usec = stv.tv_sec * 1000000 + stv.tv_usec; - usec = (etv.tv_sec * 1000000 + etv.tv_usec) - usec; - - fprintf(stderr, - "hpet_poll: expired time = 0x%lx\n", usec); - - fprintf(stderr, "hpet_poll: revents = 0x%x\n", - pfd.revents); - - if (read(fd, &data, sizeof(data)) != sizeof(data)) { - fprintf(stderr, "hpet_poll: read failed\n"); - } - else - fprintf(stderr, "hpet_poll: data 0x%lx\n", - data); - } - } - -out: - close(fd); - return; -} - -static int hpet_sigio_count; - -static void -hpet_sigio(int val) -{ - fprintf(stderr, "hpet_sigio: called\n"); - hpet_sigio_count++; -} - -void -hpet_fasync(int argc, const char **argv) -{ - unsigned long freq; - int iterations, i, fd, value; - sig_t oldsig; - struct hpet_info info; - - hpet_sigio_count = 0; - fd = -1; - - if ((oldsig = signal(SIGIO, hpet_sigio)) == SIG_ERR) { - fprintf(stderr, "hpet_fasync: failed to set signal handler\n"); - return; - } - - if (argc != 3) { - fprintf(stderr, "hpet_fasync: device-name freq iterations\n"); - goto out; - } - - fd = open(argv[0], O_RDONLY); - - if (fd < 0) { - fprintf(stderr, "hpet_fasync: failed to open %s\n", argv[0]); - return; - } - - - if ((fcntl(fd, F_SETOWN, getpid()) == 1) || - ((value = fcntl(fd, F_GETFL)) == 1) || - (fcntl(fd, F_SETFL, value | O_ASYNC) == 1)) { - fprintf(stderr, "hpet_fasync: fcntl failed\n"); - goto out; - } - - freq = atoi(argv[1]); - iterations = atoi(argv[2]); - - if (ioctl(fd, HPET_IRQFREQ, freq) < 0) { - fprintf(stderr, "hpet_fasync: HPET_IRQFREQ failed\n"); - goto out; - } - - if (ioctl(fd, HPET_INFO, &info) < 0) { - fprintf(stderr, "hpet_fasync: failed to get info\n"); - goto out; - } - - fprintf(stderr, "hpet_fasync: info.hi_flags 0x%lx\n", info.hi_flags); - - if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) { - fprintf(stderr, "hpet_fasync: HPET_EPI failed\n"); - goto out; - } - - if (ioctl(fd, HPET_IE_ON, 0) < 0) { - fprintf(stderr, "hpet_fasync, HPET_IE_ON failed\n"); - goto out; - } - - for (i = 0; i < iterations; i++) { - (void) pause(); - fprintf(stderr, "hpet_fasync: count = %d\n", hpet_sigio_count); - } - -out: - signal(SIGIO, oldsig); - - if (fd >= 0) - close(fd); - - return; -} +RTC driver framework. An example user space program is provided in +file:Documentation/timers/hpet_example.c diff --git a/Documentation/timers/hpet_example.c b/Documentation/timers/hpet_example.c new file mode 100644 index 000000000000..f9ce2d9fdfd5 --- /dev/null +++ b/Documentation/timers/hpet_example.c @@ -0,0 +1,269 @@ +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <fcntl.h> +#include <string.h> +#include <memory.h> +#include <malloc.h> +#include <time.h> +#include <ctype.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <signal.h> +#include <fcntl.h> +#include <errno.h> +#include <sys/time.h> +#include <linux/hpet.h> + + +extern void hpet_open_close(int, const char **); +extern void hpet_info(int, const char **); +extern void hpet_poll(int, const char **); +extern void hpet_fasync(int, const char **); +extern void hpet_read(int, const char **); + +#include <sys/poll.h> +#include <sys/ioctl.h> +#include <signal.h> + +struct hpet_command { + char *command; + void (*func)(int argc, const char ** argv); +} hpet_command[] = { + { + "open-close", + hpet_open_close + }, + { + "info", + hpet_info + }, + { + "poll", + hpet_poll + }, + { + "fasync", + hpet_fasync + }, +}; + +int +main(int argc, const char ** argv) +{ + int i; + + argc--; + argv++; + + if (!argc) { + fprintf(stderr, "-hpet: requires command\n"); + return -1; + } + + + for (i = 0; i < (sizeof (hpet_command) / sizeof (hpet_command[0])); i++) + if (!strcmp(argv[0], hpet_command[i].command)) { + argc--; + argv++; + fprintf(stderr, "-hpet: executing %s\n", + hpet_command[i].command); + hpet_command[i].func(argc, argv); + return 0; + } + + fprintf(stderr, "do_hpet: command %s not implemented\n", argv[0]); + + return -1; +} + +void +hpet_open_close(int argc, const char **argv) +{ + int fd; + + if (argc != 1) { + fprintf(stderr, "hpet_open_close: device-name\n"); + return; + } + + fd = open(argv[0], O_RDONLY); + if (fd < 0) + fprintf(stderr, "hpet_open_close: open failed\n"); + else + close(fd); + + return; +} + +void +hpet_info(int argc, const char **argv) +{ +} + +void +hpet_poll(int argc, const char **argv) +{ + unsigned long freq; + int iterations, i, fd; + struct pollfd pfd; + struct hpet_info info; + struct timeval stv, etv; + struct timezone tz; + long usec; + + if (argc != 3) { + fprintf(stderr, "hpet_poll: device-name freq iterations\n"); + return; + } + + freq = atoi(argv[1]); + iterations = atoi(argv[2]); + + fd = open(argv[0], O_RDONLY); + + if (fd < 0) { + fprintf(stderr, "hpet_poll: open of %s failed\n", argv[0]); + return; + } + + if (ioctl(fd, HPET_IRQFREQ, freq) < 0) { + fprintf(stderr, "hpet_poll: HPET_IRQFREQ failed\n"); + goto out; + } + + if (ioctl(fd, HPET_INFO, &info) < 0) { + fprintf(stderr, "hpet_poll: failed to get info\n"); + goto out; + } + + fprintf(stderr, "hpet_poll: info.hi_flags 0x%lx\n", info.hi_flags); + + if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) { + fprintf(stderr, "hpet_poll: HPET_EPI failed\n"); + goto out; + } + + if (ioctl(fd, HPET_IE_ON, 0) < 0) { + fprintf(stderr, "hpet_poll, HPET_IE_ON failed\n"); + goto out; + } + + pfd.fd = fd; + pfd.events = POLLIN; + + for (i = 0; i < iterations; i++) { + pfd.revents = 0; + gettimeofday(&stv, &tz); + if (poll(&pfd, 1, -1) < 0) + fprintf(stderr, "hpet_poll: poll failed\n"); + else { + long data; + + gettimeofday(&etv, &tz); + usec = stv.tv_sec * 1000000 + stv.tv_usec; + usec = (etv.tv_sec * 1000000 + etv.tv_usec) - usec; + + fprintf(stderr, + "hpet_poll: expired time = 0x%lx\n", usec); + + fprintf(stderr, "hpet_poll: revents = 0x%x\n", + pfd.revents); + + if (read(fd, &data, sizeof(data)) != sizeof(data)) { + fprintf(stderr, "hpet_poll: read failed\n"); + } + else + fprintf(stderr, "hpet_poll: data 0x%lx\n", + data); + } + } + +out: + close(fd); + return; +} + +static int hpet_sigio_count; + +static void +hpet_sigio(int val) +{ + fprintf(stderr, "hpet_sigio: called\n"); + hpet_sigio_count++; +} + +void +hpet_fasync(int argc, const char **argv) +{ + unsigned long freq; + int iterations, i, fd, value; + sig_t oldsig; + struct hpet_info info; + + hpet_sigio_count = 0; + fd = -1; + + if ((oldsig = signal(SIGIO, hpet_sigio)) == SIG_ERR) { + fprintf(stderr, "hpet_fasync: failed to set signal handler\n"); + return; + } + + if (argc != 3) { + fprintf(stderr, "hpet_fasync: device-name freq iterations\n"); + goto out; + } + + fd = open(argv[0], O_RDONLY); + + if (fd < 0) { + fprintf(stderr, "hpet_fasync: failed to open %s\n", argv[0]); + return; + } + + + if ((fcntl(fd, F_SETOWN, getpid()) == 1) || + ((value = fcntl(fd, F_GETFL)) == 1) || + (fcntl(fd, F_SETFL, value | O_ASYNC) == 1)) { + fprintf(stderr, "hpet_fasync: fcntl failed\n"); + goto out; + } + + freq = atoi(argv[1]); + iterations = atoi(argv[2]); + + if (ioctl(fd, HPET_IRQFREQ, freq) < 0) { + fprintf(stderr, "hpet_fasync: HPET_IRQFREQ failed\n"); + goto out; + } + + if (ioctl(fd, HPET_INFO, &info) < 0) { + fprintf(stderr, "hpet_fasync: failed to get info\n"); + goto out; + } + + fprintf(stderr, "hpet_fasync: info.hi_flags 0x%lx\n", info.hi_flags); + + if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) { + fprintf(stderr, "hpet_fasync: HPET_EPI failed\n"); + goto out; + } + + if (ioctl(fd, HPET_IE_ON, 0) < 0) { + fprintf(stderr, "hpet_fasync, HPET_IE_ON failed\n"); + goto out; + } + + for (i = 0; i < iterations; i++) { + (void) pause(); + fprintf(stderr, "hpet_fasync: count = %d\n", hpet_sigio_count); + } + +out: + signal(SIGIO, oldsig); + + if (fd >= 0) + close(fd); + + return; +} diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt index 02ac6ed38b2d..09bd8e902989 100644 --- a/Documentation/trace/events.txt +++ b/Documentation/trace/events.txt @@ -90,7 +90,8 @@ In order to facilitate early boot debugging, use boot option: trace_event=[event-list] -The format of this boot option is the same as described in section 2.1. +event-list is a comma separated list of events. See section 2.1 for event +format. 3. Defining an event-enabled tracepoint ======================================= @@ -238,7 +239,7 @@ subsystem's filter file. For convenience, filters for every event in a subsystem can be set or cleared as a group by writing a filter expression into the filter file -at the root of the subsytem. Note however, that if a filter for any +at the root of the subsystem. Note however, that if a filter for any event within the subsystem lacks a field specified in the subsystem filter, or if the filter can't be applied for any other reason, the filter for that event will retain its previous setting. This can @@ -250,7 +251,7 @@ fields can be guaranteed to propagate successfully to all events. Here are a few subsystem filter examples that also illustrate the above points: -Clear the filters on all events in the sched subsytem: +Clear the filters on all events in the sched subsystem: # cd /sys/kernel/debug/tracing/events/sched # echo 0 > filter @@ -260,7 +261,7 @@ none none Set a filter using only common fields for all events in the sched -subsytem (all events end up with the same filter): +subsystem (all events end up with the same filter): # cd /sys/kernel/debug/tracing/events/sched # echo common_pid == 0 > filter @@ -270,7 +271,7 @@ common_pid == 0 common_pid == 0 Attempt to set a filter using a non-common field for all events in the -sched subsytem (all events but those that have a prev_pid field retain +sched subsystem (all events but those that have a prev_pid field retain their old filters): # cd /sys/kernel/debug/tracing/events/sched diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index bab3040da548..557c1edeccaf 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -155,6 +155,9 @@ of ftrace. Here is a list of some of the key files: to be traced. Echoing names of functions into this file will limit the trace to only those functions. + This interface also allows for commands to be used. See the + "Filter commands" section for more details. + set_ftrace_notrace: This has an effect opposite to that of @@ -1337,12 +1340,14 @@ ftrace_dump_on_oops must be set. To set ftrace_dump_on_oops, one can either use the sysctl function or set it via the proc system interface. - sysctl kernel.ftrace_dump_on_oops=1 + sysctl kernel.ftrace_dump_on_oops=n or - echo 1 > /proc/sys/kernel/ftrace_dump_on_oops + echo n > /proc/sys/kernel/ftrace_dump_on_oops +If n = 1, ftrace will dump buffers of all CPUs, if n = 2 ftrace will +only dump the buffer of the CPU that triggered the oops. Here's an example of such a dump after a null pointer dereference in a kernel module: @@ -1588,7 +1593,7 @@ module author does not need to worry about it. When tracing is enabled, kstop_machine is called to prevent races with the CPUS executing code being modified (which can -cause the CPU to do undesireable things), and the nops are +cause the CPU to do undesirable things), and the nops are patched back to calls. But this time, they do not call mcount (which is just a function stub). They now call into the ftrace infrastructure. @@ -1822,6 +1827,47 @@ this special filter via: echo > set_graph_function +Filter commands +--------------- + +A few commands are supported by the set_ftrace_filter interface. +Trace commands have the following format: + +<function>:<command>:<parameter> + +The following commands are supported: + +- mod + This command enables function filtering per module. The + parameter defines the module. For example, if only the write* + functions in the ext3 module are desired, run: + + echo 'write*:mod:ext3' > set_ftrace_filter + + This command interacts with the filter in the same way as + filtering based on function names. Thus, adding more functions + in a different module is accomplished by appending (>>) to the + filter file. Remove specific module functions by prepending + '!': + + echo '!writeback*:mod:ext3' >> set_ftrace_filter + +- traceon/traceoff + These commands turn tracing on and off when the specified + functions are hit. The parameter determines how many times the + tracing system is turned on and off. If unspecified, there is + no limit. For example, to disable tracing when a schedule bug + is hit the first 5 times, run: + + echo '__schedule_bug:traceoff:5' > set_ftrace_filter + + These commands are cumulative whether or not they are appended + to set_ftrace_filter. To remove a command, prepend it by '!' + and drop the parameter: + + echo '!__schedule_bug:traceoff' > set_ftrace_filter + + trace_pipe ---------- diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt index a9100b28eb84..ec94748ae65b 100644 --- a/Documentation/trace/kprobetrace.txt +++ b/Documentation/trace/kprobetrace.txt @@ -40,7 +40,9 @@ Synopsis of kprobe_events $stack : Fetch stack address. $retval : Fetch return value.(*) +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**) - NAME=FETCHARG: Set NAME as the argument name of FETCHARG. + NAME=FETCHARG : Set NAME as the argument name of FETCHARG. + FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types + (u8/u16/u32/u64/s8/s16/s32/s64) are supported. (*) only for return probe. (**) this is useful for fetching a field of data structures. diff --git a/Documentation/usb/WUSB-Design-overview.txt b/Documentation/usb/WUSB-Design-overview.txt index c480e9c32dbd..4c5e37939344 100644 --- a/Documentation/usb/WUSB-Design-overview.txt +++ b/Documentation/usb/WUSB-Design-overview.txt @@ -381,7 +381,7 @@ descriptor that gives us the status of the transfer, its identification we issue another URB to read into the destination buffer the chunk of data coming out of the remote endpoint. Done, wait for the next guy. The callbacks for the URBs issued from here are the ones that will declare -the xfer complete at some point and call it's callback. +the xfer complete at some point and call its callback. Seems simple, but the implementation is not trivial. diff --git a/Documentation/usb/bulk-streams.txt b/Documentation/usb/bulk-streams.txt new file mode 100644 index 000000000000..ffc02021863e --- /dev/null +++ b/Documentation/usb/bulk-streams.txt @@ -0,0 +1,78 @@ +Background +========== + +Bulk endpoint streams were added in the USB 3.0 specification. Streams allow a +device driver to overload a bulk endpoint so that multiple transfers can be +queued at once. + +Streams are defined in sections 4.4.6.4 and 8.12.1.4 of the Universal Serial Bus +3.0 specification at http://www.usb.org/developers/docs/ The USB Attached SCSI +Protocol, which uses streams to queue multiple SCSI commands, can be found on +the T10 website (http://t10.org/). + + +Device-side implications +======================== + +Once a buffer has been queued to a stream ring, the device is notified (through +an out-of-band mechanism on another endpoint) that data is ready for that stream +ID. The device then tells the host which "stream" it wants to start. The host +can also initiate a transfer on a stream without the device asking, but the +device can refuse that transfer. Devices can switch between streams at any +time. + + +Driver implications +=================== + +int usb_alloc_streams(struct usb_interface *interface, + struct usb_host_endpoint **eps, unsigned int num_eps, + unsigned int num_streams, gfp_t mem_flags); + +Device drivers will call this API to request that the host controller driver +allocate memory so the driver can use up to num_streams stream IDs. They must +pass an array of usb_host_endpoints that need to be setup with similar stream +IDs. This is to ensure that a UASP driver will be able to use the same stream +ID for the bulk IN and OUT endpoints used in a Bi-directional command sequence. + +The return value is an error condition (if one of the endpoints doesn't support +streams, or the xHCI driver ran out of memory), or the number of streams the +host controller allocated for this endpoint. The xHCI host controller hardware +declares how many stream IDs it can support, and each bulk endpoint on a +SuperSpeed device will say how many stream IDs it can handle. Therefore, +drivers should be able to deal with being allocated less stream IDs than they +requested. + +Do NOT call this function if you have URBs enqueued for any of the endpoints +passed in as arguments. Do not call this function to request less than two +streams. + +Drivers will only be allowed to call this API once for the same endpoint +without calling usb_free_streams(). This is a simplification for the xHCI host +controller driver, and may change in the future. + + +Picking new Stream IDs to use +============================ + +Stream ID 0 is reserved, and should not be used to communicate with devices. If +usb_alloc_streams() returns with a value of N, you may use streams 1 though N. +To queue an URB for a specific stream, set the urb->stream_id value. If the +endpoint does not support streams, an error will be returned. + +Note that new API to choose the next stream ID will have to be added if the xHCI +driver supports secondary stream IDs. + + +Clean up +======== + +If a driver wishes to stop using streams to communicate with the device, it +should call + +void usb_free_streams(struct usb_interface *interface, + struct usb_host_endpoint **eps, unsigned int num_eps, + gfp_t mem_flags); + +All stream IDs will be deallocated when the driver releases the interface, to +ensure that drivers that don't support streams will be able to use the endpoint. diff --git a/Documentation/usb/dma.txt b/Documentation/usb/dma.txt index cfdcd16e3abf..84ef865237db 100644 --- a/Documentation/usb/dma.txt +++ b/Documentation/usb/dma.txt @@ -16,11 +16,11 @@ OR: they can now be DMA-aware. manage dma mappings for existing dma-ready buffers (see below). - URBs have an additional "transfer_dma" field, as well as a transfer_flags - bit saying if it's valid. (Control requests also have "setup_dma" and a - corresponding transfer_flags bit.) + bit saying if it's valid. (Control requests also have "setup_dma", but + drivers must not use it.) -- "usbcore" will map those DMA addresses, if a DMA-aware driver didn't do - it first and set URB_NO_TRANSFER_DMA_MAP or URB_NO_SETUP_DMA_MAP. HCDs +- "usbcore" will map this DMA address, if a DMA-aware driver didn't do + it first and set URB_NO_TRANSFER_DMA_MAP. HCDs don't manage dma mappings for URBs. - There's a new "generic DMA API", parts of which are usable by USB device @@ -43,22 +43,16 @@ and effects like cache-trashing can impose subtle penalties. kind of addresses to store in urb->transfer_buffer and urb->transfer_dma. You'd also set URB_NO_TRANSFER_DMA_MAP in urb->transfer_flags: - void *usb_buffer_alloc (struct usb_device *dev, size_t size, + void *usb_alloc_coherent (struct usb_device *dev, size_t size, int mem_flags, dma_addr_t *dma); - void usb_buffer_free (struct usb_device *dev, size_t size, + void usb_free_coherent (struct usb_device *dev, size_t size, void *addr, dma_addr_t dma); Most drivers should *NOT* be using these primitives; they don't need to use this type of memory ("dma-coherent"), and memory returned from kmalloc() will work just fine. - For control transfers you can use the buffer primitives or not for each - of the transfer buffer and setup buffer independently. Set the flag bits - URB_NO_TRANSFER_DMA_MAP and URB_NO_SETUP_DMA_MAP to indicate which - buffers you have prepared. For non-control transfers URB_NO_SETUP_DMA_MAP - is ignored. - The memory buffer returned is "dma-coherent"; sometimes you might need to force a consistent memory access ordering by using memory barriers. It's not using a streaming DMA mapping, so it's good for small transfers on @@ -130,8 +124,8 @@ of Documentation/PCI/PCI-DMA-mapping.txt, titled "What memory is DMA-able?") void usb_buffer_unmap (struct urb *urb); The calls manage urb->transfer_dma for you, and set URB_NO_TRANSFER_DMA_MAP - so that usbcore won't map or unmap the buffer. The same goes for - urb->setup_dma and URB_NO_SETUP_DMA_MAP for control requests. + so that usbcore won't map or unmap the buffer. They cannot be used for + setup_packet buffers in control requests. Note that several of those interfaces are currently commented out, since they don't have current users. See the source code. Other than the dmasync diff --git a/Documentation/usb/gadget_hid.txt b/Documentation/usb/gadget_hid.txt new file mode 100644 index 000000000000..f4a51f567427 --- /dev/null +++ b/Documentation/usb/gadget_hid.txt @@ -0,0 +1,445 @@ + + Linux USB HID gadget driver + +Introduction + + The HID Gadget driver provides emulation of USB Human Interface + Devices (HID). The basic HID handling is done in the kernel, + and HID reports can be sent/received through I/O on the + /dev/hidgX character devices. + + For more details about HID, see the developer page on + http://www.usb.org/developers/hidpage/ + +Configuration + + g_hid is a platform driver, so to use it you need to add + struct platform_device(s) to your platform code defining the + HID function descriptors you want to use - E.G. something + like: + +#include <linux/platform_device.h> +#include <linux/usb/g_hid.h> + +/* hid descriptor for a keyboard */ +static struct hidg_func_descriptor my_hid_data = { + .subclass = 0, /* No subclass */ + .protocol = 1, /* Keyboard */ + .report_length = 8, + .report_desc_length = 63, + .report_desc = { + 0x05, 0x01, /* USAGE_PAGE (Generic Desktop) */ + 0x09, 0x06, /* USAGE (Keyboard) */ + 0xa1, 0x01, /* COLLECTION (Application) */ + 0x05, 0x07, /* USAGE_PAGE (Keyboard) */ + 0x19, 0xe0, /* USAGE_MINIMUM (Keyboard LeftControl) */ + 0x29, 0xe7, /* USAGE_MAXIMUM (Keyboard Right GUI) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ + 0x75, 0x01, /* REPORT_SIZE (1) */ + 0x95, 0x08, /* REPORT_COUNT (8) */ + 0x81, 0x02, /* INPUT (Data,Var,Abs) */ + 0x95, 0x01, /* REPORT_COUNT (1) */ + 0x75, 0x08, /* REPORT_SIZE (8) */ + 0x81, 0x03, /* INPUT (Cnst,Var,Abs) */ + 0x95, 0x05, /* REPORT_COUNT (5) */ + 0x75, 0x01, /* REPORT_SIZE (1) */ + 0x05, 0x08, /* USAGE_PAGE (LEDs) */ + 0x19, 0x01, /* USAGE_MINIMUM (Num Lock) */ + 0x29, 0x05, /* USAGE_MAXIMUM (Kana) */ + 0x91, 0x02, /* OUTPUT (Data,Var,Abs) */ + 0x95, 0x01, /* REPORT_COUNT (1) */ + 0x75, 0x03, /* REPORT_SIZE (3) */ + 0x91, 0x03, /* OUTPUT (Cnst,Var,Abs) */ + 0x95, 0x06, /* REPORT_COUNT (6) */ + 0x75, 0x08, /* REPORT_SIZE (8) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0x65, /* LOGICAL_MAXIMUM (101) */ + 0x05, 0x07, /* USAGE_PAGE (Keyboard) */ + 0x19, 0x00, /* USAGE_MINIMUM (Reserved) */ + 0x29, 0x65, /* USAGE_MAXIMUM (Keyboard Application) */ + 0x81, 0x00, /* INPUT (Data,Ary,Abs) */ + 0xc0 /* END_COLLECTION */ + } +}; + +static struct platform_device my_hid = { + .name = "hidg", + .id = 0, + .num_resources = 0, + .resource = 0, + .dev.platform_data = &my_hid_data, +}; + + You can add as many HID functions as you want, only limited by + the amount of interrupt endpoints your gadget driver supports. + +Send and receive HID reports + + HID reports can be sent/received using read/write on the + /dev/hidgX character devices. See below for an example program + to do this. + + hid_gadget_test is a small interactive program to test the HID + gadget driver. To use, point it at a hidg device and set the + device type (keyboard / mouse / joystick) - E.G.: + + # hid_gadget_test /dev/hidg0 keyboard + + You are now in the prompt of hid_gadget_test. You can type any + combination of options and values. Available options and + values are listed at program start. In keyboard mode you can + send up to six values. + + For example type: g i s t r --left-shift + + Hit return and the corresponding report will be sent by the + HID gadget. + + Another interesting example is the caps lock test. Type + -–caps-lock and hit return. A report is then sent by the + gadget and you should receive the host answer, corresponding + to the caps lock LED status. + + --caps-lock + recv report:2 + + With this command: + + # hid_gadget_test /dev/hidg1 mouse + + You can test the mouse emulation. Values are two signed numbers. + + +Sample code + +/* hid_gadget_test */ + +#include <pthread.h> +#include <string.h> +#include <stdio.h> +#include <ctype.h> +#include <fcntl.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#define BUF_LEN 512 + +struct options { + const char *opt; + unsigned char val; +}; + +static struct options kmod[] = { + {.opt = "--left-ctrl", .val = 0x01}, + {.opt = "--right-ctrl", .val = 0x10}, + {.opt = "--left-shift", .val = 0x02}, + {.opt = "--right-shift", .val = 0x20}, + {.opt = "--left-alt", .val = 0x04}, + {.opt = "--right-alt", .val = 0x40}, + {.opt = "--left-meta", .val = 0x08}, + {.opt = "--right-meta", .val = 0x80}, + {.opt = NULL} +}; + +static struct options kval[] = { + {.opt = "--return", .val = 0x28}, + {.opt = "--esc", .val = 0x29}, + {.opt = "--bckspc", .val = 0x2a}, + {.opt = "--tab", .val = 0x2b}, + {.opt = "--spacebar", .val = 0x2c}, + {.opt = "--caps-lock", .val = 0x39}, + {.opt = "--f1", .val = 0x3a}, + {.opt = "--f2", .val = 0x3b}, + {.opt = "--f3", .val = 0x3c}, + {.opt = "--f4", .val = 0x3d}, + {.opt = "--f5", .val = 0x3e}, + {.opt = "--f6", .val = 0x3f}, + {.opt = "--f7", .val = 0x40}, + {.opt = "--f8", .val = 0x41}, + {.opt = "--f9", .val = 0x42}, + {.opt = "--f10", .val = 0x43}, + {.opt = "--f11", .val = 0x44}, + {.opt = "--f12", .val = 0x45}, + {.opt = "--insert", .val = 0x49}, + {.opt = "--home", .val = 0x4a}, + {.opt = "--pageup", .val = 0x4b}, + {.opt = "--del", .val = 0x4c}, + {.opt = "--end", .val = 0x4d}, + {.opt = "--pagedown", .val = 0x4e}, + {.opt = "--right", .val = 0x4f}, + {.opt = "--left", .val = 0x50}, + {.opt = "--down", .val = 0x51}, + {.opt = "--kp-enter", .val = 0x58}, + {.opt = "--up", .val = 0x52}, + {.opt = "--num-lock", .val = 0x53}, + {.opt = NULL} +}; + +int keyboard_fill_report(char report[8], char buf[BUF_LEN], int *hold) +{ + char *tok = strtok(buf, " "); + int key = 0; + int i = 0; + + for (; tok != NULL; tok = strtok(NULL, " ")) { + + if (strcmp(tok, "--quit") == 0) + return -1; + + if (strcmp(tok, "--hold") == 0) { + *hold = 1; + continue; + } + + if (key < 6) { + for (i = 0; kval[i].opt != NULL; i++) + if (strcmp(tok, kval[i].opt) == 0) { + report[2 + key++] = kval[i].val; + break; + } + if (kval[i].opt != NULL) + continue; + } + + if (key < 6) + if (islower(tok[0])) { + report[2 + key++] = (tok[0] - ('a' - 0x04)); + continue; + } + + for (i = 0; kmod[i].opt != NULL; i++) + if (strcmp(tok, kmod[i].opt) == 0) { + report[0] = report[0] | kmod[i].val; + break; + } + if (kmod[i].opt != NULL) + continue; + + if (key < 6) + fprintf(stderr, "unknown option: %s\n", tok); + } + return 8; +} + +static struct options mmod[] = { + {.opt = "--b1", .val = 0x01}, + {.opt = "--b2", .val = 0x02}, + {.opt = "--b3", .val = 0x04}, + {.opt = NULL} +}; + +int mouse_fill_report(char report[8], char buf[BUF_LEN], int *hold) +{ + char *tok = strtok(buf, " "); + int mvt = 0; + int i = 0; + for (; tok != NULL; tok = strtok(NULL, " ")) { + + if (strcmp(tok, "--quit") == 0) + return -1; + + if (strcmp(tok, "--hold") == 0) { + *hold = 1; + continue; + } + + for (i = 0; mmod[i].opt != NULL; i++) + if (strcmp(tok, mmod[i].opt) == 0) { + report[0] = report[0] | mmod[i].val; + break; + } + if (mmod[i].opt != NULL) + continue; + + if (!(tok[0] == '-' && tok[1] == '-') && mvt < 2) { + errno = 0; + report[1 + mvt++] = (char)strtol(tok, NULL, 0); + if (errno != 0) { + fprintf(stderr, "Bad value:'%s'\n", tok); + report[1 + mvt--] = 0; + } + continue; + } + + fprintf(stderr, "unknown option: %s\n", tok); + } + return 3; +} + +static struct options jmod[] = { + {.opt = "--b1", .val = 0x10}, + {.opt = "--b2", .val = 0x20}, + {.opt = "--b3", .val = 0x40}, + {.opt = "--b4", .val = 0x80}, + {.opt = "--hat1", .val = 0x00}, + {.opt = "--hat2", .val = 0x01}, + {.opt = "--hat3", .val = 0x02}, + {.opt = "--hat4", .val = 0x03}, + {.opt = "--hatneutral", .val = 0x04}, + {.opt = NULL} +}; + +int joystick_fill_report(char report[8], char buf[BUF_LEN], int *hold) +{ + char *tok = strtok(buf, " "); + int mvt = 0; + int i = 0; + + *hold = 1; + + /* set default hat position: neutral */ + report[3] = 0x04; + + for (; tok != NULL; tok = strtok(NULL, " ")) { + + if (strcmp(tok, "--quit") == 0) + return -1; + + for (i = 0; jmod[i].opt != NULL; i++) + if (strcmp(tok, jmod[i].opt) == 0) { + report[3] = (report[3] & 0xF0) | jmod[i].val; + break; + } + if (jmod[i].opt != NULL) + continue; + + if (!(tok[0] == '-' && tok[1] == '-') && mvt < 3) { + errno = 0; + report[mvt++] = (char)strtol(tok, NULL, 0); + if (errno != 0) { + fprintf(stderr, "Bad value:'%s'\n", tok); + report[mvt--] = 0; + } + continue; + } + + fprintf(stderr, "unknown option: %s\n", tok); + } + return 4; +} + +void print_options(char c) +{ + int i = 0; + + if (c == 'k') { + printf(" keyboard options:\n" + " --hold\n"); + for (i = 0; kmod[i].opt != NULL; i++) + printf("\t\t%s\n", kmod[i].opt); + printf("\n keyboard values:\n" + " [a-z] or\n"); + for (i = 0; kval[i].opt != NULL; i++) + printf("\t\t%-8s%s", kval[i].opt, i % 2 ? "\n" : ""); + printf("\n"); + } else if (c == 'm') { + printf(" mouse options:\n" + " --hold\n"); + for (i = 0; mmod[i].opt != NULL; i++) + printf("\t\t%s\n", mmod[i].opt); + printf("\n mouse values:\n" + " Two signed numbers\n" + "--quit to close\n"); + } else { + printf(" joystick options:\n"); + for (i = 0; jmod[i].opt != NULL; i++) + printf("\t\t%s\n", jmod[i].opt); + printf("\n joystick values:\n" + " three signed numbers\n" + "--quit to close\n"); + } +} + +int main(int argc, const char *argv[]) +{ + const char *filename = NULL; + int fd = 0; + char buf[BUF_LEN]; + int cmd_len; + char report[8]; + int to_send = 8; + int hold = 0; + fd_set rfds; + int retval, i; + + if (argc < 3) { + fprintf(stderr, "Usage: %s devname mouse|keyboard|joystick\n", + argv[0]); + return 1; + } + + if (argv[2][0] != 'k' && argv[2][0] != 'm' && argv[2][0] != 'j') + return 2; + + filename = argv[1]; + + if ((fd = open(filename, O_RDWR, 0666)) == -1) { + perror(filename); + return 3; + } + + print_options(argv[2][0]); + + while (42) { + + FD_ZERO(&rfds); + FD_SET(STDIN_FILENO, &rfds); + FD_SET(fd, &rfds); + + retval = select(fd + 1, &rfds, NULL, NULL, NULL); + if (retval == -1 && errno == EINTR) + continue; + if (retval < 0) { + perror("select()"); + return 4; + } + + if (FD_ISSET(fd, &rfds)) { + cmd_len = read(fd, buf, BUF_LEN - 1); + printf("recv report:"); + for (i = 0; i < cmd_len; i++) + printf(" %02x", buf[i]); + printf("\n"); + } + + if (FD_ISSET(STDIN_FILENO, &rfds)) { + memset(report, 0x0, sizeof(report)); + cmd_len = read(STDIN_FILENO, buf, BUF_LEN - 1); + + if (cmd_len == 0) + break; + + buf[cmd_len - 1] = '\0'; + hold = 0; + + memset(report, 0x0, sizeof(report)); + if (argv[2][0] == 'k') + to_send = keyboard_fill_report(report, buf, &hold); + else if (argv[2][0] == 'm') + to_send = mouse_fill_report(report, buf, &hold); + else + to_send = joystick_fill_report(report, buf, &hold); + + if (to_send == -1) + break; + + if (write(fd, report, to_send) != to_send) { + perror(filename); + return 5; + } + if (!hold) { + memset(report, 0x0, sizeof(report)); + if (write(fd, report, to_send) != to_send) { + perror(filename); + return 6; + } + } + } + } + + close(fd); + return 0; +} diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt index 2790ad48cfc2..b29d8e56cf28 100644 --- a/Documentation/usb/power-management.txt +++ b/Documentation/usb/power-management.txt @@ -107,7 +107,9 @@ 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, level, and autosuspend. +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.) power/wakeup @@ -120,7 +122,7 @@ relevant attribute files are: wakeup, level, and autosuspend. while the device is suspended, the change won't take effect until the following suspend.) - power/level + power/control This file contains one of two words: "on" or "auto". You can write those words to the file to change the @@ -148,14 +150,15 @@ relevant attribute files are: wakeup, level, and autosuspend. 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/level do +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. (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/level attribute did not exist prior to 2.6.22. power/control +was added in 2.6.34.) Changing the default idle-delay time @@ -212,7 +215,7 @@ among printers and scanners, but plenty of other types of device have the same deficiency. For this reason, by default the kernel disables autosuspend (the -power/level attribute is initialized to "on") for all devices other +power/control attribute is initialized to "on") for all devices other than hubs. Hubs, at least, appear to be reasonably well-behaved in this regard. @@ -373,7 +376,7 @@ usb_autopm_put_interface() in its close or release routine. But other patterns are possible. The autosuspend attempts mentioned above will often fail for one -reason or another. For example, the power/level attribute might be +reason or another. For example, the power/control attribute might be set to "on", or another interface in the same device might not be idle. This is perfectly normal. If the reason for failure was that the device hasn't been idle for long enough, a timer is scheduled to @@ -394,12 +397,12 @@ Drivers can enable autosuspend for their devices by calling in their probe() routine, if they know that the device is capable of suspending and resuming correctly. This is exactly equivalent to -writing "auto" to the device's power/level attribute. Likewise, +writing "auto" to the device's power/control attribute. Likewise, drivers can disable autosuspend by calling usb_disable_autosuspend(struct usb_device *udev); -This is exactly the same as writing "on" to the power/level attribute. +This is exactly the same as writing "on" to the power/control attribute. Sometimes a driver needs to make sure that remote wakeup is enabled during autosuspend. For example, there's not much point diff --git a/Documentation/usb/usb-serial.txt b/Documentation/usb/usb-serial.txt index ff2c1ff57ba2..f4d214510259 100644 --- a/Documentation/usb/usb-serial.txt +++ b/Documentation/usb/usb-serial.txt @@ -194,6 +194,10 @@ FTDI Single Port Serial Driver This is a single port DB-25 serial adapter. + Devices supported include: + -TripNav TN-200 USB GPS + -Navis Engineering Bureau CH-4711 USB GPS + For any questions or problems with this driver, please contact Bill Ryder. @@ -216,7 +220,7 @@ Cypress M8 CY4601 Family Serial Driver Devices supported: - -DeLorme's USB Earthmate (SiRF Star II lp arch) + -DeLorme's USB Earthmate GPS (SiRF Star II lp arch) -Cypress HID->COM RS232 adapter Note: Cypress Semiconductor claims no affiliation with the @@ -392,9 +396,10 @@ REINER SCT cyberJack pinpad/e-com USB chipcard reader Prolific PL2303 Driver This driver supports any device that has the PL2303 chip from Prolific - in it. This includes a number of single port USB to serial - converters and USB GPS devices. Devices from Aten (the UC-232) and - IO-Data work with this driver, as does the DCU-11 mobile-phone cable. + in it. This includes a number of single port USB to serial converters, + more than 70% of USB GPS devices (in 2010), and some USB UPSes. Devices + from Aten (the UC-232) and IO-Data work with this driver, as does + the DCU-11 mobile-phone cable. For any questions or problems with this driver, please contact Greg Kroah-Hartman at greg@kroah.com @@ -435,6 +440,22 @@ Winchiphead CH341 Driver For any questions or problems with this driver, please contact frank@kingswood-consulting.co.uk. +Moschip MCS7720, MCS7715 driver + + These chips are present in devices sold by various manufacturers, such as Syba + and Cables Unlimited. There may be others. The 7720 provides two serial + ports, and the 7715 provides one serial and one standard PC parallel port. + Support for the 7715's parallel port is enabled by a separate option, which + will not appear unless parallel port support is first enabled at the top-level + of the Device Drivers config menu. Currently only compatibility mode is + supported on the parallel port (no ECP/EPP). + + TODO: + - Implement ECP/EPP modes for the parallel port. + - Baud rates higher than 115200 are currently broken. + - Devices with a single serial port based on the Moschip MCS7703 may work + with this driver with a simple addition to the usb_device_id table. I + don't have one of these devices, so I can't say for sure. Generic Serial driver diff --git a/Documentation/video4linux/CARDLIST.bttv b/Documentation/video4linux/CARDLIST.bttv index f11c583295e9..4739d5684305 100644 --- a/Documentation/video4linux/CARDLIST.bttv +++ b/Documentation/video4linux/CARDLIST.bttv @@ -100,7 +100,7 @@ 99 -> AD-TVK503 100 -> Hercules Smart TV Stereo 101 -> Pace TV & Radio Card -102 -> IVC-200 [0000:a155,0001:a155,0002:a155,0003:a155,0100:a155,0101:a155,0102:a155,0103:a155] +102 -> IVC-200 [0000:a155,0001:a155,0002:a155,0003:a155,0100:a155,0101:a155,0102:a155,0103:a155,0800:a155,0801:a155,0802:a155,0803:a155] 103 -> Grand X-Guard / Trust 814PCI [0304:0102] 104 -> Nebula Electronics DigiTV [0071:0101] 105 -> ProVideo PV143 [aa00:1430,aa00:1431,aa00:1432,aa00:1433,aa03:1433] diff --git a/Documentation/video4linux/CARDLIST.cx88 b/Documentation/video4linux/CARDLIST.cx88 index 7ec3c4e4b60f..f2510541373b 100644 --- a/Documentation/video4linux/CARDLIST.cx88 +++ b/Documentation/video4linux/CARDLIST.cx88 @@ -82,3 +82,4 @@ 81 -> Leadtek WinFast DTV1800 Hybrid [107d:6654] 82 -> WinFast DTV2000 H rev. J [107d:6f2b] 83 -> Prof 7301 DVB-S/S2 [b034:3034] + 84 -> Samsung SMT 7020 DVB-S [18ac:dc00,18ac:dccd] diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx index 0c166ff003a0..3a623aaeae5f 100644 --- a/Documentation/video4linux/CARDLIST.em28xx +++ b/Documentation/video4linux/CARDLIST.em28xx @@ -1,5 +1,5 @@ 0 -> Unknown EM2800 video grabber (em2800) [eb1a:2800] - 1 -> Unknown EM2750/28xx video grabber (em2820/em2840) [eb1a:2710,eb1a:2820,eb1a:2821,eb1a:2860,eb1a:2861,eb1a:2862,eb1a:2870,eb1a:2881,eb1a:2883,eb1a:2868] + 1 -> Unknown EM2750/28xx video grabber (em2820/em2840) [eb1a:2710,eb1a:2820,eb1a:2821,eb1a:2860,eb1a:2861,eb1a:2862,eb1a:2863,eb1a:2870,eb1a:2881,eb1a:2883,eb1a:2868] 2 -> Terratec Cinergy 250 USB (em2820/em2840) [0ccd:0036] 3 -> Pinnacle PCTV USB 2 (em2820/em2840) [2304:0208] 4 -> Hauppauge WinTV USB 2 (em2820/em2840) [2040:4200,2040:4201] @@ -27,6 +27,7 @@ 26 -> Hercules Smart TV USB 2.0 (em2820/em2840) 27 -> Pinnacle PCTV USB 2 (Philips FM1216ME) (em2820/em2840) 28 -> Leadtek Winfast USB II Deluxe (em2820/em2840) + 29 -> EM2860/TVP5150 Reference Design (em2860) 30 -> Videology 20K14XUSB USB2.0 (em2820/em2840) 31 -> Usbgear VD204v9 (em2821) 32 -> Supercomp USB 2.0 TV (em2821) @@ -70,3 +71,4 @@ 72 -> Gadmei UTV330+ (em2861) 73 -> Reddo DVB-C USB TV Box (em2870) 74 -> Actionmaster/LinXcel/Digitus VC211A (em2800) + 75 -> Dikom DK300 (em2882) diff --git a/Documentation/video4linux/CARDLIST.saa7134 b/Documentation/video4linux/CARDLIST.saa7134 index b4a767060ed7..070f2576707e 100644 --- a/Documentation/video4linux/CARDLIST.saa7134 +++ b/Documentation/video4linux/CARDLIST.saa7134 @@ -175,3 +175,6 @@ 174 -> Asus Europa Hybrid OEM [1043:4847] 175 -> Leadtek Winfast DTV1000S [107d:6655] 176 -> Beholder BeholdTV 505 RDS [0000:5051] +177 -> Hawell HW-404M7 +179 -> Beholder BeholdTV H7 [5ace:7190] +180 -> Beholder BeholdTV A7 [5ace:7090] diff --git a/Documentation/video4linux/extract_xc3028.pl b/Documentation/video4linux/extract_xc3028.pl index 2cb816047fc1..47877deae6d7 100644 --- a/Documentation/video4linux/extract_xc3028.pl +++ b/Documentation/video4linux/extract_xc3028.pl @@ -5,12 +5,18 @@ # # In order to use, you need to: # 1) Download the windows driver with something like: +# Version 2.4 +# wget http://www.twinhan.com/files/AW/BDA T/20080303_V1.0.6.7.zip +# or wget http://www.stefanringel.de/pub/20080303_V1.0.6.7.zip +# Version 2.7 # wget http://www.steventoth.net/linux/xc5000/HVR-12x0-14x0-17x0_1_25_25271_WHQL.zip -# 2) Extract the file hcw85bda.sys from the zip into the current dir: +# 2) Extract the files from the zip into the current dir: +# unzip -j 20080303_V1.0.6.7.zip 20080303_v1.0.6.7/UDXTTM6000.sys # unzip -j HVR-12x0-14x0-17x0_1_25_25271_WHQL.zip Driver85/hcw85bda.sys # 3) run the script: # ./extract_xc3028.pl -# 4) copy the generated file: +# 4) copy the generated files: +# cp xc3028-v24.fw /lib/firmware # cp xc3028-v27.fw /lib/firmware #use strict; @@ -135,7 +141,7 @@ sub write_hunk_fix_endian($$) } } -sub main_firmware($$$$) +sub main_firmware_24($$$$) { my $out; my $j=0; @@ -146,8 +152,774 @@ sub main_firmware($$$$) for ($j = length($name); $j <32; $j++) { $name = $name.chr(0); + } + + open OUTFILE, ">$outfile"; + syswrite(OUTFILE, $name); + write_le16($version); + write_le16($nr_desc); + + # + # Firmware 0, type: BASE FW F8MHZ (0x00000003), id: (0000000000000000), size: 6635 + # + + write_le32(0x00000003); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(6635); # Size + write_hunk_fix_endian(257752, 6635); + + # + # Firmware 1, type: BASE FW F8MHZ MTS (0x00000007), id: (0000000000000000), size: 6635 + # + + write_le32(0x00000007); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(6635); # Size + write_hunk_fix_endian(264392, 6635); + + # + # Firmware 2, type: BASE FW FM (0x00000401), id: (0000000000000000), size: 6525 + # + + write_le32(0x00000401); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(6525); # Size + write_hunk_fix_endian(271040, 6525); + + # + # Firmware 3, type: BASE FW FM INPUT1 (0x00000c01), id: (0000000000000000), size: 6539 + # + + write_le32(0x00000c01); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(6539); # Size + write_hunk_fix_endian(277568, 6539); + + # + # Firmware 4, type: BASE FW (0x00000001), id: (0000000000000000), size: 6633 + # + + write_le32(0x00000001); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(6633); # Size + write_hunk_fix_endian(284120, 6633); + + # + # Firmware 5, type: BASE FW MTS (0x00000005), id: (0000000000000000), size: 6617 + # + + write_le32(0x00000005); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(6617); # Size + write_hunk_fix_endian(290760, 6617); + + # + # Firmware 6, type: STD FW (0x00000000), id: PAL/BG A2/A (0000000100000007), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000001, 0x00000007); # ID + write_le32(161); # Size + write_hunk_fix_endian(297384, 161); + + # + # Firmware 7, type: STD FW MTS (0x00000004), id: PAL/BG A2/A (0000000100000007), size: 169 + # + + write_le32(0x00000004); # Type + write_le64(0x00000001, 0x00000007); # ID + write_le32(169); # Size + write_hunk_fix_endian(297552, 169); + + # + # Firmware 8, type: STD FW (0x00000000), id: PAL/BG A2/B (0000000200000007), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000002, 0x00000007); # ID + write_le32(161); # Size + write_hunk_fix_endian(297728, 161); + + # + # Firmware 9, type: STD FW MTS (0x00000004), id: PAL/BG A2/B (0000000200000007), size: 169 + # + + write_le32(0x00000004); # Type + write_le64(0x00000002, 0x00000007); # ID + write_le32(169); # Size + write_hunk_fix_endian(297896, 169); + + # + # Firmware 10, type: STD FW (0x00000000), id: PAL/BG NICAM/A (0000000400000007), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000004, 0x00000007); # ID + write_le32(161); # Size + write_hunk_fix_endian(298072, 161); + + # + # Firmware 11, type: STD FW MTS (0x00000004), id: PAL/BG NICAM/A (0000000400000007), size: 169 + # + + write_le32(0x00000004); # Type + write_le64(0x00000004, 0x00000007); # ID + write_le32(169); # Size + write_hunk_fix_endian(298240, 169); + + # + # Firmware 12, type: STD FW (0x00000000), id: PAL/BG NICAM/B (0000000800000007), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000008, 0x00000007); # ID + write_le32(161); # Size + write_hunk_fix_endian(298416, 161); + + # + # Firmware 13, type: STD FW MTS (0x00000004), id: PAL/BG NICAM/B (0000000800000007), size: 169 + # + + write_le32(0x00000004); # Type + write_le64(0x00000008, 0x00000007); # ID + write_le32(169); # Size + write_hunk_fix_endian(298584, 169); + + # + # Firmware 14, type: STD FW (0x00000000), id: PAL/DK A2 (00000003000000e0), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000003, 0x000000e0); # ID + write_le32(161); # Size + write_hunk_fix_endian(298760, 161); + + # + # Firmware 15, type: STD FW MTS (0x00000004), id: PAL/DK A2 (00000003000000e0), size: 169 + # + + write_le32(0x00000004); # Type + write_le64(0x00000003, 0x000000e0); # ID + write_le32(169); # Size + write_hunk_fix_endian(298928, 169); + + # + # Firmware 16, type: STD FW (0x00000000), id: PAL/DK NICAM (0000000c000000e0), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x0000000c, 0x000000e0); # ID + write_le32(161); # Size + write_hunk_fix_endian(299104, 161); + + # + # Firmware 17, type: STD FW MTS (0x00000004), id: PAL/DK NICAM (0000000c000000e0), size: 169 + # + + write_le32(0x00000004); # Type + write_le64(0x0000000c, 0x000000e0); # ID + write_le32(169); # Size + write_hunk_fix_endian(299272, 169); + + # + # Firmware 18, type: STD FW (0x00000000), id: SECAM/K1 (0000000000200000), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000000, 0x00200000); # ID + write_le32(161); # Size + write_hunk_fix_endian(299448, 161); + + # + # Firmware 19, type: STD FW MTS (0x00000004), id: SECAM/K1 (0000000000200000), size: 169 + # + + write_le32(0x00000004); # Type + write_le64(0x00000000, 0x00200000); # ID + write_le32(169); # Size + write_hunk_fix_endian(299616, 169); + + # + # Firmware 20, type: STD FW (0x00000000), id: SECAM/K3 (0000000004000000), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000000, 0x04000000); # ID + write_le32(161); # Size + write_hunk_fix_endian(299792, 161); + + # + # Firmware 21, type: STD FW MTS (0x00000004), id: SECAM/K3 (0000000004000000), size: 169 + # + + write_le32(0x00000004); # Type + write_le64(0x00000000, 0x04000000); # ID + write_le32(169); # Size + write_hunk_fix_endian(299960, 169); + + # + # Firmware 22, type: STD FW D2633 DTV6 ATSC (0x00010030), id: (0000000000000000), size: 149 + # + + write_le32(0x00010030); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(149); # Size + write_hunk_fix_endian(300136, 149); + + # + # Firmware 23, type: STD FW D2620 DTV6 QAM (0x00000068), id: (0000000000000000), size: 149 + # + + write_le32(0x00000068); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(149); # Size + write_hunk_fix_endian(300296, 149); + + # + # Firmware 24, type: STD FW D2633 DTV6 QAM (0x00000070), id: (0000000000000000), size: 149 + # + + write_le32(0x00000070); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(149); # Size + write_hunk_fix_endian(300448, 149); + + # + # Firmware 25, type: STD FW D2620 DTV7 (0x00000088), id: (0000000000000000), size: 149 + # + + write_le32(0x00000088); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(149); # Size + write_hunk_fix_endian(300608, 149); + + # + # Firmware 26, type: STD FW D2633 DTV7 (0x00000090), id: (0000000000000000), size: 149 + # + + write_le32(0x00000090); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(149); # Size + write_hunk_fix_endian(300760, 149); + + # + # Firmware 27, type: STD FW D2620 DTV78 (0x00000108), id: (0000000000000000), size: 149 + # + + write_le32(0x00000108); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(149); # Size + write_hunk_fix_endian(300920, 149); + + # + # Firmware 28, type: STD FW D2633 DTV78 (0x00000110), id: (0000000000000000), size: 149 + # + + write_le32(0x00000110); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(149); # Size + write_hunk_fix_endian(301072, 149); + + # + # Firmware 29, type: STD FW D2620 DTV8 (0x00000208), id: (0000000000000000), size: 149 + # + + write_le32(0x00000208); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(149); # Size + write_hunk_fix_endian(301232, 149); + + # + # Firmware 30, type: STD FW D2633 DTV8 (0x00000210), id: (0000000000000000), size: 149 + # + + write_le32(0x00000210); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(149); # Size + write_hunk_fix_endian(301384, 149); + + # + # Firmware 31, type: STD FW FM (0x00000400), id: (0000000000000000), size: 135 + # + + write_le32(0x00000400); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le32(135); # Size + write_hunk_fix_endian(301554, 135); + + # + # Firmware 32, type: STD FW (0x00000000), id: PAL/I (0000000000000010), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000000, 0x00000010); # ID + write_le32(161); # Size + write_hunk_fix_endian(301688, 161); + + # + # Firmware 33, type: STD FW MTS (0x00000004), id: PAL/I (0000000000000010), size: 169 + # + + write_le32(0x00000004); # Type + write_le64(0x00000000, 0x00000010); # ID + write_le32(169); # Size + write_hunk_fix_endian(301856, 169); + + # + # Firmware 34, type: STD FW (0x00000000), id: SECAM/L AM (0000001000400000), size: 169 + # + + # + # Firmware 35, type: STD FW (0x00000000), id: SECAM/L NICAM (0000000c00400000), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x0000000c, 0x00400000); # ID + write_le32(161); # Size + write_hunk_fix_endian(302032, 161); + + # + # Firmware 36, type: STD FW (0x00000000), id: SECAM/Lc (0000000000800000), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000000, 0x00800000); # ID + write_le32(161); # Size + write_hunk_fix_endian(302200, 161); + + # + # Firmware 37, type: STD FW (0x00000000), id: NTSC/M Kr (0000000000008000), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000000, 0x00008000); # ID + write_le32(161); # Size + write_hunk_fix_endian(302368, 161); + + # + # Firmware 38, type: STD FW LCD (0x00001000), id: NTSC/M Kr (0000000000008000), size: 161 + # + + write_le32(0x00001000); # Type + write_le64(0x00000000, 0x00008000); # ID + write_le32(161); # Size + write_hunk_fix_endian(302536, 161); + + # + # Firmware 39, type: STD FW LCD NOGD (0x00003000), id: NTSC/M Kr (0000000000008000), size: 161 + # + + write_le32(0x00003000); # Type + write_le64(0x00000000, 0x00008000); # ID + write_le32(161); # Size + write_hunk_fix_endian(302704, 161); + + # + # Firmware 40, type: STD FW MTS (0x00000004), id: NTSC/M Kr (0000000000008000), size: 169 + # + + write_le32(0x00000004); # Type + write_le64(0x00000000, 0x00008000); # ID + write_le32(169); # Size + write_hunk_fix_endian(302872, 169); + + # + # Firmware 41, type: STD FW (0x00000000), id: NTSC PAL/M PAL/N (000000000000b700), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000000, 0x0000b700); # ID + write_le32(161); # Size + write_hunk_fix_endian(303048, 161); + + # + # Firmware 42, type: STD FW LCD (0x00001000), id: NTSC PAL/M PAL/N (000000000000b700), size: 161 + # + + write_le32(0x00001000); # Type + write_le64(0x00000000, 0x0000b700); # ID + write_le32(161); # Size + write_hunk_fix_endian(303216, 161); + + # + # Firmware 43, type: STD FW LCD NOGD (0x00003000), id: NTSC PAL/M PAL/N (000000000000b700), size: 161 + # + + write_le32(0x00003000); # Type + write_le64(0x00000000, 0x0000b700); # ID + write_le32(161); # Size + write_hunk_fix_endian(303384, 161); + + # + # Firmware 44, type: STD FW (0x00000000), id: NTSC/M Jp (0000000000002000), size: 161 + # + + write_le32(0x00000000); # Type + write_le64(0x00000000, 0x00002000); # ID + write_le32(161); # Size + write_hunk_fix_endian(303552, 161); + + # + # Firmware 45, type: STD FW MTS (0x00000004), id: NTSC PAL/M PAL/N (000000000000b700), size: 169 + # + + write_le32(0x00000004); # Type + write_le64(0x00000000, 0x0000b700); # ID + write_le32(169); # Size + write_hunk_fix_endian(303720, 169); + + # + # Firmware 46, type: STD FW MTS LCD (0x00001004), id: NTSC PAL/M PAL/N (000000000000b700), size: 169 + # + + write_le32(0x00001004); # Type + write_le64(0x00000000, 0x0000b700); # ID + write_le32(169); # Size + write_hunk_fix_endian(303896, 169); + + # + # Firmware 47, type: STD FW MTS LCD NOGD (0x00003004), id: NTSC PAL/M PAL/N (000000000000b700), size: 169 + # + + write_le32(0x00003004); # Type + write_le64(0x00000000, 0x0000b700); # ID + write_le32(169); # Size + write_hunk_fix_endian(304072, 169); + + # + # Firmware 48, type: SCODE FW HAS IF (0x60000000), IF = 3.28 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(3280); # IF + write_le32(192); # Size + write_hunk(309048, 192); + + # + # Firmware 49, type: SCODE FW HAS IF (0x60000000), IF = 3.30 MHz id: (0000000000000000), size: 192 + # + +# write_le32(0x60000000); # Type +# write_le64(0x00000000, 0x00000000); # ID +# write_le16(3300); # IF +# write_le32(192); # Size +# write_hunk(304440, 192); + + # + # Firmware 50, type: SCODE FW HAS IF (0x60000000), IF = 3.44 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(3440); # IF + write_le32(192); # Size + write_hunk(309432, 192); + + # + # Firmware 51, type: SCODE FW HAS IF (0x60000000), IF = 3.46 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(3460); # IF + write_le32(192); # Size + write_hunk(309624, 192); + + # + # Firmware 52, type: SCODE FW DTV6 ATSC OREN36 HAS IF (0x60210020), IF = 3.80 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60210020); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(3800); # IF + write_le32(192); # Size + write_hunk(306936, 192); + + # + # Firmware 53, type: SCODE FW HAS IF (0x60000000), IF = 4.00 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(4000); # IF + write_le32(192); # Size + write_hunk(309240, 192); + + # + # Firmware 54, type: SCODE FW DTV6 ATSC TOYOTA388 HAS IF (0x60410020), IF = 4.08 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60410020); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(4080); # IF + write_le32(192); # Size + write_hunk(307128, 192); + + # + # Firmware 55, type: SCODE FW HAS IF (0x60000000), IF = 4.20 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(4200); # IF + write_le32(192); # Size + write_hunk(308856, 192); + + # + # Firmware 56, type: SCODE FW MONO HAS IF (0x60008000), IF = 4.32 MHz id: NTSC/M Kr (0000000000008000), size: 192 + # + + write_le32(0x60008000); # Type + write_le64(0x00000000, 0x00008000); # ID + write_le16(4320); # IF + write_le32(192); # Size + write_hunk(305208, 192); + + # + # Firmware 57, type: SCODE FW HAS IF (0x60000000), IF = 4.45 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(4450); # IF + write_le32(192); # Size + write_hunk(309816, 192); + + # + # Firmware 58, type: SCODE FW MTS LCD NOGD MONO IF HAS IF (0x6002b004), IF = 4.50 MHz id: NTSC PAL/M PAL/N (000000000000b700), size: 192 + # + + write_le32(0x6002b004); # Type + write_le64(0x00000000, 0x0000b700); # ID + write_le16(4500); # IF + write_le32(192); # Size + write_hunk(304824, 192); + + # + # Firmware 59, type: SCODE FW LCD NOGD IF HAS IF (0x60023000), IF = 4.60 MHz id: NTSC/M Kr (0000000000008000), size: 192 + # + + write_le32(0x60023000); # Type + write_le64(0x00000000, 0x00008000); # ID + write_le16(4600); # IF + write_le32(192); # Size + write_hunk(305016, 192); + + # + # Firmware 60, type: SCODE FW DTV6 QAM DTV7 DTV78 DTV8 ZARLINK456 HAS IF (0x620003e0), IF = 4.76 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x620003e0); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(4760); # IF + write_le32(192); # Size + write_hunk(304440, 192); + + # + # Firmware 61, type: SCODE FW HAS IF (0x60000000), IF = 4.94 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(4940); # IF + write_le32(192); # Size + write_hunk(308664, 192); + + # + # Firmware 62, type: SCODE FW HAS IF (0x60000000), IF = 5.26 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(5260); # IF + write_le32(192); # Size + write_hunk(307704, 192); + + # + # Firmware 63, type: SCODE FW MONO HAS IF (0x60008000), IF = 5.32 MHz id: PAL/BG A2 NICAM (0000000f00000007), size: 192 + # + + write_le32(0x60008000); # Type + write_le64(0x0000000f, 0x00000007); # ID + write_le16(5320); # IF + write_le32(192); # Size + write_hunk(307896, 192); + + # + # Firmware 64, type: SCODE FW DTV7 DTV78 DTV8 DIBCOM52 CHINA HAS IF (0x65000380), IF = 5.40 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x65000380); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(5400); # IF + write_le32(192); # Size + write_hunk(304248, 192); + + # + # Firmware 65, type: SCODE FW DTV6 ATSC OREN538 HAS IF (0x60110020), IF = 5.58 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60110020); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(5580); # IF + write_le32(192); # Size + write_hunk(306744, 192); + + # + # Firmware 66, type: SCODE FW HAS IF (0x60000000), IF = 5.64 MHz id: PAL/BG A2 (0000000300000007), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000003, 0x00000007); # ID + write_le16(5640); # IF + write_le32(192); # Size + write_hunk(305592, 192); + + # + # Firmware 67, type: SCODE FW HAS IF (0x60000000), IF = 5.74 MHz id: PAL/BG NICAM (0000000c00000007), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x0000000c, 0x00000007); # ID + write_le16(5740); # IF + write_le32(192); # Size + write_hunk(305784, 192); + + # + # Firmware 68, type: SCODE FW HAS IF (0x60000000), IF = 5.90 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(5900); # IF + write_le32(192); # Size + write_hunk(307512, 192); + + # + # Firmware 69, type: SCODE FW MONO HAS IF (0x60008000), IF = 6.00 MHz id: PAL/DK PAL/I SECAM/K3 SECAM/L SECAM/Lc NICAM (0000000c04c000f0), size: 192 + # + + write_le32(0x60008000); # Type + write_le64(0x0000000c, 0x04c000f0); # ID + write_le16(6000); # IF + write_le32(192); # Size + write_hunk(305576, 192); + + # + # Firmware 70, type: SCODE FW DTV6 QAM ATSC LG60 F6MHZ HAS IF (0x68050060), IF = 6.20 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x68050060); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(6200); # IF + write_le32(192); # Size + write_hunk(306552, 192); + + # + # Firmware 71, type: SCODE FW HAS IF (0x60000000), IF = 6.24 MHz id: PAL/I (0000000000000010), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000000, 0x00000010); # ID + write_le16(6240); # IF + write_le32(192); # Size + write_hunk(305400, 192); + + # + # Firmware 72, type: SCODE FW MONO HAS IF (0x60008000), IF = 6.32 MHz id: SECAM/K1 (0000000000200000), size: 192 + # + + write_le32(0x60008000); # Type + write_le64(0x00000000, 0x00200000); # ID + write_le16(6320); # IF + write_le32(192); # Size + write_hunk(308472, 192); + + # + # Firmware 73, type: SCODE FW HAS IF (0x60000000), IF = 6.34 MHz id: SECAM/K1 (0000000000200000), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000000, 0x00200000); # ID + write_le16(6340); # IF + write_le32(192); # Size + write_hunk(306360, 192); + + # + # Firmware 74, type: SCODE FW MONO HAS IF (0x60008000), IF = 6.50 MHz id: PAL/DK SECAM/K3 SECAM/L NICAM (0000000c044000e0), size: 192 + # + + write_le32(0x60008000); # Type + write_le64(0x0000000c, 0x044000e0); # ID + write_le16(6500); # IF + write_le32(192); # Size + write_hunk(308280, 192); + + # + # Firmware 75, type: SCODE FW DTV6 ATSC ATI638 HAS IF (0x60090020), IF = 6.58 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60090020); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(6580); # IF + write_le32(192); # Size + write_hunk(304632, 192); + + # + # Firmware 76, type: SCODE FW HAS IF (0x60000000), IF = 6.60 MHz id: PAL/DK A2 (00000003000000e0), size: 192 + # + + write_le32(0x60000000); # Type + write_le64(0x00000003, 0x000000e0); # ID + write_le16(6600); # IF + write_le32(192); # Size + write_hunk(306168, 192); + + # + # Firmware 77, type: SCODE FW MONO HAS IF (0x60008000), IF = 6.68 MHz id: PAL/DK A2 (00000003000000e0), size: 192 + # + + write_le32(0x60008000); # Type + write_le64(0x00000003, 0x000000e0); # ID + write_le16(6680); # IF + write_le32(192); # Size + write_hunk(308088, 192); + + # + # Firmware 78, type: SCODE FW DTV6 ATSC TOYOTA794 HAS IF (0x60810020), IF = 8.14 MHz id: (0000000000000000), size: 192 + # + + write_le32(0x60810020); # Type + write_le64(0x00000000, 0x00000000); # ID + write_le16(8140); # IF + write_le32(192); # Size + write_hunk(307320, 192); + + # + # Firmware 79, type: SCODE FW HAS IF (0x60000000), IF = 8.20 MHz id: (0000000000000000), size: 192 + # + +# write_le32(0x60000000); # Type +# write_le64(0x00000000, 0x00000000); # ID +# write_le16(8200); # IF +# write_le32(192); # Size +# write_hunk(308088, 192); } +sub main_firmware_27($$$$) +{ + my $out; + my $j=0; + my $outfile = shift; + my $name = shift; + my $version = shift; + my $nr_desc = shift; + + for ($j = length($name); $j <32; $j++) { + $name = $name.chr(0); + } + open OUTFILE, ">$outfile"; syswrite(OUTFILE, $name); write_le16($version); @@ -906,20 +1678,39 @@ sub main_firmware($$$$) write_hunk(812856, 192); } + sub extract_firmware { - my $sourcefile = "hcw85bda.sys"; - my $hash = "0e44dbf63bb0169d57446aec21881ff2"; - my $outfile = "xc3028-v27.fw"; - my $name = "xc2028 firmware"; - my $version = 519; - my $nr_desc = 80; + my $sourcefile_24 = "UDXTTM6000.sys"; + my $hash_24 = "cb9deb5508a5e150af2880f5b0066d78"; + my $outfile_24 = "xc3028-v24.fw"; + my $name_24 = "xc2028 firmware"; + my $version_24 = 516; + my $nr_desc_24 = 77; + my $out; + + my $sourcefile_27 = "hcw85bda.sys"; + my $hash_27 = "0e44dbf63bb0169d57446aec21881ff2"; + my $outfile_27 = "xc3028-v27.fw"; + my $name_27 = "xc2028 firmware"; + my $version_27 = 519; + my $nr_desc_27 = 80; my $out; - verify($sourcefile, $hash); + if (-e $sourcefile_24) { + verify($sourcefile_24, $hash_24); + + open INFILE, "<$sourcefile_24"; + main_firmware_24($outfile_24, $name_24, $version_24, $nr_desc_24); + close INFILE; + } - open INFILE, "<$sourcefile"; - main_firmware($outfile, $name, $version, $nr_desc); - close INFILE; + if (-e $sourcefile_27) { + verify($sourcefile_27, $hash_27); + + open INFILE, "<$sourcefile_27"; + main_firmware_27($outfile_27, $name_27, $version_27, $nr_desc_27); + close INFILE; + } } extract_firmware; diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt index 181b9e6fd984..8f3f5d33327c 100644 --- a/Documentation/video4linux/gspca.txt +++ b/Documentation/video4linux/gspca.txt @@ -50,6 +50,8 @@ zc3xx 0458:700f Genius VideoCam Web V2 sonixj 0458:7025 Genius Eye 311Q sn9c20x 0458:7029 Genius Look 320s sonixj 0458:702e Genius Slim 310 NB +sn9c20x 0458:704a Genius Slim 1320 +sn9c20x 0458:704c Genius i-Look 1321 sn9c20x 045e:00f4 LifeCam VX-6000 (SN9C20x + OV9650) sonixj 045e:00f5 MicroSoft VX3000 sonixj 045e:00f7 MicroSoft VX1000 @@ -305,12 +307,14 @@ sonixj 0c45:6138 Sn9c120 Mo4000 sonixj 0c45:613a Microdia Sonix PC Camera sonixj 0c45:613b Surfer SN-206 sonixj 0c45:613c Sonix Pccam168 +sonixj 0c45:6142 Hama PC-Webcam AC-150 sonixj 0c45:6143 Sonix Pccam168 sonixj 0c45:6148 Digitus DA-70811/ZSMC USB PC Camera ZS211/Microdia sonixj 0c45:614a Frontech E-Ccam (JIL-2225) sn9c20x 0c45:6240 PC Camera (SN9C201 + MT9M001) sn9c20x 0c45:6242 PC Camera (SN9C201 + MT9M111) sn9c20x 0c45:6248 PC Camera (SN9C201 + OV9655) +sn9c20x 0c45:624c PC Camera (SN9C201 + MT9M112) sn9c20x 0c45:624e PC Camera (SN9C201 + SOI968) sn9c20x 0c45:624f PC Camera (SN9C201 + OV9650) sn9c20x 0c45:6251 PC Camera (SN9C201 + OV9650) @@ -323,6 +327,7 @@ sn9c20x 0c45:627f PC Camera (SN9C201 + OV9650) sn9c20x 0c45:6280 PC Camera (SN9C202 + MT9M001) sn9c20x 0c45:6282 PC Camera (SN9C202 + MT9M111) sn9c20x 0c45:6288 PC Camera (SN9C202 + OV9655) +sn9c20x 0c45:628c PC Camera (SN9C201 + MT9M112) sn9c20x 0c45:628e PC Camera (SN9C202 + SOI968) sn9c20x 0c45:628f PC Camera (SN9C202 + OV9650) sn9c20x 0c45:62a0 PC Camera (SN9C202 + OV7670) diff --git a/Documentation/video4linux/sh_mobile_ceu_camera.txt b/Documentation/video4linux/sh_mobile_ceu_camera.txt index 2ae16349a78d..cb47e723af74 100644 --- a/Documentation/video4linux/sh_mobile_ceu_camera.txt +++ b/Documentation/video4linux/sh_mobile_ceu_camera.txt @@ -17,18 +17,18 @@ Generic scaling / cropping scheme -2-- -\ | --\ | --\ -+-5-- -\ -- -3-- -| ---\ -| --- -4-- -\ -| -\ -| - -6-- ++-5-- . -- -3-- -\ +| `... -\ +| `... -4-- . - -7.. +| `. +| `. .6-- | -| - -6'- -| -/ -| --- -4'- -/ -| ---/ -+-5'- -/ -| -- -3'- +| . .6'- +| .´ +| ... -4'- .´ +| ...´ - -7'. ++-5'- .´ -/ +| -- -3'- -/ | --/ | --/ -2'- -/ @@ -36,7 +36,11 @@ Generic scaling / cropping scheme | -1'- -Produced by user requests: +In the above chart minuses and slashes represent "real" data amounts, points and +accents represent "useful" data, basically, CEU scaled amd cropped output, +mapped back onto the client's source plane. + +Such a configuration can be produced by user requests: S_CROP(left / top = (5) - (1), width / height = (5') - (5)) S_FMT(width / height = (6') - (6)) @@ -106,52 +110,30 @@ window: S_CROP ------ -If old scale applied to new crop is invalid produce nearest new scale possible - -1. Calculate current combined scales. - - scale_comb = (((4') - (4)) / ((6') - (6))) * (((2') - (2)) / ((3') - (3))) - -2. Apply iterative sensor S_CROP for new input window. - -3. If old combined scales applied to new crop produce an impossible user window, -adjust scales to produce nearest possible window. - - width_u_out = ((5') - (5)) / scale_comb +The API at http://v4l2spec.bytesex.org/spec/x1904.htm says: - if (width_u_out > max) - scale_comb = ((5') - (5)) / max; - else if (width_u_out < min) - scale_comb = ((5') - (5)) / min; +"...specification does not define an origin or units. However by convention +drivers should horizontally count unscaled samples relative to 0H." -4. Issue G_CROP to retrieve actual input window. +We choose to follow the advise and interpret cropping units as client input +pixels. -5. Using actual input window and calculated combined scales calculate sensor -target output window. - - width_s_out = ((3') - (3)) = ((2') - (2)) / scale_comb - -6. Apply iterative S_FMT for new sensor target output window. - -7. Issue G_FMT to retrieve the actual sensor output window. - -8. Calculate sensor scales. - - scale_s = ((3') - (3)) / ((2') - (2)) +Cropping is performed in the following 6 steps: -9. Calculate sensor output subwindow to be cropped on CEU by applying sensor -scales to the requested window. +1. Request exactly user rectangle from the sensor. - width_ceu = ((5') - (5)) / scale_s +2. If smaller - iterate until a larger one is obtained. Result: sensor cropped + to 2 : 2', target crop 5 : 5', current output format 6' - 6. -10. Use CEU cropping for above calculated window. +3. In the previous step the sensor has tried to preserve its output frame as + good as possible, but it could have changed. Retrieve it again. -11. Calculate CEU scales from sensor scales from results of (10) and user window -from (3) +4. Sensor scaled to 3 : 3'. Sensor's scale is (2' - 2) / (3' - 3). Calculate + intermediate window: 4' - 4 = (5' - 5) * (3' - 3) / (2' - 2) - scale_ceu = calc_scale(((5') - (5)), &width_u_out) +5. Calculate and apply host scale = (6' - 6) / (4' - 4) -12. Apply CEU scales. +6. Calculate and apply host crop: 6 - 7 = (5 - 2) * (6' - 6) / (5' - 5) -- Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de> diff --git a/Documentation/video4linux/v4l2-framework.txt b/Documentation/video4linux/v4l2-framework.txt index 5155700c206b..e831aaca66f8 100644 --- a/Documentation/video4linux/v4l2-framework.txt +++ b/Documentation/video4linux/v4l2-framework.txt @@ -545,12 +545,11 @@ unregister them: This will remove the device nodes from sysfs (causing udev to remove them from /dev). -After video_unregister_device() returns no new opens can be done. - -However, in the case of USB devices some application might still have one -of these device nodes open. You should block all new accesses to read, -write, poll, etc. except possibly for certain ioctl operations like -queueing buffers. +After video_unregister_device() returns no new opens can be done. However, +in the case of USB devices some application might still have one of these +device nodes open. So after the unregister all file operations will return +an error as well, except for the ioctl and unlocked_ioctl file operations: +those will still be passed on since some buffer ioctls may still be needed. When the last user of the video device node exits, then the vdev->release() callback is called and you can do the final cleanup there. @@ -609,3 +608,135 @@ scatter/gather method (videobuf-dma-sg), DMA with linear access Please see Documentation/video4linux/videobuf for more information on how to use the videobuf layer. + +struct v4l2_fh +-------------- + +struct v4l2_fh provides a way to easily keep file handle specific data +that is used by the V4L2 framework. Using v4l2_fh is optional for +drivers. + +The users of v4l2_fh (in the V4L2 framework, not the driver) know +whether a driver uses v4l2_fh as its file->private_data pointer by +testing the V4L2_FL_USES_V4L2_FH bit in video_device->flags. + +Useful functions: + +- v4l2_fh_init() + + Initialise the file handle. This *MUST* be performed in the driver's + v4l2_file_operations->open() handler. + +- v4l2_fh_add() + + Add a v4l2_fh to video_device file handle list. May be called after + initialising the file handle. + +- v4l2_fh_del() + + Unassociate the file handle from video_device(). The file handle + exit function may now be called. + +- v4l2_fh_exit() + + Uninitialise the file handle. After uninitialisation the v4l2_fh + memory can be freed. + +struct v4l2_fh is allocated as a part of the driver's own file handle +structure and is set to file->private_data in the driver's open +function by the driver. Drivers can extract their own file handle +structure by using the container_of macro. Example: + +struct my_fh { + int blah; + struct v4l2_fh fh; +}; + +... + +int my_open(struct file *file) +{ + struct my_fh *my_fh; + struct video_device *vfd; + int ret; + + ... + + ret = v4l2_fh_init(&my_fh->fh, vfd); + if (ret) + return ret; + + v4l2_fh_add(&my_fh->fh); + + file->private_data = &my_fh->fh; + + ... +} + +int my_release(struct file *file) +{ + struct v4l2_fh *fh = file->private_data; + struct my_fh *my_fh = container_of(fh, struct my_fh, fh); + + ... +} + +V4L2 events +----------- + +The V4L2 events provide a generic way to pass events to user space. +The driver must use v4l2_fh to be able to support V4L2 events. + +Useful functions: + +- v4l2_event_alloc() + + To use events, the driver must allocate events for the file handle. By + calling the function more than once, the driver may assure that at least n + events in total have been allocated. The function may not be called in + atomic context. + +- v4l2_event_queue() + + Queue events to video device. The driver's only responsibility is to fill + in the type and the data fields. The other fields will be filled in by + V4L2. + +- v4l2_event_subscribe() + + The video_device->ioctl_ops->vidioc_subscribe_event must check the driver + is able to produce events with specified event id. Then it calls + v4l2_event_subscribe() to subscribe the event. + +- v4l2_event_unsubscribe() + + vidioc_unsubscribe_event in struct v4l2_ioctl_ops. A driver may use + v4l2_event_unsubscribe() directly unless it wants to be involved in + unsubscription process. + + The special type V4L2_EVENT_ALL may be used to unsubscribe all events. The + drivers may want to handle this in a special way. + +- v4l2_event_pending() + + Returns the number of pending events. Useful when implementing poll. + +Drivers do not initialise events directly. The events are initialised +through v4l2_fh_init() if video_device->ioctl_ops->vidioc_subscribe_event is +non-NULL. This *MUST* be performed in the driver's +v4l2_file_operations->open() handler. + +Events are delivered to user space through the poll system call. The driver +can use v4l2_fh->events->wait wait_queue_head_t as the argument for +poll_wait(). + +There are standard and private events. New standard events must use the +smallest available event type. The drivers must allocate their events from +their own class starting from class base. Class base is +V4L2_EVENT_PRIVATE_START + n * 1000 where n is the lowest available number. +The first event type in the class is reserved for future use, so the first +available event type is 'class base + 1'. + +An example on how the V4L2 events may be used can be found in the OMAP +3 ISP driver available at <URL:http://gitorious.org/omap3camera> as of +writing this. diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX index e57d6a9dd32b..dca82d7c83d8 100644 --- a/Documentation/vm/00-INDEX +++ b/Documentation/vm/00-INDEX @@ -4,23 +4,35 @@ active_mm.txt - An explanation from Linus about tsk->active_mm vs tsk->mm. balance - various information on memory balancing. +hugepage-mmap.c + - Example app using huge page memory with the mmap system call. +hugepage-shm.c + - Example app using huge page memory with Sys V shared memory system calls. hugetlbpage.txt - a brief summary of hugetlbpage support in the Linux kernel. +hwpoison.txt + - explains what hwpoison is ksm.txt - how to use the Kernel Samepage Merging feature. locking - info on how locking and synchronization is done in the Linux vm code. +map_hugetlb.c + - an example program that uses the MAP_HUGETLB mmap flag. numa - information about NUMA specific code in the Linux vm. numa_memory_policy.txt - documentation of concepts and APIs of the 2.6 memory policy support. overcommit-accounting - description of the Linux kernels overcommit handling modes. +page-types.c + - Tool for querying page flags page_migration - description of page migration in NUMA systems. +pagemap.txt + - pagemap, from the userspace perspective slabinfo.c - source code for a tool to get reports about slabs. slub.txt - a short users guide for SLUB. -map_hugetlb.c - - an example program that uses the MAP_HUGETLB mmap flag. +unevictable-lru.txt + - Unevictable LRU infrastructure diff --git a/Documentation/vm/Makefile b/Documentation/vm/Makefile index 5bd269b3731a..9dcff328b964 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 +hostprogs-y := slabinfo page-types hugepage-mmap hugepage-shm map_hugetlb # Tell kbuild to always build the programs always := $(hostprogs-y) diff --git a/Documentation/vm/hugepage-mmap.c b/Documentation/vm/hugepage-mmap.c new file mode 100644 index 000000000000..db0dd9a33d54 --- /dev/null +++ b/Documentation/vm/hugepage-mmap.c @@ -0,0 +1,91 @@ +/* + * hugepage-mmap: + * + * Example of using huge page memory in a user application using the mmap + * system call. Before running this application, make sure that the + * administrator has mounted the hugetlbfs filesystem (on some directory + * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this + * example, the app is requesting memory of size 256MB that is backed by + * huge pages. + * + * For the ia64 architecture, the Linux kernel reserves Region number 4 for + * huge pages. That means that if one requires a fixed address, a huge page + * aligned address starting with 0x800000... will be required. If a fixed + * address is not required, the kernel will select an address in the proper + * range. + * Other architectures, such as ppc64, i386 or x86_64 are not so constrained. + */ + +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/mman.h> +#include <fcntl.h> + +#define FILE_NAME "/mnt/hugepagefile" +#define LENGTH (256UL*1024*1024) +#define PROTECTION (PROT_READ | PROT_WRITE) + +/* Only ia64 requires this */ +#ifdef __ia64__ +#define ADDR (void *)(0x8000000000000000UL) +#define FLAGS (MAP_SHARED | MAP_FIXED) +#else +#define ADDR (void *)(0x0UL) +#define FLAGS (MAP_SHARED) +#endif + +static void check_bytes(char *addr) +{ + printf("First hex is %x\n", *((unsigned int *)addr)); +} + +static void write_bytes(char *addr) +{ + unsigned long i; + + for (i = 0; i < LENGTH; i++) + *(addr + i) = (char)i; +} + +static void read_bytes(char *addr) +{ + unsigned long i; + + check_bytes(addr); + for (i = 0; i < LENGTH; i++) + if (*(addr + i) != (char)i) { + printf("Mismatch at %lu\n", i); + break; + } +} + +int main(void) +{ + void *addr; + int fd; + + fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755); + if (fd < 0) { + perror("Open failed"); + exit(1); + } + + addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + unlink(FILE_NAME); + exit(1); + } + + printf("Returned address is %p\n", addr); + check_bytes(addr); + write_bytes(addr); + read_bytes(addr); + + munmap(addr, LENGTH); + close(fd); + unlink(FILE_NAME); + + return 0; +} diff --git a/Documentation/vm/hugepage-shm.c b/Documentation/vm/hugepage-shm.c new file mode 100644 index 000000000000..07956d8592c9 --- /dev/null +++ b/Documentation/vm/hugepage-shm.c @@ -0,0 +1,98 @@ +/* + * hugepage-shm: + * + * Example of using huge page memory in a user application using Sys V shared + * memory system calls. In this example the app is requesting 256MB of + * memory that is backed by huge pages. The application uses the flag + * SHM_HUGETLB in the shmget system call to inform the kernel that it is + * requesting huge pages. + * + * For the ia64 architecture, the Linux kernel reserves Region number 4 for + * huge pages. That means that if one requires a fixed address, a huge page + * aligned address starting with 0x800000... will be required. If a fixed + * address is not required, the kernel will select an address in the proper + * range. + * Other architectures, such as ppc64, i386 or x86_64 are not so constrained. + * + * Note: The default shared memory limit is quite low on many kernels, + * you may need to increase it via: + * + * echo 268435456 > /proc/sys/kernel/shmmax + * + * This will increase the maximum size per shared memory segment to 256MB. + * The other limit that you will hit eventually is shmall which is the + * total amount of shared memory in pages. To set it to 16GB on a system + * with a 4kB pagesize do: + * + * echo 4194304 > /proc/sys/kernel/shmall + */ + +#include <stdlib.h> +#include <stdio.h> +#include <sys/types.h> +#include <sys/ipc.h> +#include <sys/shm.h> +#include <sys/mman.h> + +#ifndef SHM_HUGETLB +#define SHM_HUGETLB 04000 +#endif + +#define LENGTH (256UL*1024*1024) + +#define dprintf(x) printf(x) + +/* Only ia64 requires this */ +#ifdef __ia64__ +#define ADDR (void *)(0x8000000000000000UL) +#define SHMAT_FLAGS (SHM_RND) +#else +#define ADDR (void *)(0x0UL) +#define SHMAT_FLAGS (0) +#endif + +int main(void) +{ + int shmid; + unsigned long i; + char *shmaddr; + + if ((shmid = shmget(2, LENGTH, + SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W)) < 0) { + perror("shmget"); + exit(1); + } + printf("shmid: 0x%x\n", shmid); + + shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS); + if (shmaddr == (char *)-1) { + perror("Shared memory attach failure"); + shmctl(shmid, IPC_RMID, NULL); + exit(2); + } + printf("shmaddr: %p\n", shmaddr); + + dprintf("Starting the writes:\n"); + for (i = 0; i < LENGTH; i++) { + shmaddr[i] = (char)(i); + if (!(i % (1024 * 1024))) + dprintf("."); + } + dprintf("\n"); + + dprintf("Starting the Check..."); + for (i = 0; i < LENGTH; i++) + if (shmaddr[i] != (char)i) + printf("\nIndex %lu mismatched\n", i); + dprintf("Done.\n"); + + if (shmdt((const void *)shmaddr) != 0) { + perror("Detach failure"); + shmctl(shmid, IPC_RMID, NULL); + exit(3); + } + + shmctl(shmid, IPC_RMID, NULL); + + return 0; +} diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt index bc31636973e3..457634c1e03e 100644 --- a/Documentation/vm/hugetlbpage.txt +++ b/Documentation/vm/hugetlbpage.txt @@ -299,176 +299,11 @@ map_hugetlb.c. ******************************************************************* /* - * Example of using huge page memory in a user application using Sys V shared - * memory system calls. In this example the app is requesting 256MB of - * memory that is backed by huge pages. The application uses the flag - * SHM_HUGETLB in the shmget system call to inform the kernel that it is - * requesting huge pages. - * - * For the ia64 architecture, the Linux kernel reserves Region number 4 for - * huge pages. That means that if one requires a fixed address, a huge page - * aligned address starting with 0x800000... will be required. If a fixed - * address is not required, the kernel will select an address in the proper - * range. - * Other architectures, such as ppc64, i386 or x86_64 are not so constrained. - * - * Note: The default shared memory limit is quite low on many kernels, - * you may need to increase it via: - * - * echo 268435456 > /proc/sys/kernel/shmmax - * - * This will increase the maximum size per shared memory segment to 256MB. - * The other limit that you will hit eventually is shmall which is the - * total amount of shared memory in pages. To set it to 16GB on a system - * with a 4kB pagesize do: - * - * echo 4194304 > /proc/sys/kernel/shmall + * hugepage-shm: see Documentation/vm/hugepage-shm.c */ -#include <stdlib.h> -#include <stdio.h> -#include <sys/types.h> -#include <sys/ipc.h> -#include <sys/shm.h> -#include <sys/mman.h> - -#ifndef SHM_HUGETLB -#define SHM_HUGETLB 04000 -#endif - -#define LENGTH (256UL*1024*1024) - -#define dprintf(x) printf(x) - -#define ADDR (void *)(0x0UL) /* let kernel choose address */ -#define SHMAT_FLAGS (0) - -int main(void) -{ - int shmid; - unsigned long i; - char *shmaddr; - - if ((shmid = shmget(2, LENGTH, - SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W)) < 0) { - perror("shmget"); - exit(1); - } - printf("shmid: 0x%x\n", shmid); - - shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS); - if (shmaddr == (char *)-1) { - perror("Shared memory attach failure"); - shmctl(shmid, IPC_RMID, NULL); - exit(2); - } - printf("shmaddr: %p\n", shmaddr); - - dprintf("Starting the writes:\n"); - for (i = 0; i < LENGTH; i++) { - shmaddr[i] = (char)(i); - if (!(i % (1024 * 1024))) - dprintf("."); - } - dprintf("\n"); - - dprintf("Starting the Check..."); - for (i = 0; i < LENGTH; i++) - if (shmaddr[i] != (char)i) - printf("\nIndex %lu mismatched\n", i); - dprintf("Done.\n"); - - if (shmdt((const void *)shmaddr) != 0) { - perror("Detach failure"); - shmctl(shmid, IPC_RMID, NULL); - exit(3); - } - - shmctl(shmid, IPC_RMID, NULL); - - return 0; -} ******************************************************************* /* - * Example of using huge page memory in a user application using the mmap - * system call. Before running this application, make sure that the - * administrator has mounted the hugetlbfs filesystem (on some directory - * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this - * example, the app is requesting memory of size 256MB that is backed by - * huge pages. - * - * For the ia64 architecture, the Linux kernel reserves Region number 4 for - * huge pages. That means that if one requires a fixed address, a huge page - * aligned address starting with 0x800000... will be required. If a fixed - * address is not required, the kernel will select an address in the proper - * range. - * Other architectures, such as ppc64, i386 or x86_64 are not so constrained. + * hugepage-mmap: see Documentation/vm/hugepage-mmap.c */ -#include <stdlib.h> -#include <stdio.h> -#include <unistd.h> -#include <sys/mman.h> -#include <fcntl.h> - -#define FILE_NAME "/mnt/hugepagefile" -#define LENGTH (256UL*1024*1024) -#define PROTECTION (PROT_READ | PROT_WRITE) - -#define ADDR (void *)(0x0UL) /* let kernel choose address */ -#define FLAGS (MAP_SHARED) - -void check_bytes(char *addr) -{ - printf("First hex is %x\n", *((unsigned int *)addr)); -} - -void write_bytes(char *addr) -{ - unsigned long i; - - for (i = 0; i < LENGTH; i++) - *(addr + i) = (char)i; -} - -void read_bytes(char *addr) -{ - unsigned long i; - - check_bytes(addr); - for (i = 0; i < LENGTH; i++) - if (*(addr + i) != (char)i) { - printf("Mismatch at %lu\n", i); - break; - } -} - -int main(void) -{ - void *addr; - int fd; - - fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755); - if (fd < 0) { - perror("Open failed"); - exit(1); - } - - addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0); - if (addr == MAP_FAILED) { - perror("mmap"); - unlink(FILE_NAME); - exit(1); - } - - printf("Returned address is %p\n", addr); - check_bytes(addr); - write_bytes(addr); - read_bytes(addr); - - munmap(addr, LENGTH); - close(fd); - unlink(FILE_NAME); - - return 0; -} diff --git a/Documentation/vm/map_hugetlb.c b/Documentation/vm/map_hugetlb.c index e2bdae37f499..9969c7d9f985 100644 --- a/Documentation/vm/map_hugetlb.c +++ b/Documentation/vm/map_hugetlb.c @@ -31,12 +31,12 @@ #define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB) #endif -void check_bytes(char *addr) +static void check_bytes(char *addr) { printf("First hex is %x\n", *((unsigned int *)addr)); } -void write_bytes(char *addr) +static void write_bytes(char *addr) { unsigned long i; @@ -44,7 +44,7 @@ void write_bytes(char *addr) *(addr + i) = (char)i; } -void read_bytes(char *addr) +static void read_bytes(char *addr) { unsigned long i; diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt index be45dbb9d7f2..6690fc34ef6d 100644 --- a/Documentation/vm/numa_memory_policy.txt +++ b/Documentation/vm/numa_memory_policy.txt @@ -45,7 +45,7 @@ most general to most specific: to establish the task policy for a child task exec()'d from an executable image that has no awareness of memory policy. See the MEMORY POLICY APIS section, below, for an overview of the system call - that a task may use to set/change it's task/process policy. + that a task may use to set/change its task/process policy. In a multi-threaded task, task policies apply only to the thread [Linux kernel task] that installs the policy and any threads @@ -301,7 +301,7 @@ decrement this reference count, respectively. mpol_put() will only free the structure back to the mempolicy kmem cache when the reference count goes to zero. -When a new memory policy is allocated, it's reference count is initialized +When a new memory policy is allocated, its reference count is initialized to '1', representing the reference held by the task that is installing the new policy. When a pointer to a memory policy structure is stored in another structure, another reference is added, as the task's reference will be dropped diff --git a/Documentation/volatile-considered-harmful.txt b/Documentation/volatile-considered-harmful.txt index 991c26a6ef64..db0cb228d64a 100644 --- a/Documentation/volatile-considered-harmful.txt +++ b/Documentation/volatile-considered-harmful.txt @@ -63,9 +63,9 @@ way to perform a busy wait is: cpu_relax(); The cpu_relax() call can lower CPU power consumption or yield to a -hyperthreaded twin processor; it also happens to serve as a memory barrier, -so, once again, volatile is unnecessary. Of course, busy-waiting is -generally an anti-social act to begin with. +hyperthreaded twin processor; it also happens to serve as a compiler +barrier, so, once again, volatile is unnecessary. Of course, busy- +waiting is generally an anti-social act to begin with. There are still a few rare situations where volatile makes sense in the kernel: diff --git a/Documentation/voyager.txt b/Documentation/voyager.txt deleted file mode 100644 index 2749af552cdf..000000000000 --- a/Documentation/voyager.txt +++ /dev/null @@ -1,95 +0,0 @@ -Running Linux on the Voyager Architecture -========================================= - -For full details and current project status, see - -http://www.hansenpartnership.com/voyager - -The voyager architecture was designed by NCR in the mid 80s to be a -fully SMP capable RAS computing architecture built around intel's 486 -chip set. The voyager came in three levels of architectural -sophistication: 3,4 and 5 --- 1 and 2 never made it out of prototype. -The linux patches support only the Level 5 voyager architecture (any -machine class 3435 and above). - -The Voyager Architecture ------------------------- - -Voyager machines consist of a Baseboard with a 386 diagnostic -processor, a Power Supply Interface (PSI) a Primary and possibly -Secondary Microchannel bus and between 2 and 20 voyager slots. The -voyager slots can be populated with memory and cpu cards (up to 4GB -memory and from 1 486 to 32 Pentium Pro processors). Internally, the -voyager has a dual arbitrated system bus and a configuration and test -bus (CAT). The voyager bus speed is 40MHz. Therefore (since all -voyager cards are dual ported for each system bus) the maximum -transfer rate is 320Mb/s but only if you have your slot configuration -tuned (only memory cards can communicate with both busses at once, CPU -cards utilise them one at a time). - -Voyager SMP ------------ - -Since voyager was the first intel based SMP system, it is slightly -more primitive than the Intel IO-APIC approach to SMP. Voyager allows -arbitrary interrupt routing (including processor affinity routing) of -all 16 PC type interrupts. However it does this by using a modified -5259 master/slave chip set instead of an APIC bus. Additionally, -voyager supports Cross Processor Interrupts (CPI) equivalent to the -APIC IPIs. There are two routed voyager interrupt lines provided to -each slot. - -Processor Cards ---------------- - -These come in single, dyadic and quad configurations (the quads are -problematic--see later). The maximum configuration is 8 quad cards -for 32 way SMP. - -Quad Processors ---------------- - -Because voyager only supplies two interrupt lines to each Processor -card, the Quad processors have to be configured (and Bootstrapped) in -as a pair of Master/Slave processors. - -In fact, most Quad cards only accept one VIC interrupt line, so they -have one interrupt handling processor (called the VIC extended -processor) and three non-interrupt handling processors. - -Current Status --------------- - -The System will boot on Mono, Dyad and Quad cards. There was -originally a Quad boot problem which has been fixed by proper gdt -alignment in the initial boot loader. If you still cannot get your -voyager system to boot, email me at: - -<J.E.J.Bottomley@HansenPartnership.com> - - -The Quad cards now support using the separate Quad CPI vectors instead -of going through the VIC mailbox system. - -The Level 4 architecture (3430 and 3360 Machines) should also work -fine. - -Dump Switch ------------ - -The voyager dump switch sends out a broadcast NMI which the voyager -code intercepts and does a task dump. - -Power Switch ------------- - -The front panel power switch is intercepted by the kernel and should -cause a system shutdown and power off. - -A Note About Mixed CPU Systems ------------------------------- - -Linux isn't designed to handle mixed CPU systems very well. In order -to get everything going you *must* make sure that your lowest -capability CPU is used for booting. Also, mixing CPU classes -(e.g. 486 and 586) is really not going to work very well at all. diff --git a/Documentation/w1/w1.generic b/Documentation/w1/w1.generic index e3333eec4320..212f4ac31c01 100644 --- a/Documentation/w1/w1.generic +++ b/Documentation/w1/w1.generic @@ -25,7 +25,7 @@ When a w1 master driver registers with the w1 subsystem, the following occurs: - sysfs entries for that w1 master are created - the w1 bus is periodically searched for new slave devices -When a device is found on the bus, w1 core checks if driver for it's family is +When a device is found on the bus, w1 core checks if driver for its family is loaded. If so, the family driver is attached to the slave. If there is no driver for the family, default one is assigned, which allows to perform almost any kind of operations. Each logical operation is a transaction diff --git a/Documentation/watchdog/src/watchdog-simple.c b/Documentation/watchdog/src/watchdog-simple.c index 4cf72f3fa8e9..ba45803a2216 100644 --- a/Documentation/watchdog/src/watchdog-simple.c +++ b/Documentation/watchdog/src/watchdog-simple.c @@ -17,9 +17,6 @@ int main(void) ret = -1; break; } - ret = fsync(fd); - if (ret) - break; sleep(10); } close(fd); diff --git a/Documentation/watchdog/src/watchdog-test.c b/Documentation/watchdog/src/watchdog-test.c index a750532ffcf8..63fdc34ceb98 100644 --- a/Documentation/watchdog/src/watchdog-test.c +++ b/Documentation/watchdog/src/watchdog-test.c @@ -31,6 +31,8 @@ static void keep_alive(void) */ int main(int argc, char *argv[]) { + int flags; + fd = open("/dev/watchdog", O_WRONLY); if (fd == -1) { @@ -41,12 +43,14 @@ int main(int argc, char *argv[]) if (argc > 1) { if (!strncasecmp(argv[1], "-d", 2)) { - ioctl(fd, WDIOC_SETOPTIONS, WDIOS_DISABLECARD); + flags = WDIOS_DISABLECARD; + ioctl(fd, WDIOC_SETOPTIONS, &flags); fprintf(stderr, "Watchdog card disabled.\n"); fflush(stderr); exit(0); } else if (!strncasecmp(argv[1], "-e", 2)) { - ioctl(fd, WDIOC_SETOPTIONS, WDIOS_ENABLECARD); + flags = WDIOS_ENABLECARD; + ioctl(fd, WDIOC_SETOPTIONS, &flags); fprintf(stderr, "Watchdog card enabled.\n"); fflush(stderr); exit(0); diff --git a/Documentation/watchdog/watchdog-api.txt b/Documentation/watchdog/watchdog-api.txt index 4cc4ba9d7150..eb7132ed8bbc 100644 --- a/Documentation/watchdog/watchdog-api.txt +++ b/Documentation/watchdog/watchdog-api.txt @@ -222,11 +222,10 @@ returned value is the temperature in degrees fahrenheit. ioctl(fd, WDIOC_GETTEMP, &temperature); Finally the SETOPTIONS ioctl can be used to control some aspects of -the cards operation; right now the pcwd driver is the only one -supporting this ioctl. +the cards operation. int options = 0; - ioctl(fd, WDIOC_SETOPTIONS, options); + ioctl(fd, WDIOC_SETOPTIONS, &options); The following options are available: |