| /linux-3.3/Documentation/networking/ |
| D | scaling.txt | 26 applying a filter to each packet that assigns it to one of a small number
27 of logical flows. Packets for each flow are steered to a separate receive
37 implementation of RSS uses a 128-entry indirection table where each entry
54 for each CPU if the device supports enough queues, or otherwise at least
55 one for each memory domain, where a memory domain is a set of CPUs that
68 Each receive queue has a separate IRQ associated with it. The NIC triggers
71 that can route each interrupt to a particular CPU. The active mapping
76 affinity of each interrupt see Documentation/IRQ-affinity.txt. Some systems
90 interrupts (and thus work) grows with each additional queue.
93 processors with hyperthreading (HT), each hyperthread is represented as
[all …]
|
| /linux-3.3/Documentation/filesystems/nfs/ |
| D | pnfs.txt | 5 reference multiple devices, each of which can reference multiple data servers.
6 Each data server can be referenced by multiple devices. Each device
15 Each nfs_inode may hold a pointer to a cache of of these layout
18 We reference the header for the inode pointing to it, across each
20 LAYOUTCOMMIT), and for each lseg held within.
22 Each header is also (when non-empty) put on a list associated with
31 nfs4_deviceid_cache). The cache itself is referenced across each
33 the lifetime of each lseg referencing them.
|
| /linux-3.3/Documentation/scheduler/ |
| D | sched-domains.txt | 1 Each CPU has a "base" scheduling domain (struct sched_domain). The domain
6 Each scheduling domain spans a number of CPUs (stored in the ->span field).
9 i. The top domain for each CPU will generally span all CPUs in the system
15 Each scheduling domain must have one or more CPU groups (struct sched_group)
23 Balancing within a sched domain occurs between groups. That is, each group
25 load of each of its member CPUs, and only when the load of a group becomes
28 In kernel/sched.c, trigger_load_balance() is run periodically on each CPU
51 of SMT, you'll span all siblings of the physical CPU, with each group being
55 node. Each group being a single physical CPU. Then with NUMA, the parent
56 of the SMP domain will span the entire machine, with each group having the
|
| /linux-3.3/Documentation/cgroups/ |
| D | cgroups.txt | 58 hierarchy, and a set of subsystems; each subsystem has system-specific
59 state attached to each cgroup in the hierarchy. Each hierarchy has
63 cgroups. Each hierarchy is a partition of all tasks in the system.
77 tasks in each cgroup.
97 different subsystems - having parallel hierarchies allows each
103 At one extreme, each resource controller or subsystem could be in a
171 - Each task in the system has a reference-counted pointer to a
175 cgroup_subsys_state objects, one for each cgroup subsystem
177 the cgroup of which it's a member in each hierarchy, but this
184 field of each task_struct using the css_set, anchored at
[all …]
|
| /linux-3.3/Documentation/filesystems/ |
| D | logfs.txt | 12 Each superblock is 256 Bytes large, with another 3840 Bytes reserved
32 Segments are the primary write unit of LogFS. Within each segments,
53 store. Each segment contains a segment header and a number of
54 objects, each consisting of the object header and the payload.
69 Each segment contains objects of a single level only. As a result,
70 each level requires its own separate segment to be open for writing.
84 implementation would require that for each write or a block, all
89 of alias entries. Each alias consists of its logical address - inode
110 the GC overhead later. Each type of distinc life expectency (vim) can
111 have a separate segment open for writing. Each (level, vim) tupel can
[all …]
|
| D | squashfs.txt | 45 directory data are highly compacted, and packed on byte boundaries. Each
109 Metadata (inodes and directories) are compressed in 8Kbyte blocks. Each
120 To maximise compression there are different inodes for each file type
143 entries, each of which share the shared start block. A new directory header
148 file lookup. Directory indexes store one entry per metablock, each entry
150 in each metadata block. Directories are sorted in alphabetical order,
164 of each datablock is stored in a block list contained within the
214 The xattr table contains extended attributes for each inode. The xattrs
215 for each inode are stored in a list, each list entry containing a type,
228 location of the xattr list inside each inode, a 32-bit xattr id
|
| /linux-3.3/Documentation/devicetree/bindings/c6x/ |
| D | dscr.txt | 19 For device state control (enable/disable), each device control is assigned an
46 a lock register. Each tuple consists of the register offset, lock register
56 MAC addresses are contained in two registers. Each element of a MAC address
57 is contained in a single byte. This property has two tuples. Each tuple has
65 Each tuple describes a range of identical bitfields used to control one or
66 more devices (one bitfield per device). The layout of each tuple is:
81 for device states controlled by the DSCR. Each tuple describes a range of
83 bitfield per device). The layout of each tuple is:
|
| /linux-3.3/Documentation/infiniband/ |
| D | sysfs.txt | 3 For each InfiniBand device, the InfiniBand drivers create the
11 for each port. For example, if mthca0 is a 2-port HCA, there will
20 In each port subdirectory, the following files are created:
50 Each of these files contains the corresponding value from the port's
54 The "pkeys" and "gids" subdirectories contain one file for each
|
| /linux-3.3/arch/cris/ |
| D | Kconfig | 385 If you do not enable DMA, an interrupt for each character will be
395 If you do not enable DMA, an interrupt for each character will be
420 If you do not enable DMA, an interrupt for each character will be
430 If you do not enable DMA, an interrupt for each character will be
455 If you do not enable DMA, an interrupt for each character will be
489 If you do not enable DMA, an interrupt for each character will be
512 If you do not enable DMA, an interrupt for each character will be
522 If you do not enable DMA, an interrupt for each character will be
547 If you do not enable DMA, an interrupt for each character will be
557 If you do not enable DMA, an interrupt for each character will be
[all …]
|
| /linux-3.3/Documentation/rapidio/ |
| D | rapidio.txt | 28 Each of these components is represented in the subsystem by an associated data
36 packets (transactions). In the RapidIO subsystem each master port is represented
71 Each RapidIO network known to the system is represented by corresponding rio_net
82 rio_register_mport() for each available master port. After all active master
122 device ID are queried against a table of known RapidIO switches. Each switch
139 Enumeration beyond a switch is completed by iterating over each active egress
140 port of that switch. For each active link, a route to a default device ID
146 devices by clearing device ID locks (calls rio_clear_locks()). For each endpoint
155 devices. This way each Linux-based component of the RapidIO subsystem has
158 each agent waits for enumeration completion by the host for the configured wait
|
| /linux-3.3/Documentation/w1/ |
| D | w1.netlink | 8 1. Events. They are generated each time new master or slave device
57 Each connector message can include one or more w1_netlink_msg with
89 Each message is at most 4k in size, so if number of master devices
91 cn.seq will be increased for each one.
107 Length in each header corresponds to the size of the data behind it, so
125 Each command (either root, master or slave with or without w1_netlink_cmd
170 Each connector message includes two u32 fields as "address".
172 Each message also includes sequence and acknowledge numbers.
174 increased with each event message sent "through" this master.
|
| /linux-3.3/Documentation/driver-model/ |
| D | class.txt | 13 Each device class defines a set of semantics and a programming interface
40 Each device class structure should be exported in a header file so it
57 The device is enumerated in the class. Each time a device is added to
66 There is no list of devices in the device class. Each driver has a
69 class, iterate over the device lists of each driver in the class.
83 Each class gets a directory in the class directory, along with two
102 Each device gets a symlink in the devices/ directory that points to the
|
| D | bus.txt | 14 Each bus type in the kernel (PCI, USB, etc) should declare one static
55 iterated over, and the match callback is called for each device that
69 The LDM core provides helper functions for iterating over each list.
78 for each device or driver in the list. All list accesses are
80 count on each object in the list is incremented before the callback is
89 Each bus gets a directory in the bus directory, along with two default
107 Each device that is discovered on a bus of that type gets a symlink in
|
| /linux-3.3/arch/cris/include/asm/ |
| D | etraxgpio.h | 6 * /dev/gpioa minor 0, 8 bit GPIO, each bit can change direction
7 * /dev/gpiob minor 1, 8 bit GPIO, each bit can change direction
16 * /dev/gpioa minor 0, 8 bit GPIO, each bit can change direction
17 * /dev/gpiob minor 1, 18 bit GPIO, each bit can change direction
18 * /dev/gpioc minor 3, 18 bit GPIO, each bit can change direction
19 * /dev/gpiod minor 4, 18 bit GPIO, each bit can change direction
20 * /dev/gpioe minor 5, 18 bit GPIO, each bit can change direction
24 * /dev/gpioa minor 0, 32 bit GPIO, each bit can change direction
25 * /dev/gpiob minor 1, 32 bit GPIO, each bit can change direction
26 * /dev/gpioc minor 3, 16 bit GPIO, each bit can change direction
|
| /linux-3.3/Documentation/spi/ |
| D | spidev | 66 of devices at a time. Just provide one spi_board_info record for each such
67 SPI device, and you'll get a /dev device node for each device.
93 is right-justified in each word, so that unused (TX) or undefined (RX)
98 each SPI transfer word. The value zero signifies eight bits.
115 Each SPI device is deselected when it's not in active use, allowing
118 - There's a limit on the number of bytes each I/O request can transfer
139 each response. (Other protocol options include changing the word size
140 and bitrate for each transfer segment.)
|
| /linux-3.3/arch/arm/mach-msm/include/mach/ |
| D | dma.h | 116 * is going to walk a list of 32bit pointers as described below. Each
118 * in the list is marked with CMD_PTR_LP. The last struct in each array
166 #define CMD_DST_SWAP_BYTES (1 << 14) /* exchange each byte n with byte n+1 */
167 #define CMD_DST_SWAP_SHORTS (1 << 15) /* exchange each short n with short n+1 */
168 #define CMD_DST_SWAP_WORDS (1 << 16) /* exchange each word n with word n+1 */
170 #define CMD_SRC_SWAP_BYTES (1 << 11) /* exchange each byte n with byte n+1 */
171 #define CMD_SRC_SWAP_SHORTS (1 << 12) /* exchange each short n with short n+1 */
172 #define CMD_SRC_SWAP_WORDS (1 << 13) /* exchange each word n with word n+1 */
|
| /linux-3.3/drivers/net/wireless/iwlegacy/ |
| D | prph.h | 251 * host DRAM. It steers each frame's Tx command (which contains the frame
273 * The driver sets up each queue to work in one of two modes:
276 * block-ack (BA) win of up to 64 TFDs. In this mode, each queue
282 * each frame within the BA win, including whether it's been transmitted,
292 * 2) FIFO (a.k.a. non-Scheduler-ACK), in which each TFD is processed in order.
308 * 1) 16 TFD circular buffers, each with space for (typically) 256 TFDs.
310 * (1024 bytes for each queue).
342 * 15-00: Empty state, one for each queue -- 1: empty, 0: non-empty
349 * Each Tx queue has a BC CB in host DRAM to support Scheduler-ACK mode.
352 * Each BC CB is 2 bytes * (256 + 64) = 740 bytes, followed by 384 bytes pad.
[all …]
|
| /linux-3.3/drivers/scsi/be2iscsi/ |
| D | be_main.h | 379 * Pseudo amap definition in which each bit of the actual structure is defined
380 * as a byte: used to calculate offset/shift/mask of each field
448 * Pseudo amap definition in which each bit of the actual structure is defined
449 * as a byte: used to calculate offset/shift/mask of each field
472 * Pseudo amap definition in which each bit of the actual structure is defined
473 * as a byte: used to calculate offset/shift/mask of each field
567 * Pseudo amap definition in which each bit of the actual structure is defined
568 * as a byte: used to calculate offset/shift/mask of each field
596 * Pseudo amap definition in which each bit of the actual structure is defined
597 * as a byte: used to calculate offset/shift/mask of each field
[all …]
|
| /linux-3.3/Documentation/w1/slaves/ |
| D | w1_ds2423 | 15 Support is provided through the sysfs w1_slave file. Each opening and
19 Result of each page is provided as an ASCII output where each counter
22 Each lines will contain the values of 42 bytes read from the counter and
25 If the operation was successful, there is also in the end of each line
|
| /linux-3.3/Documentation/scsi/ |
| D | scsi_eh.txt | 32 Each SCSI command is represented with struct scsi_cmnd (== scmd). A
288 This action is taken for each error-completed
323 This action is taken for each timed out command.
324 hostt->eh_abort_handler() is invoked for each scmd. The
353 For each sdev which has failed scmds with valid sense data
386 hostt->eh_bus_reset_handler() is invoked for each channel
431 - Each failed scmd's eh_flags field is set appropriately.
433 - Each failed scmd is linked on scmd->eh_cmd_q by scmd->eh_entry.
446 - Each scmd's eh_eflags field is cleared.
448 - Each scmd is in such a state that scsi_setup_cmd_retry() on the
[all …]
|
| /linux-3.3/Documentation/sound/alsa/ |
| D | Procfile.txt | 12 Each card has its subtree cardX, where X is from 0 to 7. The
27 Lists the module of each card
65 like pcm0p or pcm1c. They hold the PCM information for each PCM
104 bit 3 = Log hwptr update at each period interrupt
105 bit 4 = Log hwptr update at each snd_pcm_update_hw_ptr()
128 the proc file shows each jiffies, position, period_size,
171 Shows the assignment and the current status of each audio stream
179 Shows the general codec information and the attribute of each
|
| /linux-3.3/drivers/acpi/acpica/ |
| D | acpredef.h | 67 * 2) PTYPE2 packages contain a Variable-length number of sub-packages. Each
68 * of the different types describe the contents of each of the sub-packages.
70 * ACPI_PTYPE2: Each subpackage contains 1 or 2 object types:
77 * ACPI_PTYPE2_COUNT: Each subpackage has a count as first element:
88 * ACPI_PTYPE2_FIXED: Each subpackage is of fixed length
91 * ACPI_PTYPE2_MIN: Each subpackage has a variable but minimum length
94 * ACPI_PTYPE2_REV_FIXED: Revision at start, each subpackage is Fixed-length
97 * ACPI_PTYPE2_FIX_VAR: Each subpackage consists of some fixed-length elements
141 * The main entries in the table each contain the following items:
200 {{"_ALR", 0, ACPI_RTYPE_PACKAGE}}, /* Variable-length (Pkgs) each 2 (Ints) */
[all …]
|
| /linux-3.3/drivers/net/wireless/iwlwifi/ |
| D | iwl-fh.h | 102 * Device has 16 base pointer registers, one for each of 16 host-DRAM-resident
105 * bytes from one another. Each TFD circular buffer in DRAM must be 256-byte
108 * Bit fields in each pointer register:
125 * concatenate up to 20 DRAM buffers to form a Tx frame, each Receive Buffer
130 * physical address of each into device registers:
134 * Each entry (1 dword) points to a receive buffer (RB) of consistent size
233 * 17-16: size of each receive buffer; '00' 4K (normal), '01' 8K,
306 * Device has one configuration register for each of 8 Tx DMA/FIFO channels
387 * 16-9:Each status bit is for one channel. Indicates that an (Error) ActDMA
391 * 7-0: Each status bit indicates a channel's TxCredit error. When an error
[all …]
|
| /linux-3.3/Documentation/devicetree/bindings/powerpc/4xx/ |
| D | cpm.txt | 16 - unused-units : specifier consist of one cell. For each
20 - idle-doze : specifier consist of one cell. For each
24 - standby : specifier consist of one cell. For each
28 - suspend : specifier consist of one cell. For each
|
| /linux-3.3/include/linux/ |
| D | atmel_tc.h | 17 * Many 32-bit Atmel SOCs include one or more TC blocks, each of which holds
19 * Depending on the SOC, each timer may have its own clock and IRQ, or those
27 * Although we expect each TC block to have a platform_device node, those
41 * @irq: irq for each of the three channels
42 * @clk: internal clock source for each of the three channels
45 * On some platforms, each TC channel has its own clocks and IRQs,
49 * Likewise, drivers should request irqs independently for each
101 * Each TC block has three "channels", each with one counter and controls.
114 * Each timer has two I/O pins, TIOA and TIOB. Waveform mode uses TIOA as a
|