apfs/linux-apfs
0
0
Fork 0
mirror of https://github.com/linux-apfs/linux-apfs.git synced 2026-05-01 15:00:59 -07:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'merge' of git://git.secretlab.ca/git/linux-2.6 into merge

Browse Source
This commit is contained in:
Paul Mackerras
2009-04-22 13:02:09 +10:00
parent 0658c16056 6d25b688ec
commit 5bd3ef84d7
1794 changed files with 127770 additions and 67927 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Documentation/ABI/testing/debugfs-pktcdvd
+3 -3
View File
@@ -1,4 +1,4 @@
What: /debug/pktcdvd/pktcdvd[0-7]
What: /sys/kernel/debug/pktcdvd/pktcdvd[0-7]
Date: Oct. 2006
KernelVersion: 2.6.20
Contact: Thomas Maier <balagi@justmail.de>
@@ -10,10 +10,10 @@ debugfs interface
The pktcdvd module (packet writing driver) creates
these files in debugfs:
/debug/pktcdvd/pktcdvd[0-7]/
/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/
info (0444) Lots of driver statistics and infos.
Example:
-------
cat /debug/pktcdvd/pktcdvd0/info
cat /sys/kernel/debug/pktcdvd/pktcdvd0/info
Documentation/DMA-mapping.txt
+9 -9
View File
@@ -136,7 +136,7 @@ exactly why.
The standard 32-bit addressing PCI device would do something like
this:
if (pci_set_dma_mask(pdev, DMA_32BIT_MASK)) {
if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
printk(KERN_WARNING
"mydev: No suitable DMA available.\n");
goto ignore_this_device;
@@ -155,9 +155,9 @@ all 64-bits when accessing streaming DMA:
int using_dac;
if (!pci_set_dma_mask(pdev, DMA_64BIT_MASK)) {
if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
using_dac = 1;
} else if (!pci_set_dma_mask(pdev, DMA_32BIT_MASK)) {
} else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
using_dac = 0;
} else {
printk(KERN_WARNING
@@ -170,14 +170,14 @@ the case would look like this:
int using_dac, consistent_using_dac;
if (!pci_set_dma_mask(pdev, DMA_64BIT_MASK)) {
if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
using_dac = 1;
consistent_using_dac = 1;
pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK);
} else if (!pci_set_dma_mask(pdev, DMA_32BIT_MASK)) {
pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
} else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
using_dac = 0;
consistent_using_dac = 0;
pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK);
pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
} else {
printk(KERN_WARNING
"mydev: No suitable DMA available.\n");
@@ -192,7 +192,7 @@ check the return value from pci_set_consistent_dma_mask().
Finally, if your device can only drive the low 24-bits of
address during PCI bus mastering you might do something like:
if (pci_set_dma_mask(pdev, DMA_24BIT_MASK)) {
if (pci_set_dma_mask(pdev, DMA_BIT_MASK(24))) {
printk(KERN_WARNING
"mydev: 24-bit DMA addressing not available.\n");
goto ignore_this_device;
@@ -213,7 +213,7 @@ most specific mask.
Here is pseudo-code showing how this might be done:
#define PLAYBACK_ADDRESS_BITS DMA_32BIT_MASK
#define PLAYBACK_ADDRESS_BITS DMA_BIT_MASK(32)
#define RECORD_ADDRESS_BITS 0x00ffffff
struct my_sound_card *card;
Documentation/DocBook/Makefile
+8 -3
View File
@@ -31,7 +31,7 @@ PS_METHOD = $(prefer-db2x)
###
# The targets that may be used.
PHONY += xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs
PHONY += xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs cleandocs
BOOKS := $(addprefix $(obj)/,$(DOCBOOKS))
xmldocs: $(BOOKS)
@@ -213,11 +213,12 @@ silent_gen_xml = :
dochelp:
@echo ' Linux kernel internal documentation in different formats:'
@echo ' htmldocs - HTML'
@echo ' installmandocs - install man pages generated by mandocs'
@echo ' mandocs - man pages'
@echo ' pdfdocs - PDF'
@echo ' psdocs - Postscript'
@echo ' xmldocs - XML DocBook'
@echo ' mandocs - man pages'
@echo ' installmandocs - install man pages generated by mandocs'
@echo ' cleandocs - clean all generated DocBook files'
###
# Temporary files left by various tools
@@ -235,6 +236,10 @@ clean-files := $(DOCBOOKS) \
clean-dirs := $(patsubst %.xml,%,$(DOCBOOKS)) man
cleandocs:
$(Q)rm -f $(call objectify, $(clean-files))
$(Q)rm -rf $(call objectify, $(clean-dirs))
# Declare the contents of the .PHONY variable as phony. We keep that
# information in a variable se we can use it in if_changed and friends.
Documentation/DocBook/kernel-api.tmpl
+1 -1
View File
@@ -259,7 +259,7 @@ X!Earch/x86/kernel/mca_32.c
!Eblock/blk-tag.c
!Iblock/blk-tag.c
!Eblock/blk-integrity.c
!Iblock/blktrace.c
!Ikernel/trace/blktrace.c
!Iblock/genhd.c
!Eblock/genhd.c
</chapter>
Documentation/DocBook/writing-an-alsa-driver.tmpl
+4 -4
View File
@@ -1137,8 +1137,8 @@
if (err < 0)
return err;
/* check PCI availability (28bit DMA) */
if (pci_set_dma_mask(pci, DMA_28BIT_MASK) < 0 ||
pci_set_consistent_dma_mask(pci, DMA_28BIT_MASK) < 0) {
if (pci_set_dma_mask(pci, DMA_BIT_MASK(28)) < 0 ||
pci_set_consistent_dma_mask(pci, DMA_BIT_MASK(28)) < 0) {
printk(KERN_ERR "error to set 28bit mask DMA\n");
pci_disable_device(pci);
return -ENXIO;
@@ -1252,8 +1252,8 @@
err = pci_enable_device(pci);
if (err < 0)
return err;
if (pci_set_dma_mask(pci, DMA_28BIT_MASK) < 0 ||
pci_set_consistent_dma_mask(pci, DMA_28BIT_MASK) < 0) {
if (pci_set_dma_mask(pci, DMA_BIT_MASK(28)) < 0 ||
pci_set_consistent_dma_mask(pci, DMA_BIT_MASK(28)) < 0) {
printk(KERN_ERR "error to set 28bit mask DMA\n");
pci_disable_device(pci);
return -ENXIO;
Documentation/blockdev/00-INDEX
+2
View File
@@ -8,6 +8,8 @@ cpqarray.txt
- info on using Compaq's SMART2 Intelligent Disk Array Controllers.
floppy.txt
- notes and driver options for the floppy disk driver.
mflash.txt
- info on mGine m(g)flash driver for linux.
nbd.txt
- info on a TCP implementation of a network block device.
paride.txt
Documentation/blockdev/mflash.txt
+84
View File
@@ -0,0 +1,84 @@
This document describes m[g]flash support in linux.
Contents
1. Overview
2. Reserved area configuration
3. Example of mflash platform driver registration
1. Overview
Mflash and gflash are embedded flash drive. The only difference is mflash is
MCP(Multi Chip Package) device. These two device operate exactly same way.
So the rest mflash repersents mflash and gflash altogether.
Internally, mflash has nand flash and other hardware logics and supports
2 different operation (ATA, IO) modes. ATA mode doesn't need any new
driver and currently works well under standard IDE subsystem. Actually it's
one chip SSD. IO mode is ATA-like custom mode for the host that doesn't have
IDE interface.
Followings are brief descriptions about IO mode.
A. IO mode based on ATA protocol and uses some custom command. (read confirm,
write confirm)
B. IO mode uses SRAM bus interface.
C. IO mode supports 4kB boot area, so host can boot from mflash.
2. Reserved area configuration
If host boot from mflash, usually needs raw area for boot loader image. All of
the mflash's block device operation will be taken this value as start offset.
Note that boot loader's size of reserved area and kernel configuration value
must be same.
3. Example of mflash platform driver registration
Working mflash is very straight forward. Adding platform device stuff to board
configuration file is all. Here is some pseudo example.
static struct mg_drv_data mflash_drv_data = {
/* If you want to polling driver set to 1 */
.use_polling = 0,
/* device attribution */
.dev_attr = MG_BOOT_DEV
};
static struct resource mg_mflash_rsc[] = {
/* Base address of mflash */
[0] = {
.start = 0x08000000,
.end = 0x08000000 + SZ_64K - 1,
.flags = IORESOURCE_MEM
},
/* mflash interrupt pin */
[1] = {
.start = IRQ_GPIO(84),
.end = IRQ_GPIO(84),
.flags = IORESOURCE_IRQ
},
/* mflash reset pin */
[2] = {
.start = 43,
.end = 43,
.name = MG_RST_PIN,
.flags = IORESOURCE_IO
},
/* mflash reset-out pin
* If you use mflash as storage device (i.e. other than MG_BOOT_DEV),
* should assign this */
[3] = {
.start = 51,
.end = 51,
.name = MG_RSTOUT_PIN,
.flags = IORESOURCE_IO
}
};
static struct platform_device mflash_dev = {
.name = MG_DEV_NAME,
.id = -1,
.dev = {
.platform_data = &mflash_drv_data,
},
.num_resources = ARRAY_SIZE(mg_mflash_rsc),
.resource = mg_mflash_rsc
};
platform_device_register(&mflash_dev);
Documentation/cgroups/cpuacct.txt
+18
View File
@@ -30,3 +30,21 @@ The above steps create a new group g1 and move the current shell
process (bash) into it. CPU time consumed by this bash and its children
can be obtained from g1/cpuacct.usage and the same is accumulated in
/cgroups/cpuacct.usage also.
cpuacct.stat file lists a few statistics which further divide the
CPU time obtained by the cgroup into user and system times. Currently
the following statistics are supported:
user: Time spent by tasks of the cgroup in user mode.
system: Time spent by tasks of the cgroup in kernel mode.
user and system are in USER_HZ unit.
cpuacct controller uses percpu_counter interface to collect user and
system times. This has two side effects:
- It is theoretically possible to see wrong values for user and system times.
This is because percpu_counter_read() on 32bit systems isn't safe
against concurrent writes.
- It is possible to see slightly outdated values for user and system times
due to the batch processing nature of percpu_counter.
Documentation/cgroups/memory.txt
+30 -21
View File
@@ -6,15 +6,14 @@ used here with the memory controller that is used in hardware.
Salient features
a. Enable control of both RSS (mapped) and Page Cache (unmapped) pages
a. Enable control of Anonymous, Page Cache (mapped and unmapped) and
Swap Cache memory pages.
b. The infrastructure allows easy addition of other types of memory to control
c. Provides *zero overhead* for non memory controller users
d. Provides a double LRU: global memory pressure causes reclaim from the
global LRU; a cgroup on hitting a limit, reclaims from the per
cgroup LRU
NOTE: Swap Cache (unmapped) is not accounted now.
Benefits and Purpose of the memory controller
The memory controller isolates the memory behaviour of a group of tasks
@@ -290,34 +289,44 @@ will be charged as a new owner of it.
moved to the parent. If you want to avoid that, force_empty will be useful.
5.2 stat file
memory.stat file includes following statistics (now)
cache - # of pages from page-cache and shmem.
rss - # of pages from anonymous memory.
pgpgin - # of event of charging
pgpgout - # of event of uncharging
active_anon - # of pages on active lru of anon, shmem.
inactive_anon - # of pages on active lru of anon, shmem
active_file - # of pages on active lru of file-cache
inactive_file - # of pages on inactive lru of file cache
unevictable - # of pages cannot be reclaimed.(mlocked etc)
Below is depend on CONFIG_DEBUG_VM.
inactive_ratio - VM internal parameter. (see mm/page_alloc.c)
recent_rotated_anon - VM internal parameter. (see mm/vmscan.c)
recent_rotated_file - VM internal parameter. (see mm/vmscan.c)
recent_scanned_anon - VM internal parameter. (see mm/vmscan.c)
recent_scanned_file - VM internal parameter. (see mm/vmscan.c)
memory.stat file includes following statistics
Memo:
cache - # of bytes of page cache memory.
rss - # of bytes of anonymous and swap cache memory.
pgpgin - # of pages paged in (equivalent to # of charging events).
pgpgout - # of pages paged out (equivalent to # of uncharging events).
active_anon - # of bytes of anonymous and swap cache memory on active
lru list.
inactive_anon - # of bytes of anonymous memory and swap cache memory on
inactive lru list.
active_file - # of bytes of file-backed memory on active lru list.
inactive_file - # of bytes of file-backed memory on inactive lru list.
unevictable - # of bytes of memory that cannot be reclaimed (mlocked etc).
The following additional stats are dependent on CONFIG_DEBUG_VM.
inactive_ratio - VM internal parameter. (see mm/page_alloc.c)
recent_rotated_anon - VM internal parameter. (see mm/vmscan.c)
recent_rotated_file - VM internal parameter. (see mm/vmscan.c)
recent_scanned_anon - VM internal parameter. (see mm/vmscan.c)
recent_scanned_file - VM internal parameter. (see mm/vmscan.c)
Memo:
recent_rotated means recent frequency of lru rotation.
recent_scanned means recent # of scans to lru.
showing for better debug please see the code for meanings.
Note:
Only anonymous and swap cache memory is listed as part of 'rss' stat.
This should not be confused with the true 'resident set size' or the
amount of physical memory used by the cgroup. Per-cgroup rss
accounting is not done yet.
5.3 swappiness
Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
Following cgroup's swapiness can't be changed.
Following cgroups' swapiness 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.
Documentation/cgroups/resource_counter.txt
+21 -6
View File
@@ -47,13 +47,18 @@ to work with it.
2. Basic accounting routines
a. void res_counter_init(struct res_counter *rc)
a. void res_counter_init(struct res_counter *rc,
struct res_counter *rc_parent)
Initializes the resource counter. As usual, should be the first
routine called for a new counter.
b. int res_counter_charge[_locked]
(struct res_counter *rc, unsigned long val)
The struct res_counter *parent can be used to define a hierarchical
child -> parent relationship directly in the res_counter structure,
NULL can be used to define no relationship.
c. int res_counter_charge(struct res_counter *rc, unsigned long val,
struct res_counter **limit_fail_at)
When a resource is about to be allocated it has to be accounted
with the appropriate resource counter (controller should determine
@@ -67,15 +72,25 @@ to work with it.
* if the charging is performed first, then it should be uncharged
on error path (if the one is called).
c. void res_counter_uncharge[_locked]
If the charging fails and a hierarchical dependency exists, the
limit_fail_at parameter is set to the particular res_counter element
where the charging failed.
d. int res_counter_charge_locked
(struct res_counter *rc, unsigned long val)
The same as res_counter_charge(), but it must not acquire/release the
res_counter->lock internally (it must be called with res_counter->lock
held).
e. void res_counter_uncharge[_locked]
(struct res_counter *rc, unsigned long val)
When a resource is released (freed) it should be de-accounted
from the resource counter it was accounted to. This is called
"uncharging".
The _locked routines imply that the res_counter->lock is taken.
The _locked routines imply that the res_counter->lock is taken.
2.1 Other accounting routines
Documentation/devices.txt
+5 -1
View File
@@ -3,7 +3,7 @@
Maintained by Alan Cox <device@lanana.org>
Last revised: 29 November 2006
Last revised: 6th April 2009
This list is the Linux Device List, the official registry of allocated
device numbers and /dev directory nodes for the Linux operating
@@ -2797,6 +2797,10 @@ Your cooperation is appreciated.
206 = /dev/ttySC1 SC26xx serial port 1
207 = /dev/ttySC2 SC26xx serial port 2
208 = /dev/ttySC3 SC26xx serial port 3
209 = /dev/ttyMAX0 MAX3100 serial port 0
210 = /dev/ttyMAX1 MAX3100 serial port 1
211 = /dev/ttyMAX2 MAX3100 serial port 2
212 = /dev/ttyMAX3 MAX3100 serial port 3
205 char Low-density serial ports (alternate device)
0 = /dev/culu0 Callout device for ttyLU0
Documentation/fb/uvesafb.txt
+4 -3
View File
@@ -59,7 +59,8 @@ Accepted options:
ypan Enable display panning using the VESA protected mode
interface. The visible screen is just a window of the
video memory, console scrolling is done by changing the
start of the window. Available on x86 only.
start of the window. This option is available on x86
only and is the default option on that architecture.
ywrap Same as ypan, but assumes your gfx board can wrap-around
the video memory (i.e. starts reading from top if it
@@ -67,7 +68,7 @@ ywrap Same as ypan, but assumes your gfx board can wrap-around
Available on x86 only.
redraw Scroll by redrawing the affected part of the screen, this
is the safe (and slow) default.
is the default on non-x86.
(If you're using uvesafb as a module, the above three options are
used a parameter of the scroll option, e.g. scroll=ypan.)
@@ -182,7 +183,7 @@ from the Video BIOS if you set pixclock to 0 in fb_var_screeninfo.
--
Michal Januszewski <spock@gentoo.org>
Last updated: 2007-06-16
Last updated: 2009-03-30
Documentation of the uvesafb options is loosely based on vesafb.txt.
Documentation/feature-removal-schedule.txt
+11 -1
View File
@@ -354,7 +354,8 @@ Who: Krzysztof Piotr Oledzki <ole@ans.pl>
---------------------------
What: i2c_attach_client(), i2c_detach_client(), i2c_driver->detach_client()
What: i2c_attach_client(), i2c_detach_client(), i2c_driver->detach_client(),
i2c_adapter->client_register(), i2c_adapter->client_unregister
When: 2.6.30
Check: i2c_attach_client i2c_detach_client
Why: Deprecated by the new (standard) device driver binding model. Use
@@ -427,3 +428,12 @@ Why: In 2.6.27, the semantics of /sys/bus/pci/slots was redefined to
After a reasonable transition period, we will remove the legacy
fakephp interface.
Who: Alex Chiang <achiang@hp.com>
---------------------------
What: i2c-voodoo3 driver
When: October 2009
Why: Superseded by tdfxfb. I2C/DDC support used to live in a separate
driver but this caused driver conflicts.
Who: Jean Delvare <khali@linux-fr.org>
Krzysztof Helt <krzysztof.h1@wp.pl>
Documentation/filesystems/00-INDEX
+2
View File
@@ -68,6 +68,8 @@ ncpfs.txt
- info on Novell Netware(tm) filesystem using NCP protocol.
nfsroot.txt
- short guide on setting up a diskless box with NFS root filesystem.
nilfs2.txt
- info and mount options for the NILFS2 filesystem.
ntfs.txt
- info and mount options for the NTFS filesystem (Windows NT).
ocfs2.txt
Documentation/filesystems/knfsd-stats.txt
+159
View File
@@ -0,0 +1,159 @@
Kernel NFS Server Statistics
============================
This document describes the format and semantics of the statistics
which the kernel NFS server makes available to userspace. These
statistics are available in several text form pseudo files, each of
which is described separately below.
In most cases you don't need to know these formats, as the nfsstat(8)
program from the nfs-utils distribution provides a helpful command-line
interface for extracting and printing them.
All the files described here are formatted as a sequence of text lines,
separated by newline '\n' characters. Lines beginning with a hash
'#' character are comments intended for humans and should be ignored
by parsing routines. All other lines contain a sequence of fields
separated by whitespace.
/proc/fs/nfsd/pool_stats
------------------------
This file is available in kernels from 2.6.30 onwards, if the
/proc/fs/nfsd filesystem is mounted (it almost always should be).
The first line is a comment which describes the fields present in
all the other lines. The other lines present the following data as
a sequence of unsigned decimal numeric fields. One line is shown
for each NFS thread pool.
All counters are 64 bits wide and wrap naturally. There is no way
to zero these counters, instead applications should do their own
rate conversion.
pool
The id number of the NFS thread pool to which this line applies.
This number does not change.
Thread pool ids are a contiguous set of small integers starting
at zero. The maximum value depends on the thread pool mode, but
currently cannot be larger than the number of CPUs in the system.
Note that in the default case there will be a single thread pool
which contains all the nfsd threads and all the CPUs in the system,
and thus this file will have a single line with a pool id of "0".
packets-arrived
Counts how many NFS packets have arrived. More precisely, this
is the number of times that the network stack has notified the
sunrpc server layer that new data may be available on a transport
(e.g. an NFS or UDP socket or an NFS/RDMA endpoint).
Depending on the NFS workload patterns and various network stack
effects (such as Large Receive Offload) which can combine packets
on the wire, this may be either more or less than the number
of NFS calls received (which statistic is available elsewhere).
However this is a more accurate and less workload-dependent measure
of how much CPU load is being placed on the sunrpc server layer
due to NFS network traffic.
sockets-enqueued
Counts how many times an NFS transport is enqueued to wait for
an nfsd thread to service it, i.e. no nfsd thread was considered
available.
The circumstance this statistic tracks indicates that there was NFS
network-facing work to be done but it couldn't be done immediately,
thus introducing a small delay in servicing NFS calls. The ideal
rate of change for this counter is zero; significantly non-zero
values may indicate a performance limitation.
This can happen either because there are too few nfsd threads in the
thread pool for the NFS workload (the workload is thread-limited),
or because the NFS workload needs more CPU time than is available in
the thread pool (the workload is CPU-limited). In the former case,
configuring more nfsd threads will probably improve the performance
of the NFS workload. In the latter case, the sunrpc server layer is
already choosing not to wake idle nfsd threads because there are too
many nfsd threads which want to run but cannot, so configuring more
nfsd threads will make no difference whatsoever. The overloads-avoided
statistic (see below) can be used to distinguish these cases.
threads-woken
Counts how many times an idle nfsd thread is woken to try to
receive some data from an NFS transport.
This statistic tracks the circumstance where incoming
network-facing NFS work is being handled quickly, which is a good
thing. The ideal rate of change for this counter will be close
to but less than the rate of change of the packets-arrived counter.
overloads-avoided
Counts how many times the sunrpc server layer chose not to wake an
nfsd thread, despite the presence of idle nfsd threads, because
too many nfsd threads had been recently woken but could not get
enough CPU time to actually run.
This statistic counts a circumstance where the sunrpc layer
heuristically avoids overloading the CPU scheduler with too many
runnable nfsd threads. The ideal rate of change for this counter
is zero. Significant non-zero values indicate that the workload
is CPU limited. Usually this is associated with heavy CPU usage
on all the CPUs in the nfsd thread pool.
If a sustained large overloads-avoided rate is detected on a pool,
the top(1) utility should be used to check for the following
pattern of CPU usage on all the CPUs associated with the given
nfsd thread pool.
- %us ~= 0 (as you're *NOT* running applications on your NFS server)
- %wa ~= 0
- %id ~= 0
- %sy + %hi + %si ~= 100
If this pattern is seen, configuring more nfsd threads will *not*
improve the performance of the workload. If this patten is not
seen, then something more subtle is wrong.
threads-timedout
Counts how many times an nfsd thread triggered an idle timeout,
i.e. was not woken to handle any incoming network packets for
some time.
This statistic counts a circumstance where there are more nfsd
threads configured than can be used by the NFS workload. This is
a clue that the number of nfsd threads can be reduced without
affecting performance. Unfortunately, it's only a clue and not
a strong indication, for a couple of reasons:
- Currently the rate at which the counter is incremented is quite
slow; the idle timeout is 60 minutes. Unless the NFS workload
remains constant for hours at a time, this counter is unlikely
to be providing information that is still useful.
- It is usually a wise policy to provide some slack,
i.e. configure a few more nfsds than are currently needed,
to allow for future spikes in load.
Note that incoming packets on NFS transports will be dealt with in
one of three ways. An nfsd thread can be woken (threads-woken counts
this case), or the transport can be enqueued for later attention
(sockets-enqueued counts this case), or the packet can be temporarily
deferred because the transport is currently being used by an nfsd
thread. This last case is not very interesting and is not explicitly
counted, but can be inferred from the other counters thus:
packets-deferred = packets-arrived - ( sockets-enqueued + threads-woken )
More
----
Descriptions of the other statistics file should go here.
Greg Banks <gnb@sgi.com>
26 Mar 2009
Documentation/filesystems/nfs41-server.txt
+161
View File
@@ -0,0 +1,161 @@
NFSv4.1 Server Implementation
Server support for minorversion 1 can be controlled using the
/proc/fs/nfsd/versions control file. The string output returned
by reading this file will contain either "+4.1" or "-4.1"
correspondingly.
Currently, server support for minorversion 1 is disabled by default.
It can be enabled at run time by writing the string "+4.1" to
the /proc/fs/nfsd/versions control file. Note that to write this
control file, the nfsd service must be taken down. Use your user-mode
nfs-utils to set this up; see rpc.nfsd(8)
The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
on the latest NFSv4.1 Internet Draft:
http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29
From the many new features in NFSv4.1 the current implementation
focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
"exactly once" semantics and better control and throttling of the
resources allocated for each client.
Other NFSv4.1 features, Parallel NFS operations in particular,
are still under development out of tree.
See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design
for more information.
The table below, taken from the NFSv4.1 document, lists
the operations that are mandatory to implement (REQ), optional
(OPT), and NFSv4.0 operations that are required not to implement (MNI)
in minor version 1. The first column indicates the operations that
are not supported yet by the linux server implementation.
The OPTIONAL features identified and their abbreviations are as follows:
pNFS Parallel NFS
FDELG File Delegations
DDELG Directory Delegations
The following abbreviations indicate the linux server implementation status.
I Implemented NFSv4.1 operations.
NS Not Supported.
NS* unimplemented optional feature.
P pNFS features implemented out of tree.
PNS pNFS features that are not supported yet (out of tree).
Operations
+----------------------+------------+--------------+----------------+
| Operation | REQ, REC, | Feature | Definition |
| | OPT, or | (REQ, REC, | |
| | MNI | or OPT) | |
+----------------------+------------+--------------+----------------+
| ACCESS | REQ | | Section 18.1 |
NS | BACKCHANNEL_CTL | REQ | | Section 18.33 |
NS | BIND_CONN_TO_SESSION | REQ | | Section 18.34 |
| CLOSE | REQ | | Section 18.2 |
| COMMIT | REQ | | Section 18.3 |
| CREATE | REQ | | Section 18.4 |
I | CREATE_SESSION | REQ | | Section 18.36 |
NS*| DELEGPURGE | OPT | FDELG (REQ) | Section 18.5 |
| DELEGRETURN | OPT | FDELG, | Section 18.6 |
| | | DDELG, pNFS | |
| | | (REQ) | |
NS | DESTROY_CLIENTID | REQ | | Section 18.50 |
I | DESTROY_SESSION | REQ | | Section 18.37 |
I | EXCHANGE_ID | REQ | | Section 18.35 |
NS | FREE_STATEID | REQ | | Section 18.38 |
| GETATTR | REQ | | Section 18.7 |
P | GETDEVICEINFO | OPT | pNFS (REQ) | Section 18.40 |
P | GETDEVICELIST | OPT | pNFS (OPT) | Section 18.41 |
| GETFH | REQ | | Section 18.8 |
NS*| GET_DIR_DELEGATION | OPT | DDELG (REQ) | Section 18.39 |
P | LAYOUTCOMMIT | OPT | pNFS (REQ) | Section 18.42 |
P | LAYOUTGET | OPT | pNFS (REQ) | Section 18.43 |
P | LAYOUTRETURN | OPT | pNFS (REQ) | Section 18.44 |
| LINK | OPT | | Section 18.9 |
| LOCK | REQ | | Section 18.10 |
| LOCKT | REQ | | Section 18.11 |
| LOCKU | REQ | | Section 18.12 |
| LOOKUP | REQ | | Section 18.13 |
| LOOKUPP | REQ | | Section 18.14 |
| NVERIFY | REQ | | Section 18.15 |
| OPEN | REQ | | Section 18.16 |
NS*| OPENATTR | OPT | | Section 18.17 |
| OPEN_CONFIRM | MNI | | N/A |
| OPEN_DOWNGRADE | REQ | | Section 18.18 |
| PUTFH | REQ | | Section 18.19 |
| PUTPUBFH | REQ | | Section 18.20 |
| PUTROOTFH | REQ | | Section 18.21 |
| READ | REQ | | Section 18.22 |
| READDIR | REQ | | Section 18.23 |
| READLINK | OPT | | Section 18.24 |
NS | RECLAIM_COMPLETE | REQ | | Section 18.51 |
| RELEASE_LOCKOWNER | MNI | | N/A |
| REMOVE | REQ | | Section 18.25 |
| RENAME | REQ | | Section 18.26 |
| RENEW | MNI | | N/A |
| RESTOREFH | REQ | | Section 18.27 |
| SAVEFH | REQ | | Section 18.28 |
| SECINFO | REQ | | Section 18.29 |
NS | SECINFO_NO_NAME | REC | pNFS files | Section 18.45, |
| | | layout (REQ) | Section 13.12 |
I | SEQUENCE | REQ | | Section 18.46 |
| SETATTR | REQ | | Section 18.30 |
| SETCLIENTID | MNI | | N/A |
| SETCLIENTID_CONFIRM | MNI | | N/A |
NS | SET_SSV | REQ | | Section 18.47 |
NS | TEST_STATEID | REQ | | Section 18.48 |
| VERIFY | REQ | | Section 18.31 |
NS*| WANT_DELEGATION | OPT | FDELG (OPT) | Section 18.49 |
| WRITE | REQ | | Section 18.32 |
Callback Operations
+-------------------------+-----------+-------------+---------------+
| Operation | REQ, REC, | Feature | Definition |
| | OPT, or | (REQ, REC, | |
| | MNI | or OPT) | |
+-------------------------+-----------+-------------+---------------+
| CB_GETATTR | OPT | FDELG (REQ) | Section 20.1 |
P | CB_LAYOUTRECALL | OPT | pNFS (REQ) | Section 20.3 |
NS*| CB_NOTIFY | OPT | DDELG (REQ) | Section 20.4 |
P | CB_NOTIFY_DEVICEID | OPT | pNFS (OPT) | Section 20.12 |
NS*| CB_NOTIFY_LOCK | OPT | | Section 20.11 |
NS*| CB_PUSH_DELEG | OPT | FDELG (OPT) | Section 20.5 |
| CB_RECALL | OPT | FDELG, | Section 20.2 |
| | | DDELG, pNFS | |
| | | (REQ) | |
NS*| CB_RECALL_ANY | OPT | FDELG, | Section 20.6 |
| | | DDELG, pNFS | |
| | | (REQ) | |
NS | CB_RECALL_SLOT | REQ | | Section 20.8 |
NS*| CB_RECALLABLE_OBJ_AVAIL | OPT | DDELG, pNFS | Section 20.7 |
| | | (REQ) | |
I | CB_SEQUENCE | OPT | FDELG, | Section 20.9 |
| | | DDELG, pNFS | |
| | | (REQ) | |
NS*| CB_WANTS_CANCELLED | OPT | FDELG, | Section 20.10 |
| | | DDELG, pNFS | |
| | | (REQ) | |
+-------------------------+-----------+-------------+---------------+
Implementation notes:
EXCHANGE_ID:
* only SP4_NONE state protection supported
* implementation ids are ignored
CREATE_SESSION:
* backchannel attributes are ignored
* backchannel security parameters are ignored
SEQUENCE:
* no support for dynamic slot table renegotiation (optional)
nfsv4.1 COMPOUND rules:
The following cases aren't supported yet:
* Enforcing of NFS4ERR_NOT_ONLY_OP for: BIND_CONN_TO_SESSION, CREATE_SESSION,
DESTROY_CLIENTID, DESTROY_SESSION, EXCHANGE_ID.
* DESTROY_SESSION MUST be the final operation in the COMPOUND request.
Documentation/filesystems/nilfs2.txt
+200
View File
@@ -0,0 +1,200 @@
NILFS2
------
NILFS2 is a log-structured file system (LFS) supporting continuous
snapshotting. In addition to versioning capability of the entire file
system, users can even restore files mistakenly overwritten or
destroyed just a few seconds ago. Since NILFS2 can keep consistency
like conventional LFS, it achieves quick recovery after system
crashes.
NILFS2 creates a number of checkpoints every few seconds or per
synchronous write basis (unless there is no change). Users can select
significant versions among continuously created checkpoints, and can
change them into snapshots which will be preserved until they are
changed back to checkpoints.
There is no limit on the number of snapshots until the volume gets
full. Each snapshot is mountable as a read-only file system
concurrently with its writable mount, and this feature is convenient
for online backup.
The userland tools are included in nilfs-utils package, which is
available from the following download page. At least "mkfs.nilfs2",
"mount.nilfs2", "umount.nilfs2", and "nilfs_cleanerd" (so called
cleaner or garbage collector) are required. Details on the tools are
described in the man pages included in the package.
Project web page: http://www.nilfs.org/en/
Download page: http://www.nilfs.org/en/download.html
Git tree web page: http://www.nilfs.org/git/
NILFS mailing lists: http://www.nilfs.org/mailman/listinfo/users
Caveats
=======
Features which NILFS2 does not support yet:
- atime
- extended attributes
- POSIX ACLs
- quotas
- writable snapshots
- remote backup (CDP)
- data integrity
- defragmentation
Mount options
=============
NILFS2 supports the following mount options:
(*) == default
barrier=on(*) This enables/disables barriers. barrier=off disables
it, barrier=on enables it.
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
user command. Only the checkpoints marked as snapshot
are mountable with this option. Snapshot is read-only,
so a read-only mount option must be specified together.
order=relaxed(*) Apply relaxed order semantics that allows modified data
blocks to be written to disk without making a
checkpoint if no metadata update is going. This mode
is equivalent to the ordered data mode of the ext3
filesystem except for the updates on data blocks still
conserve atomicity. This will improve synchronous
write performance for overwriting.
order=strict Apply strict in-order semantics that preserves sequence
of all file operations including overwriting of data
blocks. That means, it is guaranteed that no
overtaking of events occurs in the recovered file
system after a crash.
NILFS2 usage
============
To use nilfs2 as a local file system, simply:
# mkfs -t nilfs2 /dev/block_device
# mount -t nilfs2 /dev/block_device /dir
This will also invoke the cleaner through the mount helper program
(mount.nilfs2).
Checkpoints and snapshots are managed by the following commands.
Their manpages are included in the nilfs-utils package above.
lscp list checkpoints or snapshots.
mkcp make a checkpoint or a snapshot.
chcp change an existing checkpoint to a snapshot or vice versa.
rmcp invalidate specified checkpoint(s).
To mount a snapshot,
# mount -t nilfs2 -r -o cp=<cno> /dev/block_device /snap_dir
where <cno> is the checkpoint number of the snapshot.
To unmount the NILFS2 mount point or snapshot, simply:
# umount /dir
Then, the cleaner daemon is automatically shut down by the umount
helper program (umount.nilfs2).
Disk format
===========
A nilfs2 volume is equally divided into a number of segments except
for the super block (SB) and segment #0. A segment is the container
of logs. Each log is composed of summary information blocks, payload
blocks, and an optional super root block (SR):
______________________________________________________
| |SB| | Segment | Segment | Segment | ... | Segment | |
|_|__|_|____0____|____1____|____2____|_____|____N____|_|
0 +1K +4K +8M +16M +24M +(8MB x N)
. . (Typical offsets for 4KB-block)
. .
.______________________.
| log | log |... | log |
|__1__|__2__|____|__m__|
. .
. .
. .
.______________________________.
| Summary | Payload blocks |SR|
|_blocks__|_________________|__|
The payload blocks are organized per file, and each file consists of
data blocks and B-tree node blocks:
|<--- File-A --->|<--- File-B --->|
_______________________________________________________________
| Data blocks | B-tree blocks | Data blocks | B-tree blocks | ...
_|_____________|_______________|_____________|_______________|_
Since only the modified blocks are written in the log, it may have
files without data blocks or B-tree node blocks.
The organization of the blocks is recorded in the summary information
blocks, which contains a header structure (nilfs_segment_summary), per
file structures (nilfs_finfo), and per block structures (nilfs_binfo):
_________________________________________________________________________
| Summary | finfo | binfo | ... | binfo | finfo | binfo | ... | binfo |...
|_blocks__|___A___|_(A,1)_|_____|(A,Na)_|___B___|_(B,1)_|_____|(B,Nb)_|___
The logs include regular files, directory files, symbolic link files
and several meta data files. The mata data files are the files used
to maintain file system meta data. The current version of NILFS2 uses
the following meta data files:
1) Inode file (ifile) -- Stores on-disk inodes
2) Checkpoint file (cpfile) -- Stores checkpoints
3) Segment usage file (sufile) -- Stores allocation state of segments
4) Data address translation file -- Maps virtual block numbers to usual
(DAT) block numbers. This file serves to
make on-disk blocks relocatable.
The following figure shows a typical organization of the logs:
_________________________________________________________________________
| Summary | regular file | file | ... | ifile | cpfile | sufile | DAT |SR|
|_blocks__|_or_directory_|_______|_____|_______|________|________|_____|__|
To stride over segment boundaries, this sequence of files may be split
into multiple logs. The sequence of logs that should be treated as
logically one log, is delimited with flags marked in the segment
summary. The recovery code of nilfs2 looks this boundary information
to ensure atomicity of updates.
The super root block is inserted for every checkpoints. It includes
three special inodes, inodes for the DAT, cpfile, and sufile. Inodes
of regular files, directories, symlinks and other special files, are
included in the ifile. The inode of ifile itself is included in the
corresponding checkpoint entry in the cpfile. Thus, the hierarchy
among NILFS2 files can be depicted as follows:
Super block (SB)
|
v
Super root block (the latest cno=xx)
|-- DAT
|-- sufile
`-- cpfile
|-- ifile (cno=c1)
|-- ifile (cno=c2) ---- file (ino=i1)
: : |-- file (ino=i2)
`-- ifile (cno=xx) |-- file (ino=i3)
: :
`-- file (ino=yy)
( regular file, directory, or symlink )
For detail on the format of each file, please see include/linux/nilfs2_fs.h.
Documentation/hwmon/g760a
+36
View File
@@ -0,0 +1,36 @@
Kernel driver g760a
===================
Supported chips:
* Global Mixed-mode Technology Inc. G760A
Prefix: 'g760a'
Datasheet: Publicly available at the GMT website
http://www.gmt.com.tw/datasheet/g760a.pdf
Author: Herbert Valerio Riedel <hvr@gnu.org>
Description
-----------
The GMT G760A Fan Speed PWM Controller is connected directly to a fan
and performs closed-loop control of the fan speed.
The fan speed is programmed by setting the period via 'pwm1' of two
consecutive speed pulses. The period is defined in terms of clock
cycle counts of an assumed 32kHz clock source.
Setting a period of 0 stops the fan; setting the period to 255 sets
fan to maximum speed.
The measured fan rotation speed returned via 'fan1_input' is derived
from the measured speed pulse period by assuming again a 32kHz clock
source and a 2 pulse-per-revolution fan.
The 'alarms' file provides access to the two alarm bits provided by
the G760A chip's status register: Bit 0 is set when the actual fan
speed differs more than 20% with respect to the programmed fan speed;
bit 1 is set when fan speed is below 1920 RPM.
The g760a driver will not update its values more frequently than every
other second; reading them more often will do no harm, but will return
'old' values.
Documentation/infiniband/ipoib.txt
+45
View File
@@ -24,6 +24,49 @@ Partitions and P_Keys
The P_Key for any interface is given by the "pkey" file, and the
main interface for a subinterface is in "parent."
Datagram vs Connected modes
The IPoIB driver supports two modes of operation: datagram and
connected. The mode is set and read through an interface's
/sys/class/net/<intf name>/mode file.
In datagram mode, the IB UD (Unreliable Datagram) transport is used
and so the interface MTU has is equal to the IB L2 MTU minus the
IPoIB encapsulation header (4 bytes). For example, in a typical IB
fabric with a 2K MTU, the IPoIB MTU will be 2048 - 4 = 2044 bytes.
In connected mode, the IB RC (Reliable Connected) transport is used.
Connected mode is to takes advantage of the connected nature of the
IB transport and allows an MTU up to the maximal IP packet size of
64K, which reduces the number of IP packets needed for handling
large UDP datagrams, TCP segments, etc and increases the performance
for large messages.
In connected mode, the interface's UD QP is still used for multicast
and communication with peers that don't support connected mode. In
this case, RX emulation of ICMP PMTU packets is used to cause the
networking stack to use the smaller UD MTU for these neighbours.
Stateless offloads
If the IB HW supports IPoIB stateless offloads, IPoIB advertises
TCP/IP checksum and/or Large Send (LSO) offloading capability to the
network stack.
Large Receive (LRO) offloading is also implemented and may be turned
on/off using ethtool calls. Currently LRO is supported only for
checksum offload capable devices.
Stateless offloads are supported only in datagram mode.
Interrupt moderation
If the underlying IB device supports CQ event moderation, one can
use ethtool to set interrupt mitigation parameters and thus reduce
the overhead incurred by handling interrupts. The main code path of
IPoIB doesn't use events for TX completion signaling so only RX
moderation is supported.
Debugging Information
By compiling the IPoIB driver with CONFIG_INFINIBAND_IPOIB_DEBUG set
@@ -55,3 +98,5 @@ References
http://ietf.org/rfc/rfc4391.txt
IP over InfiniBand (IPoIB) Architecture (RFC 4392)
http://ietf.org/rfc/rfc4392.txt
IP over InfiniBand: Connected Mode (RFC 4755)
http://ietf.org/rfc/rfc4755.txt
Documentation/input/rotary-encoder.txt
+101
View File
@@ -0,0 +1,101 @@
rotary-encoder - a generic driver for GPIO connected devices
Daniel Mack <daniel@caiaq.de>, Feb 2009
0. Function
-----------
Rotary encoders are devices which are connected to the CPU or other
peripherals with two wires. The outputs are phase-shifted by 90 degrees
and by triggering on falling and rising edges, the turn direction can
be determined.
The phase diagram of these two outputs look like this:
_____ _____ _____
| | | | | |
Channel A ____| |_____| |_____| |____
: : : : : : : : : : : :
__ _____ _____ _____
| | | | | | |
Channel B |_____| |_____| |_____| |__
: : : : : : : : : : : :
Event a b c d a b c d a b c d
|<-------->|
one step
For more information, please see
http://en.wikipedia.org/wiki/Rotary_encoder
1. Events / state machine
-------------------------
a) Rising edge on channel A, channel B in low state
This state is used to recognize a clockwise turn
b) Rising edge on channel B, channel A in high state
When entering this state, the encoder is put into 'armed' state,
meaning that there it has seen half the way of a one-step transition.
c) Falling edge on channel A, channel B in high state
This state is used to recognize a counter-clockwise turn
d) Falling edge on channel B, channel A in low state
Parking position. If the encoder enters this state, a full transition
should have happend, unless it flipped back on half the way. The
'armed' state tells us about that.
2. Platform requirements
------------------------
As there is no hardware dependent call in this driver, the platform it is
used with must support gpiolib. Another requirement is that IRQs must be
able to fire on both edges.
3. Board integration
--------------------
To use this driver in your system, register a platform_device with the
name 'rotary-encoder' and associate the IRQs and some specific platform
data with it.
struct rotary_encoder_platform_data is declared in
include/linux/rotary-encoder.h and needs to be filled with the number of
steps the encoder has and can carry information about externally inverted
signals (because of used invertig buffer or other reasons).
Because GPIO to IRQ mapping is platform specific, this information must
be given in seperately to the driver. See the example below.
---------<snip>---------
/* board support file example */
#include <linux/input.h>
#include <linux/rotary_encoder.h>
#define GPIO_ROTARY_A 1
#define GPIO_ROTARY_B 2
static struct rotary_encoder_platform_data my_rotary_encoder_info = {
.steps = 24,
.axis = ABS_X,
.gpio_a = GPIO_ROTARY_A,
.gpio_b = GPIO_ROTARY_B,
.inverted_a = 0,
.inverted_b = 0,
};
static struct platform_device rotary_encoder_device = {
.name = "rotary-encoder",
.id = 0,
.dev = {
.platform_data = &my_rotary_encoder_info,
}
};

Some files were not shown because too many files have changed in this diff Show More