--- man-pages-2.54/man5/proc.5	2007-05-16 11:25:50.000000000 -0700
+++ man-pages-2.54/man5/proc.5.new	2007-06-09 11:10:15.000000000 -0700
@@ -41,6 +41,9 @@
 .\" 2005-09-19, mtk, added /proc/zoneinfo
 .\" 2005-03-01, mtk, moved /proc/sys/fs/mqueue/* material to
 .\"             mq_overview.7.
+.\" 2007-06-10 Added /proc/[number]/{oom_score,oom_adj,io,seccomp}
+.\"    by Jeff Schroeder <jeffschroeder@computer.org>
+.\"    mostly copied from Documentation/filesystems/proc.txt.
 .\"
 .\" FIXME 2.6.14 has /proc/PID/numa_maps (if CONFIG_NUMA is
 .\" enabled); this needs to be documented.
@@ -201,6 +204,128 @@
 .\" FIXME Describe /proc/[number]/loginuid
 .\"       Added in 2.6.11; updating requires CAP_AUDIT_CONTROL
 .TP
+.I /proc/[number]/io "Since 2.6.20"
+This file contains I/O statistics for each running process.
+It is only present when the CONFIG_TASK_IO_ACCOUNTING and
+CONFIG_TASK_XACCT kernel configuration options are enabled.
+
+.B Example
+
+.nf
+.in +5
+$ dd if=/dev/zero of=/tmp/test.dat &
+[1] 3828
+
+$ cat /proc/3828/io
+rchar: 323934931
+wchar: 323929600
+syscr: 632687
+syscw: 632675
+read_bytes: 0
+write_bytes: 323932160
+cancelled_write_bytes: 0
+.fi
+.in
+
+.B Descriptions
+.IP
+.in +5
+.I rchar
+.br
+I/O counter: chars read
+.br
+The number of bytes which this task has caused to be read from storage.
+This is simply the sum of bytes which this process passed to
+.BR read (2)
+and
+.BR pread (2).
+It includes things like tty I/O and it is unaffected by whether
+or not actual physical disk I/O was required
+(the read might have been satisfied from pagecache).
+.in
+.IP
+.in +5
+.I wchar
+.br
+I/O counter: chars written
+.br
+The number of bytes which this task has caused, or shall cause to be
+written to disk.
+Similar caveats apply here as with rchar.
+.in
+.IP
+.in +5
+.I syscr
+.br
+I/O counter: read syscalls
+.br
+Attempt to count the number of read I/O operations as in syscalls like
+.BR read (2)
+and
+.BR pread (2).
+.in
+.IP
+.in +5
+.I syscw
+.br
+I/O counter: write syscalls
+.br
+Attempt to count the number of write I/O operations as in syscalls like
+.BR write (2)
+and
+.BR pwrite (2).
+.in
+.IP
+.in +5
+.I read_bytes
+.br
+I/O counter: bytes read
+.br
+Attempt to count the number of bytes which this process caused to be
+fetched from the storage layer.
+This is done at the submit_bio() level, so it is accurate for
+block-backed filesystems.
+.in
+.IP
+.in +5
+.I write_bytes
+.br
+I/O counter: bytes written
+.br
+Attempt to count the number of bytes which this process caused to be
+sent to the storage layer.
+This is done at page-dirtying time.
+.in
+.IP
+.in +5
+.I cancelled_write_bytes
+.br
+This is to show when truncating a file overinflates the number of bytes
+written when they were in fact not actually written to disk.
+If a process writes 1MB to a file and then deletes the file, it will
+perform no writeout.
+However, it will have been accounted as having caused 1MB of write.
+This can also be seen as the number of bytes which this process caused
+to not happen, by truncating pagecache.
+A task can cause "negative" I/O too.
+If this task truncates some dirty pagecache, some I/O which another
+task has been accounted for (in it's 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.
+.in
+.IP
+.in +5
+.I Note
+.br
+As currently implemented, this is a bit racy on 32-bit systems.
+If process A reads process B's /proc/[number]/io while process
+B is updating one of those 64-bit counters, process A could see an
+intermediate result.
+
+More information can be found within the taskstats documentation in the
+kernel source code under Documentation/accounting.
+.in
+.TP
 .I /proc/[number]/maps
 A file containing the currently mapped memory regions and their access
 permissions.