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 ../linux-2.6

Browse Source
This commit is contained in:
Paul Mackerras
2006-03-29 13:24:50 +11:00
parent e8222502ee ca9ba4471c
commit bac30d1a78
779 changed files with 23033 additions and 7810 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CREDITS
+6 -3
View File
@@ -1127,8 +1127,10 @@ S: Carnegie, Pennsylvania 15106-4304
S: USA
N: Philip Gladstone
E: philip@raptor.com
E: philip@gladstonefamily.net
D: Kernel / timekeeping stuff
S: Carlisle, MA 01741
S: USA
N: Jan-Benedict Glaw
E: jbglaw@lug-owl.de
@@ -3741,10 +3743,11 @@ D: Mylex DAC960 PCI RAID driver
D: Miscellaneous kernel fixes
N: Alessandro Zummo
E: azummo@ita.flashnet.it
W: http://freepage.logicom.it/azummo/
E: a.zummo@towertech.it
D: CMI8330 support is sb_card.c
D: ISAPnP fixes in sb_card.c
D: ZyXEL omni.net lcd plus driver
D: RTC subsystem
S: Italy
N: Marc Zyngier
Documentation/DMA-mapping.txt
+2
View File
@@ -199,6 +199,8 @@ address during PCI bus mastering you might do something like:
"mydev: 24-bit DMA addressing not available.\n");
goto ignore_this_device;
}
[Better use DMA_24BIT_MASK instead of 0x00ffffff.
See linux/include/dma-mapping.h for reference.]
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
Documentation/RCU/whatisRCU.txt
+1 -1
View File
@@ -605,7 +605,7 @@ are the same as those shown in the preceding section, so they are omitted.
{
int cpu;
for_each_cpu(cpu)
for_each_possible_cpu(cpu)
run_on(cpu);
}
Documentation/arm/SA1100/Assabet
+1 -1
View File
@@ -26,7 +26,7 @@ Installing a bootloader
A couple of bootloaders able to boot Linux on Assabet are available:
BLOB (http://www.lart.tudelft.nl/lartware/blob/)
BLOB (http://www.lartmaker.nl/lartware/blob/)
BLOB is a bootloader used within the LART project. Some contributed
patches were merged into BLOB to add support for Assabet.
Documentation/arm/SA1100/LART
+1 -1
View File
@@ -11,4 +11,4 @@ is under development, with plenty of others in different stages of
planning.
The hardware designs for this board have been released under an open license;
see the LART page at http://www.lart.tudelft.nl/ for more information.
see the LART page at http://www.lartmaker.nl/ for more information.
Documentation/block/biodoc.txt
+12 -2
View File
@@ -132,8 +132,18 @@ Some new queue property settings:
limit. No highmem default.
blk_queue_max_sectors(q, max_sectors)
Maximum size request you can handle in units of 512 byte
sectors. 255 default.
Sets two variables that limit the size of the request.
- The request queue's max_sectors, which is a soft size in
in units of 512 byte sectors, and could be dynamically varied
by the core kernel.
- The request queue's max_hw_sectors, which is a hard limit
and reflects the maximum size request a driver can handle
in units of 512 byte sectors.
The default for both max_sectors and max_hw_sectors is
255. The upper limit of max_sectors is 1024.
blk_queue_max_phys_segments(q, max_segments)
Maximum physical segments you can handle in a request. 128
Documentation/cpu-hotplug.txt
+2 -2
View File
@@ -97,13 +97,13 @@ at which time hotplug is disabled.
You really dont need to manipulate any of the system cpu maps. They should
be read-only for most use. When setting up per-cpu resources almost always use
cpu_possible_map/for_each_cpu() to iterate.
cpu_possible_map/for_each_possible_cpu() to iterate.
Never use anything other than cpumask_t to represent bitmap of CPUs.
#include <linux/cpumask.h>
for_each_cpu - Iterate over cpu_possible_map
for_each_possible_cpu - Iterate over cpu_possible_map
for_each_online_cpu - Iterate over cpu_online_map
for_each_present_cpu - Iterate over cpu_present_map
for_each_cpu_mask(x,mask) - Iterate over some random collection of cpu mask.
Documentation/cputopology.txt
+2 -2
View File
@@ -1,5 +1,5 @@
Export cpu topology info by sysfs. Items (attributes) are similar
Export cpu topology info via sysfs. Items (attributes) are similar
to /proc/cpuinfo.
1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
@@ -12,7 +12,7 @@ represent the thread siblings to cpu X in the same core;
represent the thread siblings to cpu X in the same physical package;
To implement it in an architecture-neutral way, a new source file,
driver/base/topology.c, is to export the 5 attributes.
drivers/base/topology.c, is to export the 4 attributes.
If one architecture wants to support this feature, it just needs to
implement 4 defines, typically in file include/asm-XXX/topology.h.
Documentation/filesystems/00-INDEX
+47 -7
View File
@@ -1,27 +1,47 @@
00-INDEX
- this file (info on some of the filesystems supported by linux).
Exporting
- explanation of how to make filesystems exportable.
Locking
- info on locking rules as they pertain to Linux VFS.
adfs.txt
- info and mount options for the Acorn Advanced Disc Filing System.
afs.txt
- info and examples for the distributed AFS (Andrew File System) fs.
affs.txt
- info and mount options for the Amiga Fast File System.
automount-support.txt
- information about filesystem automount support.
befs.txt
- information about the BeOS filesystem for Linux.
bfs.txt
- info for the SCO UnixWare Boot Filesystem (BFS).
cifs.txt
- description of the CIFS filesystem
- description of the CIFS filesystem.
coda.txt
- description of the CODA filesystem.
configfs/
- directory containing configfs documentation and example code.
cramfs.txt
- info on the cram filesystem for small storage (ROMs etc)
- info on the cram filesystem for small storage (ROMs etc).
dentry-locking.txt
- info on the RCU-based dcache locking model.
devfs/
- directory containing devfs documentation.
directory-locking
- info about the locking scheme used for directory operations.
dlmfs.txt
- info on the userspace interface to the OCFS2 DLM.
ext2.txt
- info, mount options and specifications for the Ext2 filesystem.
ext3.txt
- info, mount options and specifications for the Ext3 filesystem.
files.txt
- info on file management in the Linux kernel.
fuse.txt
- info on the Filesystem in User SpacE including mount options.
hfs.txt
- info on the Macintosh HFS Filesystem for Linux.
hpfs.txt
- info and mount options for the OS/2 HPFS.
isofs.txt
@@ -32,23 +52,43 @@ ncpfs.txt
- info on Novell Netware(tm) filesystem using NCP protocol.
ntfs.txt
- info and mount options for the NTFS filesystem (Windows NT).
proc.txt
- info on Linux's /proc filesystem.
ocfs2.txt
- info and mount options for the OCFS2 clustered filesystem.
porting
- various information on filesystem porting.
proc.txt
- info on Linux's /proc filesystem.
ramfs-rootfs-initramfs.txt
- info on the 'in memory' filesystems ramfs, rootfs and initramfs.
reiser4.txt
- info on the Reiser4 filesystem based on dancing tree algorithms.
relayfs.txt
- info on relayfs, for efficient streaming from kernel to user space.
romfs.txt
- Description of the ROMFS filesystem.
- description of the ROMFS filesystem.
smbfs.txt
- info on using filesystems with the SMB protocol (Windows 3.11 and NT)
- info on using filesystems with the SMB protocol (Win 3.11 and NT).
spufs.txt
- info and mount options for the SPU filesystem used on Cell.
sysfs-pci.txt
- info on accessing PCI device resources through sysfs.
sysfs.txt
- info on sysfs, a ram-based filesystem for exporting kernel objects.
sysv-fs.txt
- info on the SystemV/V7/Xenix/Coherent filesystem.
tmpfs.txt
- info on tmpfs, a filesystem that holds all files in virtual memory.
udf.txt
- info and mount options for the UDF filesystem.
ufs.txt
- info on the ufs filesystem.
v9fs.txt
- v9fs is a Unix implementation of the Plan 9 9p remote fs protocol.
vfat.txt
- info on using the VFAT filesystem used in Windows NT and Windows 95
vfs.txt
- Overview of the Virtual File System
- overview of the Virtual File System
xfs.txt
- info and mount options for the XFS filesystem.
xip.txt
- info on execute-in-place for file mappings.
Documentation/ioctl-number.txt
-2
View File
@@ -78,8 +78,6 @@ Code Seq# Include File Comments
'#' 00-3F IEEE 1394 Subsystem Block for the entire subsystem
'1' 00-1F <linux/timepps.h> PPS kit from Ulrich Windl
<ftp://ftp.de.kernel.org/pub/linux/daemons/ntp/PPS/>
'6' 00-10 <asm-i386/processor.h> Intel IA32 microcode update driver
<mailto:tigran@veritas.com>
'8' all SNP8023 advanced NIC card
<mailto:mcr@solidum.com>
'A' 00-1F linux/apm_bios.h
Documentation/m68k/README.buddha
+1 -1
View File
@@ -29,7 +29,7 @@ address is written to $4a, then the whole Byte is written to
$48, while it doesn't matter how often you're writing to $4a
as long as $48 is not touched. After $48 has been written,
the whole card disappears from $e8 and is mapped to the new
address just written. Make shure $4a is written before $48,
address just written. Make sure $4a is written before $48,
otherwise your chance is only 1:16 to find the board :-).
The local memory-map is even active when mapped to $e8:
Documentation/networking/ifenslave.c
+1 -1
View File
@@ -87,7 +87,7 @@
* would fail and generate an error message in the system log.
* - For opt_c: slave should not be set to the master's setting
* while it is running. It was already set during enslave. To
* simplify things, it is now handeled separately.
* simplify things, it is now handled separately.
*
* - 2003/12/01 - Shmulik Hen <shmulik.hen at intel dot com>
* - Code cleanup and style changes
Documentation/pnp.txt
+3
View File
@@ -115,6 +115,9 @@ pnp_unregister_protocol
pnp_register_driver
- adds a PnP driver to the Plug and Play Layer
- this includes driver model integration
- returns zero for success or a negative error number for failure; count
calls to the .add() method if you need to know how many devices bind to
the driver
pnp_unregister_driver
- removes a PnP driver from the Plug and Play Layer
Documentation/robust-futex-ABI.txt
+182
View File
@@ -0,0 +1,182 @@
Started by Paul Jackson <pj@sgi.com>
The robust futex ABI
--------------------
Robust_futexes provide a mechanism that is used in addition to normal
futexes, for kernel assist of cleanup of held locks on task exit.
The interesting data as to what futexes a thread is holding is kept on a
linked list in user space, where it can be updated efficiently as locks
are taken and dropped, without kernel intervention. The only additional
kernel intervention required for robust_futexes above and beyond what is
required for futexes is:
1) a one time call, per thread, to tell the kernel where its list of
held robust_futexes begins, and
2) internal kernel code at exit, to handle any listed locks held
by the exiting thread.
The existing normal futexes already provide a "Fast Userspace Locking"
mechanism, which handles uncontested locking without needing a system
call, and handles contested locking by maintaining a list of waiting
threads in the kernel. Options on the sys_futex(2) system call support
waiting on a particular futex, and waking up the next waiter on a
particular futex.
For robust_futexes to work, the user code (typically in a library such
as glibc linked with the application) has to manage and place the
necessary list elements exactly as the kernel expects them. If it fails
to do so, then improperly listed locks will not be cleaned up on exit,
probably causing deadlock or other such failure of the other threads
waiting on the same locks.
A thread that anticipates possibly using robust_futexes should first
issue the system call:
asmlinkage long
sys_set_robust_list(struct robust_list_head __user *head, size_t len);
The pointer 'head' points to a structure in the threads address space
consisting of three words. Each word is 32 bits on 32 bit arch's, or 64
bits on 64 bit arch's, and local byte order. Each thread should have
its own thread private 'head'.
If a thread is running in 32 bit compatibility mode on a 64 native arch
kernel, then it can actually have two such structures - one using 32 bit
words for 32 bit compatibility mode, and one using 64 bit words for 64
bit native mode. The kernel, if it is a 64 bit kernel supporting 32 bit
compatibility mode, will attempt to process both lists on each task
exit, if the corresponding sys_set_robust_list() call has been made to
setup that list.
The first word in the memory structure at 'head' contains a
pointer to a single linked list of 'lock entries', one per lock,
as described below. If the list is empty, the pointer will point
to itself, 'head'. The last 'lock entry' points back to the 'head'.
The second word, called 'offset', specifies the offset from the
address of the associated 'lock entry', plus or minus, of what will
be called the 'lock word', from that 'lock entry'. The 'lock word'
is always a 32 bit word, unlike the other words above. The 'lock
word' holds 3 flag bits in the upper 3 bits, and the thread id (TID)
of the thread holding the lock in the bottom 29 bits. See further
below for a description of the flag bits.
The third word, called 'list_op_pending', contains transient copy of
the address of the 'lock entry', during list insertion and removal,
and is needed to correctly resolve races should a thread exit while
in the middle of a locking or unlocking operation.
Each 'lock entry' on the single linked list starting at 'head' consists
of just a single word, pointing to the next 'lock entry', or back to
'head' if there are no more entries. In addition, nearby to each 'lock
entry', at an offset from the 'lock entry' specified by the 'offset'
word, is one 'lock word'.
The 'lock word' is always 32 bits, and is intended to be the same 32 bit
lock variable used by the futex mechanism, in conjunction with
robust_futexes. The kernel will only be able to wakeup the next thread
waiting for a lock on a threads exit if that next thread used the futex
mechanism to register the address of that 'lock word' with the kernel.
For each futex lock currently held by a thread, if it wants this
robust_futex support for exit cleanup of that lock, it should have one
'lock entry' on this list, with its associated 'lock word' at the
specified 'offset'. Should a thread die while holding any such locks,
the kernel will walk this list, mark any such locks with a bit
indicating their holder died, and wakeup the next thread waiting for
that lock using the futex mechanism.
When a thread has invoked the above system call to indicate it
anticipates using robust_futexes, the kernel stores the passed in 'head'
pointer for that task. The task may retrieve that value later on by
using the system call:
asmlinkage long
sys_get_robust_list(int pid, struct robust_list_head __user **head_ptr,
size_t __user *len_ptr);
It is anticipated that threads will use robust_futexes embedded in
larger, user level locking structures, one per lock. The kernel
robust_futex mechanism doesn't care what else is in that structure, so
long as the 'offset' to the 'lock word' is the same for all
robust_futexes used by that thread. The thread should link those locks
it currently holds using the 'lock entry' pointers. It may also have
other links between the locks, such as the reverse side of a double
linked list, but that doesn't matter to the kernel.
By keeping its locks linked this way, on a list starting with a 'head'
pointer known to the kernel, the kernel can provide to a thread the
essential service available for robust_futexes, which is to help clean
up locks held at the time of (a perhaps unexpectedly) exit.
Actual locking and unlocking, during normal operations, is handled
entirely by user level code in the contending threads, and by the
existing futex mechanism to wait for, and wakeup, locks. The kernels
only essential involvement in robust_futexes is to remember where the
list 'head' is, and to walk the list on thread exit, handling locks
still held by the departing thread, as described below.
There may exist thousands of futex lock structures in a threads shared
memory, on various data structures, at a given point in time. Only those
lock structures for locks currently held by that thread should be on
that thread's robust_futex linked lock list a given time.
A given futex lock structure in a user shared memory region may be held
at different times by any of the threads with access to that region. The
thread currently holding such a lock, if any, is marked with the threads
TID in the lower 29 bits of the 'lock word'.
When adding or removing a lock from its list of held locks, in order for
the kernel to correctly handle lock cleanup regardless of when the task
exits (perhaps it gets an unexpected signal 9 in the middle of
manipulating this list), the user code must observe the following
protocol on 'lock entry' insertion and removal:
On insertion:
1) set the 'list_op_pending' word to the address of the 'lock word'
to be inserted,
2) acquire the futex lock,
3) add the lock entry, with its thread id (TID) in the bottom 29 bits
of the 'lock word', to the linked list starting at 'head', and
4) clear the 'list_op_pending' word.
On removal:
1) set the 'list_op_pending' word to the address of the 'lock word'
to be removed,
2) remove the lock entry for this lock from the 'head' list,
2) release the futex lock, and
2) clear the 'lock_op_pending' word.
On exit, the kernel will consider the address stored in
'list_op_pending' and the address of each 'lock word' found by walking
the list starting at 'head'. For each such address, if the bottom 29
bits of the 'lock word' at offset 'offset' from that address equals the
exiting threads TID, then the kernel will do two things:
1) if bit 31 (0x80000000) is set in that word, then attempt a futex
wakeup on that address, which will waken the next thread that has
used to the futex mechanism to wait on that address, and
2) atomically set bit 30 (0x40000000) in the 'lock word'.
In the above, bit 31 was set by futex waiters on that lock to indicate
they were waiting, and bit 30 is set by the kernel to indicate that the
lock owner died holding the lock.
The kernel exit code will silently stop scanning the list further if at
any point:
1) the 'head' pointer or an subsequent linked list pointer
is not a valid address of a user space word
2) the calculated location of the 'lock word' (address plus
'offset') is not the valud address of a 32 bit user space
word
3) if the list contains more than 1 million (subject to
future kernel configuration changes) elements.
When the kernel sees a list entry whose 'lock word' doesn't have the
current threads TID in the lower 29 bits, it does nothing with that
entry, and goes on to the next entry.
Bit 29 (0x20000000) of the 'lock word' is reserved for future use.
Documentation/robust-futexes.txt
+218
View File
@@ -0,0 +1,218 @@
Started by: Ingo Molnar <mingo@redhat.com>
Background
----------
what are robust futexes? To answer that, we first need to understand
what futexes are: normal futexes are special types of locks that in the
noncontended case can be acquired/released from userspace without having
to enter the kernel.
A futex is in essence a user-space address, e.g. a 32-bit lock variable
field. If userspace notices contention (the lock is already owned and
someone else wants to grab it too) then the lock is marked with a value
that says "there's a waiter pending", and the sys_futex(FUTEX_WAIT)
syscall is used to wait for the other guy to release it. The kernel
creates a 'futex queue' internally, so that it can later on match up the
waiter with the waker - without them having to know about each other.
When the owner thread releases the futex, it notices (via the variable
value) that there were waiter(s) pending, and does the
sys_futex(FUTEX_WAKE) syscall to wake them up. Once all waiters have
taken and released the lock, the futex is again back to 'uncontended'
state, and there's no in-kernel state associated with it. The kernel
completely forgets that there ever was a futex at that address. This
method makes futexes very lightweight and scalable.
"Robustness" is about dealing with crashes while holding a lock: if a
process exits prematurely while holding a pthread_mutex_t lock that is
also shared with some other process (e.g. yum segfaults while holding a
pthread_mutex_t, or yum is kill -9-ed), then waiters for that lock need
to be notified that the last owner of the lock exited in some irregular
way.
To solve such types of problems, "robust mutex" userspace APIs were
created: pthread_mutex_lock() returns an error value if the owner exits
prematurely - and the new owner can decide whether the data protected by
the lock can be recovered safely.
There is a big conceptual problem with futex based mutexes though: it is
the kernel that destroys the owner task (e.g. due to a SEGFAULT), but
the kernel cannot help with the cleanup: if there is no 'futex queue'
(and in most cases there is none, futexes being fast lightweight locks)
then the kernel has no information to clean up after the held lock!
Userspace has no chance to clean up after the lock either - userspace is
the one that crashes, so it has no opportunity to clean up. Catch-22.
In practice, when e.g. yum is kill -9-ed (or segfaults), a system reboot
is needed to release that futex based lock. This is one of the leading
bugreports against yum.
To solve this problem, the traditional approach was to extend the vma
(virtual memory area descriptor) concept to have a notion of 'pending
robust futexes attached to this area'. This approach requires 3 new
syscall variants to sys_futex(): FUTEX_REGISTER, FUTEX_DEREGISTER and
FUTEX_RECOVER. At do_exit() time, all vmas are searched to see whether
they have a robust_head set. This approach has two fundamental problems
left:
- it has quite complex locking and race scenarios. The vma-based
approach had been pending for years, but they are still not completely
reliable.
- they have to scan _every_ vma at sys_exit() time, per thread!
The second disadvantage is a real killer: pthread_exit() takes around 1
microsecond on Linux, but with thousands (or tens of thousands) of vmas
every pthread_exit() takes a millisecond or more, also totally
destroying the CPU's L1 and L2 caches!
This is very much noticeable even for normal process sys_exit_group()
calls: the kernel has to do the vma scanning unconditionally! (this is
because the kernel has no knowledge about how many robust futexes there
are to be cleaned up, because a robust futex might have been registered
in another task, and the futex variable might have been simply mmap()-ed
into this process's address space).
This huge overhead forced the creation of CONFIG_FUTEX_ROBUST so that
normal kernels can turn it off, but worse than that: the overhead makes
robust futexes impractical for any type of generic Linux distribution.
So something had to be done.
New approach to robust futexes
------------------------------
At the heart of this new approach there is a per-thread private list of
robust locks that userspace is holding (maintained by glibc) - which
userspace list is registered with the kernel via a new syscall [this
registration happens at most once per thread lifetime]. At do_exit()
time, the kernel checks this user-space list: are there any robust futex
locks to be cleaned up?
In the common case, at do_exit() time, there is no list registered, so
the cost of robust futexes is just a simple current->robust_list != NULL
comparison. If the thread has registered a list, then normally the list
is empty. If the thread/process crashed or terminated in some incorrect
way then the list might be non-empty: in this case the kernel carefully
walks the list [not trusting it], and marks all locks that are owned by
this thread with the FUTEX_OWNER_DEAD bit, and wakes up one waiter (if
any).
The list is guaranteed to be private and per-thread at do_exit() time,
so it can be accessed by the kernel in a lockless way.
There is one race possible though: since adding to and removing from the
list is done after the futex is acquired by glibc, there is a few
instructions window for the thread (or process) to die there, leaving
the futex hung. To protect against this possibility, userspace (glibc)
also maintains a simple per-thread 'list_op_pending' field, to allow the
kernel to clean up if the thread dies after acquiring the lock, but just
before it could have added itself to the list. Glibc sets this
list_op_pending field before it tries to acquire the futex, and clears
it after the list-add (or list-remove) has finished.
That's all that is needed - all the rest of robust-futex cleanup is done
in userspace [just like with the previous patches].
Ulrich Drepper has implemented the necessary glibc support for this new
mechanism, which fully enables robust mutexes.
Key differences of this userspace-list based approach, compared to the
vma based method:
- it's much, much faster: at thread exit time, there's no need to loop
over every vma (!), which the VM-based method has to do. Only a very
simple 'is the list empty' op is done.
- no VM changes are needed - 'struct address_space' is left alone.
- no registration of individual locks is needed: robust mutexes dont
need any extra per-lock syscalls. Robust mutexes thus become a very
lightweight primitive - so they dont force the application designer
to do a hard choice between performance and robustness - robust
mutexes are just as fast.
- no per-lock kernel allocation happens.
- no resource limits are needed.
- no kernel-space recovery call (FUTEX_RECOVER) is needed.
- the implementation and the locking is "obvious", and there are no
interactions with the VM.
Performance
-----------
I have benchmarked the time needed for the kernel to process a list of 1
million (!) held locks, using the new method [on a 2GHz CPU]:
- with FUTEX_WAIT set [contended mutex]: 130 msecs
- without FUTEX_WAIT set [uncontended mutex]: 30 msecs
I have also measured an approach where glibc does the lock notification
[which it currently does for !pshared robust mutexes], and that took 256
msecs - clearly slower, due to the 1 million FUTEX_WAKE syscalls
userspace had to do.
(1 million held locks are unheard of - we expect at most a handful of
locks to be held at a time. Nevertheless it's nice to know that this
approach scales nicely.)
Implementation details
----------------------
The patch adds two new syscalls: one to register the userspace list, and
one to query the registered list pointer:
asmlinkage long
sys_set_robust_list(struct robust_list_head __user *head,
size_t len);
asmlinkage long
sys_get_robust_list(int pid, struct robust_list_head __user **head_ptr,
size_t __user *len_ptr);
List registration is very fast: the pointer is simply stored in
current->robust_list. [Note that in the future, if robust futexes become
widespread, we could extend sys_clone() to register a robust-list head
for new threads, without the need of another syscall.]
So there is virtually zero overhead for tasks not using robust futexes,
and even for robust futex users, there is only one extra syscall per
thread lifetime, and the cleanup operation, if it happens, is fast and
straightforward. The kernel doesnt have any internal distinction between
robust and normal futexes.
If a futex is found to be held at exit time, the kernel sets the
following bit of the futex word:
#define FUTEX_OWNER_DIED 0x40000000
and wakes up the next futex waiter (if any). User-space does the rest of
the cleanup.
Otherwise, robust futexes are acquired by glibc by putting the TID into
the futex field atomically. Waiters set the FUTEX_WAITERS bit:
#define FUTEX_WAITERS 0x80000000
and the remaining bits are for the TID.
Testing, architecture support
-----------------------------
i've tested the new syscalls on x86 and x86_64, and have made sure the
parsing of the userspace list is robust [ ;-) ] even if the list is
deliberately corrupted.
i386 and x86_64 syscalls are wired up at the moment, and Ulrich has
tested the new glibc code (on x86_64 and i386), and it works for his
robust-mutex testcases.
All other architectures should build just fine too - but they wont have
the new syscalls yet.
Architectures need to implement the new futex_atomic_cmpxchg_inatomic()
inline function before writing up the syscalls (that function returns
-ENOSYS right now).
Documentation/rpc-cache.txt
+76 -45
View File
@@ -1,4 +1,4 @@
This document gives a brief introduction to the caching
This document gives a brief introduction to the caching
mechanisms in the sunrpc layer that is used, in particular,
for NFS authentication.
@@ -25,25 +25,17 @@ The common code handles such things as:
- supporting 'NEGATIVE' as well as positive entries
- allowing an EXPIRED time on cache items, and removing
items after they expire, and are no longe in-use.
Future code extensions are expect to handle
- making requests to user-space to fill in cache entries
- allowing user-space to directly set entries in the cache
- delaying RPC requests that depend on as-yet incomplete
cache entries, and replaying those requests when the cache entry
is complete.
- maintaining last-access times on cache entries
- clean out old entries when the caches become full
The code for performing a cache lookup is also common, but in the form
of a template. i.e. a #define.
Each cache defines a lookup function by using the DefineCacheLookup
macro, or the simpler DefineSimpleCacheLookup macro
- clean out old entries as they expire.
Creating a Cache
----------------
1/ A cache needs a datum to cache. This is in the form of a
1/ A cache needs a datum to store. This is in the form of a
structure definition that must contain a
struct cache_head
as an element, usually the first.
@@ -51,35 +43,69 @@ Creating a Cache
Each cache element is reference counted and contains
expiry and update times for use in cache management.
2/ A cache needs a "cache_detail" structure that
describes the cache. This stores the hash table, and some
parameters for cache management.
3/ A cache needs a lookup function. This is created using
the DefineCacheLookup macro. This lookup function is used both
to find entries and to update entries. The normal mode for
updating an entry is to replace the old entry with a new
entry. However it is possible to allow update-in-place
for those caches where it makes sense (no atomicity issues
or indirect reference counting issue)
4/ A cache needs to be registered using cache_register(). This
includes in on a list of caches that will be regularly
cleaned to discard old data. For this to work, some
thread must periodically call cache_clean
describes the cache. This stores the hash table, some
parameters for cache management, and some operations detailing how
to work with particular cache items.
The operations requires are:
struct cache_head *alloc(void)
This simply allocates appropriate memory and returns
a pointer to the cache_detail embedded within the
structure
void cache_put(struct kref *)
This is called when the last reference to an item is
is dropped. The pointer passed is to the 'ref' field
in the cache_head. cache_put should release any
references create by 'cache_init' and, if CACHE_VALID
is set, any references created by cache_update.
It should then release the memory allocated by
'alloc'.
int match(struct cache_head *orig, struct cache_head *new)
test if the keys in the two structures match. Return
1 if they do, 0 if they don't.
void init(struct cache_head *orig, struct cache_head *new)
Set the 'key' fields in 'new' from 'orig'. This may
include taking references to shared objects.
void update(struct cache_head *orig, struct cache_head *new)
Set the 'content' fileds in 'new' from 'orig'.
int cache_show(struct seq_file *m, struct cache_detail *cd,
struct cache_head *h)
Optional. Used to provide a /proc file that lists the
contents of a cache. This should show one item,
usually on just one line.
int cache_request(struct cache_detail *cd, struct cache_head *h,
char **bpp, int *blen)
Format a request to be send to user-space for an item
to be instantiated. *bpp is a buffer of size *blen.
bpp should be moved forward over the encoded message,
and *blen should be reduced to show how much free
space remains. Return 0 on success or <0 if not
enough room or other problem.
int cache_parse(struct cache_detail *cd, char *buf, int len)
A message from user space has arrived to fill out a
cache entry. It is in 'buf' of length 'len'.
cache_parse should parse this, find the item in the
cache with sunrpc_cache_lookup, and update the item
with sunrpc_cache_update.
3/ A cache needs to be registered using cache_register(). This
includes it on a list of caches that will be regularly
cleaned to discard old data.
Using a cache
-------------
To find a value in a cache, call the lookup function passing it a the
datum which contains key, and possibly content, and a flag saying
whether to update the cache with new data from the datum. Depending
on how the cache lookup function was defined, it may take an extra
argument to identify the particular cache in question.
To find a value in a cache, call sunrpc_cache_lookup passing a pointer
to the cache_head in a sample item with the 'key' fields filled in.
This will be passed to ->match to identify the target entry. If no
entry is found, a new entry will be create, added to the cache, and
marked as not containing valid data.
Except in cases of kmalloc failure, the lookup function
will return a new datum which will store the key and
may contain valid content, or may not.
This datum is typically passed to cache_check which determines the
validity of the datum and may later initiate an upcall to fill
in the data.
The item returned is typically passed to cache_check which will check
if the data is valid, and may initiate an up-call to get fresh data.
cache_check will return -ENOENT in the entry is negative or if an up
call is needed but not possible, -EAGAIN if an upcall is pending,
or 0 if the data is valid;
cache_check can be passed a "struct cache_req *". This structure is
typically embedded in the actual request and can be used to create a
@@ -90,6 +116,13 @@ item does become valid, the deferred copy of the request will be
revisited (->revisit). It is expected that this method will
reschedule the request for processing.
The value returned by sunrpc_cache_lookup can also be passed to
sunrpc_cache_update to set the content for the item. A second item is
passed which should hold the content. If the item found by _lookup
has valid data, then it is discarded and a new item is created. This
saves any user of an item from worrying about content changing while
it is being inspected. If the item found by _lookup does not contain
valid data, then the content is copied across and CACHE_VALID is set.
Populating a cache
------------------
@@ -114,8 +147,8 @@ should be create or updated to have the given content, and the
expiry time should be set on that item.
Reading from a channel is a bit more interesting. When a cache
lookup fail, or when it suceeds but finds an entry that may soon
expiry, a request is lodged for that cache item to be updated by
lookup fails, or when it succeeds but finds an entry that may soon
expire, a request is lodged for that cache item to be updated by
user-space. These requests appear in the channel file.
Successive reads will return successive requests.
@@ -130,7 +163,7 @@ Thus a user-space helper is likely to:
write a response
loop.
If it dies and needs to be restarted, any requests that have not be
If it dies and needs to be restarted, any requests that have not been
answered will still appear in the file and will be read by the new
instance of the helper.
@@ -142,10 +175,9 @@ Each cache should also define a "cache_request" method which
takes a cache item and encodes a request into the buffer
provided.
Note: If a cache has no active readers on the channel, and has had not
active readers for more than 60 seconds, further requests will not be
added to the channel but instead all looks that do not find a valid
added to the channel but instead all lookups that do not find a valid
entry will fail. This is partly for backward compatibility: The
previous nfs exports table was deemed to be authoritative and a
failed lookup meant a definite 'no'.
@@ -154,18 +186,17 @@ request/response format
-----------------------
While each cache is free to use it's own format for requests
and responses over channel, the following is recommended are
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
with precisely one newline character which should be at the end.
Fields within the record should be separated by spaces, normally one.
If spaces, newlines, or nul characters are needed in a field they
much be quotes. two mechanisms are available:
much be quoted. two mechanisms are available:
1/ If a field begins '\x' then it must contain an even number of
hex digits, and pairs of these digits provide the bytes in the
field.
2/ otherwise a \ in the field must be followed by 3 octal digits
which give the code for a byte. Other characters are treated
as them selves. At the very least, space, newlines nul, and
as them selves. At the very least, space, newline, nul, and
'\' must be quoted in this way.
MAINTAINERS
+6
View File
@@ -2233,6 +2233,12 @@ M: p_gortmaker@yahoo.com
L: linux-kernel@vger.kernel.org
S: Maintained
REAL TIME CLOCK (RTC) SUBSYSTEM
P: Alessandro Zummo
M: a.zummo@towertech.it
L: linux-kernel@vger.kernel.org
S: Maintained
REISERFS FILE SYSTEM
P: Hans Reiser
M: reiserfs-dev@namesys.com
arch/alpha/kernel/setup.c
+4 -10
View File
@@ -34,6 +34,7 @@
#include <linux/root_dev.h>
#include <linux/initrd.h>
#include <linux/eisa.h>
#include <linux/pfn.h>
#ifdef CONFIG_MAGIC_SYSRQ
#include <linux/sysrq.h>
#include <linux/reboot.h>
@@ -42,7 +43,7 @@
#include <asm/setup.h>
#include <asm/io.h>
extern struct notifier_block *panic_notifier_list;
extern struct atomic_notifier_head panic_notifier_list;
static int alpha_panic_event(struct notifier_block *, unsigned long, void *);
static struct notifier_block alpha_panic_block = {
alpha_panic_event,
@@ -241,9 +242,6 @@ reserve_std_resources(void)
request_resource(io, standard_io_resources+i);
}
#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT)
#define PFN_DOWN(x) ((x) >> PAGE_SHIFT)
#define PFN_PHYS(x) ((x) << PAGE_SHIFT)
#define PFN_MAX PFN_DOWN(0x80000000)
#define for_each_mem_cluster(memdesc, cluster, i) \
for ((cluster) = (memdesc)->cluster, (i) = 0; \
@@ -472,11 +470,6 @@ page_is_ram(unsigned long pfn)
return 0;
}
#undef PFN_UP
#undef PFN_DOWN
#undef PFN_PHYS
#undef PFN_MAX
void __init
setup_arch(char **cmdline_p)
{
@@ -507,7 +500,8 @@ setup_arch(char **cmdline_p)
}
/* Register a call for panic conditions. */
notifier_chain_register(&panic_notifier_list, &alpha_panic_block);
atomic_notifier_chain_register(&panic_notifier_list,
&alpha_panic_block);
#ifdef CONFIG_ALPHA_GENERIC
/* Assume that we've booted from SRM if we haven't booted from MILO.
arch/alpha/kernel/time.c
+2 -1
View File
@@ -314,10 +314,11 @@ time_init(void)
if (!est_cycle_freq)
est_cycle_freq = validate_cc_value(calibrate_cc_with_pit());
cc1 = rpcc_after_update_in_progress();
cc1 = rpcc();
/* Calibrate CPU clock -- attempt #2. */
if (!est_cycle_freq) {
cc1 = rpcc_after_update_in_progress();
cc2 = rpcc_after_update_in_progress();
est_cycle_freq = validate_cc_value(cc2 - cc1);
cc1 = cc2;
arch/alpha/mm/numa.c
+1 -3
View File
@@ -13,6 +13,7 @@
#include <linux/bootmem.h>
#include <linux/swap.h>
#include <linux/initrd.h>
#include <linux/pfn.h>
#include <asm/hwrpb.h>
#include <asm/pgalloc.h>
@@ -27,9 +28,6 @@ bootmem_data_t node_bdata[MAX_NUMNODES];
#define DBGDCONT(args...)
#endif
#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT)
#define PFN_DOWN(x) ((x) >> PAGE_SHIFT)
#define PFN_PHYS(x) ((x) << PAGE_SHIFT)
#define for_each_mem_cluster(memdesc, cluster, i) \
for ((cluster) = (memdesc)->cluster, (i) = 0; \
(i) < (memdesc)->numclusters; (i)++, (cluster)++)

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