After patch 2 in this series, a process that successfully calls mmap() for
a MAP_PRIVATE mapping will be guaranteed to successfully fault until a
process calls fork(). At that point, the next write fault from the parent
could fail due to COW if the child still has a reference.
We only reserve pages for the parent but a copy must be made to avoid
leaking data from the parent to the child after fork(). Reserves could be
taken for both parent and child at fork time to guarantee faults but if
the mapping is large it is highly likely we will not have sufficient pages
for the reservation, and it is common to fork only to exec() immediatly
after. A failure here would be very undesirable.
Note that the current behaviour of mainline with MAP_PRIVATE pages is
pretty bad. The following situation is allowed to occur today.
1. Process calls mmap(MAP_PRIVATE)
2. Process calls mlock() to fault all pages and makes sure it succeeds
3. Process forks()
4. Process writes to MAP_PRIVATE mapping while child still exists
5. If the COW fails at this point, the process gets SIGKILLed even though it
had taken care to ensure the pages existed
This patch improves the situation by guaranteeing the reliability of the
process that successfully calls mmap(). When the parent performs COW, it
will try to satisfy the allocation without using reserves. If that fails
the parent will steal the page leaving any children without a page.
Faults from the child after that point will result in failure. If the
child COW happens first, an attempt will be made to allocate the page
without reserves and the child will get SIGKILLed on failure.
To summarise the new behaviour:
1. If the original mapper performs COW on a private mapping with multiple
references, it will attempt to allocate a hugepage from the pool or
the buddy allocator without using the existing reserves. On fail, VMAs
mapping the same area are traversed and the page being COW'd is unmapped
where found. It will then steal the original page as the last mapper in
the normal way.
2. The VMAs the pages were unmapped from are flagged to note that pages
with data no longer exist. Future no-page faults on those VMAs will
terminate the process as otherwise it would appear that data was corrupted.
A warning is printed to the console that this situation occured.
2. If the child performs COW first, it will attempt to satisfy the COW
from the pool if there are enough pages or via the buddy allocator if
overcommit is allowed and the buddy allocator can satisfy the request. If
it fails, the child will be killed.
If the pool is large enough, existing applications will not notice that
the reserves were a factor. Existing applications depending on the
no-reserves been set are unlikely to exist as for much of the history of
hugetlbfs, pages were prefaulted at mmap(), allocating the pages at that
point or failing the mmap().
[npiggin@suse.de: fix CONFIG_HUGETLB=n build]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Adam Litke <agl@us.ibm.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: William Lee Irwin III <wli@holomorphy.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch reserves huge pages at mmap() time for MAP_PRIVATE mappings in
a similar manner to the reservations taken for MAP_SHARED mappings. The
reserve count is accounted both globally and on a per-VMA basis for
private mappings. This guarantees that a process that successfully calls
mmap() will successfully fault all pages in the future unless fork() is
called.
The characteristics of private mappings of hugetlbfs files behaviour after
this patch are;
1. The process calling mmap() is guaranteed to succeed all future faults until
it forks().
2. On fork(), the parent may die due to SIGKILL on writes to the private
mapping if enough pages are not available for the COW. For reasonably
reliable behaviour in the face of a small huge page pool, children of
hugepage-aware processes should not reference the mappings; such as
might occur when fork()ing to exec().
3. On fork(), the child VMAs inherit no reserves. Reads on pages already
faulted by the parent will succeed. Successful writes will depend on enough
huge pages being free in the pool.
4. Quotas of the hugetlbfs mount are checked at reserve time for the mapper
and at fault time otherwise.
Before this patch, all reads or writes in the child potentially needs page
allocations that can later lead to the death of the parent. This applies
to reads and writes of uninstantiated pages as well as COW. After the
patch it is only a write to an instantiated page that causes problems.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Adam Litke <agl@us.ibm.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: William Lee Irwin III <wli@holomorphy.com>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[Summary]
Split LRU-list of unused dentries to one per superblock to avoid soft
lock up during NFS mounts and remounting of any filesystem.
Previously I posted here:
http://lkml.org/lkml/2008/3/5/590
[Descriptions]
- background
dentry_unused is a list of dentries which are not referenced.
dentry_unused grows up when references on directories or files are
released. This list can be very long if there is huge free memory.
- the problem
When shrink_dcache_sb() is called, it scans all dentry_unused linearly
under spin_lock(), and if dentry->d_sb is differnt from given
superblock, scan next dentry. This scan costs very much if there are
many entries, and very ineffective if there are many superblocks.
IOW, When we need to shrink unused dentries on one dentry, but scans
unused dentries on all superblocks in the system. For example, we scan
500 dentries to unmount a filesystem, but scans 1,000,000 or more unused
dentries on other superblocks.
In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink
unused dentries on NFS, but scans 100,000,000 unused dentries on
superblocks in the system such as local ext3 filesystems. I hear NFS
mounting took 1 min on some system in use.
* : NFS uses virtual filesystem in rpc layer, so NFS is affected by
this problem.
100,000,000 is possible number on large systems.
Per-superblock LRU of unused dentried can reduce the cost in
reasonable manner.
- How to fix
I found this problem is solved by David Chinner's "Per-superblock
unused dentry LRU lists V3"(1), so I rebase it and add some fix to
reclaim with fairness, which is in Andrew Morton's comments(2).
1) http://lkml.org/lkml/2006/5/25/318
2) http://lkml.org/lkml/2006/5/25/320
Split LRU-list of unused dentries to each superblocks. Then, NFS
mounting will check dentries under a superblock instead of all. But
this spliting will break LRU of dentry-unused. So, I've attempted to
make reclaim unused dentrins with fairness by calculate number of
dentries to scan on this sb based on following way
number of dentries to scan on this sb =
count * (number of dentries on this sb / number of dentries in the machine)
- ToDo
- I have to measuring performance number and do stress tests.
- When unmount occurs during prune_dcache(), scanning on same
superblock, It is unable to reach next superblock because it is gone
away. We restart scannig superblock from first one, it causes
unfairness of reclaim unused dentries on first superblock. But I think
this happens very rarely.
- Test Results
Result on 6GB boxes with excessive unused dentries.
Without patch:
$ cat /proc/sys/fs/dentry-state
10181835 10180203 45 0 0 0
# mount -t nfs 10.124.60.70:/work/kernel-src nfs
real 0m1.830s
user 0m0.001s
sys 0m1.653s
With this patch:
$ cat /proc/sys/fs/dentry-state
10236610 10234751 45 0 0 0
# mount -t nfs 10.124.60.70:/work/kernel-src nfs
real 0m0.106s
user 0m0.002s
sys 0m0.032s
[akpm@linux-foundation.org: fix comments]
Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: David Chinner <dgc@sgi.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (82 commits)
ipw2200: Call netif_*_queue() interfaces properly.
netxen: Needs to include linux/vmalloc.h
[netdrvr] atl1d: fix !CONFIG_PM build
r6040: rework init_one error handling
r6040: bump release number to 0.18
r6040: handle RX fifo full and no descriptor interrupts
r6040: change the default waiting time
r6040: use definitions for magic values in descriptor status
r6040: completely rework the RX path
r6040: call napi_disable when puting down the interface and set lp->dev accordingly.
mv643xx_eth: fix NETPOLL build
r6040: rework the RX buffers allocation routine
r6040: fix scheduling while atomic in r6040_tx_timeout
r6040: fix null pointer access and tx timeouts
r6040: prefix all functions with r6040
rndis_host: support WM6 devices as modems
at91_ether: use netstats in net_device structure
sfc: Create one RX queue and interrupt per CPU package by default
sfc: Use a separate workqueue for resets
sfc: I2C adapter initialisation fixes
...
* git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6: (79 commits)
arm: bus_id -> dev_name() and dev_set_name() conversions
sparc64: fix up bus_id changes in sparc core code
3c59x: handle pci_name() being const
MTD: handle pci_name() being const
HP iLO driver
sysdev: Convert the x86 mce tolerant sysdev attribute to generic attribute
sysdev: Add utility functions for simple int/ulong variable sysdev attributes
sysdev: Pass the attribute to the low level sysdev show/store function
driver core: Suppress sysfs warnings for device_rename().
kobject: Transmit return value of call_usermodehelper() to caller
sysfs-rules.txt: reword API stability statement
debugfs: Implement debugfs_remove_recursive()
HOWTO: change email addresses of James in HOWTO
always enable FW_LOADER unless EMBEDDED=y
uio-howto.tmpl: use unique output names
uio-howto.tmpl: use standard copyright/legal markings
sysfs: don't call notify_change
sysdev: fix debugging statements in registration code.
kobject: should use kobject_put() in kset-example
kobject: reorder kobject to save space on 64 bit builds
...
The Linux kernel puts the filename argument of execve() into the new
address space. Many developers are surprised to learn this. Those who
know and could use it, object "But it's not documented."
Those who want to use it dislike the expression
(char *)(1+ strlen(env[-1+ n_env]) + env[-1+ n_env])
because it requires locating the last original environment variable,
and assumes that the filename follows the characters.
This patch documents the insertion of the filename, and makes it easier
to find by adding a new tag AT_EXECFN in the ElfXX_auxv_t; see <elf.h>.
In many cases readlink("/proc/self/exe",) gives the same answer. But if
all the original pages get unmapped, then the kernel erases the symlink
for /proc/self/exe. This can happen when a program decompressor does a
good job of cleaning up after uncompressing directly to memory, so that
the address space of the target program looks the same as if compression
had never happened. One example is http://upx.sourceforge.net .
One notable use of the underlying concept (what path containED the
executable) is glibc expanding $ORIGIN in DT_RUNPATH. In practice for
the near term, it may be a good idea for user-mode code to use both
/proc/self/exe and AT_EXECFN as fall-back methods for each other.
/proc/self/exe can fail due to unmapping, AT_EXECFN can fail because it
won't be present on non-new systems. The auxvec or {AT_EXECFN}.d_val
also can get overwritten, although in nearly all cases this would be the
result of a bug.
The runtime cost is one NEW_AUX_ENT using two words of stack space. The
underlying value is maintained already as bprm->exec; setup_arg_pages()
in fs/exec.c slides it for stack_shift, etc.
Signed-off-by: John Reiser <jreiser@BitWagon.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Jakub Jelinek <jakub@redhat.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
driver core: Suppress sysfs warnings for device_rename().
Renaming network devices to an already existing name is not
something we want sysfs to print a scary warning for, since the
callers can deal with this correctly. So let's introduce
sysfs_create_link_nowarn() which gets rid of the common warning.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
debugfs_remove_recursive() will remove a dentry and all its children.
Drivers can use this to zap their whole debugfs tree so that they don't
need to keep track of every single debugfs dentry they created.
It may fail to remove the whole tree in certain cases:
sh-3.2# rmmod atmel-mci < /sys/kernel/debug/mmc0/ios/clock
mmc0: card b368 removed
atmel_mci atmel_mci.0: Lost dma0chan1, falling back to PIO
sh-3.2# ls /sys/kernel/debug/mmc0/
ios
But I'm not sure if that case can be handled in any sane manner.
Signed-off-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com>
Cc: Pierre Ossman <drzeus-list@drzeus.cx>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
sysfs_chmod_file() calls notify_change() to change the permission bits
on a sysfs file. Replace with explicit call to sysfs_setattr() and
fsnotify_change().
This is equivalent, except that security_inode_setattr() is not
called. This function is called by drivers, so the security checks do
not make any sense.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Kobjects do not have a limit in name size since a while, so stop
pretending that they do.
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
device_create() is race-prone, so use the race-free
device_create_drvdata() instead as device_create() is going away.
Cc: Jan Harkes <jaharkes@cs.cmu.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
* 'for-2.6.27' of git://linux-nfs.org/~bfields/linux: (51 commits)
nfsd: nfs4xdr.c do-while is not a compound statement
nfsd: Use C99 initializers in fs/nfsd/nfs4xdr.c
lockd: Pass "struct sockaddr *" to new failover-by-IP function
lockd: get host reference in nlmsvc_create_block() instead of callers
lockd: minor svclock.c style fixes
lockd: eliminate duplicate nlmsvc_lookup_host call from nlmsvc_lock
lockd: eliminate duplicate nlmsvc_lookup_host call from nlmsvc_testlock
lockd: nlm_release_host() checks for NULL, caller needn't
file lock: reorder struct file_lock to save space on 64 bit builds
nfsd: take file and mnt write in nfs4_upgrade_open
nfsd: document open share bit tracking
nfsd: tabulate nfs4 xdr encoding functions
nfsd: dprint operation names
svcrdma: Change WR context get/put to use the kmem cache
svcrdma: Create a kmem cache for the WR contexts
svcrdma: Add flush_scheduled_work to module exit function
svcrdma: Limit ORD based on client's advertised IRD
svcrdma: Remove unused wait q from svcrdma_xprt structure
svcrdma: Remove unneeded spin locks from __svc_rdma_free
svcrdma: Add dma map count and WARN_ON
...
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (1232 commits)
iucv: Fix bad merging.
net_sched: Add size table for qdiscs
net_sched: Add accessor function for packet length for qdiscs
net_sched: Add qdisc_enqueue wrapper
highmem: Export totalhigh_pages.
ipv6 mcast: Omit redundant address family checks in ip6_mc_source().
net: Use standard structures for generic socket address structures.
ipv6 netns: Make several "global" sysctl variables namespace aware.
netns: Use net_eq() to compare net-namespaces for optimization.
ipv6: remove unused macros from net/ipv6.h
ipv6: remove unused parameter from ip6_ra_control
tcp: fix kernel panic with listening_get_next
tcp: Remove redundant checks when setting eff_sacks
tcp: options clean up
tcp: Fix MD5 signatures for non-linear skbs
sctp: Update sctp global memory limit allocations.
sctp: remove unnecessary byteshifting, calculate directly in big-endian
sctp: Allow only 1 listening socket with SO_REUSEADDR
sctp: Do not leak memory on multiple listen() calls
sctp: Support ipv6only AF_INET6 sockets.
...
* 'configfs-fixup-ptr-error' of git://oss.oracle.com/git/jlbec/linux-2.6:
configfs: Allow ->make_item() and ->make_group() to return detailed errors.
Revert "configfs: Allow ->make_item() and ->make_group() to return detailed errors."
Move the line disciplines towards a conventional ->ops arrangement. For
the moment the actual 'tty_ldisc' struct in the tty is kept as part of
the tty struct but this can then be changed if it turns out that when it
all settles down we want to refcount ldiscs separately to the tty.
Pull the ldisc code out of /proc and put it with our ldisc code.
Signed-off-by: Alan Cox <alan@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The WRITEMEM macro produces sparse warnings of the form:
fs/nfsd/nfs4xdr.c:2668:2: warning: do-while statement is not a compound statement
Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Cc: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
There are already 7 of them - time to kill some duplicate code.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pavel Machek
Mel Gorman
Kentaro Makita
Jan Beulich
Adrian Bunk
Linus Torvalds
Alexey Dobriyan
John Reiser
Cornelia Huck
Haavard Skinnemoen
Miklos Szeredi
Kay Sievers
Greg Kroah-Hartman
Alan Cox
David S. Miller
Harvey Harrison
J. Bruce Fields
Pavel Emelyanov