| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Fix the following 'make includecheck' warning:
kernel/params.c: linux/string.h is included more than once.
Signed-off-by: Jaswinder Singh Rajput <[email protected]>
Cc: André Goddard Rosa <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
"ret" needs to be signed or the error handling for splice_to_pipe() won't
work correctly.
Signed-off-by: Dan Carpenter <[email protected]>
Cc: Tom Zanussi <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: Lai Jiangshan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Add adds a debugfs interface and additional failure modes to LKDTM to
provide similar functionality to the provoke-crash driver submitted here:
http://lwn.net/Articles/371208/
Crashes can now be induced either through module parameters (as before)
or through the debugfs interface as in provoke-crash.
The patch also provides a new "direct" interface, where KPROBES are not
used, i.e., the crash is invoked directly upon write to the debugfs
file. When built without KPROBES configured, only this mode is available.
Signed-off-by: Simon Kagstrom <[email protected]>
Cc: M. Mohan Kumar <[email protected]>
Cc: Americo Wang <[email protected]>
Cc: David Woodhouse <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: "Eric W. Biederman" <[email protected]>,
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Signed-off-by: Thadeu Lima de Souza Cascardo <[email protected]>
Cc: Kay Sievers <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Alan Cox <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
The variable priv is initialized twice to the same (side effect-free)
expression. Drop one initialization.
A simplified version of the semantic match that finds this problem is:
(http://coccinelle.lip6.fr/)
// <smpl>
@forall@
idexpression *x;
identifier f!=ERR_PTR;
@@
x = f(...)
... when != x
(
x = f(...,<+...x...+>,...)
|
* x = f(...)
)
// </smpl>
Signed-off-by: Julia Lawall <[email protected]>
Cc: Tomas Winkler <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
The only in tree external users of the symbol setup_max_cpus are in
arch/x86/. The files ./kernel/alternative.c, ./kernel/visws_quirks.c, and
./mm/kmemcheck/kmemcheck.c are all guarded by CONFIG_SMP being defined.
For this case the symbol is an unsigned int and declared as an extern in
include/linux/smp.h.
When CONFIG_SMP is not defined the symbol setup_max_cpus is
a constant value that is only used in init/main.c. Make the symbol
static for this case.
Signed-off-by: H Hartley Sweeten <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
smp: Fix documentation.
Fix documentation in include/linux/smp.h: smp_processor_id()
Signed-off-by: Rakib Mullick <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
The macro any_online_node() is prone to producing sparse warnings due to
the local symbol 'node'. Since all the in-tree users are really
requesting the first online node (the mask argument is either
NODE_MASK_ALL or node_online_map) just use the first_online_node macro and
remove the any_online_node macro since there are no users.
Signed-off-by: H Hartley Sweeten <[email protected]>
Acked-by: David Rientjes <[email protected]>
Reviewed-by: KAMEZAWA Hiroyuki <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Lee Schermerhorn <[email protected]>
Acked-by: Benjamin Herrenschmidt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Milton Miller <[email protected]>
Cc: Nathan Fontenot <[email protected]>
Cc: Geoff Levand <[email protected]>
Cc: Grant Likely <[email protected]>
Cc: J. Bruce Fields <[email protected]>
Cc: Neil Brown <[email protected]>
Cc: Trond Myklebust <[email protected]>
Cc: David S. Miller <[email protected]>
Cc: Benny Halevy <[email protected]>
Cc: Chuck Lever <[email protected]>
Cc: Ricardo Labiaga <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Make sure compiler won't do weird things with limits. E.g. fetching them
twice may return 2 different values after writable limits are implemented.
I.e. either use rlimit helpers added in commit 3e10e716abf3 ("resource:
add helpers for fetching rlimits") or ACCESS_ONCE if not applicable.
Signed-off-by: Jiri Slaby <[email protected]>
Cc: Alexander Viro <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Dependent on CONFIG_SMP the num_*_cpus() functions return unsigned or
signed values. Let them always return unsigned values to avoid strange
casts.
Fixes at least one warning:
kernel/kprobes.c: In function 'register_kretprobe':
kernel/kprobes.c:1038: warning: comparison of distinct pointer types lacks a cast
Signed-off-by: Heiko Carstens <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: Ananth N Mavinakayanahalli <[email protected]>
Cc: Masami Hiramatsu <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Rusty Russell <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
The symbol 'count' is a local global variable in this file. The function
clean_rootfs() should use a different symbol name to prevent "symbol
shadows an earlier one" noise.
Signed-off-by: H Hartley Sweeten <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
- new Documentation/init.txt file describing various forms of failure
trying to load the init binary after kernel bootup
- extend the init/main.c init failure message to direct to
Documentation/init.txt
Signed-off-by: Andreas Mohr <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Additional_cpus is only supported for IA64 now. X86_64 should not be
included.
Signed-off-by: Chen Gong <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Rusty Russell <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Move the CS5535 MFGPT hrtimer kconfig option to be with the other MFGPT
options. This makes it easier to find and also removes it from the main
"Device Drivers" menu, where it should not have been.
Signed-off-by: Randy Dunlap <[email protected]>
Acked-by: Andres Salomon <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Tell git to ignore the generated files under um, except:
include/shared/kern_constants.h
include/shared/user_constants.h
which will be moved to include/generated.
Signed-off-by: WANG Cong <[email protected]>
Cc: Al Viro <[email protected]>
Cc: Jeff Dike <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Assign tty only if line is not NULL.
[[email protected]: simplification]
Signed-off-by: Alexander Beregalov <[email protected]>
Cc: Jeff Dike <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
With id 1 the wrong bp was unwatched.
Signed-off-by: Roel Kluin <[email protected]>
Cc: Mikael Starvik <[email protected]>
Cc: Jesper Nilsson <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
size_t desc_len cannot be less than 0, test before the subtraction.
Signed-off-by: Roel Kluin <[email protected]>
Cc: Mikael Starvik <[email protected]>
Cc: Jesper Nilsson <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Convert cris to use GENERIC_TIME via the arch_getoffset() infrastructure,
reducing the amount of arch specific code we need to maintain.
Signed-off-by: John Stultz <[email protected]>
Cc: Mikael Starvik <[email protected]>
Cc: Jesper Nilsson <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Reorder struct menu_device to remove 8 bytes of padding on 64 bit builds.
Size drops from 136 to 128 bytes, so possibly needing one fewer cache
lines.
Signed-off-by: Richard Kennedy <[email protected]>
Cc: Arjan van de Ven <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
The initial -EINVAL value is overwritten by `retval = PTR_ERR(name)'. If
this isn't an error pointer and typenr is not 1, 6 or 9, then this retval,
a pointer cast to a long, is returned.
Signed-off-by: Roel Kluin <[email protected]>
Acked-by: Richard Henderson <[email protected]>
Cc: Ivan Kokshaysky <[email protected]>
Cc: Matt Turner <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
No architecture except for frv has pci_dma_sync_single() and
pci_dma_sync_sg(). The APIs are deprecated.
Signed-off-by: FUJITA Tomonori <[email protected]>
Acked-by: David S. Miller <[email protected]>
Acked-by: David Howells <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
swap_duplicate()'s loop appears to miss out on returning the error code
from __swap_duplicate(), except when that's -ENOMEM. In fact this is
intentional: prior to -ENOMEM for swap_count_continuation,
swap_duplicate() was void (and the case only occurs when copy_one_pte()
hits a corrupt pte). But that's surprising behaviour, which certainly
deserves a comment.
Signed-off-by: Hugh Dickins <[email protected]>
Reported-by: Huang Shijie <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
The noMMU version of get_user_pages() fails to pin the last page when the
start address isn't page-aligned. The patch fixes this in a way that
makes find_extend_vma() congruent to its MMU cousin.
Signed-off-by: Steven J. Magnani <[email protected]>
Acked-by: Paul Mundt <[email protected]>
Cc: David Howells <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Use the same log level for printk's in show_mem(), so that those messages
can be shown completely when using log level 6.
Signed-off-by: WANG Cong <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
__GFP_NOFAIL was deprecated in dab48dab, so add a comment that no new
users should be added.
Reviewed-by: KAMEZAWA Hiroyuki <[email protected]>
Signed-off-by: David Rientjes <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
The VM currently assumes that an inactive, mapped and referenced file page
is in use and promotes it to the active list.
However, every mapped file page starts out like this and thus a problem
arises when workloads create a stream of such pages that are used only for
a short time. By flooding the active list with those pages, the VM
quickly gets into trouble finding eligible reclaim canditates. The result
is long allocation latencies and eviction of the wrong pages.
This patch reuses the PG_referenced page flag (used for unmapped file
pages) to implement a usage detection that scales with the speed of LRU
list cycling (i.e. memory pressure).
If the scanner encounters those pages, the flag is set and the page cycled
again on the inactive list. Only if it returns with another page table
reference it is activated. Otherwise it is reclaimed as 'not recently
used cache'.
This effectively changes the minimum lifetime of a used-once mapped file
page from a full memory cycle to an inactive list cycle, which allows it
to occur in linear streams without affecting the stable working set of the
system.
Signed-off-by: Johannes Weiner <[email protected]>
Reviewed-by: Rik van Riel <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: OSAKI Motohiro <[email protected]>
Cc: Lee Schermerhorn <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
page_mapping_inuse() is a historic predicate function for pages that are
about to be reclaimed or deactivated.
According to it, a page is in use when it is mapped into page tables OR
part of swap cache OR backing an mmapped file.
This function is used in combination with page_referenced(), which checks
for young bits in ptes and the page descriptor itself for the
PG_referenced bit. Thus, checking for unmapped swap cache pages is
meaningless as PG_referenced is not set for anonymous pages and unmapped
pages do not have young ptes. The test makes no difference.
Protecting file pages that are not by themselves mapped but are part of a
mapped file is also a historic leftover for short-lived things like the
exec() code in libc. However, the VM now does reference accounting and
activation of pages at unmap time and thus the special treatment on
reclaim is obsolete.
This patch drops page_mapping_inuse() and switches the two callsites to
use page_mapped() directly.
Signed-off-by: Johannes Weiner <[email protected]>
Reviewed-by: Rik van Riel <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: OSAKI Motohiro <[email protected]>
Cc: Lee Schermerhorn <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
The used-once mapped file page detection patchset.
It is meant to help workloads with large amounts of shortly used file
mappings, like rtorrent hashing a file or git when dealing with loose
objects (git gc on a bigger site?).
Right now, the VM activates referenced mapped file pages on first
encounter on the inactive list and it takes a full memory cycle to
reclaim them again. When those pages dominate memory, the system
no longer has a meaningful notion of 'working set' and is required
to give up the active list to make reclaim progress. Obviously,
this results in rather bad scanning latencies and the wrong pages
being reclaimed.
This patch makes the VM be more careful about activating mapped file
pages in the first place. The minimum granted lifetime without
another memory access becomes an inactive list cycle instead of the
full memory cycle, which is more natural given the mentioned loads.
This test resembles a hashing rtorrent process. Sequentially, 32MB
chunks of a file are mapped into memory, hashed (sha1) and unmapped
again. While this happens, every 5 seconds a process is launched and
its execution time taken:
python2.4 -c 'import pydoc'
old: max=2.31s mean=1.26s (0.34)
new: max=1.25s mean=0.32s (0.32)
find /etc -type f
old: max=2.52s mean=1.44s (0.43)
new: max=1.92s mean=0.12s (0.17)
vim -c ':quit'
old: max=6.14s mean=4.03s (0.49)
new: max=3.48s mean=2.41s (0.25)
mplayer --help
old: max=8.08s mean=5.74s (1.02)
new: max=3.79s mean=1.32s (0.81)
overall hash time (stdev):
old: time=1192.30 (12.85) thruput=25.78mb/s (0.27)
new: time=1060.27 (32.58) thruput=29.02mb/s (0.88) (-11%)
I also tested kernbench with regular IO streaming in the background to
see whether the delayed activation of frequently used mapped file
pages had a negative impact on performance in the presence of pressure
on the inactive list. The patch made no significant difference in
timing, neither for kernbench nor for the streaming IO throughput.
The first patch submission raised concerns about the cost of the extra
faults for actually activated pages on machines that have no hardware
support for young page table entries.
I created an artificial worst case scenario on an ARM machine with
around 300MHz and 64MB of memory to figure out the dimensions
involved. The test would mmap a file of 20MB, then
1. touch all its pages to fault them in
2. force one full scan cycle on the inactive file LRU
-- old: mapping pages activated
-- new: mapping pages inactive
3. touch the mapping pages again
-- old and new: fault exceptions to set the young bits
4. force another full scan cycle on the inactive file LRU
5. touch the mapping pages one last time
-- new: fault exceptions to set the young bits
The test showed an overall increase of 6% in time over 100 iterations
of the above (old: ~212sec, new: ~225sec). 13 secs total overhead /
(100 * 5k pages), ignoring the execution time of the test itself,
makes for about 25us overhead for every page that gets actually
activated. Note:
1. File mapping the size of one third of main memory, _completely_
in active use across memory pressure - i.e., most pages referenced
within one LRU cycle. This should be rare to non-existant,
especially on such embedded setups.
2. Many huge activation batches. Those batches only occur when the
working set fluctuates. If it changes completely between every full
LRU cycle, you have problematic reclaim overhead anyway.
3. Access of activated pages at maximum speed: sequential loads from
every single page without doing anything in between. In reality,
the extra faults will get distributed between actual operations on
the data.
So even if a workload manages to get the VM into the situation of
activating a third of memory in one go on such a setup, it will take
2.2 seconds instead 2.1 without the patch.
Comparing the numbers (and my user-experience over several months),
I think this change is an overall improvement to the VM.
Patch 1 is only refactoring to break up that ugly compound conditional
in shrink_page_list() and make it easy to document and add new checks
in a readable fashion.
Patch 2 gets rid of the obsolete page_mapping_inuse(). It's not
strictly related to #3, but it was in the original submission and is a
net simplification, so I kept it.
Patch 3 implements used-once detection of mapped file pages.
This patch:
Moving the big conditional into its own predicate function makes the code
a bit easier to read and allows for better commenting on the checks
one-by-one.
This is just cleaning up, no semantics should have been changed.
Signed-off-by: Johannes Weiner <[email protected]>
Reviewed-by: Rik van Riel <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: OSAKI Motohiro <[email protected]>
Cc: Lee Schermerhorn <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Add a bare description of what /sys/devices/system/node/nodeX is. Others
will follow in time but right now, none of that tree is documented. The
existence of this file might at least encourage people to document new
entries.
Signed-off-by: Mel Gorman <[email protected]>
Reviewed-by: KOSAKI Motohiro <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Add documentation for /proc/pagetypeinfo.
Signed-off-by: Mel Gorman <[email protected]>
Reviewed-by: Christoph Lameter <[email protected]>
Reviewed-by: KOSAKI Motohiro <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
free_area_init_nodes() emits pfn ranges for all zones on the system.
There may be no pages on a higher zone, however, due to memory limitations
or the use of the mem= kernel parameter. For example:
Zone PFN ranges:
DMA 0x00000001 -> 0x00001000
DMA32 0x00001000 -> 0x00100000
Normal 0x00100000 -> 0x00100000
The implementation copies the previous zone's highest pfn, if any, as the
next zone's lowest pfn. If its highest pfn is then greater than the
amount of addressable memory, the upper memory limit is used instead.
Thus, both the lowest and highest possible pfn for higher zones without
memory may be the same.
The pfn range for zones without memory is now shown as "empty" instead.
Signed-off-by: David Rientjes <[email protected]>
Cc: Mel Gorman <[email protected]>
Reviewed-by: Christoph Lameter <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
There are quite a few GFP_KERNEL memory allocations made during
suspend/hibernation and resume that may cause the system to hang, because
the I/O operations they depend on cannot be completed due to the
underlying devices being suspended.
Avoid this problem by clearing the __GFP_IO and __GFP_FS bits in
gfp_allowed_mask before suspend/hibernation and restoring the original
values of these bits in gfp_allowed_mask durig the subsequent resume.
[[email protected]: fix CONFIG_PM=n linkage]
Signed-off-by: Rafael J. Wysocki <[email protected]>
Reported-by: Maxim Levitsky <[email protected]>
Cc: Sebastian Ott <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: KOSAKI Motohiro <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
There's an off-by-one disagreement between mkswap and swapon about the
meaning of swap_header last_page: mkswap (in all versions I've looked at:
util-linux-ng and BusyBox and old util-linux; probably as far back as
1999) consistently means the offset (in page units) of the last page of
the swap area, whereas kernel sys_swapon (as far back as 2.2 and 2.3)
strangely takes it to mean the size (in page units) of the swap area.
This disagreement is the safe way round; but it's worrying people, and
loses us one page of swap.
The fix is not just to add one to nr_good_pages: we need to get maxpages
(the size of the swap_map array) right before that; and though that is an
unsigned long, be careful not to overflow the unsigned int p->max which
later holds it (probably why header uses __u32 last_page instead of size).
Why did we subtract one from the maximum swp_offset to calculate maxpages?
Though it was probably me who made that change in 2.4.10, I don't get it:
and now we should be adding one (without risk of overflow in this case).
Fix the handling of swap_header badpages: it could have overrun the
swap_map when very large swap area used on a more limited architecture.
Remove pre-initializations of swap_header, nr_good_pages and maxpages:
those date from when sys_swapon was supporting other versions of header.
Reported-by: Nitin Gupta <[email protected]>
Reported-by: Jarkko Lavinen <[email protected]>
Signed-off-by: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
When a VMA is in an inconsistent state during setup or teardown, the worst
that can happen is that the rmap code will not be able to find the page.
The mapping is in the process of being torn down (PTEs just got
invalidated by munmap), or set up (no PTEs have been instantiated yet).
It is also impossible for the rmap code to follow a pointer to an already
freed VMA, because the rmap code holds the anon_vma->lock, which the VMA
teardown code needs to take before the VMA is removed from the anon_vma
chain.
Hence, we should not need the VM_LOCK_RMAP locking at all.
Signed-off-by: Rik van Riel <[email protected]>
Cc: Nick Piggin <[email protected]>
Cc: KOSAKI Motohiro <[email protected]>
Cc: Larry Woodman <[email protected]>
Cc: Lee Schermerhorn <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
When the parent process breaks the COW on a page, both the original which
is mapped at child and the new page which is mapped parent end up in that
same anon_vma. Generally this won't be a problem, but for some workloads
it could preserve the O(N) rmap scanning complexity.
A simple fix is to ensure that, when a page which is mapped child gets
reused in do_wp_page, because we already are the exclusive owner, the page
gets moved to our own exclusive child's anon_vma.
Signed-off-by: Rik van Riel <[email protected]>
Cc: KOSAKI Motohiro <[email protected]>
Cc: Larry Woodman <[email protected]>
Cc: Lee Schermerhorn <[email protected]>
Reviewed-by: Minchan Kim <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
When an anonymous page is inherited from a parent process, the
vma->anon_vma can differ from the page anon_vma. This can trip up
__page_check_anon_rmap, which is indirectly called from do_swap_page().
Remove that obsolete check to prevent an oops.
Signed-off-by: Rik van Riel <[email protected]>
Cc: KOSAKI Motohiro <[email protected]>
Cc: Larry Woodman <[email protected]>
Cc: Lee Schermerhorn <[email protected]>
Reviewed-by: Minchan Kim <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
The old anon_vma code can lead to scalability issues with heavily forking
workloads. Specifically, each anon_vma will be shared between the parent
process and all its child processes.
In a workload with 1000 child processes and a VMA with 1000 anonymous
pages per process that get COWed, this leads to a system with a million
anonymous pages in the same anon_vma, each of which is mapped in just one
of the 1000 processes. However, the current rmap code needs to walk them
all, leading to O(N) scanning complexity for each page.
This can result in systems where one CPU is walking the page tables of
1000 processes in page_referenced_one, while all other CPUs are stuck on
the anon_vma lock. This leads to catastrophic failure for a benchmark
like AIM7, where the total number of processes can reach in the tens of
thousands. Real workloads are still a factor 10 less process intensive
than AIM7, but they are catching up.
This patch changes the way anon_vmas and VMAs are linked, which allows us
to associate multiple anon_vmas with a VMA. At fork time, each child
process gets its own anon_vmas, in which its COWed pages will be
instantiated. The parents' anon_vma is also linked to the VMA, because
non-COWed pages could be present in any of the children.
This reduces rmap scanning complexity to O(1) for the pages of the 1000
child processes, with O(N) complexity for at most 1/N pages in the system.
This reduces the average scanning cost in heavily forking workloads from
O(N) to 2.
The only real complexity in this patch stems from the fact that linking a
VMA to anon_vmas now involves memory allocations. This means vma_adjust
can fail, if it needs to attach a VMA to anon_vma structures. This in
turn means error handling needs to be added to the calling functions.
A second source of complexity is that, because there can be multiple
anon_vmas, the anon_vma linking in vma_adjust can no longer be done under
"the" anon_vma lock. To prevent the rmap code from walking up an
incomplete VMA, this patch introduces the VM_LOCK_RMAP VMA flag. This bit
flag uses the same slot as the NOMMU VM_MAPPED_COPY, with an ifdef in mm.h
to make sure it is impossible to compile a kernel that needs both symbolic
values for the same bitflag.
Some test results:
Without the anon_vma changes, when AIM7 hits around 9.7k users (on a test
box with 16GB RAM and not quite enough IO), the system ends up running
>99% in system time, with every CPU on the same anon_vma lock in the
pageout code.
With these changes, AIM7 hits the cross-over point around 29.7k users.
This happens with ~99% IO wait time, there never seems to be any spike in
system time. The anon_vma lock contention appears to be resolved.
[[email protected]: cleanups]
Signed-off-by: Rik van Riel <[email protected]>
Cc: KOSAKI Motohiro <[email protected]>
Cc: Larry Woodman <[email protected]>
Cc: Lee Schermerhorn <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
mm/memcontrol.c:2548:32: warning: Using plain integer as NULL pointer
Signed-off-by: Thiago Farina <[email protected]>
Acked-by: Balbir Singh <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
It was tolerable until Eric went and added 8388608.
Cc: Eric Paris <[email protected]>
Cc: Wu Fengguang <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
This fixes inefficient page-by-page reads on POSIX_FADV_RANDOM.
POSIX_FADV_RANDOM used to set ra_pages=0, which leads to poor performance:
a 16K read will be carried out in 4 _sync_ 1-page reads.
In other places, ra_pages==0 means
- it's ramfs/tmpfs/hugetlbfs/sysfs/configfs
- some IO error happened
where multi-page read IO won't help or should be avoided.
POSIX_FADV_RANDOM actually want a different semantics: to disable the
*heuristic* readahead algorithm, and to use a dumb one which faithfully
submit read IO for whatever application requests.
So introduce a flag FMODE_RANDOM for POSIX_FADV_RANDOM.
Note that the random hint is not likely to help random reads performance
noticeably. And it may be too permissive on huge request size (its IO
size is not limited by read_ahead_kb).
In Quentin's report (http://lkml.org/lkml/2009/12/24/145), the overall
(NFS read) performance of the application increased by 313%!
Tested-by: Quentin Barnes <[email protected]>
Signed-off-by: Wu Fengguang <[email protected]>
Cc: Nick Piggin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Steven Whitehouse <[email protected]>
Cc: David Howells <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Cc: Al Viro <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Trond Myklebust <[email protected]>
Cc: Chuck Lever <[email protected]>
Cc: <[email protected]> [2.6.33.x]
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
We'll introduce FMODE_RANDOM which will be runtime modified. So protect
all runtime modification to f_mode with f_lock to avoid races.
Signed-off-by: Wu Fengguang <[email protected]>
Cc: Al Viro <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Trond Myklebust <[email protected]>
Cc: Chuck Lever <[email protected]>
Cc: <[email protected]> [2.6.33.x]
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
commit 01b1ae63c2 ("memcg: simple migration handling") removed
mem_cgroup_uncharge_cache_page() call from migrate_page_copy. Local
variable `anon' is now unused.
Signed-off-by: KOSAKI Motohiro <[email protected]>
Cc: KAMEZAWA Hiroyuki <[email protected]>
Cc: Daisuke Nishimura <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Currently, do_migrate_pages() have very long comment and this is not
indent properly. I often misunderstand it is function starting commnents
and confused it.
this patch fixes it.
note: this patch doesn't break 80 column rule. I guess original
author intended this indentaion, but an accident corrupted it.
Signed-off-by: KOSAKI Motohiro <[email protected]>
Reviewed-by: Christoph Lameter <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
A memmap is a directory in sysfs which includes 3 text files: start, end
and type. For example:
start: 0x100000
end: 0x7e7b1cff
type: System RAM
Interface firmware_map_add was not called explicitly. Remove it and add
function firmware_map_add_hotplug as hotplug interface of memmap.
Each memory entry has a memmap in sysfs, When we hot-add new memory, sysfs
does not export memmap entry for it. We add a call in function add_memory
to function firmware_map_add_hotplug.
Add a new function add_sysfs_fw_map_entry() to create memmap entry, it
will be called when initialize memmap and hot-add memory.
[[email protected]: un-kernedoc a no longer kerneldoc comment]
Signed-off-by: Shaohui Zheng <[email protected]>
Acked-by: Andi Kleen <[email protected]>
Acked-by: Yasunori Goto <[email protected]>
Reviewed-by: Wu Fengguang <[email protected]>
Cc: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Strangely, current mbind() doesn't merge vma with neighbor vma although it's possible.
Unfortunately, many vma can reduce performance...
This patch fixes it.
reproduced program
----------------------------------------------------------------
#include <numaif.h>
#include <numa.h>
#include <sys/mman.h>
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <string.h>
static unsigned long pagesize;
int main(int argc, char** argv)
{
void* addr;
int ch;
int node;
struct bitmask *nmask = numa_allocate_nodemask();
int err;
int node_set = 0;
char buf[128];
while ((ch = getopt(argc, argv, "n:")) != -1){
switch (ch){
case 'n':
node = strtol(optarg, NULL, 0);
numa_bitmask_setbit(nmask, node);
node_set = 1;
break;
default:
;
}
}
argc -= optind;
argv += optind;
if (!node_set)
numa_bitmask_setbit(nmask, 0);
pagesize = getpagesize();
addr = mmap(NULL, pagesize*3, PROT_READ|PROT_WRITE,
MAP_ANON|MAP_PRIVATE, 0, 0);
if (addr == MAP_FAILED)
perror("mmap "), exit(1);
fprintf(stderr, "pid = %d \n" "addr = %p\n", getpid(), addr);
/* make page populate */
memset(addr, 0, pagesize*3);
/* first mbind */
err = mbind(addr+pagesize, pagesize, MPOL_BIND, nmask->maskp,
nmask->size, MPOL_MF_MOVE_ALL);
if (err)
error("mbind1 ");
/* second mbind */
err = mbind(addr, pagesize*3, MPOL_DEFAULT, NULL, 0, 0);
if (err)
error("mbind2 ");
sprintf(buf, "cat /proc/%d/maps", getpid());
system(buf);
return 0;
}
----------------------------------------------------------------
result without this patch
addr = 0x7fe26ef09000
[snip]
7fe26ef09000-7fe26ef0a000 rw-p 00000000 00:00 0
7fe26ef0a000-7fe26ef0b000 rw-p 00000000 00:00 0
7fe26ef0b000-7fe26ef0c000 rw-p 00000000 00:00 0
7fe26ef0c000-7fe26ef0d000 rw-p 00000000 00:00 0
=> 0x7fe26ef09000-0x7fe26ef0c000 have three vmas.
result with this patch
addr = 0x7fc9ebc76000
[snip]
7fc9ebc76000-7fc9ebc7a000 rw-p 00000000 00:00 0
7fffbe690000-7fffbe6a5000 rw-p 00000000 00:00 0 [stack]
=> 0x7fc9ebc76000-0x7fc9ebc7a000 have only one vma.
[[email protected]: fix file offset passed to vma_merge()]
Signed-off-by: KOSAKI Motohiro <[email protected]>
Reviewed-by: Christoph Lameter <[email protected]>
Cc: Nick Piggin <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Lee Schermerhorn <[email protected]>
Signed-off-by: Minchan Kim <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
commit e815af95 ("change all_unreclaimable zone member to flags") changed
all_unreclaimable member to bit flag. But it had an undesireble side
effect. free_one_page() is one of most hot path in linux kernel and
increasing atomic ops in it can reduce kernel performance a bit.
Thus, this patch revert such commit partially. at least
all_unreclaimable shouldn't share memory word with other zone flags.
[[email protected]: fix patch interaction]
Signed-off-by: KOSAKI Motohiro <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Wu Fengguang <[email protected]>
Cc: KAMEZAWA Hiroyuki <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Huang Shijie <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
free_hot_page() is just a wrapper around free_hot_cold_page() with
parameter 'cold = 0'. After adding a clear comment for
free_hot_cold_page(), it is reasonable to remove a level of call.
[[email protected]: fix build]
Signed-off-by: Li Hong <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Larry Woodman <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Li Ming Chun <[email protected]>
Cc: KOSAKI Motohiro <[email protected]>
Cc: Americo Wang <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Move a call of trace_mm_page_free_direct() from free_hot_page() to
free_hot_cold_page(). It is clearer and close to kmemcheck_free_shadow(),
as it is done in function __free_pages_ok().
Signed-off-by: Li Hong <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Larry Woodman <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Li Ming Chun <[email protected]>
Cc: KOSAKI Motohiro <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
trace_mm_page_free_direct() is called in function __free_pages(). But it
is called again in free_hot_page() if order == 0 and produce duplicate
records in trace file for mm_page_free_direct event. As below:
K-PID CPU# TIMESTAMP FUNCTION
gnome-terminal-1567 [000] 4415.246466: mm_page_free_direct: page=ffffea0003db9f40 pfn=1155800 order=0
gnome-terminal-1567 [000] 4415.246468: mm_page_free_direct: page=ffffea0003db9f40 pfn=1155800 order=0
gnome-terminal-1567 [000] 4415.246506: mm_page_alloc: page=ffffea0003db9f40 pfn=1155800 order=0 migratetype=0 gfp_flags=GFP_KERNEL
gnome-terminal-1567 [000] 4415.255557: mm_page_free_direct: page=ffffea0003db9f40 pfn=1155800 order=0
gnome-terminal-1567 [000] 4415.255557: mm_page_free_direct: page=ffffea0003db9f40 pfn=1155800 order=0
This patch removes the first call and adds a call to
trace_mm_page_free_direct() in __free_pages_ok().
Signed-off-by: Li Hong <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Larry Woodman <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Li Ming Chun <[email protected]>
Cc: KOSAKI Motohiro <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|