Fix an oops experienced on the Cell architecture when init-time functions,
early_*(), are called at runtime. It alters the call paths to make sure
that the callers explicitly say whether the call is being made on behalf of
a hotplug even, or happening at boot-time.
It has been compile tested on ppc64, ia64, s390, i386 and x86_64.
Acked-by: Arnd Bergmann <[email protected]>
Signed-off-by: Dave Hansen <[email protected]>
Cc: Yasunori Goto <[email protected]>
Acked-by: Andy Whitcroft <[email protected]>
Cc: Christoph Lameter <[email protected]>
Cc: Martin Schwidefsky <[email protected]>
Acked-by: Heiko Carstens <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Some filesystems, instead of simply decrementing i_nlink, simply zero it
during an unlink operation. We need to catch these in addition to the
decrement operations.
Signed-off-by: Dave Hansen <[email protected]>
Acked-by: Christoph Hellwig <[email protected]>
Cc: Al Viro <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This is mostly included for parity with dec_nlink(), where we will have some
more hooks. This one should stay pretty darn straightforward for now.
Signed-off-by: Dave Hansen <[email protected]>
Acked-by: Christoph Hellwig <[email protected]>
Cc: Al Viro <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
When a filesystem decrements i_nlink to zero, it means that a write must be
performed in order to drop the inode from the filesystem.
We're shortly going to have keep filesystems from being remounted r/o between
the time that this i_nlink decrement and that write occurs.
So, add a little helper function to do the decrements. We'll tie into it in a
bit to note when i_nlink hits zero.
Signed-off-by: Dave Hansen <[email protected]>
Acked-by: Christoph Hellwig <[email protected]>
Cc: Al Viro <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The code around vfs_create() in open_namei() is getting a bit too complex.
Right now, there is at least the reference count on the dentry, and the
i_mutex to worry about. Soon, we'll also have mnt_writecount.
So, break the vfs_create() call out of open_namei(), and into a helper
function. This duplicates the call to may_open(), but that isn't such a bad
thing since the arguments (acc_mode and flag) were being heavily massaged
anyway.
Signed-off-by: Dave Hansen <[email protected]>
Acked-by: Christoph Hellwig <[email protected]>
Cc: Al Viro <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
We're shortly going to be adding a bunch more permission checks in these
functions. That requires adding either a bunch of new if() conditions, or
some gotos. This patch collapses existing if()s and uses gotos instead to
prepare for the upcoming changes.
Signed-off-by: Dave Hansen <[email protected]>
Acked-by: Christoph Hellwig <[email protected]>
Cc: Al Viro <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The current VMSPLIT Kconfig option is disabled whenever highmem is on.
This is a bit screwy because the people who need to change VMSPLIT the most
tend to be the ones with highmem and constrained lowmem.
So, remove the highmem dependency. But, re-include the dependency for the
"full 1GB of lowmem" option. You can't have the full 1GB of lowmem and
highmem because of the need for the vmalloc(), kmap(), etc... areas.
I thought there would be at least a bit of tweaking to do to
get it to work, but everything seems OK.
Boot tested on a 4GB x86 machine, and a 12GB 3-node NUMA-Q:
elm3b82:~# cat /proc/meminfo
MemTotal: 3695412 kB
MemFree: 3659540 kB
...
LowTotal: 2909008 kB
LowFree: 2892324 kB
...
elm3b82:~# zgrep PAE /proc/config.gz
CONFIG_X86_PAE=y
larry:~# cat /proc/meminfo
MemTotal: 11845900 kB
MemFree: 11786748 kB
...
LowTotal: 2855180 kB
LowFree: 2830092 kB
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The generic linux/numa.h file defines NODES_SHIFT to 0 in case
the architecture did not.
Every architecture which has a NUMA config option defines
NODES_SHIFT in its asm-$ARCH headers, but only if NUMA is
enabled, except for x86_64.
This should make it like all the rest.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andi Kleen <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Just about every architecture defines some macros to do operations on pfns.
They're all virtually identical. This patch consolidates all of them.
One minor glitch is that at least i386 uses them in a very skeletal header
file. To keep away from #include dependency hell, I stuck the new
definitions in a new, isolated header.
Of all of the implementations, sh64 is the only one that varied by a bit.
It used some masks to ensure that any sign-extension got ripped away before
the arithmetic is done. This has been posted to that sh64 maintainers and
the development list.
Compiles on x86, x86_64, ia64 and ppc64.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This was reported because someone was getting oopses reading /proc/iomem.
It was tracked down to a zero-sized 'struct resource' entry which was
located right at 4GB.
You need two conditions to hit this bug: a BIOS E820_RAM area starting at
exactly the boundary where you specify mem= (to get a zero-sized entry),
and for the legacy_init_iomem_resources() loop to skip that resource (which
only happens at exactly 4G).
I think the killing zero-sized e820 entry is the easiest way to fix this.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Here is a set of ppc64 specific patches that at least allow
compilation/booting with the following configurations:
FLATMEM
SPARSEMEN
SPARSEMEM + MEMORY_HOTPLUG
Signed-off-by: Mike Kravetz <[email protected]>
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Adds the necessary for non-NUMA hot-add of highmem to an existing zone on
i386.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
From: IWAMOTO Toshihiro <[email protected]>
> I found the tests does not work well with Dave's patchset.
> I've found the followings:
>
> - setup_per_zone_pages_min() calls should be added in
> capture_page_range() and online_pages()
> - lru_add_drain() should be called before try_to_migrate_pages()
The following patch deals with the first item.
Signed-off-by: IWAMOTO Toshihiro <[email protected]>
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This basically keeps up from having to extern __kmalloc_section_memmap().
The vaddr_in_vmalloc_area() helper could go in a vmalloc header, but that
header gets hard to work with, because it needs some arch-specific macros.
Just stick it in here for now, instead of creating another header.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Lion Vollnhals <[email protected]>
Signed-off-by: Jiri Slaby <[email protected]>
Signed-off-by: Yasunori Goto <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This adds generic memory add/remove and supporting functions for memory
hotplug into a new file as well as a memory hotplug kernel config option.
Individual architecture patches will follow.
For now, disable memory hotplug when swsusp is enabled. There's a lot of
churn there right now. We'll fix it up properly once it calms down.
Signed-off-by: Matt Tolentino <[email protected]>
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
See the "fixup bad_range()" patch for more information, but this actually
creates a the lock to protect things making assumptions about a zone's size
staying constant at runtime.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
pgdat->node_size_lock is basically only neeeded in one place in the normal
code: show_mem(), which is the arch-specific sysrq-m printing function.
Strictly speaking, the architectures not doing memory hotplug do no need this
locking in show_mem(). However, they are all included for completeness. This
should also make any future consolidation of all of the implementations a
little more straightforward.
This lock is also held in the sparsemem code during a memory removal, as
sections are invalidated. This is the place there pfn_valid() is made false
for a memory area that's being removed. The lock is only required when doing
pfn_valid() operations on memory which the user does not already have a
reference on the page, such as in show_mem().
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
When doing memory hotplug operations, the size of existing zones can obviously
change. This means that zone->zone_{start_pfn,spanned_pages} can change.
There are currently no locks that protect these structure members. However,
they are rarely accessed at runtime. Outside of swsusp, the only place that I
can find is bad_range().
So, split bad_range() up into two pieces: one that needs to be locked and
anther that doesn't.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
If a zone is empty at boot-time and then hot-added to later, it needs to run
the same init code that would have been run on it at boot.
This patch breaks out zone table and per-cpu-pages functions for use by the
hotplug code. You can almost see all of the free_area_init_core() function on
one page now. :)
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The following series implements memory hot-add for ppc64 and i386. There are
x86_64 and ia64 implementations that will be submitted shortly as well,
through the normal maintainers.
This patch:
local_mapnr is unused, except for in an alpha header. Keep the alpha one,
kill the rest.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This splits up sparse_index_alloc() into two pieces. This is needed
because we'll allocate the memory for the second level in a different place
from where we actually consume it to keep the allocation from happening
underneath a lock
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Bob Picco <[email protected]>
Cc: Andy Whitcroft <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Create sysfs "device" files for hostap
I was writing some scripts to automatically build kismet source lines,
and I noticed that hostap devices don't have device files, unlike my
prism54 and ipw2200 cards:
$ ls -l /sys/class/net/eth0/device
/sys/class/net/eth0/device -> ../../../devices/pci0000:00/0000:00:1e.0/0000:02:01.0
$ ls -l /sys/class/net/wifi0
ls: /sys/class/net/wifi0/device: No such file or directory
$ ls -l /sys/class/net/wlan0
ls: /sys/class/net/wlan0/device: No such file or directory
The following (quite small) patch makes sure that both the wlan and wifi
net devices have that pointer to the bus device.
This way, I can do things like
for i in /sys/class/net/*; do
if ! [ -e $i/device/drive ]; then
continue;
fi;
driver=$(basename $(readlink $i/device/driver))
case $driver in
hostap*)
echo -- hostap,$i,$i-$driver
break;
ipw2?00)
echo -- $driver,$i,$i-$driver
break;
prism54)
echo prism54g,$i
esac
done
Which should generate a working set of source lines for kismet no matter
what order I plug the cards in.
It might also be handy to have a link between the two net devices, but
that's a patch for another day.
That patch is against 2.6.13-rc1-mm1.
-- Dave
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Jouni Malinen <[email protected]>
Signed-off-by: Jeff Garzik <[email protected]>
Somewhere recently, the TSC got re-enabled for timekeeping on NUMAQ
machines. However, the hardware makes these get unsynchronized quite
badly. So badly, in fact, that the code to fix up the skew can just hang
on boot.
This patch re-disables them. It's nicely confined to the numaq.c file. It
would be great if this could make it into 2.6.13, I think it counts as a
bugfix.
Tested on a 16-proc 4-node NUMAQ.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This gives DISCONTIGMEM a bit more help text to explain what it does, not just
when to choose it.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
I got some feedback from users who think that the new "Memory Model" menu is a
little invasive. This patch will hide that menu, except when
CONFIG_EXPERIMENTAL is enabled *or* when an individual architecture wants it.
An individual arch may want to enable it because they've removed their
arch-specific DISCONTIG prompt in favor of the mm/Kconfig one.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This used to be used to disable FLATMEM selection, but I decided to change it
to be done generically when DISCONTIG is enabled. The option is unused, so
this kills it.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The following patch applies on top of 2.6.12-rc2-mm1. It fixes a minor
user interaction issue, and an early reference to SPARSEMEM.
This "choice" menu would always default to FLATMEM, as it was listed first.
Move it to the end so that the other defaults have a chance first.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
There is some confusion that arose when working on SPARSEMEM patch between
what is needed for DISCONTIG vs. NUMA.
Multiple pg_data_t's are needed for DISCONTIGMEM or NUMA, independently.
All of the current NUMA implementations require an implementation of
DISCONTIG. Because of this, quite a lot of code which is really needed for
NUMA is actually under DISCONTIG #ifdefs. For SPARSEMEM, we changed some
of these #ifdefs to CONFIG_NUMA, but that broke the DISCONTIG=y and NUMA=n
case.
Introducing this new NEED_MULTIPLE_NODES config option allows code that is
needed for both NUMA or DISCONTIG to be separated out from code that is
specific to DISCONTIG.
One great advantage of this approach is that it doesn't require every
architecture to be converted over. All of the current implementations
should "just work", only the ones implementing SPARSEMEM will have to be
fixed up.
The change to free_area_init() makes it work inside, or out of the new
config option.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This will at least suppress one prompt that users would have received the
first time they compile with the new DISCONTIG arch option. They'll still
get the "Memory Model" prompt, but 99% of them will have the default work
there.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
For all architectures, this just means that you'll see a "Memory Model"
choice in your architecture menu. For those that implement DISCONTIGMEM,
you may eventually want to make your ARCH_DISCONTIGMEM_ENABLE a "def_bool
y" and make your users select DISCONTIGMEM right out of the new choice
menu. The only disadvantage might be if you have some specific things that
you need in your help option to explain something about DISCONTIGMEM.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Adrian Bunk <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
With sparsemem being introduced, we need a central place for new
memory-related .config options: mm/Kconfig. This allows us to remove many
of the duplicated arch-specific options.
The new option, CONFIG_FLATMEM, is there to enable us to detangle NUMA and
DISCONTIGMEM. This is a requirement for sparsemem because sparsemem uses
the NUMA code without the presence of DISCONTIGMEM. The sparsemem patches
use CONFIG_FLATMEM in generic code, so this patch is a requirement before
applying them.
Almost all places that used to do '#ifndef CONFIG_DISCONTIGMEM' should use
'#ifdef CONFIG_FLATMEM' instead.
Signed-off-by: Andy Whitcroft <[email protected]>
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
discontig.c has some assumptions that mem_map[]s inside of a node are
contiguous. Teach it to make sure that each region that it's bringing online
is actually made up of valid ranges of ram.
Written-by: Andy Whitcroft <[email protected]>
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Generify the value fields in the page_flags. The aim is to allow the location
and size of these fields to be varied. Additionally we want to move away from
fixed allocations per field whilst still enforcing the overall bit utilisation
limits. We rely on the compiler to spot and optimise the accessor functions.
Signed-off-by: Andy Whitcroft <[email protected]>
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Introduce a simple allocator for the NUMA remap space. This space is very
scarce, used for structures which are best allocated node local.
This mechanism is also used on non-NUMA ia64 systems with a vmem_map to keep
the pgdat->node_mem_map initialized in a consistent place for all
architectures.
Issues:
o alloc_remap takes a node_id where we might expect a pgdat which was intended
to allow us to allocate the pgdat's using this mechanism; which we do not yet
do. Could have alloc_remap_node() and alloc_remap_nid() for this purpose.
Signed-off-by: Andy Whitcroft <[email protected]>
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The following four patches provide the last needed changes before the
introduction of sparsemem. For a more complete description of what this
will do, please see this patch:
http://www.sr71.net/patches/2.6.11/2.6.11-bk7-mhp1/broken-out/B-sparse-150-sparsemem.patch
or previous posts on the subject:
http://marc.theaimsgroup.com/?t=110868540700001&r=1&w=2http://marc.theaimsgroup.com/?l=linux-mm&m=109897373315016&w=2
Three of these are i386-only, but one of them reorganizes the macros
used to manage the space in page->flags, and will affect all platforms.
There are analogous patches to the i386 ones for ppc64, ia64, and
x86_64, but those will be submitted by the normal arch maintainers.
The combination of the four patches has been test-booted on a variety of
i386 hardware, and compiled for ppc64, i386, and x86-64 with about 17
different .configs. It's also been runtime-tested on ia64 configs (with
more patches on top).
This patch:
We _know_ which node pages in general belong to, at least at a very gross
level in node_{start,end}_pfn[]. Use those to target the allocations of
pages.
Signed-off-by: Andy Whitcroft <[email protected]>
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This patch effectively eliminates direct use of pgdat->node_mem_map outside
of the DISCONTIG code. On a flat memory system, these fields aren't
currently used, neither are they on a sparsemem system.
There was also a node_mem_map(nid) macro on many architectures. Its use
along with the use of ->node_mem_map itself was not consistent. It has
been removed in favor of two new, more explicit, arch-independent macros:
pgdat_page_nr(pgdat, pagenr)
nid_page_nr(nid, pagenr)
I called them "pgdat" and "nid" because we overload the term "node" to mean
"NUMA node", "DISCONTIG node" or "pg_data_t" in very confusing ways. I
believe the newer names are much clearer.
These macros can be overridden in the sparsemem case with a theoretically
slower operation using node_start_pfn and pfn_to_page(), instead. We could
make this the only behavior if people want, but I don't want to change too
much at once. One thing at a time.
This patch removes more code than it adds.
Compile tested on alpha, alpha discontig, arm, arm-discontig, i386, i386
generic, NUMAQ, Summit, ppc64, ppc64 discontig, and x86_64. Full list
here: http://sr71.net/patches/2.6.12/2.6.12-rc1-mhp2/configs/
Boot tested on NUMAQ, x86 SMP and ppc64 power4/5 LPARs.
Signed-off-by: Dave Hansen <[email protected]>
Signed-off-by: Martin J. Bligh <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Dave Hansen