The commit b5810039a5 contains the note
A last caveat: the ZERO_PAGE is now refcounted and managed with rmap
(and thus mapcounted and count towards shared rss). These writes to
the struct page could cause excessive cacheline bouncing on big
systems. There are a number of ways this could be addressed if it is
an issue.
And indeed this cacheline bouncing has shown up on large SGI systems.
There was a situation where an Altix system was essentially livelocked
tearing down ZERO_PAGE pagetables when an HPC app aborted during startup.
This situation can be avoided in userspace, but it does highlight the
potential scalability problem with refcounting ZERO_PAGE, and corner
cases where it can really hurt (we don't want the system to livelock!).
There are several broad ways to fix this problem:
1. add back some special casing to avoid refcounting ZERO_PAGE
2. per-node or per-cpu ZERO_PAGES
3. remove the ZERO_PAGE completely
I will argue for 3. The others should also fix the problem, but they
result in more complex code than does 3, with little or no real benefit
that I can see.
Why? Inserting a ZERO_PAGE for anonymous read faults appears to be a
false optimisation: if an application is performance critical, it would
not be doing many read faults of new memory, or at least it could be
expected to write to that memory soon afterwards. If cache or memory use
is critical, it should not be working with a significant number of
ZERO_PAGEs anyway (a more compact representation of zeroes should be
used).
As a sanity check -- mesuring on my desktop system, there are never many
mappings to the ZERO_PAGE (eg. 2 or 3), thus memory usage here should not
increase much without it.
When running a make -j4 kernel compile on my dual core system, there are
about 1,000 mappings to the ZERO_PAGE created per second, but about 1,000
ZERO_PAGE COW faults per second (less than 1 ZERO_PAGE mapping per second
is torn down without being COWed). So removing ZERO_PAGE will save 1,000
page faults per second when running kbuild, while keeping it only saves
less than 1 page clearing operation per second. 1 page clear is cheaper
than a thousand faults, presumably, so there isn't an obvious loss.
Neither the logical argument nor these basic tests give a guarantee of no
regressions. However, this is a reasonable opportunity to try to remove
the ZERO_PAGE from the pagefault path. If it is found to cause regressions,
we can reintroduce it and just avoid refcounting it.
The /dev/zero ZERO_PAGE usage and TLB tricks also get nuked. I don't see
much use to them except on benchmarks. All other users of ZERO_PAGE are
converted just to use ZERO_PAGE(0) for simplicity. We can look at
replacing them all and maybe ripping out ZERO_PAGE completely when we are
more satisfied with this solution.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus "snif" Torvalds <torvalds@linux-foundation.org>
We need to move even more stuff into the header so that folks can use
the splice_to_pipe() implementation instead of open-coding a lot of
pipe knowledge (see relay implementation), so move to our own header
file finally.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Instead of having /dev/port support dependent in multiple places on a
string of preprocessor symbols, define a new configuration directive for
it. This ensures that all four places remain consistent with each other.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove includes of <linux/smp_lock.h> where it is not used/needed.
Suggested by Al Viro.
Builds cleanly on x86_64, i386, alpha, ia64, powerpc, sparc,
sparc64, and arm (all 59 defconfigs).
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
While digging through my MAP_FIXED changes, I found that rather obvious
bug in /dev/mem mmap implementation for nommu archs. get_unmapped_area()
is expected to return an address, not a pfn.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-By: David Howells <dhowells@redhat.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This reverts commit 99a10a60ba.
As per Hugh Dickins:
"Nadia Derbey has reported that mmap of /dev/kmem no longer works with
the kernel virtual address as offset, and Franck has confirmed that
his patch came from a misunderstanding of what an offset means to
/dev/kmem - whereas his patch description seems to say that he was
correcting the offset on a few plaforms, there was no such problem to
correct, and his patch was in fact changing its API on all platforms."
Suggested-by: Hugh Dickins <hugh@veritas.com>
Cc: Franck Bui-Huu <fbuihuu@gmail.com>
Cc: Nadia Derbey <Nadia.Derbey@bull.net>
Cc: Andi Kleen <ak@suse.de>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ramiro Voicu hits the BUG_ON(!pte_none(*pte)) in zeromap_pte_range: kernel
bugzilla 7645. Right: read_zero_pagealigned uses down_read of mmap_sem,
but another thread's racing read of /dev/zero, or a normal fault, can
easily set that pte again, in between zap_page_range and zeromap_page_range
getting there. It's been wrong ever since 2.4.3.
The simple fix is to use down_write instead, but that would serialize reads
of /dev/zero more than at present: perhaps some app would be badly
affected. So instead let zeromap_page_range return the error instead of
BUG_ON, and read_zero_pagealigned break to the slower clear_user loop in
that case - there's no need to optimize for it.
Use -EEXIST for when a pte is found: BUG_ON in mmap_zero (the other user of
zeromap_page_range), though it really isn't interesting there. And since
mmap_zero wants -EAGAIN for out-of-memory, the zeromaps better return that
than -ENOMEM.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Cc: Ramiro Voicu: <Ramiro.Voicu@cern.ch>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The recent commit (99a10a60ba) to fix up
mmap_kmem() broke compiles because it used PFN_DOWN() without including
<linux/pfn.h>.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
vma->vm_pgoff is an pfn _offset_ relatif to the begining
of the memory start. The previous code was doing at first:
vma->vm_pgoff << PAGE_SHIFT
which results into a wrong physical address since some
platforms have a physical mem start that can be different
from 0. After that the previous call __pa() on this
wrong physical address, however __pa() is used to convert
a _virtual_ address into a physical one.
This patch rewrites this convertion. It calculates the
pfn of PAGE_OFFSET which is the pfn of the mem start
then it adds the vma->vm_pgoff to it.
It also uses virt_to_phys() instead of __pa() since the
latter shouldn't be used by drivers.
Signed-off-by: Franck Bui-Huu <fbuihuu@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This change corrects the logic on the preprocessor conditionals that
include support for ISA port i/o (/dev/ioports) into the mem character
driver.
This fixes the following error when building for powerpc platforms with
CONFIG_PCI=n.
drivers/built-in.o: undefined reference to `pci_io_base'
Signed-off-by: Geoff Levand <geoffrey.levand@am.sony.com>
Acked-by: Linas Vepstas <lins@austin.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Set the backing device info capabilities for /dev/mem and /dev/kmem to
permit direct sharing under no-MMU conditions and full mapping capabilities
under MMU conditions. Make the BDI used by these available to all directly
mappable character devices.
Also comment the capabilities for /dev/zero.
[akpm@osdl.org: ifdef reductions]
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Newer ARMs have a 40 bit physical address space, but mapping physical
memory above 4G needs a special page table format which we (currently?) do
not use for userspace mappings, so what happens instead is that mapping an
address >= 4G will happily discard the upper bits and wrap.
There is a valid_mmap_phys_addr_range() arch hook where we could check for
>= 4G addresses and deny the mapping, but this hook takes an unsigned long
address:
static inline int valid_mmap_phys_addr_range(unsigned long addr, size_t size);
And drivers/char/mem.c:mmap_mem() calls it like this:
static int mmap_mem(struct file * file, struct vm_area_struct * vma)
{
size_t size = vma->vm_end - vma->vm_start;
if (!valid_mmap_phys_addr_range(vma->vm_pgoff << PAGE_SHIFT, size))
So that's not much help either.
This patch makes the hook take a pfn instead of a phys address.
Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
Cc: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Mark the static struct file_operations in drivers/char as const. Making
them const prevents accidental bugs, and moves them to the .rodata section
so that they no longer do any false sharing; in addition with the proper
debug option they are then protected against corruption..
[akpm@osdl.org: build fix]
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Mark the f_ops members of inodes as const, as well as fix the
ripple-through this causes by places that copy this f_ops and then "do
stuff" with it.
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Pass the size, not a pointer to the size, to efi_mem_attribute_range().
This function validates memory regions for the /dev/mem read/write/mmap paths.
The pointer allows arches to reduce the size of the range, but I think that's
unnecessary complexity. Simplifying it will let me use
efi_mem_attribute_range() to improve the ia64 ioremap() implementation.
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: Matt Domsch <Matt_Domsch@dell.com>
Cc: "Tolentino, Matthew E" <matthew.e.tolentino@intel.com>
Cc: "Brown, Len" <len.brown@intel.com>
Cc: Andi Kleen <ak@muc.de>
Acked-by: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The /dev/mem and /dev/kmem write handlers weren't fully POSIX compliant in
that they wouldn't always force the file pointer to be updated when
returning success status.
The /dev/port write handler was inconsistent with the /dev/mem and
/dev/kmem handlers in that when encountering a -EFAULT condition after
already having written a number of items it would return -EFAULT rather
than the number of bytes written.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This reverts part of "ppc64 iSeries: allow build with no PCI"
(145d01e428) which affected generic code
and applies a fix in the arch specific code.
Commit "partly merge iseries do_IRQ"
(5fee9b3b39eb55c7e3619a3b36ceeabffeb8f144) introduced iSeries_get_irq
which was only available if CONFIG_PCI is set.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch converts the inode semaphore to a mutex. I have tested it on
XFS and compiled as much as one can consider on an ia64. Anyway your
luck with it might be different.
Modified-by: Ingo Molnar <mingo@elte.hu>
(finished the conversion)
Signed-off-by: Jes Sorensen <jes@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add a hook so architectures can validate /dev/mem mmap requests.
This is analogous to validation we already perform in the read/write
paths.
The identity mapping scheme used on ia64 requires that each 16MB or
64MB granule be accessed with exactly one attribute (write-back or
uncacheable). This avoids "attribute aliasing", which can cause a
machine check.
Sample problem scenario:
- Machine supports VGA, so it has uncacheable (UC) MMIO at 640K-768K
- efi_memmap_init() discards any write-back (WB) memory in the first granule
- Application (e.g., "hwinfo") mmaps /dev/mem, offset 0
- hwinfo receives UC mapping (the default, since memmap says "no WB here")
- Machine check abort (on chipsets that don't support UC access to WB
memory, e.g., sx1000)
In the scenario above, the only choices are
- Use WB for hwinfo mmap. Can't do this because it causes attribute
aliasing with the UC mapping for the VGA MMIO space.
- Use UC for hwinfo mmap. Can't do this because the chipset may not
support UC for that region.
- Disallow the hwinfo mmap with -EINVAL. That's what this patch does.
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Tidy up __HAVE_PHYS_MEM_ACCESS_PROT usage to make mmap_mem() easier to read.
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
kmsg_write returns with printk, so some programs may be confused by a
successful write() with a return value different than the buffer length.
# /bin/echo something > /dev/kmsg
/bin/echo: write error: Inappropriate ioctl for device
The drawbacks is that the printk return value can no more be quickly
checked from userspace.
Signed-off-by: Guillaume Chazarain <guichaz@yahoo.fr>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This replaces the (in my opinion horrible) VM_UNMAPPED logic with very
explicit support for a "remapped page range" aka VM_PFNMAP. It allows a
VM area to contain an arbitrary range of page table entries that the VM
never touches, and never considers to be normal pages.
Any user of "remap_pfn_range()" automatically gets this new
functionality, and doesn't even have to mark the pages reserved or
indeed mark them any other way. It just works. As a side effect, doing
mmap() on /dev/mem works for arbitrary ranges.
Sparc update from David in the next commit.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
It's strange enough to be looking out for anonymous pages in VM_UNPAGED areas,
let's not insert the ZERO_PAGE there - though whether it would matter will
depend on what we decide about ZERO_PAGE refcounting.
But whereas do_anonymous_page may (exceptionally) be called on a VM_UNPAGED
area, do_no_page should never be: just BUG_ON.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Change the phys_mem_access_prot() function to take a pfn instead of an
address. This allows mmap64() to work on /dev/mem for addresses above 4G
on 32-bit architectures. We start with a pfn in mmap_mem(), so there's no
need to convert to an address; in fact, it's actively bad, since the
conversion can overflow when the address is above 4G.
Similarly fix the ppc32 page_is_ram() function to avoid a conversion to an
address by directly comparing to max_pfn. Working with max_pfn instead of
high_memory fixes page_is_ram() to give the right answer for highmem pages.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Cc: Anton Blanchard <anton@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The previous patch adding the ability to nest struct class_device
changed the paramaters to the call class_device_create(). This patch
fixes up all in-kernel users of the function.
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This leaves the issue of whether we should deprecate the whole thing (or
if we should check the whole mmap range, for that matter) open. Just do
the minimal fix for now.
o Following patch provides purely cosmetic changes and corrects CodingStyle
guide lines related certain issues like below in kexec related files
o braces for one line "if" statements, "for" loops,
o more than 80 column wide lines,
o No space after "while", "for" and "switch" key words
o Changes:
o take-2: Removed the extra tab before "case" key words.
o take-3: Put operator at the end of line and space before "*/"
Signed-off-by: Maneesh Soni <maneesh@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Removed the dependency on backup region. Now all the information is encoded
in ELF format. /dev/oldmem is a dummy interface. User space tool need to be
intelligent enough to parse the elf headers and read the relevant memory areas
with the help of /dev/oldmem.
Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Hariprasad Nellitheertha <hari@in.ibm.com>
This patch contains the code that enables us to access the previous kernel's
memory as /dev/oldmem.
Signed-off-by: Eric Biederman <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch allows iSeries to build with CONFIG_PCI=n. This is useful for
partitions that have only virtual I/O.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
