As explained in commit 1c0fe6e3bd, we want to call the architecture independent
oom killer when getting an unexplained OOM from handle_mm_fault, rather than
simply killing current.
Cc: linuxppc-dev@ozlabs.org
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linux-arch@vger.kernel.org
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We need to keep track of the backing pages that get allocated by
vmemmap_populate() so that when we use kdump, the dump-capture kernel knows
where these pages are.
We use a simple linked list of structures that contain the physical address
of the backing page and corresponding virtual address to track the backing
pages.
To save space, we just use a pointer to the next struct vmemmap_backing. We
can also do this because we never remove nodes. We call the pointer "list"
to be compatible with changes made to the crash utility.
vmemmap_populate() is called either at boot-time or on a memory hotplug
operation. We don't have to worry about the boot-time calls because they
will be inherently single-threaded, and for a memory hotplug operation
vmemmap_populate() is called through:
sparse_add_one_section()
|
V
kmalloc_section_memmap()
|
V
sparse_mem_map_populate()
|
V
vmemmap_populate()
and in sparse_add_one_section() we're protected by pgdat_resize_lock().
So, we don't need a spinlock to protect the vmemmap_list.
We allocate space for the vmemmap_backing structs by allocating whole pages
in vmemmap_list_alloc() and then handing out chunks of this to
vmemmap_list_populate().
This means that we waste at most just under one page, but this keeps the code
is simple.
Signed-off-by: Mark Nelson <markn@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
So we tried to speed things up a bit using flush_hash_pages() directly
but that falls over on 603 of course meaning we fail to flush the TLB
properly and we may even end up having it corrupt memory randomly by
accessing a hash table that doesn't exist.
This removes the "optimization" by always going through flush_tlb_page()
for now at least.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch adds the base support for the 476 processor. The code was
primarily written by Ben Herrenschmidt and Torez Smith, but I've been
maintaining it for a while.
The goal is to have a single binary that will run on 44x and 47x, but
we still have some details to work out. The biggest is that the L1 cache
line size differs on the two platforms, but it's currently a compile-time
option.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Torez Smith <lnxtorez@linux.vnet.ibm.com>
Signed-off-by: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
The bypassing of this test is a leftover from 2.4 vintage
kernels, and is no longer appropriate, or even used by KGDB.
Currently KGDB uses probe_kernel_write() for all access to
memory via the KGDB core, so it can simply be deleted.
This fixes CVE-2010-1446.
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Wufei <fei.wu@windriver.com>
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Firmware changed the way it represents memory and cpu affinity on POWER7.
Unfortunately the old method now caps the topology to work around issues
with legacy operating systems. For Linux to get the correct topology we
need to use the new form 1 affinity information.
We set the form 1 field in the client architecture, and if we see "1" in the
ibm,associativity-form property firmware supports form 1 affinity and
we should look at the first field in the ibm,associativity-reference-points
array. If not we use the second field as we always have.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The code was looking for this in cpu_features, not mmu_features. Fix this.
Signed-off-by: Becky Bruce <beckyb@kernel.crashing.org>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Data address breakpoint exceptions are currently handled along with page-faults
which require interrupts to remain in enabled state. Since exception handling
for data breakpoints aren't pre-empt safe, we handle them separately.
Signed-off-by: K.Prasad <prasad@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We can't just clear the user read permission in book3e pte, because
that will also clear supervisor read permission. This surely isn't
desired. Fix the problem by adding the supervisor read back.
BenH: Slightly simplified the ifdef and applied to ppc64 too
Signed-off-by: Li Yang <leoli@freescale.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
powerpc initializes swiotlb before parsing the kernel boot options so
swiotlb options (e.g. specifying the swiotlb buffer size) are ignored.
Any time before freeing bootmem works for swiotlb so this patch moves
powerpc's swiotlb initialization after parsing the kernel boot
options, mem_init (as x86 does).
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Tested-by: Becky Bruce <beckyb@kernel.crashing.org>
Tested-by: Albert Herranz <albert_herranz@yahoo.es>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
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 <hsweeten@visionengravers.com>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Milton Miller <miltonm@bga.com>
Cc: Nathan Fontenot <nfont@austin.ibm.com>
Cc: Geoff Levand <geoffrey.levand@am.sony.com>
Cc: Grant Likely <grant.likely@secretlab.ca>
Cc: J. Bruce Fields <bfields@fieldses.org>
Cc: Neil Brown <neilb@suse.de>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Benny Halevy <bhalevy@panasas.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Ricardo Labiaga <Ricardo.Labiaga@netapp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On VIVT ARM, when we have multiple shared mappings of the same file
in the same MM, we need to ensure that we have coherency across all
copies. We do this via make_coherent() by making the pages
uncacheable.
This used to work fine, until we allowed highmem with highpte - we
now have a page table which is mapped as required, and is not available
for modification via update_mmu_cache().
Ralf Beache suggested getting rid of the PTE value passed to
update_mmu_cache():
On MIPS update_mmu_cache() calls __update_tlb() which walks pagetables
to construct a pointer to the pte again. Passing a pte_t * is much
more elegant. Maybe we might even replace the pte argument with the
pte_t?
Ben Herrenschmidt would also like the pte pointer for PowerPC:
Passing the ptep in there is exactly what I want. I want that
-instead- of the PTE value, because I have issue on some ppc cases,
for I$/D$ coherency, where set_pte_at() may decide to mask out the
_PAGE_EXEC.
So, pass in the mapped page table pointer into update_mmu_cache(), and
remove the PTE value, updating all implementations and call sites to
suit.
Includes a fix from Stephen Rothwell:
sparc: fix fallout from update_mmu_cache API change
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
tlbivax_lock needs to be a real spinlock in RT. Convert it to
raw_spinlock.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
native_tlbie_lock needs to be a real spinlock in RT. Convert it to
raw_spinlock.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
context_lock needs to be a real spinlock in RT. Convert it to
raw_spinlock.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Now we have real bit locks use them instead of open coding it.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch adds support for boards with more that 512MByte RAM. Currently
only 512MB of memory are enabled in the DCCR/ICCR real-mode cache
control registers. This patch now enables caching in real-mode for
2GByte.
Signed-off-by: Stefan Roese <sr@denx.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Josh Boyer <jwboyer@linux.vnet.ibm.com>
Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
Commit f71dc176aa 'Make
hpte_need_flush() correctly mask for multiple page sizes' introduced
bug, which is triggered when a kernel with a 64k base page size is run
on a system whose hardware does not 64k hash PTEs. In this case, we
emulate 64k pages with multiple 4k hash PTEs, however in
hpte_need_flush() we incorrectly only mask the hardware page size from
the address, instead of the logical page size. This causes things to
go wrong when we later attempt to iterate through the hardware
subpages of the logical page.
This patch corrects the error. It has been tested on pSeries bare
metal by Michael Neuling.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We can use the much more lightweight ida allocator since we don't
need the pointer storage idr provides.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
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
3e10e716ab
or ACCESS_ONCE if not applicable.
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Commit d28513bc7f ("Fix bug in pagetable
cache cleanup with CONFIG_PPC_SUBPAGE_PROT"), itself a fix for
breakage caused by an earlier clean up patch of mine, contains a
stupid bug. I changed the parameters of the subpage_protection()
function, but failed to update one of the callers.
This patch fixes it, and replaces a void * with a typed pointer so
that the compiler will warn on such an error in future.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The function name of cpumask_clear_cpu was not correct. Fortunately
nobody uses that code with hotplug yet :-)
Reported-by: Jin Qing <b24347@freescale.com>
Signed-off-by: Li Yang <leoli@freescale.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This time without the funny characters.
Fix following build errors generated with DEBUG=1
cc1: warnings being treated as errors
arch/powerpc/mm/hash_utils_64.c: In function 'htab_dt_scan_page_sizes':
arch/powerpc/mm/hash_utils_64.c:343: error: format '%04x' expects type 'unsigned int', but argument 4 has type 'long unsigned int'
arch/powerpc/mm/hash_utils_64.c:343: error: format '%08x' expects type 'unsigned int', but argument 5 has type 'long unsigned int'
arch/powerpc/mm/hash_utils_64.c: In function 'htab_initialize':
arch/powerpc/mm/hash_utils_64.c:666: error: format '%x' expects type 'unsigned int', but argument 4 has type 'long unsigned int'
... SNIP ...
Signed-off-by: Sachin Sant <sachinp@in.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Set need to call __set_pte_at() and not set_pte_at() from __change_page_attr()
since the later will perform checks with CONFIG_DEBUG_VM that aren't suitable
to the way we override an existing PTE. (More specifically, it doesn't let
you write over a present PTE).
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Today's linux-next build (powerpc ppc44x_defconfig) failed like this:
arch/powerpc/mm/pgtable_32.c: In function 'mapin_ram':
arch/powerpc/mm/pgtable_32.c:318: error: too many arguments to function 'mmu_mapin_ram'
Casued by commit de32400dd2 ("wii: use both
mem1 and mem2 as ram").
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Add a flag to let a platform ioremap memory regions marked as reserved.
This flag will be used later by the Nintendo Wii support code to allow
ioremapping the I/O region sitting between MEM1 and MEM2 and marked
as reserved RAM in the patch "wii: use both mem1 and mem2 as ram".
This will no longer be needed when proper discontig memory support
for 32-bit PowerPC is added to the kernel.
Signed-off-by: Albert Herranz <albert_herranz@yahoo.es>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
The Nintendo Wii video game console has two discontiguous RAM regions:
- MEM1: 24MB @ 0x00000000
- MEM2: 64MB @ 0x10000000
Unfortunately, the kernel currently does not support discontiguous RAM
memory regions on 32-bit PowerPC platforms.
This patch adds a series of workarounds to allow the use of the second
memory region (MEM2) as RAM by the kernel.
Basically, a single range of memory from the beginning of MEM1 to the
end of MEM2 is reported to the kernel, and a memory reservation is
created for the hole between MEM1 and MEM2.
With this patch the system is able to use all the available RAM and not
just ~27% of it.
This will no longer be needed when proper discontig memory support
for 32-bit PowerPC is added to the kernel.
Signed-off-by: Albert Herranz <albert_herranz@yahoo.es>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
8xx sometimes need to load a invalid/non-present TLBs in
it DTLB asm handler.
These must be invalidated separaly as linux mm don't.
Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Commit a0668cdc15 cleans up the handling
of kmem_caches for allocating various levels of pagetables.
Unfortunately, it conflicts badly with CONFIG_PPC_SUBPAGE_PROT, due to
the latter's cleverly hidden technique of adding some extra allocation
space to the top level page directory to store the extra information
it needs.
Since that extra allocation really doesn't fit into the cleaned up
page directory allocating scheme, this patch alters
CONFIG_PPC_SUBPAGE_PROT to instead allocate its struct
subpage_prot_table as part of the mm_context_t.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This reverts commit c045256d14.
It breaks build when CONFIG_PPC_SUBPAGE_PROT is not set. I will
commit a fixed version separately
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Commit a4fe3ce769 introduced a new
get_user_pages() path for hugepages on powerpc. Unfortunately, there
is a bug in it's loop logic, which can cause it to overrun the end of
the intended region. This came about by copying the logic from the
normal page path, which assumes the address and end parameters have
been pagesize aligned at the top-level. Since they're not *hugepage*
size aligned, the simplistic logic could step over the end of the gup
region without triggering the loop end condition.
This patch fixes the bug by using the technique that the normal page
path uses in levels above the lowest to truncate the ending address to
something we know we'll match with.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Commit a0668cdc15 cleans up the handling
of kmem_caches for allocating various levels of pagetables.
Unfortunately, it conflicts badly with CONFIG_PPC_SUBPAGE_PROT, due to
the latter's cleverly hidden technique of adding some extra allocation
space to the top level page directory to store the extra information
it needs.
Since that extra allocation really doesn't fit into the cleaned up
page directory allocating scheme, this patch alters
CONFIG_PPC_SUBPAGE_PROT to instead allocate its struct
subpage_prot_table as part of the mm_context_t.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Re-write the code so its more standalone and fixed some issues:
* Bump'd # of CAM entries to 64 to support e500mc
* Make the code handle MAS7 properly
* Use pr_cont instead of creating a string as we go
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
For KVM we need to allocate a new context id, but don't really care about
all the mm context around it.
So let's split the alloc and destroy functions for the context id, so we can
grab one without allocating an mm context.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We want to be able to build KVM as a module. To enable us doing so, we
need some more exports from core Linux parts.
This patch exports all functions and variables that are required for KVM.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
I inadvertently left that debug code enabled, causing the number of
contexts to be clamped to 31 which is going to slow things down on
4xx and just plain breaks 8xx
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The hugepage arch code provides a number of hook functions/macros
which mirror the functionality of various normal page pte access
functions. Various changes in the normal page accessors (in
particular BenH's recent changes to the handling of lazy icache
flushing and PAGE_EXEC) have caused the hugepage versions to get out
of sync with the originals. In some cases, this is a bug, at least on
some MMU types.
One of the reasons that some hooks were not identical to the normal
page versions, is that the fact we're dealing with a hugepage needed
to be passed down do use the correct dcache-icache flush function.
This patch makes the main flush_dcache_icache_page() function hugepage
aware (by checking for the PageCompound flag). That in turn means we
can make set_huge_pte_at() just a call to set_pte_at() bringing it
back into sync. As a bonus, this lets us remove the
hash_huge_page_do_lazy_icache() function, replacing it with a call to
the hash_page_do_lazy_icache() function it was based on.
Some other hugepage pte access hooks - huge_ptep_get_and_clear() and
huge_ptep_clear_flush() - are not so easily unified, but this patch at
least brings them back into sync with the current versions of the
corresponding normal page functions.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch separates the parts of hugetlbpage.c which are inherently
specific to the hash MMU into a new hugelbpage-hash64.c file.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch simplifies the logic used to initialize hugepages on
powerpc. The somewhat oddly named set_huge_psize() is renamed to
add_huge_page_size() and now does all necessary verification of
whether it's given a valid hugepage sizes (instead of just some) and
instantiates the generic hstate structure (but no more).
hugetlbpage_init() now steps through the available pagesizes, checks
if they're valid for hugepages by calling add_huge_page_size() and
initializes the kmem_caches for the hugepage pagetables. This means
we can now eliminate the mmu_huge_psizes array, since we no longer
need to pass the sizing information for the pagetable caches from
set_huge_psize() into hugetlbpage_init()
Determination of the default huge page size is also moved from the
hash code into the general hugepage code.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Currently each available hugepage size uses a slightly different
pagetable layout: that is, the bottem level table of pointers to
hugepages is a different size, and may branch off from the normal page
tables at a different level. Every hugepage aware path that needs to
walk the pagetables must therefore look up the hugepage size from the
slice info first, and work out the correct way to walk the pagetables
accordingly. Future hardware is likely to add more possible hugepage
sizes, more layout options and more mess.
This patch, therefore reworks the handling of hugepage pagetables to
reduce this complexity. In the new scheme, instead of having to
consult the slice mask, pagetable walking code can check a flag in the
PGD/PUD/PMD entries to see where to branch off to hugepage pagetables,
and the entry also contains the information (eseentially hugepage
shift) necessary to then interpret that table without recourse to the
slice mask. This scheme can be extended neatly to handle multiple
levels of self-describing "special" hugepage pagetables, although for
now we assume only one level exists.
This approach means that only the pagetable allocation path needs to
know how the pagetables should be set out. All other (hugepage)
pagetable walking paths can just interpret the structure as they go.
There already was a flag bit in PGD/PUD/PMD entries for hugepage
directory pointers, but it was only used for debug. We alter that
flag bit to instead be a 0 in the MSB to indicate a hugepage pagetable
pointer (normally it would be 1 since the pointer lies in the linear
mapping). This means that asm pagetable walking can test for (and
punt on) hugepage pointers with the same test that checks for
unpopulated page directory entries (beq becomes bge), since hugepage
pointers will always be positive, and normal pointers always negative.
While we're at it, we get rid of the confusing (and grep defeating)
#defining of hugepte_shift to be the same thing as mmu_huge_psizes.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Currently we have a fair bit of rather fiddly code to manage the
various kmem_caches used to store page tables of various levels. We
generally have two caches holding some combination of PGD, PUD and PMD
tables, plus several more for the special hugepage pagetables.
This patch cleans this all up by taking a different approach. Rather
than the caches being designated as for PUDs or for hugeptes for 16M
pages, the caches are simply allocated to be a specific size. Thus
sharing of caches between different types/levels of pagetables happens
naturally. The pagetable size, where needed, is passed around encoded
in the same way as {PGD,PUD,PMD}_INDEX_SIZE; that is n where the
pagetable contains 2^n pointers.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Currently, hpte_need_flush() only correctly flushes the given address
for normal pages. Callers for hugepages are required to mask the
address themselves.
But hpte_need_flush() already looks up the page sizes for its own
reasons, so this is a rather silly imposition on the callers. This
patch alters it to mask based on the pagesize it has looked up itself,
and removes the awkward masking code in the hugepage caller.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
On pSeries, we always force the IO space to be mapped using 4K
pages even with a 64K base page size to cope with some limitations
in the HV interface to some devices.
However, the SLB miss handler code to discriminate between vmalloc
and ioremap space uses a CPU feature section such that the code
is nop'ed out when the processor support large pages non-cachable
mappings.
Thus, we end up always using the ioremap page size for vmalloc
segments on such processors, causing a discrepency between the
segment and the hash table, and thus a hang continously hashing
the page.
It works for the first segment of the vmalloc space since that
segment is "bolted" in by C code correctly, and thankfully we
almost never use the vmalloc space beyond the first segment,
but the new percpu code made the bug happen.
This fixes it by removing the feature section from the assembly,
we now always do the comparison between vmalloc and ioremap.
Signed-off-by; Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
After upgrading to the latest kernel on my mpc875 userspace started
running incredibly slow (hours to get to a shell, even!).
I tracked it down to commit 8d30c14cab,
that patch removed a work-around for the 8xx. Adding it
back makes my problem go away.
Signed-off-by: Rex Feany <rfeany@mrv.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
For /proc/kcore, each arch registers its memory range by kclist_add().
In usual,
- range of physical memory
- range of vmalloc area
- text, etc...
are registered but "range of physical memory" has some troubles. It
doesn't updated at memory hotplug and it tend to include unnecessary
memory holes. Now, /proc/iomem (kernel/resource.c) includes required
physical memory range information and it's properly updated at memory
hotplug. Then, it's good to avoid using its own code(duplicating
information) and to rebuild kclist for physical memory based on
/proc/iomem.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Jiri Slaby <jirislaby@gmail.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: WANG Cong <xiyou.wangcong@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Benjamin Herrenschmidt